Update documentation requirements

* update SLES 15.4 prerequisites

* update wordlist from develop

* fix spelling errors

* more spelling fixes

.github/workflows/linting.yml

@@ -5,10 +5,14 @@ on:
     branches: 
     - develop
     - main
+    - 'docs/*'
+    - 'roc**'    
   pull_request:
     branches: 
     - develop
     - main
+    - 'docs/*'
+    - 'roc**'
 
 concurrency:
   group: ${{ github.ref }}-${{ github.workflow }}

.readthedocs.yaml

@@ -3,12 +3,19 @@
 
 version: 2
 
+build:
+   os: ubuntu-22.04
+   tools:
+      python: "3.10"
+   apt_packages:
+     - "doxygen"
+     - "graphviz" # For dot graphs in doxygen
+
+python:
+   install:
+   - requirements: docs/sphinx/requirements.txt
+
 sphinx:
    configuration: docs/conf.py
 
-formats: [htmlzip, pdf, epub]
-
-python:
-   version: "3.8"
-   install:
-   - requirements: docs/sphinx/requirements.txt
+formats: []

.wordlist.txt

@@ -1,29 +1,686 @@
-# isv_deployment_win
+AAC
 ABI
-# gpu_aware_mpi
+ACE
+ACEs
+AccVGPR
+AccVGPRs
+ALU
+AMD
+AMDGPU
+AMDGPUs
+AMDMIGraphX
+AMI
+AOCC
+AOMP
+APIC
+APIs
+APU
+ASIC
+ASICs
+ASan
+ASm
+ATI
+AddressSanitizer
+AlexNet
+Arb
+BLAS
+BMC
+BitCode
+Blit
+Bluefield
+CCD
+CDNA
+CIFAR
+CLI
+CLion
+CMake
+CMakeLists
+CMakePackage
+CP
+CPC
+CPF
+CPP
+CPU
+CPUs
+CSC
+CSE
+CSV
+CSn
+CTests
+CU
+CUDA
+CUs
+CXX
+Cavium
+CentOS
+ChatGPT
+CoRR
+Codespaces
+Commitizen
+CommonMark
+Concretized
+Conda
+ConnectX
+DGEMM
+DKMS
+DL
 DMA
+DNN
+DNNL
+DPM
+DRI
+DW
+DWORD
+Dask
+DataFrame
+DataLoader
+DataParallel
+DeepSpeed
+Dependabot
+DevCap
+Dockerfile
+Doxygen
+ELMo
+ENDPGM
+EPYC
+ESXi
+FFT
+FFTs
+FFmpeg
+FHS
+FMA
+FP
+Filesystem
+Flang
+Fortran
+Fuyu
+GALB
+GCD
+GCDs
+GCN
+GDB
+GDDR
 GDR
+GDS
+GEMM
+GEMMs
+GFortran
+GiB
+GIM
+GL
+GLXT
+GMI
+GPG
+GPR
+GPT
+GPU
+GPU's
+GPUs
+GRBM
+GenAI
+GenZ
+GitHub
+Gitpod
+HBM
 HCA
-MPI
-MVAPICH
-Mellanox's
-NIC
-OFED
-OSU
-OpenFabrics
-PeerDirect
-RDMA
-UCX
-ib_core
-# linear algebra
+HIPCC
+HIPExtension
+HIPIFY
+HPC
+HPCG
+HPE
+HPL
+HSA
+HWE
+Haswell
+Higgs
+Hyperparameters
+ICV
+IDE
+IDEs
+IMDb
+IOMMU
+IOP
+IOPM
+IOV
+IRQ
+ISA
+ISV
+ISVs
+ImageNet
+InfiniBand
+Inlines
+IntelliSense
+Intersphinx
+Intra
+Ioffe
+JSON
+Jupyter
+KFD
+KiB
+KVM
+Keras
+Khronos
 LAPACK
+LCLK
+LDS
+LLM
+LLMs
+LLVM
+LM
+LSAN
+LTS
+LoRA
+MEM
+MERCHANTABILITY
+MFMA
+MiB
+MIGraphX
+MIOpen
+MIOpenGEMM
+MIVisionX
+MLM
 MMA
+MMIO
+MMIOH
+MNIST
+MPI
+MSVC
+MVAPICH
+MVFFR
+Makefile
+Makefiles
+Matplotlib
+Megatron
+Mellanox
+Mellanox's
+Meta's
+MirroredStrategy
+Multicore
+Multithreaded
+MyEnvironment
+MyST
+NBIO
+NBIOs
+NIC
+NICs
+NLI
+NLP
+NPS
+NSP
+NUMA
+NVCC
+NVIDIA
+NVPTX
+NaN
+Nano
+Navi
+Noncoherently
+NousResearch's
+NumPy
+OAM
+OAMs
+OCP
+OEM
+OFED
+OMP
+OMPI
+OMPT
+OMPX
+ONNX
+OSS
+OSU
+OpenCL
+OpenCV
+OpenFabrics
+OpenGL
+OpenMP
+OpenSSL
+OpenVX
+PCI
+PCIe
+PEFT
+PIL
+PILImage
+PRNG
+PRs
+PaLM
+Pageable
+PeerDirect
+Perfetto
+PipelineParallel
+PnP
+PowerShell
+PyPi
+PyTorch
+Qcycles
+RAII
+RCCL
+RDC
+RDMA
+RDNA
+RHEL
+ROC
+ROCProfiler
+ROCTracer
+ROCclr
+ROCdbgapi
+ROCgdb
+ROCk
+ROCm
+ROCmCC
+ROCmSoftwarePlatform
+ROCmValidationSuite
+ROCr
+RST
+RW
+Radeon
+RelWithDebInfo
+Req
+Rickle
+RoCE
+Ryzen
+SALU
+SBIOS
+SCA
+SDK
+SDMA
+SDRAM
+SENDMSG
+SGPR
+SGPRs
+SHA
+SIGQUIT
+SIMD
+SIMDs
+SKU
+SKUs
+SLES
+SMEM
+SMI
+SMT
+SPI
+SQs
+SRAM
+SRAMECC
+SVD
+SWE
+SerDes
+Shlens
+Skylake
+Softmax
+Spack
+Supermicro
+Szegedy
+TCA
+TCC
+TCI
+TCIU
+TCP
+TCR
+TF
+TFLOPS
+TPU
+TPUs
+TensorBoard
+TensorFlow
+TensorParallel
+ToC
+TorchAudio
+TorchMIGraphX
+TorchScript
+TorchServe
+TorchVision
+TransferBench
+TrapStatus
+UAC
+UC
+UCC
+UCX
+UIF
+USM
+UTCL
+UTIL
+Uncached
+Unhandled
+VALU
+VBIOS
+VGPR
+VGPRs
+VM
+VMEM
+VMWare
+VRAM
+VSIX
+VSkipped
+Vanhoucke
+Vulkan
+WGP
+WGPs
+WX
+WikiText
+Wojna
+Workgroups
+Writebacks
+XCD
+XCDs
+XGBoost
+XGBoost's
+XGMI
+XT
+XTX
+Xeon
+Xilinx
+Xnack
+Xteam
+YAML
+YML
+YModel
+ZeRO
+ZenDNN
+accuracies
+activations
+addr
+alloc
+allocator
+allocators
+amdgpu
+api
+atmi
+atomics
+autogenerated
+avx
+awk
+backend
 backends
+benchmarking
+bfloat
+bilinear
+bitsandbytes
+blit
+boson
+bosons
+buildable
+bursty
+bzip
+cacheable
+cd
+centos
+centric
+changelog
+chiplet
+cmake
+cmd
+coalescable
+codename
+collater
+comgr
+completers
+composable
+concretization
+config
+conformant
+convolutional
+convolves
+cpp
+csn
+cuBLAS
+cuFFT
+cuLIB
+cuRAND
 cuSOLVER
 cuSPARSE
-# tuning_guides
-BMC
-DGEMM
-HPCG
-HPL
-IOPM
+dataset
+datasets
+dataspace
+datatype
+datatypes
+dbgapi
+de
+deallocation
+denoise
+denoised
+denoises
+denormalize
+deserializers
+detections
+dev
+devicelibs
+devsel
+dimensionality
+disambiguates
+distro
+el
+embeddings
+enablement
+endpgm
+encodings
+env
+epilog
+etcetera
+ethernet
+exascale
+executables
+ffmpeg
+filesystem
+fortran
+galb
+gcc
+gdb
+gfortran
+gfx
+githooks
+github
+gnupg
+grayscale
+gzip
+heterogenous
+hipBLAS
+hipBLASLt
+hipCUB
+hipFFT
+hipLIB
+hipRAND
+hipSOLVER
+hipSPARSE
+hipSPARSELt
+hipTensor
+hipamd
+hipblas
+hipcub
+hipfft
+hipfort
+hipify
+hipsolver
+hipsparse
+hpp
+hsa
+hsakmt
+hyperparameter
+ib_core
+inband
+incrementing
+inferencing
+inflight
+init
+initializer
+inlining
+installable
+interprocedural
+intra
+invariants
+invocating
+ipo
+kdb
+latencies
+libfabric
+libjpeg
+libs
+linearized
+linter
+linux
+llvm
+localscratch
+logits
+lossy
+macOS
+matchers
+microarchitecture
+migraphx
+miopen
+miopengemm
+mivisionx
+mkdir
+mlirmiopen
+mtypes
+mvffr
+namespace
+namespaces
+numref
+ocl
+opencl
+opencv
+openmp
+openssl
+optimizers
+os
+pageable
+parallelization
+parameterization
+passthrough
+perfcounter
+performant
+perl
+pragma
+pre
+prebuilt
+precompiled
+prefetch
+prefetchable
+preprocess
+preprocessed
+preprocessing
+prequantized
+prerequisites
+profiler
+protobuf
+pseudorandom
+py
+quasirandom
+queueing
+rccl
+rdc
+reStructuredText
+reformats
+repos
+representativeness
+req
+resampling
+rescaling
+reusability
+roadmap
+roc
+rocAL
+rocALUTION
+rocBLAS
+rocFFT
+rocLIB
+rocMLIR
+rocPRIM
+rocRAND
+rocSOLVER
+rocSPARSE
+rocThrust
+rocWMMA
+rocalution
+rocblas
+rocclr
+rocfft
+rocm
+rocminfo
+rocprim
+rocprof
+rocprofiler
+rocr
+rocrand
+rocsolver
+rocsparse
+rocthrust
+roctracer
+runtime
+runtimes
+sL
+scalability
+scalable
+sendmsg
+serializers
+shader
+sharding
+sigmoid
+sm
+smi
+softmax
+spack
+src
+stochastically
+strided
+subdirectory
+subexpression
+subfolder
+subfolders
+supercomputing
+tensorfloat
+th
+tokenization
+tokenize
+tokenized
+tokenizer
+tokenizes
+toolchain
+toolchains
+toolset
+toolsets
+torchvision
+tqdm
+tracebacks
+txt
+uarch
+uncached
+uncorrectable
+uninstallation
+unsqueeze
+unstacking
+unswitching
+untrusted
+untuned
+upvote
+USM
+UTCL
+UTIL
+utils
+vL
+variational
+vdi
+vectorizable
+vectorization
+vectorize
+vectorized
+vectorizer
+vectorizes
+vjxb
+walkthrough
+walkthroughs
+wavefront
+wavefronts
+whitespaces
+workgroup
+workgroups
+writeback
+writebacks
+wrreq
+wzo
+xargs
+xz
+yaml
+ysvmadyb
+zypper

CHANGELOG.md

@@ -15,14 +15,595 @@ The release notes for the ROCm platform.
 
 -------------------
 
+## ROCm 5.6.0
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable no-duplicate-header -->
+<!-- markdownlint-disable header-increment -->
+#### Release Highlights
+
+ROCm 5.6 consists of several AI software ecosystem improvements to our fast-growing user base. A few examples include:
+
+- New documentation portal at https://rocm.docs.amd.com
+- Ongoing software enhancements for LLMs, ensuring full compliance with the HuggingFace unit test suite
+- OpenAI Triton, CuPy, HIP Graph support, and many other library performance enhancements
+- Improved ROCm deployment and development tools, including CPU-GPU (rocGDB) debugger, profiler, and docker containers
+- New pseudorandom generators are available in rocRAND.  Added support for half-precision transforms in hipFFT/rocFFT.  Added LU refactorization and linear system solver for sparse matrices in rocSOLVER.  
+
+#### OS and GPU Support Changes
+
+- SLES15 SP5 support was added this release. SLES15 SP3 support was dropped.
+- AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively referred to as gfx906 GPUs) will be entering the maintenance mode starting Q3 2023. This will be aligned with ROCm 5.7 GA release date.
+  - No new features and performance optimizations will be supported for the gfx906 GPUs beyond ROCm 5.7
+  - Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance [EOM])(will be aligned with the closest ROCm release)
+  - Bug fixes during the maintenance will be made to the next ROCm point release
+  - Bug fixes will not be back ported to older ROCm releases for this SKU
+  - Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM.
+
+#### AMDSMI CLI 23.0.0.4
+
+##### Added
+
+- AMDSMI CLI tool enabled for Linux Bare Metal & Guest
+
+- Package: amd-smi-lib
+ 
+##### Known Issues
+
+- not all Error Correction Code (ECC) fields are currently supported
+
+- RHEL 8 & SLES 15 have extra install steps
+
+#### Kernel Modules (DKMS)
+
+##### Fixes
+
+- Stability fix for multi GPU system reproducilble via ROCm_Bandwidth_Test as reported in [Issue 2198](https://github.com/RadeonOpenCompute/ROCm/issues/2198).
+
+#### HIP 5.6 (For ROCm 5.6)
+
+##### Optimizations
+
+- Consolidation of hipamd, rocclr and OpenCL projects in clr
+- Optimized lock for graph global capture mode
+
+##### Added
+
+- Added hipRTC support for amd_hip_fp16
+- Added hipStreamGetDevice implementation to get the device associated with the stream
+- Added HIP_AD_FORMAT_SIGNED_INT16 in hipArray formats
+- hipArrayGetInfo for getting information about the specified array
+- hipArrayGetDescriptor for getting 1D or 2D array descriptor
+- hipArray3DGetDescriptor to get 3D array descriptor
+
+##### Changed
+
+- hipMallocAsync to return success for zero size allocation to match hipMalloc
+- Separation of hipcc perl binaries from HIP project to hipcc project. hip-devel package depends on newly added hipcc package
+- Consolidation of hipamd, ROCclr, and OpenCL repositories into a single repository called clr. Instructions are updated to build HIP from sources in the HIP Installation guide
+- Removed hipBusBandwidth and hipCommander samples from hip-tests
+
+##### Fixed
+
+- Fixed regression in hipMemCpyParam3D when offset is applied
+
+##### Known Issues
+
+- Limited testing on xnack+ configuration
+  - Multiple HIP tests failures (gpuvm fault or hangs)
+- hipSetDevice and hipSetDeviceFlags APIs return hipErrorInvalidDevice instead of hipErrorNoDevice, on a system without GPU
+- Known memory leak when code object files are loaded/unloaded via hipModuleLoad/hipModuleUnload APIs. Issue will be fixed in a future ROCm release
+
+##### Upcoming changes in future release
+
+- Removal of gcnarch from hipDeviceProp_t structure
+- Addition of new fields in hipDeviceProp_t structure
+  - maxTexture1D
+  - maxTexture2D
+  - maxTexture1DLayered
+  - maxTexture2DLayered
+  - sharedMemPerMultiprocessor
+  - deviceOverlap
+  - asyncEngineCount
+  - surfaceAlignment
+  - unifiedAddressing
+  - computePreemptionSupported
+  - uuid
+- Removal of deprecated code
+  - hip-hcc codes from hip code tree
+- Correct hipArray usage in HIP APIs such as hipMemcpyAtoH and hipMemcpyHtoA
+- HIPMEMCPY_3D fields correction (unsigned int -> size_t)
+- Renaming of 'memoryType' in hipPointerAttribute_t structure to 'type'
+
+#### ROCgdb-13 (For ROCm 5.6.0)
+
+##### Optimized
+
+- Improved performances when handling the end of a process with a large number of threads.
+
+Known Issues
+
+- On certain configurations, ROCgdb can show the following warning message:
+
+  `warning: Probes-based dynamic linker interface failed. Reverting to original interface.`
+
+  This does not affect ROCgdb's functionalities.
+
+#### ROCprofiler (For ROCm 5.6.0)
+
+In ROCm 5.6 the `rocprofilerv1` and `rocprofilerv2` include and library files of
+ROCm 5.5 are split into separate files. The `rocmtools` files that were
+deprecated in ROCm 5.5 have been removed.
+
+  | ROCm 5.6        | rocprofilerv1                       | rocprofilerv2                          |
+  |-----------------|-------------------------------------|----------------------------------------|
+  | **Tool script** | `bin/rocprof`                       | `bin/rocprofv2`                        |
+  | **API include** | `include/rocprofiler/rocprofiler.h` | `include/rocprofiler/v2/rocprofiler.h` |
+  | **API library** | `lib/librocprofiler.so.1`           | `lib/librocprofiler.so.2`              |
+
+The ROCm Profiler Tool that uses `rocprofilerV1` can be invoked using the
+following command:
+
+```sh
+$ rocprof …
+```
+
+To write a custom tool based on the `rocprofilerV1` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/rocprofiler.h> // Use the rocprofilerV1 API
+int main() {
+  // Use the rocprofilerV1 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.1`.
+
+The ROCm Profiler that uses `rocprofilerV2` API can be invoked using the
+following command:
+
+```sh
+$ rocprofv2 …
+```
+
+To write a custom tool based on the `rocprofilerV2` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/v2/rocprofiler.h> // Use the rocprofilerV2 API
+int main() {
+  // Use the rocprofilerV2 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64-v2
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.2`.
+
+##### Optimized
+
+- Improved Test Suite
+
+##### Added
+
+- 'end_time' need to be disabled in roctx_trace.txt
+
+##### Fixed
+
+- rocprof in ROcm/5.4.0 gpu selector broken.
+- rocprof in ROCm/5.4.1 fails to generate kernel info.
+- rocprof clobbers LD_PRELOAD.
+
+### Library Changes in ROCM 5.6.0
+
+| Library | Version |
+|---------|---------|
+| hipBLAS |  ⇒ [1.0.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.6.0) |
+| hipCUB |  ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.6.0) |
+| hipFFT |  ⇒ [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.6.0) |
+| hipSOLVER |  ⇒ [1.8.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.6.0) |
+| hipSPARSE |  ⇒ [2.3.6](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.6.0) |
+| MIOpen |  ⇒ [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.6.0) |
+| rccl |  ⇒ [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.6.0) |
+| rocALUTION |  ⇒ [2.1.9](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.6.0) |
+| rocBLAS |  ⇒ [3.0.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.6.0) |
+| rocFFT |  ⇒ [1.0.23](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.6.0) |
+| rocm-cmake |  ⇒ [0.9.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.6.0) |
+| rocPRIM |  ⇒ [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.6.0) |
+| rocRAND |  ⇒ [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.6.0) |
+| rocSOLVER |  ⇒ [3.22.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.6.0) |
+| rocSPARSE |  ⇒ [2.5.2](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.6.0) |
+| rocThrust |  ⇒ [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.6.0) |
+| rocWMMA |  ⇒ [1.1.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.6.0) |
+| Tensile |  ⇒ [4.37.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.6.0) |
+
+#### hipBLAS 1.0.0
+
+hipBLAS 1.0.0 for ROCm 5.6.0
+
+##### Changed
+
+- added const qualifier to hipBLAS functions (swap, sbmv, spmv, symv, trsm) where missing
+
+##### Removed
+
+- removed support for deprecated hipblasInt8Datatype_t enum
+- removed support for deprecated hipblasSetInt8Datatype and hipblasGetInt8Datatype functions
+
+##### Deprecated
+
+- in-place trmm is deprecated. It will be replaced by trmm which includes both in-place and
+  out-of-place functionality
+
+#### hipCUB 2.13.1
+
+hipCUB 2.13.1 for ROCm 5.6.0
+
+##### Added
+
+- Benchmarks for `BlockShuffle`, `BlockLoad`, and `BlockStore`.
+
+##### Changed
+
+- CUB backend references CUB and Thrust version 1.17.2.
+- Improved benchmark coverage of `BlockScan` by adding `ExclusiveScan`, benchmark coverage of `BlockRadixSort` by adding `SortBlockedToStriped`, and benchmark coverage of `WarpScan` by adding `Broadcast`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+##### Known Issues
+
+- `BlockRadixRankMatch` is currently broken under the rocPRIM backend.
+- `BlockRadixRankMatch` with a warp size that does not exactly divide the block size is broken under the CUB backend.
+
+#### hipFFT 1.0.12
+
+hipFFT 1.0.12 for ROCm 5.6.0
+
+##### Added
+
+- Implemented the hipfftXtMakePlanMany, hipfftXtGetSizeMany, hipfftXtExec APIs, to allow requesting half-precision transforms.
+
+##### Changed
+
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+#### hipSOLVER 1.8.0
+
+hipSOLVER 1.8.0 for ROCm 5.6.0
+
+##### Added
+
+- Added compatibility API with hipsolverRf prefix
+
+#### hipSPARSE 2.3.6
+
+hipSPARSE 2.3.6 for ROCm 5.6.0
+
+##### Added
+
+- Added SpGEMM algorithms
+
+##### Changed
+
+- For hipsparseXbsr2csr and hipsparseXcsr2bsr, blockDim == 0 now returns HIPSPARSE_STATUS_INVALID_SIZE
+
+#### MIOpen 2.19.0
+
+MIOpen 2.19.0 for ROCm 5.6.0
+
+##### Added
+
+- ROCm 5.5 support for gfx1101 (Navi32)
+
+##### Changed
+
+- Tuning results for MLIR on ROCm 5.5
+- Bumping MLIR commit to 5.5.0 release tag
+
+##### Fixed
+
+- Fix 3d convolution Host API bug
+- [HOTFIX][MI200][FP16] Disabled ConvHipImplicitGemmBwdXdlops when FP16_ALT is required.
+
+#### rccl 2.15.5
+
+RCCL 2.15.5 for ROCm 5.6.0
+
+##### Changed
+
+- Compatibility with NCCL 2.15.5
+- Unit test executable renamed to rccl-UnitTests
+
+##### Added
+
+- HW-topology aware binary tree implementation
+- Experimental support for MSCCL
+- New unit tests for hipGraph support
+- NPKit integration
+
+##### Fixed
+
+- rocm-smi ID conversion
+- Support for HIP_VISIBLE_DEVICES for unit tests
+- Support for p2p transfers to non (HIP) visible devices
+
+##### Removed
+
+- Removed TransferBench from tools.  Exists in standalone repo: https://github.com/ROCmSoftwarePlatform/TransferBench
+
+#### rocALUTION 2.1.9
+
+rocALUTION 2.1.9 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed synchronization issues in level 1 routines
+
+#### rocBLAS 3.0.0
+
+rocBLAS 3.0.0 for ROCm 5.6.0
+
+##### Optimizations
+
+- Improved performance of Level 2 rocBLAS GEMV on gfx90a GPU for non-transposed problems having small matrices and larger batch counts. Performance enhanced for problem sizes when m and n &lt;= 32 and batch_count &gt;= 256.
+- Improved performance of rocBLAS syr2k for single, double, and double-complex precision, and her2k for double-complex precision. Slightly improved performance for general sizes on gfx90a.
+
+##### Added
+
+- Added bf16 inputs and f32 compute support to Level 1 rocBLAS Extension functions axpy_ex, scal_ex and nrm2_ex.
+
+##### Deprecated
+
+- trmm inplace is deprecated. It will be replaced by trmm that has both inplace and out-of-place functionality
+- rocblas_query_int8_layout_flag() is deprecated and will be removed in a future release
+- rocblas_gemm_flags_pack_int8x4 enum is deprecated and will be removed in a future release
+- rocblas_set_device_memory_size() is deprecated and will be replaced by a future function rocblas_increase_device_memory_size()
+- rocblas_is_user_managing_device_memory() is deprecated and will be removed in a future release
+
+##### Removed
+
+- is_complex helper was deprecated and now removed.  Use rocblas_is_complex instead.
+- The enum truncate_t and the value truncate was deprecated and now removed from. It was replaced by rocblas_truncate_t and rocblas_truncate, respectively.
+- rocblas_set_int8_type_for_hipblas was deprecated and is now removed.
+- rocblas_get_int8_type_for_hipblas was deprecated and is now removed.
+
+##### Dependencies
+
+- build only dependency on python joblib added as used by Tensile build
+- fix for cmake install on some OS when performed by install.sh -d --cmake_install
+
+##### Fixed
+
+- make trsm offset calculations 64 bit safe
+
+##### Changed
+
+- refactor rotg test code
+
+#### rocFFT 1.0.23
+
+rocFFT 1.0.23 for ROCm 5.6.0
+
+##### Added
+
+- Implemented half-precision transforms, which can be requested by passing rocfft_precision_half to rocfft_plan_create.
+- Implemented a hierarchical solution map which saves how to decompose a problem and the kernels to be used.
+- Implemented a first version of offline-tuner to support tuning kernels for C2C/Z2Z problems.
+
+##### Changed
+
+- Replaced std::complex with hipComplex data types for data generator.
+- FFT plan dimensions are now sorted to be row-major internally where possible, which produces better plans if the dimensions were accidentally specified in a different order (column-major, for example).
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+##### Fixed
+
+- Fixed over-allocation of LDS in some real-complex kernels, which was resulting in kernel launch failure.
+
+#### rocm-cmake 0.9.0
+
+rocm-cmake 0.9.0 for ROCm 5.6.0
+
+##### Added
+
+- Added the option ROCM_HEADER_WRAPPER_WERROR
+    - Compile-time C macro in the wrapper headers causes errors to be emitted instead of warnings.
+    - Configure-time CMake option sets the default for the C macro.
+
+#### rocPRIM 2.13.0
+
+rocPRIM 2.13.0 for ROCm 5.6.0
+
+##### Added
+
+- New block level `radix_rank` primitive.
+- New block level `radix_rank_match` primitive.
+- Added a stable block sorting implementation. This be used with `block_sort` by using the `block_sort_algorithm::stable_merge_sort` algorithm.
+
+##### Changed
+
+- Improved the performance of `block_radix_sort` and `device_radix_sort`.
+- Improved the performance of `device_merge_sort`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core). Contributed by: [v01dXYZ](https://github.com/v01dXYZ).
+
+##### Known Issues
+
+- Disabled GPU error messages relating to incorrect warp operation usage with Navi GPUs on Windows, due to GPU printf performance issues on Windows.
+- When `ROCPRIM_DISABLE_LOOKBACK_SCAN` is set, `device_scan` fails for input sizes bigger than `scan_config::size_limit`, which defaults to `std::numeric_limits&lt;unsigned int&gt;::max()`.
+
+#### rocRAND 2.10.17
+
+rocRAND 2.10.17 for ROCm 5.6.0
+
+##### Added
+
+- MT19937 pseudo random number generator based on M. Matsumoto and T. Nishimura, 1998, Mersenne Twister: A 623-dimensionally equidistributed uniform pseudorandom number generator.
+- New benchmark for the device API using Google Benchmark, `benchmark_rocrand_device_api`, replacing `benchmark_rocrand_kernel`. `benchmark_rocrand_kernel` is deprecated and will be removed in a future version. Likewise, `benchmark_curand_host_api` is added to replace `benchmark_curand_generate` and `benchmark_curand_device_api` is added to replace `benchmark_curand_kernel`.
+- experimental HIP-CPU feature
+- ThreeFry pseudorandom number generator based on Salmon et al., 2011, &#34;Parallel random numbers: as easy as 1, 2, 3&#34;.
+
+##### Changed
+
+- Python 2.7 is no longer officially supported.
+
+#### rocSOLVER 3.22.0
+
+rocSOLVER 3.22.0 for ROCm 5.6.0
+
+##### Added
+
+- LU refactorization for sparse matrices
+    - CSRRF_ANALYSIS
+    - CSRRF_SUMLU
+    - CSRRF_SPLITLU
+    - CSRRF_REFACTLU
+- Linear system solver for sparse matrices
+    - CSRRF_SOLVE
+- Added type `rocsolver_rfinfo` for use with sparse matrix routines
+
+##### Optimized
+
+- Improved the performance of BDSQR and GESVD when singular vectors are requested
+
+##### Fixed
+
+- BDSQR and GESVD should no longer hang when the input contains `NaN` or `Inf`
+
+#### rocSPARSE 2.5.2
+
+rocSPARSE 2.5.2 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed a memory leak in csritsv
+- Fixed a bug in csrsm and bsrsm
+
+#### rocThrust 2.18.0
+
+rocThrust 2.18.0 for ROCm 5.6.0
+
+##### Fixed 
+
+- `lower_bound`, `upper_bound`, and `binary_search` failed to compile for certain types.
+
+##### Changed
+
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+#### rocWMMA 1.1.0
+
+rocWMMA 1.1.0 for ROCm 5.6.0
+
+##### Added
+
+- Added cross-lane operation backends (Blend, Permute, Swizzle and Dpp)
+- Added GPU kernels for rocWMMA unit test pre-process and post-process operations (fill, validation)
+- Added performance gemm samples for half, single and double precision
+- Added rocWMMA cmake versioning
+- Added vectorized support in coordinate transforms
+- Included ROCm smi for runtime clock rate detection
+- Added fragment transforms for transpose and change data layout
+
+##### Changed
+
+- Default to GPU rocBLAS validation against rocWMMA
+- Re-enabled int8 gemm tests on gfx9
+- Upgraded to C++17
+- Restructured unit test folder for consistency
+- Consolidated rocWMMA samples common code
+
+#### Tensile 4.37.0
+
+Tensile 4.37.0 for ROCm 5.6.0
+
+##### Added
+
+- Added user driven tuning API
+- Added decision tree fallback feature
+- Added SingleBuffer + AtomicAdd option for GlobalSplitU
+- DirectToVgpr support for fp16 and Int8 with TN orientation
+- Added new test cases for various functions
+- Added SingleBuffer algorithm for ZGEMM/CGEMM
+- Added joblib for parallel map calls
+- Added support for MFMA + LocalSplitU + DirectToVgprA+B
+- Added asmcap check for MIArchVgpr
+- Added support for MFMA + LocalSplitU
+- Added frequency, power, and temperature data to the output
+
+##### Optimizations
+
+- Improved the performance of GlobalSplitU with SingleBuffer algorithm
+- Reduced the running time of the extended and pre_checkin tests
+- Optimized the Tailloop section of the assembly kernel
+- Optimized complex GEMM (fixed vgpr allocation, unified CGEMM and ZGEMM code in MulMIoutAlphaToArch)
+- Improved the performance of the second kernel of MultipleBuffer algorithm
+
+##### Changed
+
+- Updated custom kernels with 64-bit offsets
+- Adapted 64-bit offset arguments for assembly kernels
+- Improved temporary register re-use to reduce max sgpr usage
+- Removed some restrictions on VectorWidth and DirectToVgpr
+- Updated the dependency requirements for Tensile
+- Changed the range of AssertSummationElementMultiple
+- Modified the error messages for more clarity
+- Changed DivideAndReminder to vectorStaticRemainder in case quotient is not used
+- Removed dummy vgpr for vectorStaticRemainder
+- Removed tmpVgpr parameter from vectorStaticRemainder/Divide/DivideAndReminder
+- Removed qReg parameter from vectorStaticRemainder
+
+##### Fixed
+
+- Fixed tmp sgpr allocation to avoid over-writing values (alpha)
+- 64-bit offset parameters for post kernels
+- Fixed gfx908 CI test failures
+- Fixed offset calculation to prevent overflow for large offsets
+- Fixed issues when BufferLoad and BufferStore are equal to zero
+- Fixed StoreCInUnroll + DirectToVgpr + no useInitAccVgprOpt mismatch
+- Fixed DirectToVgpr + LocalSplitU + FractionalLoad mismatch
+- Fixed the memory access error related to StaggerU + large stride
+- Fixed ZGEMM 4x4 MatrixInst mismatch
+- Fixed DGEMM 4x4 MatrixInst mismatch
+- Fixed ASEM + GSU + NoTailLoop opt mismatch
+- Fixed AssertSummationElementMultiple + GlobalSplitU issues
+- Fixed ASEM + GSU + TailLoop inner unroll
+
+-------------------
+
 ## ROCm 5.5.1
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable no-duplicate-header -->
 ### What's New in This Release
 
+#### HIP SDK for Windows
+
+AMD is pleased to announce the availability of the HIP SDK for Windows as part
+of the ROCm platform. The
+[HIP SDK OS and GPU support page](https://rocm.docs.amd.com/en/docs-5.5.1/release/windows_support.html)
+lists the versions of Windows and GPUs validated by AMD. HIP SDK features on
+Windows are described in detail in our
+[What is ROCm?](https://rocm.docs.amd.com/en/docs-5.5.1/rocm.html#rocm-on-windows)
+page and differs from the Linux feature set. Visit
+[Quick Start](https://rocm.docs.amd.com/en/docs-5.5.1/deploy/windows/quick_start.html#)
+page to get started. Known issues are tracked on
+[GitHub](https://github.com/RadeonOpenCompute/ROCm/issues?q=is%3Aopen+label%3A5.5.1+label%3A%22Verified+Issue%22+label%3AWindows).
+
 #### HIP API Change
 
-The following HIP API is updated in the ROCm v5.5.1 release,
+The following HIP API is updated in the ROCm 5.5.1 release:
 
 ##### `hipDeviceSetCacheConfig`
 
@@ -37,10 +618,12 @@ The following HIP API is updated in the ROCm v5.5.1 release,
 | hipFFT | [1.0.11](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.5.1) |
 | hipSOLVER | [1.7.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.5.1) |
 | hipSPARSE | [2.3.5](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.5.1) |
+| MIOpen | [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.5.1) |
 | rccl | [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.5.1) |
 | rocALUTION | [2.1.8](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.5.1) |
 | rocBLAS | [2.47.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.5.1) |
 | rocFFT | [1.0.22](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.5.1) |
+| rocm-cmake | [0.8.1](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.5.1) |
 | rocPRIM | [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.5.1) |
 | rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.5.1) |
 | rocSOLVER | [3.21.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.5.1) |
@@ -80,6 +663,29 @@ The following hipcc changes are implemented in this release:
   - `hipCommander` at <https://github.com/ROCm-Developer-Tools/hip-tests/tree/develop/samples/1_Utils/hipCommander>
 
   Note that the samples will continue to be available in previous release branches.
+- Removal of gcnarch from hipDeviceProp_t structure
+- Addition of new fields in hipDeviceProp_t structure
+  - maxTexture1D
+  - maxTexture2D
+  - maxTexture1DLayered
+  - maxTexture2DLayered
+  - sharedMemPerMultiprocessor
+  - deviceOverlap
+  - asyncEngineCount
+  - surfaceAlignment
+  - unifiedAddressing
+  - computePreemptionSupported
+  - hostRegisterSupported
+  - uuid
+- Removal of deprecated code
+  - hip-hcc codes from hip code tree
+- Correct hipArray usage in HIP APIs such as hipMemcpyAtoH and hipMemcpyHtoA
+- HIPMEMCPY_3D fields correction to avoid truncation of "size_t" to "unsigned int" inside hipMemcpy3D()
+- Renaming of 'memoryType' in hipPointerAttribute_t structure to 'type'
+- Correct hipGetLastError to return the last error instead of last API call's return code
+- Update hipExternalSemaphoreHandleDesc to add "unsigned int reserved[16]"
+- Correct handling of flag values in hipIpcOpenMemHandle for hipIpcMemLazyEnablePeerAccess
+- Remove hiparray* and make it opaque with hipArray_t
 
 ##### New HIP APIs in This Release
 
@@ -348,10 +954,12 @@ Multiple HIP directed tests fail.
 | hipFFT | 1.0.10 ⇒ [1.0.11](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.5.0) |
 | hipSOLVER | 1.6.0 ⇒ [1.7.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.5.0) |
 | hipSPARSE | 2.3.3 ⇒ [2.3.5](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.5.0) |
+| MIOpen |  ⇒ [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.5.0) |
 | rccl | 2.13.4 ⇒ [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.5.0) |
 | rocALUTION | 2.1.3 ⇒ [2.1.8](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.5.0) |
 | rocBLAS | 2.46.0 ⇒ [2.47.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.5.0) |
 | rocFFT | 1.0.21 ⇒ [1.0.22](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.5.0) |
+| rocm-cmake | 0.8.0 ⇒ [0.8.1](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.5.0) |
 | rocPRIM | 2.12.0 ⇒ [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.5.0) |
 | rocRAND | 2.10.16 ⇒ [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.5.0) |
 | rocSOLVER | 3.20.0 ⇒ [3.21.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.5.0) |
@@ -441,6 +1049,24 @@ hipSPARSE 2.3.5 for ROCm 5.5.0
 - Improved documentation
 - Fixed a bug with deprecation messages when using gcc9 (Thanks @Maetveis)
 
+#### MIOpen 2.19.0
+
+MIOpen 2.19.0 for ROCm 5.5.0
+
+##### Added
+
+- ROCm 5.5 support for gfx1101 (Navi32)
+
+##### Changed
+
+- Tuning results for MLIR on ROCm 5.5
+- Bumping MLIR commit to 5.5.0 release tag
+
+##### Fixed
+
+- Fix 3d convolution Host API bug
+- [HOTFIX][MI200][FP16] Disabled ConvHipImplicitGemmBwdXdlops when FP16_ALT is required.
+
 #### rccl 2.15.5
 
 RCCL 2.15.5 for ROCm 5.5.0
@@ -552,6 +1178,18 @@ rocFFT 1.0.22 for ROCm 5.5.0
 - Removed zero-length twiddle table allocations, which fixes errors from hipMallocManaged.
 - Fixed incorrect freeing of HIP stream handles during twiddle computation when multiple devices are present.
 
+#### rocm-cmake 0.8.1
+
+rocm-cmake 0.8.1 for ROCm 5.5.0
+
+##### Fixed
+
+- ROCMInstallTargets: Added compatibility symlinks for included cmake files in `&lt;ROCM&gt;/lib/cmake/&lt;PACKAGE&gt;`.
+
+##### Changed
+
+- ROCMHeaderWrapper: The wrapper header deprecation message is now a deprecation warning.
+
 #### rocPRIM 2.13.0
 
 rocPRIM 2.13.0 for ROCm 5.5.0
@@ -867,6 +1505,7 @@ This issue is under investigation, and the known workaround is not to use -save-
 | rocALUTION | [2.1.3](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.4.3) |
 | rocBLAS | [2.46.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.4.3) |
 | rocFFT | 1.0.20 ⇒ [1.0.21](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.4.3) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.4.3) |
 | rocPRIM | [2.12.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.4.3) |
 | rocRAND | [2.10.16](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.4.3) |
 | rocSOLVER | [3.20.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.4.3) |
@@ -930,6 +1569,7 @@ This is a known issue and will be fixed in a future release.
 | rocALUTION | [2.1.3](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.4.2) |
 | rocBLAS | [2.46.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.4.2) |
 | rocFFT | [1.0.20](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.4.2) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.4.2) |
 | rocPRIM | [2.12.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.4.2) |
 | rocRAND | [2.10.16](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.4.2) |
 | rocSOLVER | [3.20.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.4.2) |
@@ -1019,6 +1659,7 @@ Maintenance update #3, combined with ROCm 5.4.1, now provides SRIOV virtualizati
 | rocALUTION | [2.1.3](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.4.1) |
 | rocBLAS | [2.46.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.4.1) |
 | rocFFT | 1.0.19 ⇒ [1.0.20](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.4.1) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.4.1) |
 | rocPRIM | [2.12.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.4.1) |
 | rocRAND | [2.10.16](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.4.1) |
 | rocSOLVER | [3.20.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.4.1) |
@@ -1135,6 +1776,8 @@ The `hipcc` and `hipconfig` Perl scripts are deprecated. In a future release, co
 >
 > There will be a transition period where the Perl scripts and compiled binaries are available  before the scripts are removed. There will be no functional difference between the Perl scripts and their compiled binary counterpart. No user action is required. Once these are available, users can optionally switch to `hipcc.bin` and `hipconfig.bin`. The `hipcc`/`hipconfig` soft link will be assimilated to point from `hipcc`/`hipconfig` to the respective compiled binaries as the default option.
 
+(5_4_0_filesystem_reorg_deprecation_notice)=
+
 ##### Linux Filesystem Hierarchy Standard for ROCm
 
 ROCm packages have adopted the Linux foundation filesystem hierarchy standard in this release to ensure ROCm components follow open source conventions for Linux-based distributions. While moving to a new filesystem hierarchy, ROCm ensures backward compatibility with its 5.1 version or older filesystem hierarchy. See below for a detailed explanation of the new filesystem hierarchy and backward compatibility.
@@ -1245,9 +1888,8 @@ The test was incorrectly using the `hipDeviceAttributePageableMemoryAccess` devi
 
 `hipHostMalloc()` allocates memory with fine-grained access by default when the environment variable `HIP_HOST_COHERENT=1` is used.
 
-For more information, refer to the HIP Programming Guide at
+For more information, refer to {doc}`hip:.doxygen/docBin/html/index`.
 
-<https://docs.amd.com/bundle/HIP-Programming-Guide-v5.4/page/Introduction_to_HIP_Programming_Guide.html>
 
 #### SoftHang with `hipStreamWithCUMask` test on AMD Instinct™
 
@@ -1278,6 +1920,7 @@ GPU IDs reported by ROCTracer and ROCProfiler or ROCm Tools are HSA Driver Node
 | rocALUTION | 2.1.0 ⇒ [2.1.3](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.4.0) |
 | rocBLAS | 2.45.0 ⇒ [2.46.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.4.0) |
 | rocFFT | 1.0.18 ⇒ [1.0.19](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.4.0) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.4.0) |
 | rocPRIM | 2.11.0 ⇒ [2.12.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.4.0) |
 | rocRAND | 2.10.15 ⇒ [2.10.16](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.4.0) |
 | rocSOLVER | 3.19.0 ⇒ [3.20.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.4.0) |
@@ -1605,6 +2248,7 @@ This issue is resolved with the following fixes to compilation failures:
 | rocALUTION | [2.1.0](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.3.3) |
 | rocBLAS | [2.45.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.3.3) |
 | rocFFT | [1.0.18](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.3.3) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.3.3) |
 | rocPRIM | [2.11.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.3.3) |
 | rocRAND | [2.10.15](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.3.3) |
 | rocSOLVER | [3.19.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.3.3) |
@@ -1674,6 +2318,7 @@ This issue is currently under investigation and will be resolved in a future rel
 | rocALUTION | [2.1.0](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.3.2) |
 | rocBLAS | [2.45.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.3.2) |
 | rocFFT | [1.0.18](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.3.2) |
+| rocm-cmake | [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.3.2) |
 | rocPRIM | [2.11.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.3.2) |
 | rocRAND | [2.10.15](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.3.2) |
 | rocSOLVER | [3.19.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.3.2) |
@@ -1857,6 +2502,7 @@ Workaround: To avoid the system crash, add `amd_iommu=on iommu=pt` as the kernel
 | rocALUTION | 2.0.3 ⇒ [2.1.0](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.3.0) |
 | rocBLAS | 2.44.0 ⇒ [2.45.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.3.0) |
 | rocFFT | 1.0.17 ⇒ [1.0.18](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.3.0) |
+| rocm-cmake |  ⇒ [0.8.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.3.0) |
 | rocPRIM | 2.10.14 ⇒ [2.11.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.3.0) |
 | rocRAND | 2.10.14 ⇒ [2.10.15](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.3.0) |
 | rocSOLVER | 3.18.0 ⇒ [3.19.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.3.0) |
@@ -2039,6 +2685,21 @@ rocFFT 1.0.18 for ROCm 5.3.0
   An example is 98^3 R2C out-of-place.
 - Fixed bugs in SBRC_ERC type.
 
+#### rocm-cmake 0.8.0
+
+rocm-cmake 0.8.0 for ROCm 5.3.0
+
+##### Fixed
+
+- Fixed error in prerm scripts created by `rocm_create_package` that could break uninstall for packages using the `PTH` option.
+
+##### Changed
+
+- `ROCM_USE_DEV_COMPONENT` set to on by default for all platforms. This means that Windows will now generate runtime and devel packages by default
+- ROCMInstallTargets now defaults `CMAKE_INSTALL_LIBDIR` to `lib` if not otherwise specified.
+- Changed default Debian compression type to xz and enabled multi-threaded package compression.
+- `rocm_create_package` will no longer warn upon failure to determine version of program rpmbuild.
+
 #### rocPRIM 2.11.0
 
 rocPRIM 2.11.0 for ROCm 5.3.0
@@ -2561,7 +3222,8 @@ The new APIs for virtual memory management are as follows:
   hipError_t hipMemUnmap(void* ptr, size_t size);
   ```
 
-For more information, refer to the HIP API documentation at <https://docs.amd.com/bundle/HIP_API_Guide/page/modules.html>
+For more information, refer to the HIP API documentation at
+{doc}`hip:.doxygen/docBin/html/modules`.
 
 ##### Planned HIP Changes in Future Releases
 
@@ -2577,7 +3239,8 @@ This release introduces a new ROCm C++ library for accelerating mixed precision
 
 rocWMMA is released as a header library and includes test and sample projects to validate and illustrate example usages of the C++ API. GEMM matrix multiplication is used as primary validation given the heavy precedent for the library. However, the usage portfolio is growing significantly and demonstrates different ways rocWMMA may be consumed.
 
-For more information, refer to <https://docs.amd.com/category/libraries>.
+For more information, refer to
+[Communication Libraries](../../../../docs/reference/gpu_libraries/communication.md).
 
 #### OpenMP Enhancements in This Release
 
@@ -3171,7 +3834,8 @@ ROCDebugger Machine Interface (MI) extends support to lanes. The following enhan
 
 - MI varobjs are now lane-aware.
 
-For more information, refer to the ROC Debugger User Guide at <https://docs.amd.com>.
+For more information, refer to the ROC Debugger User Guide at
+{doc}`ROCgdb <rocgdb:index>`.
 
 ##### Enhanced - clone-inferior Command
 
@@ -3193,7 +3857,7 @@ This release includes support for AMD Radeon™ Pro W6800, in addition to other
 
 - Various other bug fixes and performance improvements
 
-For more information, see <https://docs.amd.com/bundle/MIOpen_gh-pages/page/releasenotes.html>
+For more information, see {doc}`Documentation <miopen:index>`.
 
 #### Checkpoint Restore Support With CRIU
 

RELEASE.md

@@ -15,40 +15,568 @@ The release notes for the ROCm platform.
 
 -------------------
 
-## ROCm 5.5.1
+## ROCm 5.6.0
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable no-duplicate-header -->
-### What's New in This Release
+<!-- markdownlint-disable header-increment -->
+#### Release Highlights
 
-#### HIP API Change
+ROCm 5.6 consists of several AI software ecosystem improvements to our fast-growing user base. A few examples include:
 
-The following HIP API is updated in the ROCm v5.5.1 release,
+- New documentation portal at https://rocm.docs.amd.com
+- Ongoing software enhancements for LLMs, ensuring full compliance with the HuggingFace unit test suite
+- OpenAI Triton, CuPy, HIP Graph support, and many other library performance enhancements
+- Improved ROCm deployment and development tools, including CPU-GPU (rocGDB) debugger, profiler, and docker containers
+- New pseudorandom generators are available in rocRAND.  Added support for half-precision transforms in hipFFT/rocFFT.  Added LU refactorization and linear system solver for sparse matrices in rocSOLVER.  
 
-##### `hipDeviceSetCacheConfig`
+#### OS and GPU Support Changes
 
-- The return value for `hipDeviceSetCacheConfig` is updated from `hipErrorNotSupported` to `hipSuccess`
+- SLES15 SP5 support was added this release. SLES15 SP3 support was dropped.
+- AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively referred to as gfx906 GPUs) will be entering the maintenance mode starting Q3 2023. This will be aligned with ROCm 5.7 GA release date.
+  - No new features and performance optimizations will be supported for the gfx906 GPUs beyond ROCm 5.7
+  - Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance [EOM])(will be aligned with the closest ROCm release)
+  - Bug fixes during the maintenance will be made to the next ROCm point release
+  - Bug fixes will not be back ported to older ROCm releases for this SKU
+  - Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM.
 
-### Library Changes in ROCM 5.5.1
+#### AMDSMI CLI 23.0.0.4
+
+##### Added
+
+- AMDSMI CLI tool enabled for Linux Bare Metal & Guest
+
+- Package: amd-smi-lib
+ 
+##### Known Issues
+
+- not all Error Correction Code (ECC) fields are currently supported
+
+- RHEL 8 & SLES 15 have extra install steps
+
+#### Kernel Modules (DKMS)
+
+##### Fixes
+
+- Stability fix for multi GPU system reproducilble via ROCm_Bandwidth_Test as reported in [Issue 2198](https://github.com/RadeonOpenCompute/ROCm/issues/2198).
+
+#### HIP 5.6 (For ROCm 5.6)
+
+##### Optimizations
+
+- Consolidation of hipamd, rocclr and OpenCL projects in clr
+- Optimized lock for graph global capture mode
+
+##### Added
+
+- Added hipRTC support for amd_hip_fp16
+- Added hipStreamGetDevice implementation to get the device associated with the stream
+- Added HIP_AD_FORMAT_SIGNED_INT16 in hipArray formats
+- hipArrayGetInfo for getting information about the specified array
+- hipArrayGetDescriptor for getting 1D or 2D array descriptor
+- hipArray3DGetDescriptor to get 3D array descriptor
+
+##### Changed
+
+- hipMallocAsync to return success for zero size allocation to match hipMalloc
+- Separation of hipcc perl binaries from HIP project to hipcc project. hip-devel package depends on newly added hipcc package
+- Consolidation of hipamd, ROCclr, and OpenCL repositories into a single repository called clr. Instructions are updated to build HIP from sources in the HIP Installation guide
+- Removed hipBusBandwidth and hipCommander samples from hip-tests
+
+##### Fixed
+
+- Fixed regression in hipMemCpyParam3D when offset is applied
+
+##### Known Issues
+
+- Limited testing on xnack+ configuration
+  - Multiple HIP tests failures (gpuvm fault or hangs)
+- hipSetDevice and hipSetDeviceFlags APIs return hipErrorInvalidDevice instead of hipErrorNoDevice, on a system without GPU
+- Known memory leak when code object files are loaded/unloaded via hipModuleLoad/hipModuleUnload APIs. Issue will be fixed in a future ROCm release
+
+##### Upcoming changes in future release
+
+- Removal of gcnarch from hipDeviceProp_t structure
+- Addition of new fields in hipDeviceProp_t structure
+  - maxTexture1D
+  - maxTexture2D
+  - maxTexture1DLayered
+  - maxTexture2DLayered
+  - sharedMemPerMultiprocessor
+  - deviceOverlap
+  - asyncEngineCount
+  - surfaceAlignment
+  - unifiedAddressing
+  - computePreemptionSupported
+  - uuid
+- Removal of deprecated code
+  - hip-hcc codes from hip code tree
+- Correct hipArray usage in HIP APIs such as hipMemcpyAtoH and hipMemcpyHtoA
+- HIPMEMCPY_3D fields correction (unsigned int -> size_t)
+- Renaming of 'memoryType' in hipPointerAttribute_t structure to 'type'
+
+#### ROCgdb-13 (For ROCm 5.6.0)
+
+##### Optimized
+
+- Improved performances when handling the end of a process with a large number of threads.
+
+Known Issues
+
+- On certain configurations, ROCgdb can show the following warning message:
+
+  `warning: Probes-based dynamic linker interface failed. Reverting to original interface.`
+
+  This does not affect ROCgdb's functionalities.
+
+#### ROCprofiler (For ROCm 5.6.0)
+
+In ROCm 5.6 the `rocprofilerv1` and `rocprofilerv2` include and library files of
+ROCm 5.5 are split into separate files. The `rocmtools` files that were
+deprecated in ROCm 5.5 have been removed.
+
+  | ROCm 5.6        | rocprofilerv1                       | rocprofilerv2                          |
+  |-----------------|-------------------------------------|----------------------------------------|
+  | **Tool script** | `bin/rocprof`                       | `bin/rocprofv2`                        |
+  | **API include** | `include/rocprofiler/rocprofiler.h` | `include/rocprofiler/v2/rocprofiler.h` |
+  | **API library** | `lib/librocprofiler.so.1`           | `lib/librocprofiler.so.2`              |
+
+The ROCm Profiler Tool that uses `rocprofilerV1` can be invoked using the
+following command:
+
+```sh
+$ rocprof …
+```
+
+To write a custom tool based on the `rocprofilerV1` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/rocprofiler.h> // Use the rocprofilerV1 API
+int main() {
+  // Use the rocprofilerV1 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.1`.
+
+The ROCm Profiler that uses `rocprofilerV2` API can be invoked using the
+following command:
+
+```sh
+$ rocprofv2 …
+```
+
+To write a custom tool based on the `rocprofilerV2` API do the following:
+
+```C
+main.c:
+#include <rocprofiler/v2/rocprofiler.h> // Use the rocprofilerV2 API
+int main() {
+  // Use the rocprofilerV2 API
+  return 0;
+}
+```
+
+This can be built in the following manner:
+
+```sh
+$ gcc main.c -I/opt/rocm-5.6.0/include -L/opt/rocm-5.6.0/lib -lrocprofiler64-v2
+```
+
+The resulting `a.out` will depend on
+`/opt/rocm-5.6.0/lib/librocprofiler64.so.2`.
+
+##### Optimized
+
+- Improved Test Suite
+
+##### Added
+
+- 'end_time' need to be disabled in roctx_trace.txt
+
+##### Fixed
+
+- rocprof in ROcm/5.4.0 gpu selector broken.
+- rocprof in ROCm/5.4.1 fails to generate kernel info.
+- rocprof clobbers LD_PRELOAD.
+
+### Library Changes in ROCM 5.6.0
 
 | Library | Version |
 |---------|---------|
-| hipBLAS | [0.54.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.5.1) |
-| hipCUB | [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.5.1) |
-| hipFFT | [1.0.11](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.5.1) |
-| hipSOLVER | [1.7.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.5.1) |
-| hipSPARSE | [2.3.5](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.5.1) |
-| rccl | [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.5.1) |
-| rocALUTION | [2.1.8](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.5.1) |
-| rocBLAS | [2.47.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.5.1) |
-| rocFFT | [1.0.22](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.5.1) |
-| rocPRIM | [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.5.1) |
-| rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.5.1) |
-| rocSOLVER | [3.21.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.5.1) |
-| rocSPARSE | [2.5.1](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.5.1) |
-| rocThrust | [2.17.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.5.1) |
-| rocWMMA | [1.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.5.1) |
-| Tensile | [4.36.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.5.1) |
+| hipBLAS |  ⇒ [1.0.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.6.0) |
+| hipCUB |  ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.6.0) |
+| hipFFT |  ⇒ [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.6.0) |
+| hipSOLVER |  ⇒ [1.8.0](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.6.0) |
+| hipSPARSE |  ⇒ [2.3.6](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.6.0) |
+| MIOpen |  ⇒ [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.6.0) |
+| rccl |  ⇒ [2.15.5](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.6.0) |
+| rocALUTION |  ⇒ [2.1.9](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.6.0) |
+| rocBLAS |  ⇒ [3.0.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.6.0) |
+| rocFFT |  ⇒ [1.0.23](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.6.0) |
+| rocm-cmake |  ⇒ [0.9.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.6.0) |
+| rocPRIM |  ⇒ [2.13.0](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.6.0) |
+| rocRAND |  ⇒ [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.6.0) |
+| rocSOLVER |  ⇒ [3.22.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.6.0) |
+| rocSPARSE |  ⇒ [2.5.2](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.6.0) |
+| rocThrust |  ⇒ [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.6.0) |
+| rocWMMA |  ⇒ [1.1.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.6.0) |
+| Tensile |  ⇒ [4.37.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.6.0) |
 
-## Older versions
+#### hipBLAS 1.0.0
 
-The release notes for older versions can be found in [the changelog](./CHANGELOG.md).
+hipBLAS 1.0.0 for ROCm 5.6.0
+
+##### Changed
+
+- added const qualifier to hipBLAS functions (swap, sbmv, spmv, symv, trsm) where missing
+
+##### Removed
+
+- removed support for deprecated hipblasInt8Datatype_t enum
+- removed support for deprecated hipblasSetInt8Datatype and hipblasGetInt8Datatype functions
+
+##### Deprecated
+
+- in-place trmm is deprecated. It will be replaced by trmm which includes both in-place and
+  out-of-place functionality
+
+#### hipCUB 2.13.1
+
+hipCUB 2.13.1 for ROCm 5.6.0
+
+##### Added
+
+- Benchmarks for `BlockShuffle`, `BlockLoad`, and `BlockStore`.
+
+##### Changed
+
+- CUB backend references CUB and Thrust version 1.17.2.
+- Improved benchmark coverage of `BlockScan` by adding `ExclusiveScan`, benchmark coverage of `BlockRadixSort` by adding `SortBlockedToStriped`, and benchmark coverage of `WarpScan` by adding `Broadcast`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+##### Known Issues
+
+- `BlockRadixRankMatch` is currently broken under the rocPRIM backend.
+- `BlockRadixRankMatch` with a warp size that does not exactly divide the block size is broken under the CUB backend.
+
+#### hipFFT 1.0.12
+
+hipFFT 1.0.12 for ROCm 5.6.0
+
+##### Added
+
+- Implemented the hipfftXtMakePlanMany, hipfftXtGetSizeMany, hipfftXtExec APIs, to allow requesting half-precision transforms.
+
+##### Changed
+
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+#### hipSOLVER 1.8.0
+
+hipSOLVER 1.8.0 for ROCm 5.6.0
+
+##### Added
+
+- Added compatibility API with hipsolverRf prefix
+
+#### hipSPARSE 2.3.6
+
+hipSPARSE 2.3.6 for ROCm 5.6.0
+
+##### Added
+
+- Added SpGEMM algorithms
+
+##### Changed
+
+- For hipsparseXbsr2csr and hipsparseXcsr2bsr, blockDim == 0 now returns HIPSPARSE_STATUS_INVALID_SIZE
+
+#### MIOpen 2.19.0
+
+MIOpen 2.19.0 for ROCm 5.6.0
+
+##### Added
+
+- ROCm 5.5 support for gfx1101 (Navi32)
+
+##### Changed
+
+- Tuning results for MLIR on ROCm 5.5
+- Bumping MLIR commit to 5.5.0 release tag
+
+##### Fixed
+
+- Fix 3d convolution Host API bug
+- [HOTFIX][MI200][FP16] Disabled ConvHipImplicitGemmBwdXdlops when FP16_ALT is required.
+
+#### rccl 2.15.5
+
+RCCL 2.15.5 for ROCm 5.6.0
+
+##### Changed
+
+- Compatibility with NCCL 2.15.5
+- Unit test executable renamed to rccl-UnitTests
+
+##### Added
+
+- HW-topology aware binary tree implementation
+- Experimental support for MSCCL
+- New unit tests for hipGraph support
+- NPKit integration
+
+##### Fixed
+
+- rocm-smi ID conversion
+- Support for HIP_VISIBLE_DEVICES for unit tests
+- Support for p2p transfers to non (HIP) visible devices
+
+##### Removed
+
+- Removed TransferBench from tools.  Exists in standalone repo: https://github.com/ROCmSoftwarePlatform/TransferBench
+
+#### rocALUTION 2.1.9
+
+rocALUTION 2.1.9 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed synchronization issues in level 1 routines
+
+#### rocBLAS 3.0.0
+
+rocBLAS 3.0.0 for ROCm 5.6.0
+
+##### Optimizations
+
+- Improved performance of Level 2 rocBLAS GEMV on gfx90a GPU for non-transposed problems having small matrices and larger batch counts. Performance enhanced for problem sizes when m and n &lt;= 32 and batch_count &gt;= 256.
+- Improved performance of rocBLAS syr2k for single, double, and double-complex precision, and her2k for double-complex precision. Slightly improved performance for general sizes on gfx90a.
+
+##### Added
+
+- Added bf16 inputs and f32 compute support to Level 1 rocBLAS Extension functions axpy_ex, scal_ex and nrm2_ex.
+
+##### Deprecated
+
+- trmm inplace is deprecated. It will be replaced by trmm that has both inplace and out-of-place functionality
+- rocblas_query_int8_layout_flag() is deprecated and will be removed in a future release
+- rocblas_gemm_flags_pack_int8x4 enum is deprecated and will be removed in a future release
+- rocblas_set_device_memory_size() is deprecated and will be replaced by a future function rocblas_increase_device_memory_size()
+- rocblas_is_user_managing_device_memory() is deprecated and will be removed in a future release
+
+##### Removed
+
+- is_complex helper was deprecated and now removed.  Use rocblas_is_complex instead.
+- The enum truncate_t and the value truncate was deprecated and now removed from. It was replaced by rocblas_truncate_t and rocblas_truncate, respectively.
+- rocblas_set_int8_type_for_hipblas was deprecated and is now removed.
+- rocblas_get_int8_type_for_hipblas was deprecated and is now removed.
+
+##### Dependencies
+
+- build only dependency on python joblib added as used by Tensile build
+- fix for cmake install on some OS when performed by install.sh -d --cmake_install
+
+##### Fixed
+
+- make trsm offset calculations 64 bit safe
+
+##### Changed
+
+- refactor rotg test code
+
+#### rocFFT 1.0.23
+
+rocFFT 1.0.23 for ROCm 5.6.0
+
+##### Added
+
+- Implemented half-precision transforms, which can be requested by passing rocfft_precision_half to rocfft_plan_create.
+- Implemented a hierarchical solution map which saves how to decompose a problem and the kernels to be used.
+- Implemented a first version of offline-tuner to support tuning kernels for C2C/Z2Z problems.
+
+##### Changed
+
+- Replaced std::complex with hipComplex data types for data generator.
+- FFT plan dimensions are now sorted to be row-major internally where possible, which produces better plans if the dimensions were accidentally specified in a different order (column-major, for example).
+- Added --precision argument to benchmark/test clients.  --double is still accepted but is deprecated as a method to request a double-precision transform.
+
+##### Fixed
+
+- Fixed over-allocation of LDS in some real-complex kernels, which was resulting in kernel launch failure.
+
+#### rocm-cmake 0.9.0
+
+rocm-cmake 0.9.0 for ROCm 5.6.0
+
+##### Added
+
+- Added the option ROCM_HEADER_WRAPPER_WERROR
+    - Compile-time C macro in the wrapper headers causes errors to be emitted instead of warnings.
+    - Configure-time CMake option sets the default for the C macro.
+
+#### rocPRIM 2.13.0
+
+rocPRIM 2.13.0 for ROCm 5.6.0
+
+##### Added
+
+- New block level `radix_rank` primitive.
+- New block level `radix_rank_match` primitive.
+- Added a stable block sorting implementation. This be used with `block_sort` by using the `block_sort_algorithm::stable_merge_sort` algorithm.
+
+##### Changed
+
+- Improved the performance of `block_radix_sort` and `device_radix_sort`.
+- Improved the performance of `device_merge_sort`.
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core). Contributed by: [v01dXYZ](https://github.com/v01dXYZ).
+
+##### Known Issues
+
+- Disabled GPU error messages relating to incorrect warp operation usage with Navi GPUs on Windows, due to GPU printf performance issues on Windows.
+- When `ROCPRIM_DISABLE_LOOKBACK_SCAN` is set, `device_scan` fails for input sizes bigger than `scan_config::size_limit`, which defaults to `std::numeric_limits&lt;unsigned int&gt;::max()`.
+
+#### rocRAND 2.10.17
+
+rocRAND 2.10.17 for ROCm 5.6.0
+
+##### Added
+
+- MT19937 pseudo random number generator based on M. Matsumoto and T. Nishimura, 1998, Mersenne Twister: A 623-dimensionally equidistributed uniform pseudorandom number generator.
+- New benchmark for the device API using Google Benchmark, `benchmark_rocrand_device_api`, replacing `benchmark_rocrand_kernel`. `benchmark_rocrand_kernel` is deprecated and will be removed in a future version. Likewise, `benchmark_curand_host_api` is added to replace `benchmark_curand_generate` and `benchmark_curand_device_api` is added to replace `benchmark_curand_kernel`.
+- experimental HIP-CPU feature
+- ThreeFry pseudorandom number generator based on Salmon et al., 2011, &#34;Parallel random numbers: as easy as 1, 2, 3&#34;.
+
+##### Changed
+
+- Python 2.7 is no longer officially supported.
+
+#### rocSOLVER 3.22.0
+
+rocSOLVER 3.22.0 for ROCm 5.6.0
+
+##### Added
+
+- LU refactorization for sparse matrices
+    - CSRRF_ANALYSIS
+    - CSRRF_SUMLU
+    - CSRRF_SPLITLU
+    - CSRRF_REFACTLU
+- Linear system solver for sparse matrices
+    - CSRRF_SOLVE
+- Added type `rocsolver_rfinfo` for use with sparse matrix routines
+
+##### Optimized
+
+- Improved the performance of BDSQR and GESVD when singular vectors are requested
+
+##### Fixed
+
+- BDSQR and GESVD should no longer hang when the input contains `NaN` or `Inf`
+
+#### rocSPARSE 2.5.2
+
+rocSPARSE 2.5.2 for ROCm 5.6.0
+
+##### Improved
+
+- Fixed a memory leak in csritsv
+- Fixed a bug in csrsm and bsrsm
+
+#### rocThrust 2.18.0
+
+rocThrust 2.18.0 for ROCm 5.6.0
+
+##### Fixed 
+
+- `lower_bound`, `upper_bound`, and `binary_search` failed to compile for certain types.
+
+##### Changed
+
+- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
+
+#### rocWMMA 1.1.0
+
+rocWMMA 1.1.0 for ROCm 5.6.0
+
+##### Added
+
+- Added cross-lane operation backends (Blend, Permute, Swizzle and Dpp)
+- Added GPU kernels for rocWMMA unit test pre-process and post-process operations (fill, validation)
+- Added performance gemm samples for half, single and double precision
+- Added rocWMMA cmake versioning
+- Added vectorized support in coordinate transforms
+- Included ROCm smi for runtime clock rate detection
+- Added fragment transforms for transpose and change data layout
+
+##### Changed
+
+- Default to GPU rocBLAS validation against rocWMMA
+- Re-enabled int8 gemm tests on gfx9
+- Upgraded to C++17
+- Restructured unit test folder for consistency
+- Consolidated rocWMMA samples common code
+
+#### Tensile 4.37.0
+
+Tensile 4.37.0 for ROCm 5.6.0
+
+##### Added
+
+- Added user driven tuning API
+- Added decision tree fallback feature
+- Added SingleBuffer + AtomicAdd option for GlobalSplitU
+- DirectToVgpr support for fp16 and Int8 with TN orientation
+- Added new test cases for various functions
+- Added SingleBuffer algorithm for ZGEMM/CGEMM
+- Added joblib for parallel map calls
+- Added support for MFMA + LocalSplitU + DirectToVgprA+B
+- Added asmcap check for MIArchVgpr
+- Added support for MFMA + LocalSplitU
+- Added frequency, power, and temperature data to the output
+
+##### Optimizations
+
+- Improved the performance of GlobalSplitU with SingleBuffer algorithm
+- Reduced the running time of the extended and pre_checkin tests
+- Optimized the Tailloop section of the assembly kernel
+- Optimized complex GEMM (fixed vgpr allocation, unified CGEMM and ZGEMM code in MulMIoutAlphaToArch)
+- Improved the performance of the second kernel of MultipleBuffer algorithm
+
+##### Changed
+
+- Updated custom kernels with 64-bit offsets
+- Adapted 64-bit offset arguments for assembly kernels
+- Improved temporary register re-use to reduce max sgpr usage
+- Removed some restrictions on VectorWidth and DirectToVgpr
+- Updated the dependency requirements for Tensile
+- Changed the range of AssertSummationElementMultiple
+- Modified the error messages for more clarity
+- Changed DivideAndReminder to vectorStaticRemainder in case quotient is not used
+- Removed dummy vgpr for vectorStaticRemainder
+- Removed tmpVgpr parameter from vectorStaticRemainder/Divide/DivideAndReminder
+- Removed qReg parameter from vectorStaticRemainder
+
+##### Fixed
+
+- Fixed tmp sgpr allocation to avoid over-writing values (alpha)
+- 64-bit offset parameters for post kernels
+- Fixed gfx908 CI test failures
+- Fixed offset calculation to prevent overflow for large offsets
+- Fixed issues when BufferLoad and BufferStore are equal to zero
+- Fixed StoreCInUnroll + DirectToVgpr + no useInitAccVgprOpt mismatch
+- Fixed DirectToVgpr + LocalSplitU + FractionalLoad mismatch
+- Fixed the memory access error related to StaggerU + large stride
+- Fixed ZGEMM 4x4 MatrixInst mismatch
+- Fixed DGEMM 4x4 MatrixInst mismatch
+- Fixed ASEM + GSU + NoTailLoop opt mismatch
+- Fixed AssertSummationElementMultiple + GlobalSplitU issues
+- Fixed ASEM + GSU + TailLoop inner unroll

default.xml

@@ -12,44 +12,41 @@ fetch="https://github.com/GPUOpen-ProfessionalCompute-Libraries/" />
 fetch="https://github.com/GPUOpen-Tools/" />
     <remote name="KhronosGroup"
 fetch="https://github.com/KhronosGroup/" />
-    <default revision="refs/tags/rocm-5.5.1"
+    <default revision="refs/tags/rocm-5.6.0"
      remote="roc-github"
      sync-c="true"
      sync-j="4" />
 <!--list of projects for ROCM-->
-    <project name="ROCK-Kernel-Driver" />
-    <project name="ROCT-Thunk-Interface" />
-    <project name="ROCR-Runtime" />
-    <project name="rocm_smi_lib" />
-    <project name="rocm-core" />
-    <project name="rocm-cmake" />
-    <project name="rocminfo" />
+    <project name="ROCK-Kernel-Driver" remote="roc-github" />
+    <project name="ROCT-Thunk-Interface" remote="roc-github" />
+    <project name="ROCR-Runtime" remote="roc-github" />
+    <project name="rocm_smi_lib" remote="roc-github" />
+    <project name="rocm-core" remote="roc-github" />
+    <project name="rocm-cmake" remote="roc-github" />
+    <project name="rocminfo" remote="roc-github" />
     <project name="rocprofiler" remote="rocm-devtools" />
     <project name="roctracer" remote="rocm-devtools" />
-    <project name="ROCm-OpenCL-Runtime" />
     <project path="ROCm-OpenCL-Runtime/api/opencl/khronos/icd" name="OpenCL-ICD-Loader" remote="KhronosGroup" revision="6c03f8b58fafd9dd693eaac826749a5cfad515f8" />
-    <project name="clang-ocl" />
+    <project name="clang-ocl" remote="roc-github" />
 <!--HIP Projects-->
     <project name="HIP" remote="rocm-devtools" />
-    <project name="hipamd" remote="rocm-devtools" />
+    <project name="clr" remote="rocm-devtools" />
     <project name="HIP-Examples" remote="rocm-devtools" />
-    <project name="ROCclr" remote="rocm-devtools" />
     <project name="HIPIFY" remote="rocm-devtools" />
     <project name="HIPCC" remote="rocm-devtools" />
 <!-- The following projects are all associated with the AMDGPU LLVM compiler -->
-    <project name="llvm-project" />
-    <project name="ROCm-Device-Libs" />
-    <project name="atmi" />
-    <project name="ROCm-CompilerSupport" />
+    <project name="llvm-project" remote="roc-github" />
+    <project name="ROCm-Device-Libs" remote="roc-github" />
+    <project name="ROCm-CompilerSupport" remote="roc-github" />
     <project name="rocr_debug_agent" remote="rocm-devtools" />
-    <project name="rocm_bandwidth_test" />
+    <project name="rocm_bandwidth_test" remote="roc-github" />
     <project name="half" remote="rocm-swplat" revision="37742ce15b76b44e4b271c1e66d13d2fa7bd003e" />
     <project name="RCP" remote="gpuopen-tools" revision="3a49405a1500067c49d181844ec90aea606055bb" />
 <!-- gdb projects -->
     <project name="ROCgdb" remote="rocm-devtools" />
     <project name="ROCdbgapi" remote="rocm-devtools" />
 <!-- ROCm Libraries -->
-    <project name="rdc" />
+    <project name="rdc" remote="roc-github" />
     <project groups="mathlibs" name="rocBLAS" remote="rocm-swplat" />
     <project groups="mathlibs" name="Tensile" remote="rocm-swplat" />
     <project groups="mathlibs" name="hipBLAS" remote="rocm-swplat" />
@@ -61,7 +58,6 @@ fetch="https://github.com/KhronosGroup/" />
     <project groups="mathlibs" name="hipSOLVER" remote="rocm-swplat" />
     <project groups="mathlibs" name="hipSPARSE" remote="rocm-swplat" />
     <project groups="mathlibs" name="rocALUTION" remote="rocm-swplat" />
-    <project name="MIOpenGEMM" remote="rocm-swplat" />
     <project name="MIOpen" remote="rocm-swplat" />
     <project groups="mathlibs" name="rccl" remote="rocm-swplat" />
     <project name="MIVisionX" remote="gpuopen-libs" />

docs/about.md

@@ -5,9 +5,9 @@ Documentation is built using open source toolchains. Contributions to our
 documentation is encouraged and welcome. As a contributor, please familiarize
 yourself with our documentation toolchain.
 
-## ReadTheDocs
+## Read The Docs
 
-[ReadTheDocs](https://docs.readthedocs.io/en/stable/) is our front end for the
+[Read the Docs](https://docs.readthedocs.io/en/stable/) is our front end for the
 our documentation. By front end, this is the tool that serves our HTML based
 documentation to our end users.
 

docs/conf.py

@@ -14,12 +14,28 @@ shutil.copy2('../RELEASE.md','./release.md')
 # Keep capitalization due to similar linking on GitHub's markdown preview.
 shutil.copy2('../CHANGELOG.md','./CHANGELOG.md')
 
+latex_engine = "xelatex"
+
+# configurations for PDF output by Read the Docs
+project = "ROCm Documentation"
+author = "Advanced Micro Devices, Inc."
+copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved."
+version = "5.6.0"
+release = "5.6.0"
+
+
 setting_all_article_info = True
-all_article_info_os = ["linux"]
+all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""
 
 # pages with specific settings
 article_pages = [
+    {
+        "file":"release",
+        "os":["linux", "windows"],
+        "date":"2023-07-27"
+    },
+
     {"file":"deploy/linux/index", "os":["linux"]},
     {"file":"deploy/linux/install_overview", "os":["linux"]},
     {"file":"deploy/linux/prerequisites", "os":["linux"]},
@@ -30,7 +46,20 @@ article_pages = [
     {"file":"deploy/linux/package_manager_integration", "os":["linux"]},
     {"file":"deploy/docker", "os":["linux"]},
     
+    {"file":"deploy/windows/cli/index", "os":["windows"]},
+    {"file":"deploy/windows/cli/install", "os":["windows"]},
+    {"file":"deploy/windows/cli/uninstall", "os":["windows"]},
+    {"file":"deploy/windows/cli/upgrade", "os":["windows"]},
+    {"file":"deploy/windows/gui/index", "os":["windows"]},
+    {"file":"deploy/windows/gui/install", "os":["windows"]},
+    {"file":"deploy/windows/gui/uninstall", "os":["windows"]},
+    {"file":"deploy/windows/gui/upgrade", "os":["windows"]},
+    {"file":"deploy/windows/index", "os":["windows"]},
+    {"file":"deploy/windows/prerequisites", "os":["windows"]},
+    {"file":"deploy/windows/quick_start", "os":["windows"]},
+
     {"file":"release/gpu_os_support", "os":["linux"]},
+    {"file":"release/windows_support", "os":["windows"]},
     {"file":"release/docker_support_matrix", "os":["linux"]},
     
     {"file":"reference/gpu_libraries/communication", "os":["linux"]},
@@ -57,7 +86,7 @@ article_pages = [
 
 external_toc_path = "./sphinx/_toc.yml"
 
-docs_core = ROCmDocs("ROCm Documentation Home")
+docs_core = ROCmDocs("ROCm 5.6.0 Documentation Home")
 docs_core.setup()
 
 external_projects_current_project = "rocm"

docs/data/deploy/quick_start_windows/image planning

@@ -1 +0,0 @@
-

docs/deploy/linux/installer/index.md

@@ -21,7 +21,7 @@ Instructions for upgrading an existing ROCm installation.
 :link: uninstall
 :link-type: doc
 
-Steps for removing ROCm packages libraries and tools.
+Steps for removing ROCm packages, libraries and tools.
 :::
 
 ::::

docs/deploy/linux/installer/install.md

@@ -18,8 +18,8 @@ following commands based on your distribution.
 
 ```shell
 sudo apt update
-wget https://repo.radeon.com/amdgpu-install/5.5.1/ubuntu/focal/amdgpu-install_5.5.50501-1_all.deb
-sudo apt install ./amdgpu-install_5.5.50501-1_all.deb
+wget https://repo.radeon.com/amdgpu-install/5.6/ubuntu/focal/amdgpu-install_5.6.50600-1_all.deb
+sudo apt install ./amdgpu-install_5.6.50600-1_all.deb
 ```
 
 :::
@@ -28,8 +28,8 @@ sudo apt install ./amdgpu-install_5.5.50501-1_all.deb
 
 ```shell
 sudo apt update
-wget https://repo.radeon.com/amdgpu-install/5.5.1/ubuntu/jammy/amdgpu-install_5.5.50501-1_all.deb
-sudo apt install ./amdgpu-install_5.5.50501-1_all.deb
+wget https://repo.radeon.com/amdgpu-install/5.6/ubuntu/jammy/amdgpu-install_5.6.50600-1_all.deb
+sudo apt install ./amdgpu-install_5.6.50600-1_all.deb
 ```
 
 :::
@@ -39,21 +39,21 @@ sudo apt install ./amdgpu-install_5.5.50501-1_all.deb
 :sync: RHEL
 
 ::::{tab-set}
-:::{tab-item} RHEL 8.6
-:sync: RHEL-8.6
-:sync: RHEL-8
-
-```shell
-sudo yum install https://repo.radeon.com/amdgpu-install/5.5.1/rhel/8.6/amdgpu-install-5.5.50501-1.el8.noarch.rpm
-```
-
-:::
 :::{tab-item} RHEL 8.7
 :sync: RHEL-8.7
 :sync: RHEL-8
 
 ```shell
-sudo yum install https://repo.radeon.com/amdgpu-install/5.5.1/rhel/8.7/amdgpu-install-5.5.50501-1.el8.noarch.rpm
+sudo yum install https://repo.radeon.com/amdgpu-install/5.6/rhel/8.7/amdgpu-install-5.6.50600-1.el8.noarch.rpm
+```
+
+:::
+:::{tab-item} RHEL 8.8
+:sync: RHEL-8.8
+:sync: RHEL-8
+
+```shell
+sudo yum install https://repo.radeon.com/amdgpu-install/5.6/rhel/8.8/amdgpu-install-5.6.50600-1.el8.noarch.rpm
 ```
 
 :::
@@ -62,21 +62,38 @@ sudo yum install https://repo.radeon.com/amdgpu-install/5.5.1/rhel/8.7/amdgpu-in
 :sync: RHEL-9
 
 ```shell
-sudo yum install https://repo.radeon.com/amdgpu-install/5.5.1/rhel/9.1/amdgpu-install-5.5.50501-1.el8.noarch.rpm
+sudo yum install https://repo.radeon.com/amdgpu-install/5.6/rhel/9.1/amdgpu-install-5.6.50600-1.el9.noarch.rpm
+```
+
+:::
+:::{tab-item} RHEL 9.2
+:sync: RHEL-9.2
+:sync: RHEL-9
+
+```shell
+sudo yum install https://repo.radeon.com/amdgpu-install/5.6/rhel/9.2/amdgpu-install-5.6.50600-1.el9.noarch.rpm
 ```
 
 :::
 ::::
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ::::{tab-set}
-:::{tab-item} Service Pack 4
-:sync: SLES15-SP4
+:::{tab-item} SLES 15.4
+:sync: SLES-15.4
 
 ```shell
-sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/5.5.1/sle/15.4/amdgpu-install-5.5.50501-1.noarch.rpm
+sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/5.6/sle/15.4/amdgpu-install-5.6.50600-1.noarch.rpm
+```
+
+:::
+:::{tab-item} SLES 15.5
+:sync: SLES-15.5
+
+```shell
+sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/5.6/sle/15.5/amdgpu-install-5.6.50600-1.noarch.rpm
 ```
 
 :::
@@ -155,9 +172,9 @@ the installer script will install packages in the single-version layout.
 For the multi-version ROCm installation you must use the installer script from
 the latest release of ROCm that you wish to install.
 
-**Example:** If you want to install ROCm releases 5.3.3 and 5.5.1
+**Example:** If you want to install ROCm releases 5.3.3 and 5.4.3
 simultaneously, you are required to download the installer from the latest ROCm
-release v5.5.1.
+release v5.4.3.
 
 ### Add Required Repositories
 
@@ -242,14 +259,14 @@ sudo yum clean all
 :::
 ::::
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ```shell
 for ver in 5.3.3 5.4.3; do
 sudo tee --append /etc/zypp/repos.d/rocm.repo <<EOF
 name=rocm
-baseurl=https://repo.radeon.com/rocm/$ver/sle/15.4/main/x86_64
+baseurl=https://repo.radeon.com/rocm/zyp/$ver/main
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -272,12 +289,12 @@ sudo amdgpu-install --usecase=rocm --rocmrelease=<release-number-3>
 ```
 
 Following are examples of ROCm multi-version installation. The kernel-mode
-driver, associated with the ROCm release v5.5.1, will be installed as its latest
+driver, associated with the ROCm release v5.4.3, will be installed as its latest
 release in the list.
 
 ```none
 sudo amdgpu-install --usecase=rocm --rocmrelease=5.3.3
-sudo amdgpu-install --usecase=rocm --rocmrelease=5.5.1
+sudo amdgpu-install --usecase=rocm --rocmrelease=5.4.3
 ```
 
 ## Additional options

docs/deploy/linux/os-native/install.md

@@ -52,8 +52,11 @@ To add the AMDGPU repository, follow these steps:
 :sync: ubuntu-20.04
 
 ```shell
+# version
+ver=5.6
+
 # amdgpu repository for focal
-echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.5.1/ubuntu focal main' \
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$ver/ubuntu focal main" \
     | sudo tee /etc/apt/sources.list.d/amdgpu.list
 sudo apt update
 ```
@@ -63,8 +66,11 @@ sudo apt update
 :sync: ubuntu-22.04
 
 ```shell
+# version
+ver=5.6
+
 # amdgpu repository for jammy
-echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.5.1/ubuntu jammy main' \
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$ver/ubuntu jammy main" \
     | sudo tee /etc/apt/sources.list.d/amdgpu.list
 sudo apt update
 ```
@@ -91,7 +97,7 @@ To add the ROCm repository, use the following steps:
 
 ```shell
 # ROCm repositories for focal
-for ver in 5.3.3 5.4.3 5.5.1; do
+for ver in 5.3.3 5.4.3 5.5.1 5.6; do
 echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$ver focal main" \
     | sudo tee --append /etc/apt/sources.list.d/rocm.list
 done
@@ -106,7 +112,7 @@ sudo apt update
 
 ```shell
 # ROCm repositories for jammy
-for ver in 5.3.3 5.4.3 5.5.1; do
+for ver in 5.3.3 5.4.3 5.5.1 5.6; do
 echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$ver jammy main" \
     | sudo tee --append /etc/apt/sources.list.d/rocm.list
 done
@@ -136,7 +142,7 @@ For a comprehensive list of meta-packages, refer to
 - Sample Multi-version installation
 
    ```shell
-   sudo apt install rocm-hip-sdk5.5.1 rocm-hip-sdk5.3.3
+   sudo apt install rocm-hip-sdk5.6 rocm-hip-sdk5.3.3
    ```
 
 :::::
@@ -152,15 +158,18 @@ section.
 ```
 
 ::::{tab-set}
-:::{tab-item} RHEL 8.6
-:sync: RHEL-8.6
+:::{tab-item} RHEL 8.7
+:sync: RHEL-8.7
 :sync: RHEL-8
 
 ```shell
+# version
+ver=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/8.6/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/8.7/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -171,15 +180,18 @@ sudo yum clean all
 
 :::
 
-:::{tab-item} RHEL 8.7
-:sync: RHEL-8.7
+:::{tab-item} RHEL 8.8
+:sync: RHEL-8.8
 :sync: RHEL-8
 
 ```shell
+# version
+ver=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/8.7/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/8.8/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -195,10 +207,35 @@ sudo yum clean all
 :sync: RHEL-9
 
 ```shell
+# version
+ver=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/9.1/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/9.1/main/x86_64/
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+sudo yum clean all
+```
+
+:::
+
+:::{tab-item} RHEL 9.2
+:sync: RHEL-9.2
+:sync: RHEL-9
+
+```shell
+# version
+ver=5.6
+
+sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/9.2/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -228,7 +265,7 @@ To add the ROCm repository, use the following steps, based on your distribution:
 :sync: RHEL-8
 
 ```shell
-for ver in 5.3.3 5.4.3 5.5.1; do
+for ver in 5.3.3 5.4.3 5.5.1 5.6; do
 sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
 [ROCm-$ver]
 name=ROCm$ver
@@ -247,7 +284,7 @@ sudo yum clean all
 :sync: RHEL-9
 
 ```shell
-for ver in 5.3.3 5.4.3 5.5.1; do
+for ver in 5.3.3 5.4.3 5.5.1 5.6; do
 sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
 [ROCm-$ver]
 name=ROCm$ver
@@ -282,12 +319,12 @@ For a comprehensive list of meta-packages, refer to
 - Sample Multi-version installation
 
    ```shell
-   sudo yum install rocm-hip-sdk5.5.1 rocm-hip-sdk5.3.3
+   sudo yum install rocm-hip-sdk5.6 rocm-hip-sdk5.3.3
    ```
 
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ::::{rubric} 1. Add the AMDGPU Repository and Install the Kernel-mode Driver
 ::::
@@ -297,11 +334,18 @@ If you have a version of the kernel-mode driver installed, you may skip this
 section.
 ```
 
+::::{tab-set}
+:::{tab-item} SLES 15.4
+:sync: SLES-15.4
+
 ```shell
+# version
+ver=5.6
+
 sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/sle/15.4/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/$ver/sle/15.4/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -309,6 +353,28 @@ EOF
 sudo zypper ref
 ```
 
+:::
+:::{tab-item} SLES 15.5
+:sync: SLES-15.5
+
+```shell
+# version
+ver=5.6
+
+sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/$ver/sle/15.5/main/x86_64
+enabled=1
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+sudo zypper ref
+```
+
+:::
+::::
+
 Install the kernel mode driver and reboot the system using the following
 commands:
 
@@ -323,7 +389,7 @@ sudo reboot
 To add the ROCm repository, use the following steps:
 
 ```shell
-for ver in 5.3.3 5.4.3 5.5.1; do
+for ver in 5.3.3 5.4.3 5.5.1 5.6; do
 sudo tee --append /etc/zypp/repos.d/rocm.repo <<EOF
 [ROCm-$ver]
 name=ROCm$ver
@@ -355,7 +421,7 @@ For a comprehensive list of meta-packages, refer to
 - Sample Multi-version installation
 
    ```shell
-   sudo zypper --gpg-auto-import-keys install rocm-hip-sdk5.5.1 rocm-hip-sdk5.3.3
+   sudo zypper --gpg-auto-import-keys install rocm-hip-sdk5.6 rocm-hip-sdk5.3.3
    ```
 
 :::::
@@ -392,7 +458,7 @@ but are generally useful. Verification of the install is advised.
 2. Add binary paths to the `PATH` environment variable.
 
    ```shell
-   export PATH=$PATH:/opt/rocm-5.5.1/bin:/opt/rocm-5.5.1/opencl/bin
+   export PATH=$PATH:/opt/rocm-5.6/bin:/opt/rocm-5.6/opencl/bin
    ```
 
    ```{attention}

docs/deploy/linux/os-native/uninstall.md

@@ -114,8 +114,8 @@ sudo yum autoremove amdgpu-dkms
    ```
 
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ::::{rubric} Uninstalling Specific Meta-packages
 ::::

docs/deploy/linux/os-native/upgrade.md

@@ -25,8 +25,11 @@ repository to the new release.
 :sync: ubuntu-20.04
 
 ```shell
+# version
+version=5.6
+
 # amdgpu repository for focal
-echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.5.1/ubuntu focal main' \
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$version/ubuntu focal main" \
     | sudo tee /etc/apt/sources.list.d/amdgpu.list
 sudo apt update
 ```
@@ -36,8 +39,11 @@ sudo apt update
 :sync: ubuntu-22.04
 
 ```shell
+# version
+version=5.6
+
 # amdgpu repository for jammy
-echo 'deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.5.1/ubuntu jammy main' \
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$version/ubuntu jammy main" \
     | sudo tee /etc/apt/sources.list.d/amdgpu.list
 sudo apt update
 ```
@@ -49,15 +55,18 @@ sudo apt update
 :sync: RHEL
 
 ::::{tab-set}
-:::{tab-item} RHEL 8.6
-:sync: RHEL-8.6
+:::{tab-item} RHEL 8.7
+:sync: RHEL-8.7
 :sync: RHEL-8
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/8.6/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$version/rhel/8.7/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -67,15 +76,18 @@ sudo yum clean all
 ```
 
 :::
-:::{tab-item} RHEL 8.7
-:sync: RHEL-8.7
+:::{tab-item} RHEL 8.8
+:sync: RHEL-8.8
 :sync: RHEL-8
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/8.7/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$version/rhel/8.8/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -90,10 +102,34 @@ sudo yum clean all
 :sync: RHEL-9
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/rhel/9.1/main/x86_64/
+baseurl=https://repo.radeon.com/amdgpu/$version/rhel/9.1/main/x86_64/
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+sudo yum clean all
+```
+
+:::
+:::{tab-item} RHEL 9.2
+:sync: RHEL-9.2
+:sync: RHEL-9
+
+```shell
+# version
+version=5.6
+
+sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/$version/rhel/9.2/main/x86_64/
 enabled=1
 priority=50
 gpgcheck=1
@@ -105,14 +141,21 @@ sudo yum clean all
 :::
 ::::
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
+
+::::{tab-set}
+:::{tab-item} SLES 15.4
+:sync: SLES-15.4
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/5.5.1/sle/15.4/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/$version/sle/15.4/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -120,6 +163,24 @@ EOF
 sudo zypper ref
 ```
 
+:::
+:::{tab-item} SLES 15.5
+:sync: SLES-15.5
+
+```shell
+sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/5.6/sle/15.5/main/x86_64
+enabled=1
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+sudo zypper ref
+```
+
+:::
+::::
 :::::
 ::::::
 
@@ -147,8 +208,8 @@ sudo reboot
 ```
 
 :::
-:::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ```shell
 sudo zypper --gpg-auto-import-keys install amdgpu-dkms
@@ -172,7 +233,10 @@ repository to the new release.
 :sync: ubuntu-20.04
 
 ```shell
-echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.5.1 focal main" \
+# version
+version=5.6
+
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$version focal main" \
     | sudo tee /etc/apt/sources.list.d/rocm.list
 echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' \
     | sudo tee /etc/apt/preferences.d/rocm-pin-600
@@ -184,7 +248,10 @@ sudo apt update
 :sync: ubuntu-22.04
 
 ```shell
-echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.5.1 jammy main" \
+# version
+version=5.6
+
+echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$version jammy main" \
     | sudo tee /etc/apt/sources.list.d/rocm.list
 echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' \
     | sudo tee /etc/apt/preferences.d/rocm-pin-600
@@ -202,10 +269,13 @@ sudo apt update
 :sync: RHEL-8
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/yum.repos.d/rocm.repo <<EOF
-[ROCm-5.5.1]
-name=ROCm5.5.1
-baseurl=https://repo.radeon.com/rocm/rhel8/5.5.1/main
+[ROCm-$ver]
+name=ROCm$ver
+baseurl=https://repo.radeon.com/rocm/rhel8/$version/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -219,10 +289,13 @@ sudo yum clean all
 :sync: RHEL-9
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/yum.repos.d/rocm.repo <<EOF
-[ROCm-5.5.1]
-name=ROCm5.5.1
-baseurl=https://repo.radeon.com/rocm/rhel9/5.5.1/main
+[ROCm-$ver]
+name=ROCm$ver
+baseurl=https://repo.radeon.com/rocm/rhel9/$version/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -234,15 +307,18 @@ sudo yum clean all
 :::
 ::::
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
-:sync: SLES15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 ```shell
+# version
+version=5.6
+
 sudo tee /etc/zypp/repos.d/rocm.repo <<EOF
-[ROCm-5.5.1]
-name=ROCm5.5.1
+[ROCm-$ver]
+name=ROCm$ver
 name=rocm
-baseurl=https://repo.radeon.com/rocm/zyp/5.5.1/main
+baseurl=https://repo.radeon.com/rocm/zyp/$version/main
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -275,8 +351,8 @@ sudo yum update rocm-hip-sdk
 ```
 
 :::
-:::{tab-item} Suse Linux Enterprise Server 15
-:sync: SLES15
+:::{tab-item} Suse Linux Enterprise Server
+:sync: SLES
 
 ```shell
 sudo zypper --gpg-auto-import-keys update rocm-hip-sdk

docs/deploy/linux/prerequisites.md

@@ -91,6 +91,7 @@ sudo rpm -ivh epel-release-latest-8.noarch.rpm
 
 :::
 :::{tab-item} RHEL 9
+:sync: RHEL-9
 
 ```shell
 wget https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm
@@ -110,14 +111,33 @@ sudo crb enable
 ```
 
 :::::
-:::::{tab-item} SUSE Linux Enterprise Server 15
+:::::{tab-item} SUSE Linux Enterprise Server
+:sync: SLES
 
 Add the perl languages repository.
 
-```shell
-zypper addrepo https://download.opensuse.org/repositories/devel:languages:perl/SLE_15_SP4/devel:languages:perl.repo
+```{note}
+Mar 25, 2024: We currently need to install the Perl module from SLES 15 SP5 as a workaround. The module was removed for SLES 15 SP4.
 ```
 
+::::{tab-set}
+:::{tab-item} SLES 15.4
+:sync: SLES-15.4
+
+```shell
+zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/perl/15.5/devel:languages:perl.repo
+```
+
+:::
+:::{tab-item} SLES 15.5
+:sync: SLES-15.5
+
+```shell
+zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/perl/15.5/devel:languages:perl.repo
+```
+
+:::
+::::
 :::::
 ::::::
 

docs/deploy/linux/quick_start.md

@@ -29,11 +29,11 @@ wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
 ```shell
 # Kernel driver repository for focal
 sudo tee /etc/apt/sources.list.d/amdgpu.list <<'EOF'
-deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu focal main
+deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.6/ubuntu focal main
 EOF
 # ROCm repository for focal
 sudo tee /etc/apt/sources.list.d/rocm.list <<'EOF'
-deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/debian focal main
+deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.6 focal main
 EOF
 ```
 
@@ -44,13 +44,14 @@ EOF
 ```shell
 # Kernel driver repository for jammy
 sudo tee /etc/apt/sources.list.d/amdgpu.list <<'EOF'
-deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/latest/ubuntu jammy main
+deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/5.6/ubuntu jammy main
 EOF
 # ROCm repository for jammy
 sudo tee /etc/apt/sources.list.d/rocm.list <<'EOF'
-deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/debian jammy main
-echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
+deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/5.6 jammy main
 EOF
+# Prefer packages from the rocm repository over system packages
+echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
 ```
 
 :::
@@ -72,15 +73,15 @@ sudo apt update
 ::::
 
 ::::{tab-set}
-:::{tab-item} RHEL 8.6
-:sync: RHEL-8.6
+:::{tab-item} RHEL 8.7
+:sync: RHEL-8.7
 
 ```shell
-# Add the amdgpu module repository for RHEL 8.6
+# Add the amdgpu module repository for RHEL 8.7
 sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/latest/rhel/8.6/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/5.6/rhel/8.7/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -89,7 +90,7 @@ EOF
 sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
 [rocm]
 name=rocm
-baseurl=https://repo.radeon.com/rocm/rhel8/latest/main
+baseurl=https://repo.radeon.com/rocm/rhel8/5.6/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -99,15 +100,15 @@ EOF
 
 :::
 
-:::{tab-item} RHEL 8.7
-:sync: RHEL-8.7
+:::{tab-item} RHEL 8.8
+:sync: RHEL-8.8
 
 ```shell
-# Add the amdgpu module repository for RHEL 8.7
+# Add the amdgpu module repository for RHEL 8.8
 sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/latest/rhel/8.7/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/5.6/rhel/8.8/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -116,7 +117,7 @@ EOF
 sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
 [rocm]
 name=rocm
-baseurl=https://repo.radeon.com/rocm/rhel8/latest/main
+baseurl=https://repo.radeon.com/rocm/rhel8/5.6/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -134,7 +135,7 @@ EOF
 sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/latest/rhel/9.1/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/5.6/rhel/9.1/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
@@ -143,7 +144,34 @@ EOF
 sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
 [rocm]
 name=rocm
-baseurl=https://repo.radeon.com/rocm/rhel9/latest/main
+baseurl=https://repo.radeon.com/rocm/rhel9/5.6/main
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+```
+
+:::
+
+:::{tab-item} RHEL 9.2
+:sync: RHEL-9.2
+
+```shell
+# Add the amdgpu module repository for RHEL 9.2
+sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/5.6/rhel/9.2/main/x86_64
+enabled=1
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+# Add the rocm repository for RHEL 9
+sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
+[rocm]
+name=rocm
+baseurl=https://repo.radeon.com/rocm/rhel9/5.6/main
 enabled=1
 priority=50
 gpgcheck=1
@@ -170,8 +198,8 @@ sudo yum clean all
 ::::
 
 ::::{tab-set}
-:::{tab-item} SLES 15 SP4
-:sync: SLES15-SP4
+:::{tab-item} SLES 15.4
+:sync: SLES-15.4
 
 ```shell
 
@@ -179,7 +207,34 @@ sudo yum clean all
 sudo tee /etc/zypp/repos.d/amdgpu.repo <<'EOF'
 [amdgpu]
 name=amdgpu
-baseurl=https://repo.radeon.com/amdgpu/latest/sle/15.4/main/x86_64
+baseurl=https://repo.radeon.com/amdgpu/5.6/sle/15.4/main/x86_64
+enabled=1
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+# Add the rocm repository for SLES
+sudo tee /etc/zypp/repos.d/rocm.repo <<'EOF'
+[rocm]
+name=rocm
+baseurl=https://repo.radeon.com/rocm/zyp/zypper
+enabled=1
+priority=50
+gpgcheck=1
+gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
+EOF
+```
+
+:::
+:::{tab-item} SLES 15.5
+:sync: SLES-15.5
+
+```shell
+
+# Add the amdgpu module repository for SLES 15.5
+sudo tee /etc/zypp/repos.d/amdgpu.repo <<'EOF'
+[amdgpu]
+name=amdgpu
+baseurl=https://repo.radeon.com/amdgpu/5.6/sle/15.5/main/x86_64
 enabled=1
 gpgcheck=1
 gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key

docs/deploy/windows/cli/index.md

@@ -0,0 +1,31 @@
+# Command Line Installation
+
+::::{grid} 2 3 3 3
+:gutter: 1
+
+:::{grid-item-card} Install
+:link: install
+:link-type: doc
+
+How to install ROCm?
+:::
+
+:::{grid-item-card} Upgrade
+:link: upgrade
+:link-type: doc
+
+Instructions for upgrading an existing ROCm installation.
+:::
+
+:::{grid-item-card} Uninstall
+:link: uninstall
+:link-type: doc
+
+Steps for removing ROCm packages and libraries.
+:::
+
+::::
+
+## See Also
+
+- {doc}`/release/gpu_os_support`

docs/deploy/windows/cli/install.md

@@ -0,0 +1,56 @@
+# Installation Using the Command Line Interface
+
+The steps to install the HIP SDK for Windows are described in this document.
+
+## System Requirements
+
+The HIP SDK is supported on Windows 10 and 11. The HIP SDK may be installed on a
+system without AMD GPUs to use the build toolchains. To run HIP applications, a
+compatible GPU is required. Please see the supported GPU guide for more details.
+
+## HIP SDK Installation
+
+The command line installer is the same executable which is used by the graphical
+front-end. Download the installer from the
+[HIP-SDK download page](https://www.amd.com/en/developer/rocm-hub/hip-sdk.html).
+The options supported by the command line interface are summarized in
+{numref}`hip-sdk-cli-options`.
+
+```{table} HIP SDK Command Line Options
+:name: hip-sdk-cli-options
+| **Install Option** | **Description** |
+|:------------------:|:---------------:|
+| `-install` | Command used to install packages, both driver and applications. No output to the screen. |
+| `-install -boot` | Silent install with auto reboot. |
+| `-install -log <absolute path>` | Write install result code to the specified log file. The specified log file must be on a local machine. Double quotes are needed if there are spaces in the log file path. |
+| `-uninstall` | Command to uninstall all packages installed by this installer on the system. There is no option to specify which packages to uninstall. |
+| `-uninstall -boot` | Silent uninstall with auto reboot. |
+| `/?` or /help | Shows a brief description of all switch commands. |
+```
+
+```{note}
+Unlike the graphical installer, the command line interface doesn't support
+selectively installing parts of the SDK bundle. It's all or nothing.
+```
+
+### Launching the Installer From the Command Line
+
+The installer is still a graphical application with a `WinMain` entry point, even
+when called on the command line. This means that the application lifetime is
+tied to a window, even on headless systems where that window may not be visible.
+To launch the installer from PowerShell that will block until the installer
+exits, one may use the following pattern:
+
+```pwsh
+Start-Process $InstallerExecutable -ArgumentList $InstallerArgs -NoNewWindow -Wait
+```
+
+```{important}
+Running the installer requires Administrator Privileges.
+```
+
+For example, installing all components and
+
+```pwsh
+Start-Process ~\Downloads\Setup.exe -ArgumentList '-install','-log',"${env:USERPROFILE}\installer_log.txt" -NoNewWindow -Wait
+```

docs/deploy/windows/cli/uninstall.md

@@ -0,0 +1,48 @@
+# Uninstallation Using the Command Line Interface
+
+The steps to uninstall the HIP SDK for Windows are described in this document.
+
+## HIP SDK Uninstallation
+
+The command line installer is the same executable which is used by the graphical
+front-end. The options supported by the command line interface are summarized in
+{numref}`hip-sdk-cli-options`.
+
+```{table} HIP SDK Command Line Options
+:name: hip-sdk-cli-options
+| **Install Option** | **Description** |
+|:------------------:|:---------------:|
+| `-install` | Command used to install packages, both driver and applications. No output to the screen. |
+| `-install -boot` | Silent install with auto reboot. |
+| `-install -log <absolute path>` | Write install result code to the specified log file. The specified log file must be on a local machine. Double quotes are needed if there are spaces in the log file path. |
+| `-uninstall` | Command to uninstall all packages installed by this installer on the system. There is no option to specify which packages to uninstall. |
+| `-uninstall -boot` | Silent uninstall with auto reboot. |
+| `/?` or /help | Shows a brief description of all switch commands. |
+```
+
+```{note}
+Unlike the graphical installer, the command line interface doesn't support
+selectively installing parts of the SDK bundle. It's all or nothing.
+```
+
+### Launching the Installer From the Command Line
+
+The installer is still a graphical application with a `WinMain` entry point, even
+when called on the command line. This means that the application lifetime is
+tied to a window, even on headless systems where that window may not be visible.
+To launch the installer from PowerShell that will block until the installer
+exits, one may use the following pattern:
+
+```pwsh
+Start-Process $InstallerExecutable -ArgumentList $InstallerArgs -NoNewWindow -Wait
+```
+
+```{important}
+Running the installer requires Administrator Privileges.
+```
+
+For example, uninstalling all components and
+
+```pwsh
+Start-Process ~\Downloads\Setup.exe -ArgumentList '-uninstall' -NoNewWindow -Wait
+```

docs/deploy/windows/cli/upgrade.md

@@ -0,0 +1,14 @@
+# Upgrading Using the Graphical Interface
+
+The steps to uninstall the HIP SDK for Windows are described in this document.
+
+## HIP SDK Upgrade
+
+To upgrade an existing installation of the HIP SDK without preserving the
+previous version, first uninstall it, then install the new version following the
+instructions in {doc}`/deploy/windows/cli/uninstall` and
+{doc}`/deploy/windows/cli/install` using the old and new installers
+respectively.
+
+To upgrade by installing both versions side-by-side, just run the installer of
+the newer version.

docs/deploy/windows/gui/index.md

@@ -0,0 +1,31 @@
+# Graphical Installation
+
+::::{grid} 2 3 3 3
+:gutter: 1
+
+:::{grid-item-card} Install
+:link: install
+:link-type: doc
+
+How to install ROCm?
+:::
+
+:::{grid-item-card} Upgrade
+:link: upgrade
+:link-type: doc
+
+Instructions for upgrading an existing ROCm installation.
+:::
+
+:::{grid-item-card} Uninstall
+:link: uninstall
+:link-type: doc
+
+Steps for removing ROCm packages and libraries.
+:::
+
+::::
+
+## See Also
+
+- {doc}`/release/gpu_os_support`

docs/deploy/windows/gui/install.md

@@ -0,0 +1,163 @@
+# Installation Using the Graphical Interface
+
+The steps to install the HIP SDK for Windows are described in this document.
+
+## System Requirements
+
+The HIP SDK is supported on Windows 10 and 11. The HIP SDK may be installed on a
+system without AMD GPUs to use the build toolchains. To run HIP applications, a
+compatible GPU is required. Please see the supported GPU guide for more details.
+
+## HIP SDK Installation
+
+### Download the installer
+
+Download the installer from the
+[HIP-SDK download page](https://www.amd.com/en/developer/rocm-hub/hip-sdk.html).
+
+### Launching the installer
+
+To launch the AMD HIP SDK Installer, click the **Setup** icon shown in
+{numref}`setup-icon`.
+
+```{figure} /data/deploy/windows/000-setup-icon.png
+:name: setup-icon
+:alt: Icon with AMD arrow logo and User Access Control Shield overlayed.
+Setup Icon
+```
+
+The installer requires Administrator Privileges, so you may be greeted with a
+User Access Control (UAC) pop-up. Click Yes.
+
+```{figure} /data/deploy/windows/001-uac-dark.png
+:name: uac-dark
+:class: only-dark
+:alt: User Access Control pop-up
+User Access Control pop-up
+```
+
+```{figure} /data/deploy/windows/001-uac-light.png
+:name: uac-light
+:class: only-light
+:alt: User Access Control pop-up
+User Access Control pop-up
+```
+
+The installer executable will temporarily extract installer packages to `C:\AMD`
+which it will remove after installation completes. This extraction is signified
+by the "Initializing install" window in {numref}`init-install`.
+
+```{figure} /data/deploy/windows/002-initializing.png
+:name: init-install
+:alt: Window with AMD arrow logo, futuristic background and progress counter.
+Installer initialization window
+```
+
+The installer will then detect your system configuration as per
+{numref}`detecting-system-components` to decide, which installable components
+are applicable to your system.
+
+```{figure} /data/deploy/windows/003-detecting-system-config.png
+:name: detecting-system-components
+:alt: Window with AMD arrow logo, futuristic background and activity indicator.
+Installer initialization window.
+```
+
+### Customizing the install
+
+When the installer launches, it displays a window that lets the user customize
+the installation. By default, all components are selected for installation.
+Refer to {numref}`installer-window` for an instance when the Select All option
+is turned on.
+
+```{figure} /data/deploy/windows/004-installer-window.png
+:name: installer-window
+:alt: Window with AMD arrow logo, futuristic background and activity indicator.
+Installer initialization window.
+```
+
+#### HIP SDK Installer
+
+The HIP SDK installation options are listed in {numref}`hip-sdk-options`.
+
+```{table} HIP SDK Components for Installation
+:name: hip-sdk-options
+| **HIP Components** | **Install Type** | **Additional Options** |
+|:------------------:|:----------------:|:----------------------:|
+| HIP SDK Core         | 5.5.0               | Install location                        |
+| HIP Libraries        | Full, Partial, None | Runtime, Development (Libs and headers) |
+| HIP Runtime Compiler | Full, Partial, None | Runtime, Development (Headers)          |
+| HIP Ray Tracing      | Full, Partial, None | Runtime, Development (Headers)          |
+| Visual Studio Plugin | Full, Partial, None | Visual Studio 2017, 2019, 2022 Plugin   |
+```
+
+```{note}
+The Select/DeSelect All option only applies to the installation of HIP SDK
+components. To install the bundled AMD Display Driver, manually select the
+install type.
+```
+
+```{tip}
+Should you only wish to install a few select components,
+DeSelecting All and then picking the individual components may be more
+convenient.
+```
+
+#### AMD Display Driver
+
+The HIP SDK installer bundles an AMD Radeon Software PRO 23.10 installer. The
+supported install options are summarized by
+{numref}`display-driver-install-options`:
+
+```{table} AMD Display Driver Install Options
+:name: display-driver-install-options
+| **Install Option** | **Description** |
+|:------------------:|:---------------:|
+| Install Location         | Location on disk to store driver files. |
+| Install Type             | The breadth of components to be installed. Refer to {numref}`display-driver-install-types` for details. |
+| Factory Reset (Optional) | A Factory Reset will remove all prior versions of AMD HIP SDK and drivers. You will not be able to roll back to previously installed drivers. |
+```
+
+```{table} AMD Display Driver Install Types
+:name: display-driver-install-types
+| **Install Type** | **Description** |
+|:----------------:|:---------------:|
+| Full Install     | Provides all AMD Software features and controls for gaming, recording, streaming, and tweaking the performance on your graphics hardware. |
+| Minimal Install  | Provides only the basic controls for AMD Software features and does not include advanced features such as performance tweaking or recording and capturing content. |
+| Driver Only      | Provides no user interface for AMD Software features. |
+```
+
+```{note}
+You must perform a system restart for a complete installation of the
+Display Driver.
+```
+
+### Installing Components
+
+Please wait for the installation to complete during as shown in
+{numref}`install-progress`.
+
+```{figure} /data/deploy/windows/012-install-progress.png
+:name: install-progress
+:alt: Window with AMD arrow logo, futuristic background and progress meter.
+Installation Progress
+```
+
+### Installation Complete
+
+Once the installation is complete, the installer window may prompt you for a
+system restart. Click **Restart** at the lower right corner, shown in
+{numref}`install-complete`
+
+```{figure} /data/deploy/windows/013-install-complete.png
+:name: install-complete
+:alt: Window with AMD arrow logo, futuristic background and completion notice.
+Installation Complete
+```
+
+```{error}
+Should the installer terminate due to unexpcted circumstances, or the user
+forcibly terminates the installer, the temporary directory created under
+`C:\AMD` may be safely removed. Installed components will not depend on this
+folder (unless the user specifies `C:\AMD` as an install folder explicitly).
+```

docs/deploy/windows/gui/uninstall.md

@@ -0,0 +1,27 @@
+# Uninstallation Using the Graphical Interface
+
+The steps to uninstall the HIP SDK for Windows are described in this document.
+
+## Uninstallation
+
+All components, except visual studio plug-in should be uninstalled through
+control panel -> Add/Remove Program. For visual studio extension uninstallation,
+please refer to
+<https://github.com/ROCm-Developer-Tools/HIP-VS/blob/master/README.md>.
+Uninstallation of the HIP SDK components can be done through the Windows
+Settings app. Navigate to "Apps > Installed apps", click the "..." on the far
+right next to the component to uninstall, and click "Uninstall".
+
+```{figure} /data/deploy/windows/014-uninstall-dark.png
+:name: uninstall-dark
+:class: only-dark
+:alt: Installed apps section of the Setting app showing installed HIP SDK components.
+Removing the SDK via the Setting app
+```
+
+```{figure} /data/deploy/windows/014-uninstall-light.png
+:name: uninstall-light
+:class: only-light
+:alt: Installed apps section of the Setting app showing installed HIP SDK components.
+Removing the SDK via the Setting app
+```

docs/deploy/windows/gui/upgrade.md

@@ -0,0 +1,4 @@
+# Upgrading Using the Graphical Interface
+
+The steps to upgrade an existing HIP SDK installation for Windows are described
+in this document.

docs/deploy/windows/index.md

@@ -0,0 +1,44 @@
+# Deploy ROCm on Windows
+
+Start with {doc}`/deploy/windows/quick_start` or follow the detailed
+instructions below.
+
+## Prepare to Install
+
+::::{grid} 1 1 2 2
+:gutter: 1
+
+:::{grid-item-card} Prerequisites
+:link: prerequisites
+:link-type: doc
+
+The prerequisites page lists the required steps to verify that the system
+supports ROCm.
+:::
+
+::::
+
+## Choose your install method
+
+::::{grid} 1 1 2 2
+:gutter: 1
+
+:::{grid-item-card} Graphical Installation
+:link: gui/index
+:link-type: doc
+
+Use the graphical front-end of the installer.
+:::
+
+:::{grid-item-card} Command Line Installation
+:link: cli/index
+:link-type: doc
+
+Use the command line front-end of the installer.
+:::
+
+::::
+
+## See Also
+
+- {doc}`/release/gpu_os_support`

docs/deploy/windows/prerequisites.md

@@ -0,0 +1,74 @@
+# Installation Prerequisites (Windows)
+
+You must perform the following steps before installing ROCm and check if the
+system meets all the requirements to proceed with the installation.
+
+## Confirm the System Is Supported
+
+The ROCm installation is supported only on specific host architectures, Windows
+SKUs and update versions.
+
+### Check the Windows SKU and Update Version on Your System
+
+This section discusses obtaining information about the host architecture,
+Windows SKU and update version.
+
+#### Command Line Check
+
+Verify the Windows SKU using the following steps:
+
+1. To obtain the Linux distribution information, type the following command on
+   your system from a PowerShell Command Line Interface (CLI):
+
+   ```pwsh
+   Get-ComputerInfo | Format-Table CsSystemType,OSName,OSDisplayVersion
+   ```
+
+2. Confirm that the obtained information matches with those listed in
+   {ref}`supported_skus`.
+
+   **Example:** Running the command above on a Windows system may result in the
+   following output:
+
+   ```output
+   CsSystemType OsName                   OSDisplayVersion
+   ------------ ------                   ----------------
+   x64-based PC Microsoft Windows 11 Pro 22H2
+   ```
+
+#### Graphical Check
+
+1. Open the Setting app.
+
+   ```{figure} /data/deploy/windows/000-settings-dark.png
+   :name: settings-dark
+   :class: only-dark
+   :alt: Gear icon of the Windows Settings app
+   Windows Settings app icon
+   ```
+
+   ```{figure} /data/deploy/windows/000-settings-light.png
+   :name: settings-light
+   :class: only-light
+   :alt: Gear icon of the Windows Settings app
+   Windows Settings app icon
+   ```
+
+2. Navigate to **System > About**.
+
+   ```{figure} /data/deploy/windows/001-about-dark.png
+   :name: about-dark
+   :class: only-dark
+   :alt: Settings app panel showing Device and OS information
+   Settings > About page
+   ```
+
+   ```{figure} /data/deploy/windows/001-about-light.png
+   :name: about-light
+   :class: only-light
+   :alt: Settings app panel showing Device and OS information
+   Settings > About page
+   ```
+
+3. Confirm that the obtained information matches with those listed in
+   {ref}`supported_skus`.

docs/deploy/windows/quick_start.md

@@ -0,0 +1,187 @@
+# Quick Start (Windows)
+
+The steps to install the HIP SDK for Windows are described in this document.
+
+## System Requirements
+
+The HIP SDK is supported on Windows 10 and 11. The HIP SDK may be installed on a
+system without AMD GPUs to use the build toolchains. To run HIP applications, a
+compatible GPU is required. Please see the supported GPU guide for more details.
+
+## HIP SDK Installation
+
+### Download the installer
+
+Download the installer from the
+[HIP-SDK download page](https://www.amd.com/en/developer/rocm-hub/hip-sdk.html).
+
+### Launching the installer
+
+To launch the AMD HIP SDK Installer, click the **Setup** icon shown in
+{numref}`setup-icon`.
+
+```{figure} /data/deploy/windows/000-setup-icon.png
+:name: setup-icon
+:alt: Icon with AMD arrow logo and User Access Control Shield overlayed.
+Setup Icon
+```
+
+The installer requires Administrator Privileges, so you may be greeted with a
+User Access Control (UAC) pop-up. Click Yes.
+
+```{figure} /data/deploy/windows/001-uac-dark.png
+:name: uac-dark
+:class: only-dark
+:alt: User Access Control pop-up
+User Access Control pop-up
+```
+
+```{figure} /data/deploy/windows/001-uac-light.png
+:name: uac-light
+:class: only-light
+:alt: User Access Control pop-up
+User Access Control pop-up
+```
+
+The installer executable will temporarily extract installer packages to `C:\AMD`
+which it will remove after installation completes. This extraction is signified
+by the "Initializing install" window in {numref}`init-install`.
+
+```{figure} /data/deploy/windows/002-initializing.png
+:name: init-install
+:alt: Window with AMD arrow logo, futuristic background and progress counter.
+Installer initialization window
+```
+
+The installer will then detect your system configuration as per
+{numref}`detecting-system-components` to decide, which installable components
+are applicable to your system.
+
+```{figure} /data/deploy/windows/003-detecting-system-config.png
+:name: detecting-system-components
+:alt: Window with AMD arrow logo, futuristic background and activity indicator.
+Installer initialization window.
+```
+
+### Customizing the install
+
+When the installer launches, it displays a window that lets the user customize
+the installation. By default, all components are selected for installation.
+Refer to {numref}`installer-window` for an instance when the Select All option
+is turned on.
+
+```{figure} /data/deploy/windows/004-installer-window.png
+:name: installer-window
+:alt: Window with AMD arrow logo, futuristic background and activity indicator.
+Installer initialization window.
+```
+
+#### HIP SDK Installer
+
+The HIP SDK installation options are listed in {numref}`hip-sdk-options`.
+
+```{table} HIP SDK Components for Installation
+:name: hip-sdk-options
+| **HIP Components** | **Install Type** | **Additional Options** |
+|:------------------:|:----------------:|:----------------------:|
+| HIP SDK Core         | 5.5.0               | Install location                        |
+| HIP Libraries        | Full, Partial, None | Runtime, Development (Libs and headers) |
+| HIP Runtime Compiler | Full, Partial, None | Runtime, Development (Headers)          |
+| HIP Ray Tracing      | Full, Partial, None | Runtime, Development (Headers)          |
+| Visual Studio Plugin | Full, Partial, None | Visual Studio 2017, 2019, 2022 Plugin   |
+```
+
+```{note}
+The Select/DeSelect All option only applies to the installation of HIP SDK
+components. To install the bundled AMD Display Driver, manually select the
+install type.
+```
+
+```{tip}
+Should you only wish to install a few select components,
+DeSelecting All and then picking the individual components may be more
+convenient.
+```
+
+#### AMD Display Driver
+
+The HIP SDK installer bundles an AMD Radeon Software PRO 23.10 installer. The
+supported install options are summarized by
+{numref}`display-driver-install-options`:
+
+```{table} AMD Display Driver Install Options
+:name: display-driver-install-options
+| **Install Option** | **Description** |
+|:------------------:|:---------------:|
+| Install Location         | Location on disk to store driver files. |
+| Install Type             | The breadth of components to be installed. Refer to {numref}`display-driver-install-types` for details. |
+| Factory Reset (Optional) | A Factory Reset will remove all prior versions of AMD HIP SDK and drivers. You will not be able to roll back to previously installed drivers. |
+```
+
+```{table} AMD Display Driver Install Types
+:name: display-driver-install-types
+| **Install Type** | **Description** |
+|:----------------:|:---------------:|
+| Full Install     | Provides all AMD Software features and controls for gaming, recording, streaming, and tweaking the performance on your graphics hardware. |
+| Minimal Install  | Provides only the basic controls for AMD Software features and does not include advanced features such as performance tweaking or recording and capturing content. |
+| Driver Only      | Provides no user interface for AMD Software features. |
+```
+
+```{note}
+You must perform a system restart for a complete installation of the
+Display Driver.
+```
+
+### Installing Components
+
+Please wait for the installation to complete during as shown in
+{numref}`install-progress`.
+
+```{figure} /data/deploy/windows/012-install-progress.png
+:name: install-progress
+:alt: Window with AMD arrow logo, futuristic background and progress meter.
+Installation Progress
+```
+
+### Installation Complete
+
+Once the installation is complete, the installer window may prompt you for a
+system restart. Click **Restart** at the lower right corner, shown in
+{numref}`install-complete`
+
+```{figure} /data/deploy/windows/013-install-complete.png
+:name: install-complete
+:alt: Window with AMD arrow logo, futuristic background and completion notice.
+Installation Complete
+```
+
+```{error}
+Should the installer terminate due to unexpcted circumstances, or the user
+forcibly terminates the installer, the temporary directory created under
+`C:\AMD` may be safely removed. Installed components will not depend on this
+folder (unless the user specifies `C:\AMD` as an install folder explicitly).
+```
+
+## Uninstallation
+
+All components, except visual studio plug-in should be uninstalled through
+control panel -> Add/Remove Program. For visual studio extension uninstallation,
+please refer to
+<https://github.com/ROCm-Developer-Tools/HIP-VS/blob/master/README.md>.
+Uninstallation of the HIP SDK components can be done through the Windows
+Settings app. Navigate to "Apps > Installed apps", click the "..." on the far
+right next to the component to uninstall, and click "Uninstall".
+
+```{figure} /data/deploy/windows/014-uninstall-dark.png
+:name: uninstall-dark
+:class: only-dark
+:alt: Installed apps section of the Setting app showing installed HIP SDK components.
+Removing the SDK via the Setting app
+```
+
+```{figure} /data/deploy/windows/014-uninstall-light.png
+:name: uninstall-light
+:class: only-light
+:alt: Installed apps section of the Setting app showing installed HIP SDK components.
+Removing the SDK via the Setting app
+```

docs/examples/machine_learning/migraphx_optimization.md

@@ -24,7 +24,7 @@ MIGraphX is a graph compiler focused on accelerating the Machine Learning infere
 
 After doing all these transformations, MIGraphX emits code for the AMD GPU by calling to MIOpen or rocBLAS or creating HIP kernels for a particular operator. MIGraphX can also target CPUs using DNNL or ZenDNN libraries.
 
-MIGraphX provides easy-to-use APIs in C++ and Python to import machine models in ONNX or TensorFlow. Users can compile, save, load, and run these models using MIGraphX's C++ and Python APIs. Internally, MIGraphX parses ONNX or TensorFlow models into internal graph representation where each operator in the model gets mapped to an operator within MIGraphX. Each of these operators defines various attributes such as:
+MIGraphX provides easy-to-use APIs in C++ and Python to import machine models in ONNX or TensorFlow. Users can compile, save, load, and run these models using MIGraphX C++ and Python APIs. Internally, MIGraphX parses ONNX or TensorFlow models into internal graph representation where each operator in the model gets mapped to an operator within MIGraphX. Each of these operators defines various attributes such as:
 
 - Number of arguments
 
@@ -187,7 +187,7 @@ Follow these steps:
     }
     ```
 
-2. To compile this program, you can use CMake and you only need to link the `migraphx::c` library to use MIGraphX's C++ API. The following is the `CMakeLists.txt` file that can build the earlier example:
+2. To compile this program, you can use CMake and you only need to link the `migraphx::c` library to use the MIGraphX C++ API. The following is the `CMakeLists.txt` file that can build the earlier example:
 
     ```cmake
     cmake_minimum_required(VERSION 3.5)
@@ -327,7 +327,7 @@ To run generated `.mxr` files through `migraphx-driver`, use the following:
 ./path/to/migraphx-driver run --migraphx resnet50.mxr --enable-offload-copy
 ```
 
-Alternatively, you can use MIGraphX's C++ or Python API to generate `.mxr` file. Refer to {numref}`image018` for an example.
+Alternatively, you can use the MIGraphX C++ or Python API to generate `.mxr` file. Refer to {numref}`image018` for an example.
 
 ```{figure} ../../data/understand/deep_learning/image.018.png
 :name: image018

docs/how_to/gpu_aware_mpi.md

@@ -22,7 +22,7 @@ MPI project is an open source implementation of the Message Passing Interface
 and industry partners.
 
 Several MPI implementations can be made ROCm-aware by compiling them with
-[Unified Communication Framework](http://www.openucx.org/) (UCX) support. One
+[Unified Communication Framework](https://www.openucx.org/) (UCX) support. One
 notable exception is MVAPICH2: It directly supports AMD GPUs without using UCX,
 and you can download it [here](http://mvapich.cse.ohio-state.edu/downloads/).
 Use the latest version of the MVAPICH2-GDR package.
@@ -32,7 +32,7 @@ whose goal is to provide a common set of communication interfaces that targets a
 broad set of network programming models and interfaces. UCX is ROCm-aware, and
 ROCm technologies are used directly to implement various network operation
 primitives. For more details on the UCX design, refer to it's
-[documentation](http://www.openucx.org/documentation).
+[documentation](https://www.openucx.org/documentation).
 
 ## Building UCX
 

docs/how_to/pytorch_install/pytorch_install.md

@@ -60,7 +60,7 @@ Follow these steps:
 PyTorch supports the ROCm platform by providing tested wheels packages. To
 access this feature, refer to
 [https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/)
-and choose the "ROCm" compute platform. {numref}`Installation-Matrix-from-Pytorch` is a matrix from <http://pytorch.org/> that illustrates the installation compatibility between ROCm and the PyTorch build.
+and choose the "ROCm" compute platform. {numref}`Installation-Matrix-from-Pytorch` is a matrix from <https://pytorch.org/> that illustrates the installation compatibility between ROCm and the PyTorch build.
 
 ```{figure} ../../data/how_to/magma_install/image.006.png
 :name: Installation-Matrix-from-Pytorch
@@ -83,7 +83,7 @@ To install PyTorch using the wheels package, follow these installation steps:
       installation directions in the section
       [Installation](../../deploy/linux/install.md). ROCm 5.2 is installed in
       this example, as supported by the installation matrix from
-      <http://pytorch.org/>.
+      <https://pytorch.org/>.
 
    or
 
@@ -299,7 +299,7 @@ USE_ROCM=1 MAX_JOBS=4 python3 setup.py install --user
 ### Test the PyTorch Installation
 
 You can use PyTorch unit tests to validate a PyTorch installation. If using a
-prebuilt PyTorch Docker image from AMD ROCm DockerHub or installing an official
+prebuilt PyTorch Docker image from AMD ROCm Docker Hub or installing an official
 wheels package, these tests are already run on those configurations.
 Alternatively, you can manually run the unit tests to validate the PyTorch
 installation fully.
@@ -405,6 +405,22 @@ Follow these steps:
    python3 main.py
    ```
 
+## Using MIOpen kdb files with ROCm PyTorch wheels
+
+PyTorch uses MIOpen for machine learning primitives. These primitives are compiled into kernels at runtime. Runtime compilation causes a small warm-up phase when starting PyTorch. MIOpen kdb files contain precompiled kernels that can speed up the warm-up phase of an application. More information is available in the {doc}`MIOpeninstallation page <miopen:install>`.
+
+MIOpen kdb files can be used with ROCm PyTorch wheels. However, the kdb files need to be placed in a specific location with respect to the PyTorch installation path. A helper script simplifies this task for the user. The script takes in the ROCm version and user's GPU architecture as inputs, and works for Ubuntu and CentOS.
+
+Helper script: [install_kdb_files_for_pytorch_wheels.sh](https://raw.githubusercontent.com/wiki/ROCmSoftwarePlatform/pytorch/files/install_kdb_files_for_pytorch_wheels.sh)
+
+Usage:
+
+After installing ROCm PyTorch wheels:
+
+1. [Optional] `export GFX_ARCH=gfx90a`
+2. [Optional] `export ROCM_VERSION=5.5`
+3. `./install_kdb_files_for_pytorch_wheels.sh`
+
 ## References
 
 C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," CoRR, p. abs/1512.00567, 2015

docs/how_to/tensorflow_install/tensorflow_install.md

@@ -33,8 +33,8 @@ Follow these steps:
 2. Once you have pulled the image, run it by using the command below:
 
    ```bash
-   docker run -it --network=host --device=/dev/kfd --device=/dev/dri
-   --ipc=host --shm-size 16G --group-add video --cap-add=SYS_PTRACE
+   docker run -it --network=host --device=/dev/kfd --device=/dev/dri \
+   --ipc=host --shm-size 16G --group-add video --cap-add=SYS_PTRACE \
    --security-opt seccomp=unconfined rocm/tensorflow:latest
    ```
 

docs/how_to/tuning_guides/mi100.md

@@ -275,7 +275,7 @@ sudo yum install cpupowerutils
 
 :::
 
-:::{tab-item} SUSE Linux Enterprise Server 15
+:::{tab-item} SUSE Linux Enterprise Server
 :sync: SLES
 
 ```shell
@@ -453,7 +453,7 @@ sudo yum install rocm-bandwidth-test
 
 :::
 
-:::{tab-item} SUSE Linux Enterprise Server 15
+:::{tab-item} SUSE Linux Enterprise Server
 :sync: SLES
 
 ```shell

docs/how_to/tuning_guides/mi200.md

@@ -258,7 +258,7 @@ sudo yum install cpupowerutils
 
 :::
 
-:::{tab-item} SUSE Linux Enterprise Server 15
+:::{tab-item} SUSE Linux Enterprise Server
 :sync: SLES
 
 ```shell
@@ -436,7 +436,7 @@ sudo yum install rocm-bandwidth-test
 
 :::
 
-:::{tab-item} SUSE Linux Enterprise Server 15
+:::{tab-item} SUSE Linux Enterprise Server
 :sync: SLES
 
 ```shell

docs/reference/ai_tools.md

@@ -7,20 +7,26 @@
 AMD's library for high performance machine learning primitives.
 
 - {doc}`Documentation <miopen:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/MIOpen)
+- [Changelog](https://github.com/ROCmSoftwarePlatform/MIOpen/blob/develop/CHANGELOG.md)
 
 :::
 
-:::{grid-item-card} {doc}`Composable Kernel <composable-kernel:index>`
+:::{grid-item-card} {doc}`Composable Kernel <composable_kernel:index>`
 Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators
 
-- {doc}`Documentation <composable-kernel:index>`
+- {doc}`Documentation <composable_kernel:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/composable_kernel)
+- [Changelog](https://github.com/ROCmSoftwarePlatform/composable_kernel/blob/develop/CHANGELOG.md)
 
 :::
 
-:::{grid-item-card} {doc}`MIGraphX <migraphx:index>`
+:::{grid-item-card} {doc}`MIGraphX <amdmigraphx:index>`
 AMD MIGraphX is AMD's graph inference engine that accelerates machine learning model inference.
 
-- {doc}`Documentation <migraphx:index>`
+- {doc}`Documentation <amdmigraphx:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/AMDMIGraphX)
+- [Changelog](https://github.com/ROCmSoftwarePlatform/AMDMIGraphX/blob/develop/CHANGELOG.md)
 
 :::
 

docs/reference/all.md

@@ -8,8 +8,9 @@
 :::{grid-item-card} [HIP](./hip)
 HIP is both AMD's GPU programming language extension and the GPU runtime.
 
-- {doc}`hip:.doxygen/docBin/html/index`
-- [Examples](https://github.com/amd/rocm-examples/tree/develop/HIP-Basic)
+- {doc}`HIP <hip:index>`
+- [HIP Examples](https://github.com/amd/rocm-examples/tree/develop/HIP-Basic)
+- {doc}`HIPIFY <hipify:index>`
 
 :::
 
@@ -42,8 +43,8 @@ Inter and intra-node communication is supported by the following projects:
 Libraries related to AI.
 
 - {doc}`MIOpen <miopen:index>`
-- {doc}`Composable Kernel <composable-kernel:index>`
-- {doc}`MIGraphX <migraphx:index>`
+- {doc}`Composable Kernel <composable_kernel:index>`
+- {doc}`MIGraphX <amdmigraphx:index>`
 
 :::
 
@@ -64,6 +65,7 @@ Computer vision related projects.
 :::{grid-item-card} [Compilers and Tools](compilers)
 
 - [ROCmCC](/reference/rocmcc/rocmcc)
+- {doc}`ROCdbgapi <rocdbgapi:index>`
 - {doc}`ROCgdb <rocgdb:index>`
 - {doc}`ROCProfiler <rocprofiler:rocprof>`
 - {doc}`ROCTracer <roctracer:index>`
@@ -72,15 +74,15 @@ Computer vision related projects.
 
 :::{grid-item-card} [Management Tools](management_tools)
 
-- AMD SMI
-- [ROCm SMI](https://rocmdocs.amd.com/projects/rocmsmi/en/latest/)
-- {doc}`ROCm Datacenter Tool <rdc:index>`
+- {doc}`AMD SMI <amdsmi:index>`
+- {doc}`ROCm SMI <rocm_smi_lib:index>`
+- {doc}`ROCm Data Center Tool <rdc:index>`
 
 :::
 
 :::{grid-item-card} [Validation Tools](validation_tools)
 
-- {doc}`ROCm Validation Suite <rocm-validation-suite:index>`
+- {doc}`ROCm Validation Suite <rocmvalidationsuite:index>`
 - {doc}`TransferBench <transferbench:index>`
 
 :::

docs/reference/compilers.md

@@ -3,42 +3,46 @@
 :::::{grid} 1 1 2 2
 :gutter: 1
 
-:::{grid-item-card} ROCmCC
-:link: /reference/rocmcc/rocmcc
-:link-type: doc
+:::{grid-item-card} {doc}`ROCdbgapi <rocdbgapi:index>`
+The AMD Debugger API is a library that provides all the support necessary for a
+debugger and other tools to perform low level control of the execution and
+inspection of execution state of AMD's commercially available GPU architectures.
+
+- {doc}`Documentation <rocdbgapi:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/ROCdbgapi/)
+
+:::
+
+:::{grid-item-card} [ROCmCC](./rocmcc/rocmcc)
 ROCmCC is a Clang/LLVM-based compiler. It is optimized for high-performance
 computing on AMD GPUs and CPUs and supports various heterogeneous programming
 models such as HIP, OpenMP, and OpenCL.
 
+- [Documentation](./rocmcc/rocmcc)
+
 :::
 
-:::{grid-item-card} ROCgdb
-:link: rocgdb:index
-:link-type: doc
+:::{grid-item-card} {doc}`ROCgdb <rocgdb:index>`
 This is ROCgdb, the ROCm source-level debugger for Linux, based on GDB, the GNU source-level debugger.
 
+- {doc}`Documentation <rocgdb:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/ROCgdb/)
+
 :::
 
-:::{grid-item-card} ROCProfiler
-:link: rocprofiler:rocprof
-:link-type: doc
+:::{grid-item-card} {doc}`ROCProfiler <rocprofiler:rocprof>`
 ROC profiler library. Profiling with performance counters and derived metrics. Library supports GFX8/GFX9. Hardware specific low-level performance analysis interface for profiling of GPU compute applications. The profiling includes hardware performance counters with complex performance metrics.
 
-:::
-
-:::{grid-item-card} ROCTracer
-:link: roctracer:index
-:link-type: doc
-Callback/Activity Library for Performance tracing AMD GPU's
+- {doc}`Documentation <rocprofiler:rocprof>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/rocprofiler/)
 
 :::
 
-:::{grid-item-card} ROCdbgapi
-:link: rocdbgapi:index
-:link-type: doc
-The AMD Debugger API is a library that provides all the support necessary for a
-debugger and other tools to perform low level control of the execution and
-inspection of execution state of AMD's commercially available GPU architectures.
+:::{grid-item-card} {doc}`ROCTracer <roctracer:index>`
+Callback/Activity Library for Performance tracing AMD GPUs
+
+- {doc}`Documentation <roctracer:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/roctracer)
 
 :::
 

docs/reference/computer_vision.md

@@ -7,6 +7,8 @@
 MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX also delivers a highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions.
 
 - {doc}`Documentation <mivisionx:README>`
+- [GitHub](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/)
+- [Changelog](https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/blob/master/CHANGELOG.md)
 
 :::
 

docs/reference/gpu_libraries/c++_primitives.md

@@ -11,6 +11,7 @@ transforms, reductions, scans, etc. It also serves as a common back-end for
 similar libraries found inside ROCm.
 
 - {doc}`Documentation <rocprim:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocPRIM/)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocPRIM/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/Libraries/rocPRIM)
 
@@ -22,6 +23,7 @@ interface. Their CPU back-ends are identical, while the GPU back-end calls into
 rocPRIM.
 
 - {doc}`Documentation <rocthrust:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocThrust)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocThrust/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/Libraries/rocThrust)
 
@@ -32,6 +34,7 @@ hipCUB is a template library of algorithm primitives with a CUB-compatible
 interface. It's back-end is rocPRIM.
 
 - {doc}`Documentation <hipcub:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipCUB)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipCUB/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/Libraries/hipCUB)
 

docs/reference/gpu_libraries/communication.md

@@ -10,6 +10,7 @@ The collective operations are implemented using ring and tree algorithms and hav
 throughput and latency.
 
 - {doc}`Documentation <rccl:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rccl)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocFFT/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/ROCmSoftwarePlatform/rccl/tree/develop/tools)
 

docs/reference/gpu_libraries/fft.md

@@ -9,6 +9,7 @@ ROCm libraries for FFT are as follows:
 rocFFT is an AMD GPU optimized library for FFT.
 
 - {doc}`Documentation <rocfft:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocFFT)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocFFT/blob/develop/CHANGELOG.md)
 
 :::
@@ -19,6 +20,7 @@ using rocFFT. hipFFT allows for a common interface for other non AMD GPU
 FFT libraries.
 
 - {doc}`Documentation <hipfft:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipFFT)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipFFT/blob/develop/CHANGELOG.md)
 
 :::

docs/reference/gpu_libraries/linear_algebra.md

@@ -9,6 +9,7 @@ ROCm libraries for linear algebra are as follows:
 `rocBLAS` is an AMD GPU optimized library for BLAS (Basic Linear Algebra Subprograms).
 
 - {doc}`Documentation <rocblas:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocBLAS)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocBLAS/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/Libraries/rocBLAS)
 
@@ -20,6 +21,7 @@ via `rocBLAS` and `rocSOLVER`. `hipBLAS` allows for a common interface for other
 BLAS libraries.
 
 - {doc}`Documentation <hipblas:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipBLAS)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipBLAS/blob/develop/CHANGELOG.md)
 
 :::
@@ -31,6 +33,7 @@ flexible API and extends functionalities beyond traditional BLAS library.
 optimized generator as a back-end kernel provider.
 
 - {doc}`Documentation <hipblaslt:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipBLASLt)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipBLASLt/blob/develop/CHANGELOG.md)
 
 :::
@@ -41,6 +44,7 @@ fine-grained parallelism on top of AMD's ROCm runtime and toolchains, targeting
 modern CPU and GPU platforms.
 
 - {doc}`Documentation <rocalution:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocALUTION)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocALUTION/blob/develop/CHANGELOG.md)
 
 :::
@@ -50,6 +54,7 @@ modern CPU and GPU platforms.
 (MMA) problems into fragments and distributes these over GPU wavefronts.
 
 - {doc}`Documentation <rocwmma:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocWMMA)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocWMMA/blob/develop/CHANGELOG.md)
 
 :::
@@ -58,6 +63,7 @@ modern CPU and GPU platforms.
 `rocSOLVER` provides a subset of LAPACK (Linear Algebra Package) functionality on the ROCm platform.
 
 - {doc}`Documentation <rocsolver:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocSOLVER)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/CHANGELOG.md)
 
 :::
@@ -67,6 +73,7 @@ modern CPU and GPU platforms.
 as backends whilst exporting a unified interface.
 
 - {doc}`Documentation <hipsolver:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipSOLVER)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipSOLVER/blob/develop/CHANGELOG.md)
 
 :::
@@ -75,6 +82,7 @@ as backends whilst exporting a unified interface.
 `rocSPARSE` is a library to provide BLAS for sparse computations.
 
 - {doc}`Documentation <rocsparse:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocSPARSE)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocSOLVER/blob/develop/CHANGELOG.md)
 
 :::
@@ -84,6 +92,7 @@ as backends whilst exporting a unified interface.
 supporting both `rocSPARSE` and `cuSPARSE` as backends.
 
 - {doc}`Documentation <hipsparse:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipSPARSE)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipSOLVER/blob/develop/CHANGELOG.md)
 
 :::

docs/reference/gpu_libraries/rand.md

@@ -7,6 +7,7 @@
 rocRAND is an AMD GPU optimized library for pseudo-random number generators (PRNG).
 
 - {doc}`Documentation <rocrand:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/rocRAND/)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/rocRAND/blob/develop/CHANGELOG.md)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/Libraries/rocRAND)
 
@@ -18,6 +19,7 @@ generation (PRNG) optimized for AMD GPUs using rocRAND. hipRAND allows for a
 common interface for other non AMD GPU PRNG libraries.
 
 - {doc}`Documentation <hiprand:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/hipRAND/)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/hipRAND/blob/develop/CHANGELOG.md)
 
 :::

docs/reference/hip.md

@@ -12,7 +12,8 @@ page introduces the HIP runtime and other HIP libraries and tools.
 The HIP Runtime is used to enable GPU acceleration for all HIP language based
 products.
 
-- {doc}`hip:.doxygen/docBin/html/index`
+- {doc}`Documentation <hip:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/HIP)
 - [Examples](https://github.com/amd/rocm-examples/tree/develop/HIP-Basic)
 
 :::
@@ -28,7 +29,9 @@ products.
 HIPIFY assists with porting applications from based on CUDA to the HIP Runtime.
 Supported CUDA APIs are documented here as well.
 
-- {doc}`Reference Manual <hipify:index>`
+- {doc}`Documentation <hipify:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/HIPIFY/)
+- [Changelog](https://github.com/ROCm-Developer-Tools/HIPIFY/blob/amd-staging/CHANGELOG.md)
 
 :::
 

docs/reference/management_tools.md

@@ -3,28 +3,29 @@
 :::::{grid} 1 1 3 3
 :gutter: 1
 
-:::{grid-item-card} AMD SMI
+:::{grid-item-card} {doc}`AMD SMI <amdsmi:index>`
 The AMD System Management Interface Library, or AMD SMI library, is a C library for Linux that provides a user space interface for applications to monitor and control AMD devices.
 
+- {doc}`Documentation <amdsmi:index>`
 - [GitHub](https://github.com/RadeonOpenCompute/amdsmi)
 - [Examples](https://github.com/amd/go_amd_smi#example)
 
 :::
 
-:::{grid-item-card} [ROCm SMI](https://rocmdocs.amd.com/projects/rocmsmi/en/latest/)
+:::{grid-item-card} {doc}`ROCm SMI LIB <rocm_smi_lib:index>`
 This tool acts as a command line interface for manipulating and monitoring the AMD GPU kernel, and is intended to replace and deprecate the existing `rocm_smi.py` CLI tool. It uses `ctypes` to call the `rocm_smi_lib` API.
 
-- [Documentation](https://rocmdocs.amd.com/projects/rocmsmi/en/latest/)
+- {doc}`Documentation <rocm_smi_lib:index>`
 - [GitHub](https://github.com/RadeonOpenCompute/rocm_smi_lib)
 - [Examples](https://github.com/RadeonOpenCompute/rocm_smi_lib/tree/master/python_smi_tools)
 
 :::
 
-:::{grid-item-card} {doc}`ROCm Datacenter Tool <rdc:index>`
+:::{grid-item-card} {doc}`ROCm Data Center Tool <rdc:index>`
 The ROCm™ Data Center Tool simplifies the administration and addresses key infrastructure challenges in AMD GPUs in cluster and data center environments.
 
-- {doc}`Documentation <rdc:index>`
 - [GitHub](https://github.com/RadeonOpenCompute/rdc)
+- [Changelog](https://github.com/RadeonOpenCompute/rdc/blob/master/CHANGELOG.md)
 - [Examples](https://github.com/RadeonOpenCompute/rdc/tree/master/example)
 
 :::

docs/reference/openmp/openmp.md

@@ -53,11 +53,10 @@ that are required for target offload from an OpenMP program:
 ```
 
 :::{note}
-The Makefile in the example above uses a more classical and verbose set of flags
-which can also be used:
+The compiler also accepts the alternative offloading notation:
 
 ```bash
--fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa
+-fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=<gpu-arch> 
 ```
 
 :::
@@ -142,8 +141,8 @@ For more details on tracing, refer to the ROCm Profiling Tools document on
 
 :::{table}
 :widths: auto
-| Environment Variable        | Description |
-| --------------------------- | ----------- |
+| Environment Variable        | Description                  |
+| --------------------------- | ---------------------------- |
 | `OMP_NUM_TEAMS`             | The implementation chooses the number of teams for kernel launch. The user can change this number for performance tuning using this environment variable, subject to implementation limits. |
 | `LIBOMPTARGET_KERNEL_TRACE` | This environment variable is used to print useful statistics for device operations. Setting it to 1 and running the program emits the name of every kernel launched, the number of teams and threads used, and the corresponding register usage. Setting it to 2 additionally emits timing information for kernel launches and data transfer operations between the host and the device. |
 | `LIBOMPTARGET_INFO`         | This environment variable is used to print informational messages from the device runtime as the program executes. Users can request fine-grain information by setting it to the value of 1 or higher and can set the value of -1 for complete information. |
@@ -158,6 +157,14 @@ implemented in the past releases.
 
 (openmp_usm)=
 
+### Asynchronous Behavior in OpenMP Target Regions
+
+- Multithreaded offloading on the same device
+The `libomptarget` plugin for GPU offloading allows creation of separate configurable HSA queues per chiplet, which enables two or more threads to concurrently offload to the same device.
+
+- Parallel memory copy invocations
+Implicit asynchronous execution of single target region enables parallel memory copy invocations.
+
 ### Unified Shared Memory
 
 Unified Shared Memory (USM) provides a pointer-based approach to memory
@@ -178,39 +185,34 @@ with Xnack capability.
 When enabled, Xnack capability allows GPU threads to access CPU (system) memory,
 allocated with OS-allocators, such as `malloc`, `new`, and `mmap`. Xnack must be
 enabled both at compile- and run-time. To enable Xnack support at compile-time,
-the programmer should use
+use:
 
 ```bash
 --offload-arch=gfx908:xnack+
 ```
 
-Or, equivalently
+Or use another functionally equivalent option Xnack-any:
 
 ```bash
 --offload-arch=gfx908
 ```
 
-:::{note}
-The second case is called Xnack-any and it is functionally equivalent to the
-first case.
-:::
-
-At runtime, programmers enable Xnack functionality on a per-application basis
-using an environment variable:
+To enable Xnack functionality at runtime on a per-application basis,
+use environment variable:
 
 ```bash
 HSA_XNACK=1
 ```
 
-When Xnack support is not needed, then applications can be built to maximize
-resource utilization using:
+When Xnack support is not needed:
+
+- Build the applications to maximize resource utilization using:
 
 ```bash
 --offload-arch=gfx908:xnack-
 ```
 
-At runtime, the `HSA_XNACK` environment variable can be set to 0, as Xnack
-functionality is not needed.
+- At runtime, set the `HSA_XNACK` environment variable to 0.
 
 #### Unified Shared Memory Pragma
 
@@ -264,7 +266,7 @@ The difference between the memory pages pointed to by these two variables is
 that the pages pointed by “a” are in fine-grain memory, while the pages pointed
 to by “b” are in coarse-grain memory during and after the execution of the
 target region. This is accomplished in the OpenMP runtime library with calls to
-the ROCR runtime to set the pages pointed by “b” as coarse grain.
+the ROCr runtime to set the pages pointed by “b” as coarse grain.
 
 ### OMPT Target Support
 
@@ -431,43 +433,46 @@ for(int i=0; i<N; i++){
 See the complete sample code for global buffer overflow
 [here](https://github.com/ROCm-Developer-Tools/aomp/blob/aomp-dev/examples/tools/asan/global_buffer_overflow/openmp/vecadd-GBO.cpp).
 
-### No-loop Kernel Generation
+### Clang Compiler Option for Kernel Optimization
 
-The No-loop kernel generation feature optimizes the compiler performance by
-generating a specialized kernel for certain OpenMP Target Constructs such as
-target teams distribute parallel for. The specialized kernel generation assumes
-that every thread executes a single iteration of the user loop, which implies
-that the runtime launches a total number of GPU threads equal to or greater than
-the iteration space size of the target region loop. This allows the compiler to
-generate code for the loop body without an enclosing loop, resulting in reduced
-control-flow complexity and potentially better performance.
+You can use the clang compiler option `-fopenmp-target-fast` for kernel optimization if certain constraints implied by its component options are satisfied. `-fopenmp-target-fast` enables the following options:
 
-To enable the generation of the specialized kernel, follow these guidelines:
+- `-fopenmp-target-ignore-env-vars`: It enables code generation of specialized kernels including No-loop and Cross-team reductions.
 
-- Do not specify teams, threads, and schedule-related environment variables. The
-  `num_teams` or a `thread_limit` clause in an OpenMP target construct acts as
-  an override and prevents the generation of the specialized kernel. As the user
-  is unable to specify the number of teams and threads used within target
-  regions in the absence of the above-mentioned environment variables, the
-  runtime will select the best values for the launch configuration based on
-  runtime knowledge of the program.
+- `-fopenmp-assume-no-thread-state`: It enables the compiler to assume that no thread in a parallel region modifies an Internal Control Variable (`ICV`), thus potentially reducing the device runtime code execution.
 
-- Assert the absence of the above-mentioned environment variables by adding the
-  command-line option `-fopenmp-target-ignore-env-vars`. This option also allows
-  programmers to enable the No-loop functionality at lower optimization levels.
+- `-fopenmp-assume-no-nested-parallelism`: It enables the compiler to assume that no thread in a parallel region encounters a parallel region, thus potentially reducing the device runtime code execution.
 
-- Also, the No-loop functionality is automatically enabled when `-O3` or
-  `-Ofast` is used for compilation. To disable this feature, use
-  `-fno-openmp-target-ignore-env-vars`.
+- `-O3` if no `-O*` is specified by the user.
 
-Note The compiler might not generate the No-loop kernel in certain scenarios
-where the performance improvement is not substantial.
+### Specialized Kernels
 
-### Cross-Team Optimized Reductions
+Clang will attempt to generate specialized kernels based on compiler options and OpenMP constructs. The following specialized kernels are supported:
 
-In scenarios where a No-loop kernel is generated but the OpenMP construct has a
-reduction clause, the compiler may generate optimized code utilizing efficient
-Cross-Team (Xteam) communication. No separate user option is required, and there
-is a significant performance improvement with Xteam reduction. New APIs for
-Xteam reduction are implemented in the device runtime, and clang generates these
-APIs automatically.
+- No-Loop
+
+- Big-Jump-Loop
+
+- Cross-Team (Xteam) Reductions
+
+To enable the generation of specialized kernels, follow these guidelines:
+
+- Do not specify teams, threads, and schedule-related environment variables. The `num_teams` clause in an OpenMP target construct acts as an override and prevents the generation of the No-Loop kernel. If the specification of `num_teams` clause is a user requirement then clang tries to generate the Big-Jump-Loop kernel instead of the No-Loop kernel.
+
+- Assert the absence of the teams, threads, and schedule-related environment variables by adding the command-line option `-fopenmp-target-ignore-env-vars`.
+
+- To automatically enable the specialized kernel generation, use `-Ofast` or `-fopenmp-target-fast` for compilation.
+
+- To disable specialized kernel generation, use `-fno-openmp-target-ignore-env-vars`.
+
+#### No-Loop Kernel Generation
+
+The No-loop kernel generation feature optimizes the compiler performance by generating a specialized kernel for certain OpenMP target constructs such as target teams distribute parallel for. The specialized kernel generation feature assumes every thread executes a single iteration of the user loop, which leads the runtime to launch a total number of GPU threads equal to or greater than the iteration space size of the target region loop. This allows the compiler to generate code for the loop body without an enclosing loop, resulting in reduced control-flow complexity and potentially better performance.
+
+#### Big-Jump-Loop Kernel Generation
+
+A No-Loop kernel is not generated if the OpenMP teams construct uses a `num_teams` clause. Instead, the compiler attempts to generate a different specialized kernel called the Big-Jump-Loop kernel. The compiler launches the kernel with a grid size determined by the number of teams specified by the OpenMP `num_teams` clause and the `blocksize` chosen either by the compiler or specified by the corresponding OpenMP clause.
+
+#### Xteam Optimized Reduction Kernel Generation
+
+If the OpenMP construct has a reduction clause, the compiler attempts to generate optimized code by utilizing efficient Xteam communication. New APIs for Xteam reduction are implemented in the device runtime and are automatically generated by clang.

docs/reference/validation_tools.md

@@ -3,10 +3,12 @@
 :::::{grid} 1 1 2 2
 :gutter: 1
 
-:::{grid-item-card} {doc}`RVS <rocm-validation-suite:index>`
+:::{grid-item-card} {doc}`RVS <rocmvalidationsuite:index>`
 The ROCm Validation Suite is a system administrator’s and cluster manager's tool for detecting and troubleshooting common problems affecting AMD GPU(s) running in a high-performance computing environment, enabled using the ROCm software stack on a compatible platform.
 
-- {doc}`Documentation <rocm-validation-suite:index>`
+- {doc}`Documentation <rocmvalidationsuite:index>`
+- [GitHub](https://github.com/ROCm-Developer-Tools/ROCmValidationSuite)
+- [Changelog](https://github.com/ROCm-Developer-Tools/ROCmValidationSuite/blob/master/CHANGELOG.md)
 
 :::
 
@@ -14,6 +16,7 @@ The ROCm Validation Suite is a system administrator’s and cluster manager's to
 TransferBench is a simple utility capable of benchmarking simultaneous transfers between user-specified devices (CPUs/GPUs).
 
 - {doc}`Documentation <transferbench:index>`
+- [GitHub](https://github.com/ROCmSoftwarePlatform/TransferBench/)
 - [Changelog](https://github.com/ROCmSoftwarePlatform/TransferBench/blob/develop/CHANGELOG.md)
 - {doc}`transferbench:examples/index`
 

docs/release/3rd_party_support_matrix.md

@@ -19,6 +19,7 @@ TensorFlow
 | 5.3.x | 1.10.1, 1.11, 1.12.1, 1.13 | 2.8, 2.9, 2.10       |       |
 | 5.4.x | 1.10.1, 1.11, 1.12.1, 1.13 | 2.8, 2.9, 2.10, 2.11 | 2.5.4 |
 | 5.5.x | 1.10.1, 1.11, 1.12.1, 1.13 | 2.10, 2.11           | 2.5.4 |
+| 5.6   | 1.11, 1.12.1, 1.13.1       | 2.12                 | 2.5.4 |
 
 ## Communication libraries
 
@@ -47,6 +48,7 @@ contemporary CUDA / NVIDIA HPC SDK alternatives.
 | 5.3.x | 1.16         | 22.7       |
 | 5.4.x | 1.16         | 22.9       |
 | 5.5.x | 1.17         | 22.9       |
+| 5.6   | 1.17.2       | 22.9       |
 
 For the latest documentation of these libraries, refer to the
 [associated documentation](../reference/gpu_libraries/c%2B%2B_primitives.md).

docs/release/docker_image_support_matrix.md

@@ -8,7 +8,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `Ubuntu+ rocm5.6_internal_testing +169530b`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.8](https://www.python.org/downloads/release/python-380/)
 * [Torch 2.0.0](https://github.com/ROCmSoftwarePlatform/pytorch/tree/rocm5.6_internal_testing)
 * [Apex 0.1](https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1)
@@ -21,7 +21,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `CentOS7+ rocm5.6_internal_testing +169530b`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.8](https://www.python.org/downloads/release/python-380/)
 * [Torch 2.0.0](https://github.com/ROCmSoftwarePlatform/pytorch/tree/rocm5.6_internal_testing)
 * [Apex 0.1](https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1)
@@ -31,7 +31,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `1.13 +bfeb431`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.8](https://www.python.org/downloads/release/python-380/)
 * [Torch 1.13.1](https://github.com/ROCmSoftwarePlatform/pytorch/tree/release/1.13)
 * [Apex 0.1](https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1)
@@ -44,7 +44,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `1.12 +05d5d04`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.8](https://www.python.org/downloads/release/python-380/)
 * [Torch 1.12.1](https://github.com/ROCmSoftwarePlatform/pytorch/tree/release/1.12)
 * [Apex 0.1](https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1)
@@ -59,7 +59,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `tensorflow_develop-upstream-QA-rocm56 +c88a9f4`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.9](https://www.python.org/downloads/release/python-390/)
 * `tensorflow-rocm` 2.13.0
 * [OFED 5.3](https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz)
@@ -69,7 +69,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `r2.11-rocm-enhanced +5be4141`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.9](https://www.python.org/downloads/release/python-390/)
 * [`tensorflow-rocm` 2.11.0](https://pypi.org/project/tensorflow-rocm/2.11.0.540/)
 * [OFED 5.3](https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz)
@@ -79,7 +79,7 @@ The software support matrices for ROCm container releases is listed.
 
 #### `r2.10-rocm-enhanced +72789a3`
 
-* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
+* [ROCm5.6](https://repo.radeon.com/rocm/apt/5.6/)
 * [Python 3.9](https://www.python.org/downloads/release/python-390/)
 * [`tensorflow-rocm` 2.10.1](https://pypi.org/project/tensorflow-rocm/2.10.1.540/)
 * [OFED 5.3](https://content.mellanox.com/ofed/MLNX_OFED-5.3-1.0.5.0/MLNX_OFED_LINUX-5.3-1.0.5.0-ubuntu20.04-x86_64.tgz)

docs/release/gpu_os_support.md

@@ -1,18 +1,52 @@
-# GPU and OS Support (Linux)
+# GPU Support and OS Compatibility (Linux)
 
 (supported_distributions)=
 
-## Supported Distributions
+## Supported Linux Distributions
 
 AMD ROCm™ Platform supports the following Linux distributions.
 
-| Distribution       |Processor Architectures| Validated Kernel   |
-|--------------------|-----------------------|--------------------|
-| RHEL 9.1           | x86-64                | 5.14               |
-| RHEL 8.6 to 8.7    | x86-64                | 4.18               |
-| SLES 15 SP4        | x86-64                |                    |
-| Ubuntu 20.04.5 LTS | x86-64                | 5.15               |
-| Ubuntu 22.04.1 LTS | x86-64                | 5.15, OEM 5.17     |
+::::{tab-set}
+
+:::{tab-item} Supported
+
+| Distribution | Processor Architectures | Validated Kernel | Support |
+| :----------- | :---------------------: | :--------------: | ------: |
+| RHEL 9.2       | x86-64 | 5.14 (5.14.0-284.11.1.el9_2.x86_64)        | ✅ |
+| RHEL 9.1       | x86-64 | 5.14.0-284.11.1.el9_2.x86_64             | ✅ |
+| RHEL 8.8       | x86-64 | 4.18.0-477.el8.x86_64        | ✅ |
+| RHEL 8.7       | x86-64 | 4.18.0-425.10.1.el8_7.x86_64              | ✅ |
+| SLES 15 SP5    | x86-64 |  5.14.21-150500.53-default       | ✅ |
+| SLES 15 SP4    | x86-64 | 5.14.21-150400.24.63-default               | ✅ |
+| Ubuntu 22.04.2 | x86-64 | 5.19.0-45-generic | ✅ |
+| Ubuntu 20.04.5 | x86-64 | 5.15.0-75-generic          | ✅ |
+
+:::{versionadded} 5.6
+
+- RHEL 8.8 and 9.2 support is added.
+- SLES 15 SP5 support is added
+
+:::
+
+:::{tab-item} Unsupported
+
+| Distribution | Processor Architectures | Validated Kernel | Support |
+| :----------- | :---------------------: | :--------------: | ------: |
+| RHEL 9.0       | x86-64 | 5.14               | ❌ |
+| RHEL 8.6       | x86-64 | 5.14               | ❌ |
+| SLES 15 SP3    | x86-64 | 5.3                | ❌ |
+| Ubuntu 22.04.0 | x86-64 | 5.15 LTS, 5.17 OEM | ❌ |
+| Ubuntu 20.04.4 | x86-64 | 5.13 HWE, 5.13 OEM | ❌ |
+| Ubuntu 22.04.1 | x86-64 | 5.15 LTS           | ❌ |
+
+:::
+
+::::
+
+- ✅: **Supported** - AMD performs full testing of all ROCm components on distro
+  GA image.
+- ❌: **Unsupported** - AMD no longer performs builds and testing on these
+  previously supported distro GA images.
 
 ## Virtualization Support
 
@@ -26,7 +60,11 @@ ROCm supports virtualization for select GPUs only as shown below.
 
 (supported_gpus)=
 
-## GPU Support Table
+## Linux Supported GPUs
+
+The table below shows supported GPUs for Instinct™, Radeon Pro™ and Radeon™
+GPUs. Please click the tabs below to switch between GPU product lines. If a GPU
+is not listed on this table, the GPU is not officially supported by AMD.
 
 ::::{tab-set}
 
@@ -59,6 +97,17 @@ Use Driver Shipped with ROCm
 
 :::
 
+:::{tab-item} Radeon™
+:sync: radeonpro
+
+[Use Radeon Pro Driver](https://www.amd.com/en/support/linux-drivers)
+
+| Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Support|
+|:----:|:------------:|:--------------------------------------------------------------------:|:-------:|
+| AMD Radeon™ VII     | GCN5.1 | gfx906  | ✅ |
+
+:::
+
 ::::
 
 ### Support Status

docs/release/licensing.md

@@ -5,7 +5,6 @@ The following table is a list of ROCm components with links to their respective
 terms. These components may include third party components subject to
 additional licenses. Please review individual repositories for more information.
 The table shows ROCm components, the name of license and link to the license terms.
-The table is ordered to follow ROCm's manifest file.
 
 <!-- spellcheck-disable -->
 | Component                                                                                        | License                                                                                                                    |

docs/release/windows_support.md

@@ -0,0 +1,83 @@
+# GPU and OS Support (Windows)
+
+(supported_skus)=
+
+## Supported SKUs
+
+AMD ROCm™ Platform supports the following Windows SKU.
+
+| Distribution        |Processor Architectures| Validated update   |
+|---------------------|-----------------------|--------------------|
+| Windows 10          | x86-64                | 22H2 (GA)          |
+| Windows 11          | x86-64                | 22H2 (GA)          |
+| Windows Server 2022 | x86-64                |                    |
+
+## Windows Supported GPUs
+
+The table below shows supported GPUs for Radeon Pro™ and Radeon™ GPUs. Please
+click the tabs below to switch between GPU product lines. If a GPU is not listed
+on this table, the GPU is not officially supported by AMD.
+
+::::{tab-set}
+
+:::{tab-item} Radeon Pro™
+:sync: radeonpro
+
+| Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Runtime | HIP SDK |
+|:----:|:------------:|:--------------------------------------------------------------------:|:-------:|:----------------:|
+| AMD Radeon Pro™ W7900   | RDNA3  | gfx1100 | ✅ | ✅ |
+| AMD Radeon Pro™ W7800   | RDNA3  | gfx1100 | ✅ | ✅ |
+| AMD Radeon Pro™ W6800   | RDNA2  | gfx1030 | ✅ | ✅ |
+| AMD Radeon Pro™ W6600   | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon Pro™ W5500   | RDNA1  | gfx1012 | ❌ | ❌ |
+| AMD Radeon Pro™ VII     | GCN5.1 | gfx906  | ❌ | ❌ |
+
+:::
+
+:::{tab-item} Radeon™
+:sync: radeon
+
+| Name | Architecture | [LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Runtime | HIP SDK |
+|:----:|:------------:|:--------------------------------------------------------------------:|:-------:|:----------------:|
+| AMD Radeon™ RX 7900 XTX | RDNA3  | gfx1100 | ✅ | ✅ |
+| AMD Radeon™ RX 7900 XT  | RDNA3  | gfx1100 | ✅ | ✅ |
+| AMD Radeon™ RX 7600     | RDNA3  | gfx1100 | ✅ | ✅ |
+| AMD Radeon™ RX 6950 XT  | RDNA2  | gfx1030 | ✅ | ✅ |
+| AMD Radeon™ RX 6900 XT  | RDNA2  | gfx1030 | ✅ | ✅ |
+| AMD Radeon™ RX 6800 XT  | RDNA2  | gfx1030 | ✅ | ✅ |
+| AMD Radeon™ RX 6800     | RDNA2  | gfx1030 | ✅ | ✅ |
+| AMD Radeon™ RX 6750     | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon™ RX 6700 XT  | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon™ RX 6700     | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon™ RX 6650 XT  | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon™ RX 6600 XT  | RDNA2  | gfx1032 | ✅ | ❌ |
+| AMD Radeon™ RX 6600     | RDNA2  | gfx1032 | ✅ | ❌ |
+
+:::
+
+::::
+
+### Component Support
+
+ROCm components are described in the [reference](../reference/all) page. Support
+on Windows is provided with two levels on enablement.
+
+- **Runtime**: Runtime enables the use of the HIP/OpenCL runtimes only.
+- **HIP SDK**: Runtime plus additional components refer to libraries found under
+  [Math Libraries](../reference/gpu_libraries/math.md) and
+  [C++ Primitive Libraries](../reference/gpu_libraries/c%2B%2B_primitives.md).
+  Some [Math Libraries](../reference/gpu_libraries/math.md) are Linux exclusive,
+  please check the library details.
+
+### Support Status
+
+- ✅: **Supported** - AMD enables these GPUs in our software distributions for
+  the corresponding ROCm product.
+- ⚠️: **Deprecated** - Support will be removed in a future release.
+- ❌: **Unsupported** - This configuration is not enabled in our software
+  distributions.
+
+## CPU Support
+
+ROCm requires CPUs that support PCIe™ Atomics. Modern CPUs after the release of
+1st generation AMD Zen CPU and Intel™ Haswell support PCIe Atomics.

docs/rocm.md

@@ -18,7 +18,97 @@ integrated into ML frameworks such as PyTorch and TensorFlow. ROCm can be
 deployed in many ways, including through the use of containers such as Docker,
 Spack, and your own build from source.
 
-ROCm’s goal is to allow our users to maximize their GPU hardware investment.
+The goal of ROCm is to allow our users to maximize their GPU hardware investment.
 ROCm is designed to help develop, test and deploy GPU accelerated HPC, AI,
 scientific computing, CAD, and other applications in a free, open-source,
 integrated and secure software ecosystem.
+
+## ROCm on Windows
+
+Starting with ROCm 5.5, the HIP SDK brings a subset of ROCm to developers on Windows.
+The collection of features enabled on Windows is referred to as the HIP SDK.
+These features allow developers to use the HIP runtime, HIP math libraries
+and HIP Primitive libraries. The following table shows the differences
+between Windows and Linux releases.
+
+|Component|Linux|Windows|
+|---------|-----|-------|
+|Driver|Radeon Software for Linux |AMD Software Pro Edition|
+|Compiler|`hipcc`/`amdclang++`|`hipcc`/`clang++`|
+|Debugger|`rocgdb`|no debugger available|
+|Profiler|`rocprof`|[Radeon GPU Profiler](https://gpuopen.com/rgp/)|
+|Porting Tools|HIPIFY|Coming Soon|
+|Runtime|HIP (Open Sourced)|HIP (closed source)|
+|Math Libraries|Supported|Supported|
+|Primitives Libraries|Supported|Supported|
+|Communication Libraries|Supported|Not Available|
+|AI Libraries|MIOpen, MIGraphX|Not Available|
+|System Management|`rocm-smi-lib`, RDC, `rocminfo`|`amdsmi`, `hipInfo`|
+|AI Frameworks|PyTorch, TensorFlow, etc.|Not Available|
+|CMake HIP Language|Enabled|Unsupported|
+|Visual Studio| Not applicable| Plugin Available|
+|HIP Ray Tracing| Supported|Supported|
+
+AMD is continuing to invest in Windows support and AMD plans to release enhanced
+features in subsequent revisions.
+
+```{note}
+The 5.5 Windows Installer collectively groups the Math and Primitives
+libraries.
+```
+
+```{note}
+GPU support on Windows and Linux may differ. You must refer to
+Windows and Linux GPU support tables separately.
+```
+
+```{note}
+HIP Ray Tracing is not distributed via ROCm in Linux.
+```
+
+### ROCm release versioning
+
+Linux OS releases set the canonical version numbers for ROCm. Windows will
+follow Linux version numbers as Windows releases are based on Linux ROCm
+releases. However, not all Linux ROCm releases will have a corresponding Windows
+release. The following table shows the ROCm releases on Windows and Linux. Releases
+with both Windows and Linux are referred to as a joint release. Releases with
+only Linux support are referred to as a skipped release from the Windows
+perspective.
+
+|Release version|Linux|Windows|
+|---------------|-----|-------|
+|5.5|✅|✅|
+|5.6|✅|❌|
+
+ROCm Linux releases are versioned with following the Major.Minor.Patch
+version number system. Windows releases will only be versioned with Major.Minor.
+
+In general, Windows releases will trail Linux releases. Software developers that
+wish to support both Linux and Windows using a single ROCm version should
+refrain from upgrading ROCm unless there is a joint release.
+
+### Windows Documentation implications
+
+The ROCm documentation website contains both Windows and Linux documentation.
+Just below each article title, a convenient article information section states
+whether the page applies to Linux only, Windows only or both OSes. To find the
+exact Windows documentation for a release of the HIP SDK, please view the ROCm documentation with the same
+Major.Minor version number while ignoring the Patch version. The Patch version
+only matters for Linux releases.  For convenience,
+Windows documentation will continue to be included in the overall ROCm
+documentation for the skipped Windows releases.
+
+Windows release notes will contain only information pertinent to Windows.
+The software developer must read all the previous ROCm release notes (including)
+skipped ROCm versions on Windows for information on all the changes present in
+the Windows release.
+
+### Windows Builds from Source
+
+Not all source code required to build Windows from source is available under a
+permissive open source license. Build instructions on Windows is only provided
+for projects that can be built from source on Windows using a toolchain that
+has closed source build prerequisites. The ROCm manifest file is not valid for
+Windows. AMD does not release a manifest or tag our components in Windows.
+Users may use corresponding Linux tags to build on Windows.

docs/sphinx/_toc.yml.in

@@ -38,6 +38,32 @@ subtrees:
                 title: Upgrade
               - file: deploy/linux/installer/uninstall
                 title: Uninstallation
+  - file: deploy/windows/quick_start
+    title: Windows Quick Start
+  - file: deploy/windows/index
+    title: Windows Overview
+    subtrees:
+      - entries:
+        - file: deploy/windows/prerequisites
+          title: Prerequisites
+        - file: deploy/windows/gui/index
+          subtrees:
+            - entries:
+              - file: deploy/windows/gui/install
+                title: Installation
+              - file: deploy/windows/gui/upgrade
+                title: Upgrade
+              - file: deploy/windows/gui/uninstall
+                title: Uninstallation
+        - file: deploy/windows/cli/index
+          subtrees:
+            - entries:
+              - file: deploy/windows/cli/install
+                title: Installation
+              - file: deploy/windows/cli/upgrade
+                title: Upgrade
+              - file: deploy/windows/cli/uninstall
+                title: Uninstallation
   - file: deploy/docker
     title: Docker
 
@@ -47,6 +73,7 @@ subtrees:
   - file: CHANGELOG
     title: Changelog
   - file: release/gpu_os_support
+  - file: release/windows_support
   - url: https://github.com/RadeonOpenCompute/ROCm/labels/Verified%20Issue
     title: Known Issues
   - file: release/compatibility
@@ -61,20 +88,6 @@ subtrees:
 - caption: APIs and Reference
   entries:
     - file: reference/all
-    - file: reference/compilers
-      title: Compilers and Tools
-      subtrees:
-        - entries:
-          - file: reference/rocmcc/rocmcc
-            title: ROCmCC
-          - url: ${project:rocgdb}
-            title: ROCgdb
-          - url: ${project:rocprofiler}
-            title: rocprofiler
-          - url: ${project:roctracer}
-            title: roctracer
-          - url: ${project:rocdbgapi}
-            title: ROCdbgapi
     - file: reference/hip
       subtrees:
         - entries:
@@ -82,8 +95,6 @@ subtrees:
               url: ${project:hip}
             - title: HIPify - Port Your Code
               url: ${project:hipify}
-    - file: reference/openmp/openmp
-      title: OpenMP
     - file: reference/gpu_libraries/math
       title: Math Libraries
       subtrees:
@@ -148,9 +159,9 @@ subtrees:
           - title: MIOpen - Machine Intelligence
             url: ${project:miopen}
           - title: Composable Kernel
-            url: ${project:composable-kernel}
+            url: ${project:composable_kernel}
           - title: MIGraphX - Graph Optimization
-            url: ${project:migraphx}
+            url: ${project:amdmigraphx}
     - file: reference/computer_vision
       subtrees:
         - entries:
@@ -159,13 +170,29 @@ subtrees:
         - entries:
           - url: ${project:rocal}
             title: rocAL 
+    - file: reference/openmp/openmp
+      title: OpenMP
+    - file: reference/compilers
+      title: Compilers and Tools
+      subtrees:
+        - entries:
+          - file: reference/rocmcc/rocmcc
+            title: ROCmCC
+          - url: ${project:rocgdb}
+            title: ROCgdb
+          - url: ${project:rocprofiler}
+            title: rocprofiler
+          - url: ${project:roctracer}
+            title: roctracer
+          - url: ${project:rocdbgapi}
+            title: ROCdbgapi
     - file: reference/management_tools
       title: Management Tools
       subtrees:
         - entries:
           - url: https://rocm.docs.amd.com/projects/amdsmi/en/{branch}/
             title: AMD SMI
-          - url: https://rocm.docs.amd.com/projects/rocmsmi/en/{branch}/
+          - url: https://rocm.docs.amd.com/projects/rocm_smi_lib/en/{branch}/
             title: ROCm SMI
           - url: ${project:rdc}
             title: ROCm Datacenter Tool
@@ -173,7 +200,7 @@ subtrees:
       title: Validation Tools
       subtrees:
         - entries:
-          - url: ${project:rocm-validation-suite}
+          - url: ${project:rocmvalidationsuite}
             title: RVS
           - url: ${project:transferbench}
             title: TransferBench

docs/sphinx/requirements.in

@@ -1 +1,2 @@
-rocm-docs-core==0.13.4
+rocm-docs-core==1.8.0
+sphinx-reredirects

docs/sphinx/requirements.txt

@@ -1,110 +1,106 @@
 #
-# This file is autogenerated by pip-compile with Python 3.8
+# This file is autogenerated by pip-compile with Python 3.10
 # by the following command:
 #
-#    pip-compile sphinx/requirements.in
+#    pip-compile requirements.in
 #
-accessible-pygments==0.0.3
+accessible-pygments==0.0.5
     # via pydata-sphinx-theme
-alabaster==0.7.13
+alabaster==1.0.0
     # via sphinx
-babel==2.11.0
+babel==2.16.0
     # via
     #   pydata-sphinx-theme
     #   sphinx
-beautifulsoup4==4.11.2
+beautifulsoup4==4.12.3
     # via pydata-sphinx-theme
-breathe==4.34.0
+breathe==4.35.0
     # via rocm-docs-core
-certifi==2022.12.7
+certifi==2024.8.30
     # via requests
-cffi==1.15.1
+cffi==1.17.1
     # via
     #   cryptography
     #   pynacl
-charset-normalizer==2.1.1
+charset-normalizer==3.3.2
     # via requests
-click==8.1.3
+click==8.1.7
     # via sphinx-external-toc
-cryptography==40.0.2
+cryptography==43.0.1
     # via pyjwt
-deprecated==1.2.13
+deprecated==1.2.14
     # via pygithub
-docutils==0.19
+docutils==0.21.2
     # via
     #   breathe
     #   myst-parser
     #   pydata-sphinx-theme
     #   sphinx
-fastjsonschema==2.16.3
+fastjsonschema==2.20.0
     # via rocm-docs-core
-gitdb==4.0.10
+gitdb==4.0.11
     # via gitpython
-gitpython==3.1.30
+gitpython==3.1.43
     # via rocm-docs-core
-idna==3.4
+idna==3.10
     # via requests
 imagesize==1.4.1
     # via sphinx
-jinja2==3.1.2
+jinja2==3.1.4
     # via
     #   myst-parser
     #   sphinx
-linkify-it-py==1.0.3
-    # via myst-parser
-markdown-it-py==2.2.0
+markdown-it-py==3.0.0
     # via
     #   mdit-py-plugins
     #   myst-parser
-markupsafe==2.1.2
+markupsafe==2.1.5
     # via jinja2
-mdit-py-plugins==0.3.4
+mdit-py-plugins==0.4.2
     # via myst-parser
 mdurl==0.1.2
     # via markdown-it-py
-myst-parser[linkify]==1.0.0
+myst-parser==4.0.0
     # via rocm-docs-core
-packaging==23.0
+packaging==24.1
     # via
     #   pydata-sphinx-theme
     #   sphinx
-pycparser==2.21
+pycparser==2.22
     # via cffi
-pydata-sphinx-theme==0.13.3
+pydata-sphinx-theme==0.15.4
     # via
     #   rocm-docs-core
     #   sphinx-book-theme
-pygithub==1.58.1
+pygithub==2.4.0
     # via rocm-docs-core
-pygments==2.14.0
+pygments==2.18.0
     # via
     #   accessible-pygments
     #   pydata-sphinx-theme
     #   sphinx
-pyjwt[crypto]==2.6.0
+pyjwt[crypto]==2.9.0
     # via pygithub
 pynacl==1.5.0
     # via pygithub
-pytz==2022.7.1
-    # via babel
-pyyaml==6.0
+pyyaml==6.0.2
     # via
     #   myst-parser
     #   rocm-docs-core
     #   sphinx-external-toc
-requests==2.28.1
+requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==0.13.4
+rocm-docs-core==1.8.0
     # via -r requirements.in
-smmap==5.0.0
+smmap==5.0.1
     # via gitdb
 snowballstemmer==2.2.0
     # via sphinx
-soupsieve==2.4
+soupsieve==2.6
     # via beautifulsoup4
-sphinx==5.3.0
+sphinx==8.0.2
     # via
     #   breathe
     #   myst-parser
@@ -115,33 +111,40 @@ sphinx==5.3.0
     #   sphinx-design
     #   sphinx-external-toc
     #   sphinx-notfound-page
-sphinx-book-theme==1.0.1
+    #   sphinx-reredirects
+sphinx-book-theme==1.1.3
     # via rocm-docs-core
-sphinx-copybutton==0.5.1
+sphinx-copybutton==0.5.2
     # via rocm-docs-core
-sphinx-design==0.4.1
+sphinx-design==0.6.1
     # via rocm-docs-core
-sphinx-external-toc==0.3.1
+sphinx-external-toc==1.0.1
     # via rocm-docs-core
-sphinx-notfound-page==0.8.3
+sphinx-notfound-page==1.0.4
     # via rocm-docs-core
-sphinxcontrib-applehelp==1.0.4
+sphinx-reredirects==0.1.5
+    # via -r requirements.in
+sphinxcontrib-applehelp==2.0.0
     # via sphinx
-sphinxcontrib-devhelp==1.0.2
+sphinxcontrib-devhelp==2.0.0
     # via sphinx
-sphinxcontrib-htmlhelp==2.0.1
+sphinxcontrib-htmlhelp==2.1.0
     # via sphinx
 sphinxcontrib-jsmath==1.0.1
     # via sphinx
-sphinxcontrib-qthelp==1.0.3
+sphinxcontrib-qthelp==2.0.0
     # via sphinx
-sphinxcontrib-serializinghtml==1.1.5
+sphinxcontrib-serializinghtml==2.0.0
     # via sphinx
-typing-extensions==4.5.0
-    # via pydata-sphinx-theme
-uc-micro-py==1.0.1
-    # via linkify-it-py
-urllib3==1.26.13
-    # via requests
-wrapt==1.14.1
+tomli==2.0.1
+    # via sphinx
+typing-extensions==4.12.2
+    # via
+    #   pydata-sphinx-theme
+    #   pygithub
+urllib3==2.2.3
+    # via
+    #   pygithub
+    #   requests
+wrapt==1.16.0
     # via deprecated

docs/understand/More-about-how-ROCm-uses-PCIe-Atomics.rst

@@ -13,7 +13,7 @@ The full list of HSA system architecture platform requirements are here: `HSA Sy
 
 The ROCm Platform uses the new PCI Express 3.0 (PCIe 3.0) features for Atomic Read-Modify-Write Transactions which extends inter-processor synchronization mechanisms to IO to support the defined set of HSA capabilities needed for queuing and signaling memory operations.
 
-The new PCIe AtomicOps operate as completers for ``CAS`` (Compare and Swap), ``FetchADD``, ``SWAP`` atomics. The AtomicsOps are initiated by the
+The new PCIe atomic operations operate as completers for ``CAS`` (Compare and Swap), ``FetchADD``, ``SWAP`` atomics. The atomic operations are initiated by the
 I/O device which support 32-bit, 64-bit and 128-bit operand which target address have to be naturally aligned to operation sizes.
 
 For ROCm the Platform atomics are used in ROCm in the following ways:
@@ -22,11 +22,11 @@ For ROCm the Platform atomics are used in ROCm in the following ways:
    * Update HSA queue’s write_dispatch_id: 64 bit atomic add used by the CPU and GPU agent to support multi-writer queue insertions.
    * Update HSA Signals – 64bit atomic ops are used for CPU & GPU synchronization.
 
-The PCIe 3.0 AtomicOp feature allows atomic transactions to be requested by, routed through and completed by PCIe components. Routing and completion does not require software support. Component support for each is detectable via the DEVCAP2 register. Upstream bridges need to have AtomicOp routing enabled or the Atomic Operations will fail even though PCIe endpoint and PCIe I/O Devices has the capability to Atomics Operations.
+The PCIe 3.0 atomic operations feature allows atomic transactions to be requested by, routed through and completed by PCIe components. Routing and completion does not require software support. Component support for each is detectable via the DEVCAP2 register. Upstream bridges need to have atomic operations routing enabled or the Atomic Operations will fail even though PCIe endpoint and PCIe I/O Devices has the capability to Atomics Operations.
 
-To do AtomicOp routing capability between two or more Root Ports, each associated Root Port must indicate that capability via the AtomicOp Routing Supported bit in the Device Capabilities 2 register.
+To do atomic operations routing capability between two or more Root Ports, each associated Root Port must indicate that capability via the atomic operations routing supported bit in the Device Capabilities 2 register.
 
-If your system has a PCIe Express Switch it needs to support AtomicsOp routing. Again AtomicOp requests are permitted only if a component’s ``DEVCTL2.ATOMICOP_REQUESTER_ENABLE`` field is set. These requests can only be serviced if the upstream components support AtomicOp completion and/or routing to a component which does. AtomicOp Routing Support=1 Routing is supported, AtomicOp Routing Support=0 routing is not supported.
+If your system has a PCIe Express Switch it needs to support atomic operations routing. Atomic operations requests are permitted only if a component’s ``DEVCTL2.ATOMICOP_REQUESTER_ENABLE`` field is set. These requests can only be serviced if the upstream components support atomic operations completion and/or routing to a component which does. Atomic operations routing support=1, routing is supported; Atomic operations routing support=0, routing is not supported.
 
 Atomic Operation is a Non-Posted transaction supporting 32-bit and 64-bit address formats, there must be a response for Completion containing the result of the operation. Errors associated with the operation (uncorrectable error accessing the target location or carrying out the Atomic operation) are signaled to the requester by setting the Completion Status field in the completion descriptor, they are set to to Completer Abort (CA) or Unsupported Request (UR).
 
@@ -39,14 +39,14 @@ There are also a number of papers which talk about these new capabilities:
   * `Atomic Read Modify Write Primitives by Intel <https://www.intel.es/content/dam/doc/white-paper/atomic-read-modify-write-primitives-i-o-devices-paper.pdf>`_
   * `PCI express 3 Accelerator Whitepaper by Intel <https://www.intel.sg/content/dam/doc/white-paper/pci-express3-accelerator-white-paper.pdf>`_
   * `Intel PCIe Generation 3 Hotchips Paper <https://www.hotchips.org/wp-content/uploads/hc_archives/hc21/1_sun/HC21.23.1.SystemInterconnectTutorial-Epub/HC21.23.131.Ajanovic-Intel-PCIeGen3.pdf>`_
-  * `PCIe Generation 4 Base Specification includes Atomics Operation <http://composter.com.ua/documents/PCI_Express_Base_Specification_Revision_4.0.Ver.0.3.pdf>`_
+  * `PCIe Generation 4 Base Specification includes Atomics Operation <https://astralvx.com/storage/2020/11/PCI_Express_Base_4.0_Rev0.3_February19-2014.pdf>`_
 
 Other I/O devices with PCIe Atomics support
 
    * `Mellanox ConnectX-5 InfiniBand Card <http://www.mellanox.com/related-docs/prod_adapter_cards/PB_ConnectX-5_VPI_Card.pdf>`_
    * `Cray Aries Interconnect <http://www.hoti.org/hoti20/slides/Bob_Alverson.pdf>`_
-   * `Xilinx PCIe Ultrascale Whitepaper <https://www.xilinx.com/support/documentation/white_papers/wp464-PCIe-ultrascale.pdf>`_
-   * `Xilinx 7 Series Devices <https://www.xilinx.com/support/documentation/ip_documentation/pcie_7x/v3_1/pg054-7series-pcie.pdf>`_
+   * `Xilinx PCIe Ultrascale Whitepaper <https://docs.xilinx.com/v/u/8OZSA2V1b1LLU2rRCDVGQw>`_
+   * `Xilinx 7 Series Devices <https://docs.xilinx.com/v/u/1nfXeFNnGpA0ywyykvWHWQ>`_
 
 Future bus technology with richer I/O Atomics Operation Support
 
@@ -54,8 +54,8 @@ Future bus technology with richer I/O Atomics Operation Support
 
 New PCIe Endpoints with support beyond AMD Ryzen and EPYC CPU; Intel Haswell or newer CPU’s with PCIe Generation 3.0 support.
 
-  * `Mellanox Bluefield SOC <http://www.mellanox.com/related-docs/npu-multicore-processors/PB_Bluefield_SoC.pdf>`_
-  * `Cavium Thunder X2 <http://www.cavium.com/ThunderX2_ARM_Processors.html>`_
+  * `Mellanox Bluefield SOC <https://docs.nvidia.com/networking/display/BlueFieldSWv25111213/BlueField+Software+Overview>`_
+  * `Cavium Thunder X2 <https://en.wikichip.org/wiki/cavium/thunderx2>`_
 
 In ROCm, we also take advantage of PCIe ID based ordering technology for P2P when the GPU originates two writes to two different targets:  
 
@@ -71,7 +71,7 @@ BAR Memory Overview
 *******************
 On a Xeon E5 based system in the BIOS we can turn on above 4GB PCIe addressing, if so he need to set MMIO Base address ( MMIOH Base) and Range ( MMIO High Size) in the BIOS.
 
-In SuperMicro system in the system bios you need to see the following
+In Supermicro system in the system bios you need to see the following
 
    * Advanced->PCIe/PCI/PnP configuration-> Above 4G Decoding = Enabled
   
@@ -79,7 +79,7 @@ In SuperMicro system in the system bios you need to see the following
 
    * Advanced->PCIe/PCI/PnP Configuration->MMIO High Size = 256G
 
-When we support Large Bar Capability there is a Large Bar Vbios which also disable the IO bar.
+When we support Large Bar Capability there is a Large Bar VBIOS which also disable the IO bar.
 
 For GFX9 and Vega10 which have Physical Address up 44 bit and 48 bit Virtual address.
 
@@ -118,32 +118,5 @@ Legend:
 
 5 : Expansion ROM – This is required for the AMD Driver SW to access the GPU’s video-bios. This is currently fixed at 128KB.
 
-Excepts form Overview of Changes to PCI Express 3.0
-===================================================
-By Mike Jackson, Senior Staff Architect, MindShare, Inc.
-********************************************************
-Atomic Operations – Goal:
-*************************
-Support SMP-type operations across a PCIe network to allow for things like offloading tasks between CPU cores and accelerators like a GPU. The spec says this enables advanced synchronization mechanisms that are particularly useful with multiple producers or consumers that need to be synchronized in a non-blocking fashion. Three new atomic non-posted requests were added, plus the corresponding completion (the address must be naturally aligned with the operand size or the TLP is malformed):
-
-  * Fetch and Add – uses one operand as the “add” value. Reads the target location, adds the operand, and then writes the result back 	  to the original location.
-
-  * Unconditional Swap – uses one operand as the “swap” value. Reads the target location and then writes the swap value to it.
-
-  * Compare and Swap – uses 2 operands: first data is compare value, second is swap value. Reads the target location, checks it     	against the compare value and, if equal, writes the swap value to the target location.
-
-  * AtomicOpCompletion – new completion to give the result so far atomic request and indicate that the atomicity of the transaction 	has been maintained.
-
-Since AtomicOps are not locked they don't have the performance downsides of the PCI locked protocol. Compared to locked cycles, they provide “lower latency, higher scalability, advanced synchronization algorithms, and dramatically lower impact on other PCIe traffic.” The lock mechanism can still be used across a bridge to PCI or PCI-X to achieve the desired operation.
-
-AtomicOps can go from device to device, device to host, or host to device. Each completer indicates whether it supports this capability and guarantees atomic access if it does. The ability to route AtomicOps is also indicated in the registers for a given port.
-
-ID-based Ordering – Goal:
-*************************
-Improve performance by avoiding stalls caused by ordering rules. For example, posted writes are never normally allowed to pass each other in a queue, but if they are requested by different functions, we can have some confidence that the requests are not dependent on each other. The previously reserved Attribute bit [2] is now combined with the RO bit to indicate ID ordering with or without relaxed ordering.
-
-This only has meaning for memory requests, and is reserved for Configuration or IO requests. Completers are not required to copy this bit into a completion, and only use the bit if their enable bit is set for this operation.
-
-To read more on PCIe Gen 3 new options https://www.mindshare.com/files/resources/PCIe%203-0.pdf
-
-
+For more information, you can review
+`Overview of Changes to PCI Express 3.0 <https://www.mindshare.com/files/resources/PCIe%203-0.pdf>`_.

docs/understand/cmake_packages.rst

@@ -4,7 +4,7 @@ Using CMake
 
 Most components in ROCm support CMake. Projects depending on header-only or
 library components typically require CMake 3.5 or higher whereas those wanting
-to make use of CMake's HIP language support will require CMake 3.21 or higher.
+to make use of the CMake HIP language support will require CMake 3.21 or higher.
 
 Finding Dependencies
 ====================
@@ -16,7 +16,7 @@ Finding Dependencies
    <https://cmake.org/cmake/help/latest/command/find_package.html>`_ and the
    `Using Dependencies Guide
    <https://cmake.org/cmake/help/latest/guide/using-dependencies/index.html>`_
-   to get an overview of CMake's related facilities.
+   to get an overview of CMake related facilities.
 
 In short, CMake supports finding dependencies in two ways:
 
@@ -28,7 +28,7 @@ In short, CMake supports finding dependencies in two ways:
    regards needed to consume it.
 
 ROCm predominantly relies on Config mode, one notable exception being the Module
-driving the compilation of HIP programs on Nvidia runtimes. As such, when
+driving the compilation of HIP programs on NVIDIA runtimes. As such, when
 dependencies are not found in standard system locations, one either has to
 instruct CMake to search for package config files in additional folders using
 the ``CMAKE_PREFIX_PATH`` variable (a semi-colon separated list of filesystem
@@ -55,8 +55,8 @@ to the installation guides in these docs (`Linux <../deploy/linux/index.html>`_)
 Using HIP in CMake
 ==================
 
-ROCm componenents providing a C/C++ interface support being consumed using any
-C/C++ toolchain that CMake knows how to drive. ROCm also supports CMake's HIP
+ROCm components providing a C/C++ interface support being consumed using any
+C/C++ toolchain that CMake knows how to drive. ROCm also supports the CMake HIP
 language features, allowing users to program using the HIP single-source
 programming model. When a program (or translation-unit) uses the HIP API without
 compiling any GPU device code, HIP can be treated in CMake as a simple C/C++
@@ -172,7 +172,7 @@ all the flags necessary for device compilation.
 .. note::
     Compiling for the GPU device requires at least C++11.
 
-This project can then be configured with for eg.
+This project can then be configured with the following CMake commands:
 
 -  Windows: ``cmake -D CMAKE_CXX_COMPILER:PATH=${env:HIP_PATH}\bin\clang++.exe``
 
@@ -186,7 +186,7 @@ When using the CXX language support to compile HIP device code, selecting the
 target GPU architectures is done via setting the ``GPU_TARGETS`` variable.
 ``CMAKE_HIP_ARCHITECTURES`` only exists when the HIP language is enabled. By
 default, this is set to some subset of the currently supported architectures of
-AMD ROCm. It can be set to eg. ``-D GPU_TARGETS="gfx1032;gfx1035"``.
+AMD ROCm. It can be set to the CMake option ``-D GPU_TARGETS="gfx1032;gfx1035"``.
 
 ROCm CMake Packages
 -------------------
@@ -251,9 +251,9 @@ options.
 
 IDEs supporting CMake (Visual Studio, Visual Studio Code, CLion, etc.) all came
 up with their own way to register command-line fragments of different purpose in
-a setup'n'forget fashion for quick assembly using graphical front-ends. This is
+a setup-and-forget fashion for quick assembly using graphical front-ends. This is
 all nice, but configurations aren't portable, nor can they be reused in
-Continuous Intergration (CI) pipelines. CMake has condensed existing practice
+Continuous Integration (CI) pipelines. CMake has condensed existing practice
 into a portable JSON format that works in all IDEs and can be invoked from any
 command-line. This is
 `CMake Presets <https://cmake.org/cmake/help/latest/manual/cmake-presets.7.html>`_

docs/understand/compiler_disambiguation.md

@@ -10,6 +10,6 @@ disambiguates compiler naming used throughout the documentation.
 | `amdclang++` | Clang/LLVM-based compiler that is part of `rocm-llvm` package. The source code is available at <a href="https://github.com/RadeonOpenCompute/llvm-project" target="_blank">https://github.com/RadeonOpenCompute/llvm-project</a>. |
 | AOCC | Closed-source clang-based compiler that includes additional CPU optimizations. Offered as part of ROCm via the `rocm-llvm-alt` package. See for details, <a href="https://developer.amd.com/amd-aocc/" target="_blank">https://developer.amd.com/amd-aocc/</a>. |
 | HIP-Clang | Informal term for the `amdclang++` compiler |
-| HIPify | Tools including `hipify-clang` and `hipify-perl`, used to automatically translate CUDA source code into portable HIP C++. The source code is available at <a href="https://github.com/ROCm-Developer-Tools/HIPIFY" target="_blank">https://github.com/ROCm-Developer-Tools/HIPIFY</a> |
+| HIPIFY | Tools including `hipify-clang` and `hipify-perl`, used to automatically translate CUDA source code into portable HIP C++. The source code is available at <a href="https://github.com/ROCm-Developer-Tools/HIPIFY" target="_blank">https://github.com/ROCm-Developer-Tools/HIPIFY</a> |
 | `hipcc` | HIP compiler driver. A utility that invokes `clang` or `nvcc` depending on the target and passes the appropriate include and library options for the target compiler and HIP infrastructure. The source code is available at <a href="https://github.com/ROCm-Developer-Tools/HIPCC" target="_blank">https://github.com/ROCm-Developer-Tools/HIPCC</a>. |
 | ROCmCC | Clang/LLVM-based compiler. ROCmCC in itself is not a binary but refers to the overall compiler. |

docs/understand/file_reorg.md

@@ -1,10 +1,12 @@
-# Linux Folder Structure Reorganization
+# ROCm FHS Reorganization
 
 ## Introduction
 
-ROCm™ packages have adopted the Linux foundation file system hierarchy standard
-to ensure ROCm components follow open source conventions for Linux-based
-distributions. Following is the ROCm proposed file structure.
+The ROCm platform has adopted the Linux foundation Filesystem Hierarchy Standard (FHS) [https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html](https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html) in order to to ensure ROCm is consistent with standard open source conventions. The following sections specify how current and future releases of ROCm adhere to FHS, how the previous ROCm filesystem is supported, and how improved versioning specifications are applied to ROCm.
+
+## Adopting the Linux foundation Filesystem Hierarchy Standard (FHS)
+
+In order to standardize ROCm directory structure and directory content layout ROCm has adopted the [FHS](https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html), adhering to open source conventions for Linux-based distribution. FHS ensures internal consistency within the ROCm stack, as well as external consistency with other systems and distributions. The ROCm proposed file structure is outlined below:
 
 ```none
 /opt/rocm-<ver>
@@ -42,14 +44,13 @@ distributions. Following is the ROCm proposed file structure.
               | -- architecture independent misc files
 ```
 
-## Changes from earlier ROCm versions
+## Changes From Earlier ROCm Versions
 
-ROCm with the file reorganization is going to have a lean structure. Following
-table gives the comparison with new and old folder structure.
+The following table provides a brief overview of the new ROCm FHS layout, compared to the layout of earlier ROCm versions. Note that /opt/ is used to denote the default rocm-installation-path and should be replaced in case of a non-standard installation location of the ROCm distribution.
 
 ```none
  ______________________________________________________
-|  New File Structure         |  Old File Structure    |
+|  New ROCm Layout            |  Previous ROCm Layout  |
 |_____________________________|________________________|
 | /opt/rocm-<ver>             | /opt/rocm-<ver>        |
 |     | -- bin                |     | -- bin           |
@@ -72,39 +73,28 @@ table gives the comparison with new and old folder structure.
 |______________________________________________________|
 ```
 
-## ROCm File reorganization transition plan
+## ROCm FHS Reorganization: Backward Compatibility
 
-New file organization for ROCm was first introduced ROCm v5.2 release. Backward
-compatibility was in place to make sure users had a chance to change their
-applications using ROCm. ROCm has moved header files and libraries to its new
-location as indicated in the above structure and included symbolic-link and
-wrapper header files in its old location for backward compatibility.
+The FHS file organization for ROCm was first introduced in the release of ROCm 5.2 . Backward compatibility was implemented to make sure users could still run their ROCm applications while transitioning to the new FHS. ROCm has moved header files and libraries to their new locations as indicated in the above structure, and included symbolic-links and wrapper header files in their old location for backward compatibility. The following sections detail ROCm backward compatibility implementation for wrapper header files, executable files, library files and CMake config files.
 
-### Wrapper header files
+### Wrapper Header Files
 
 Wrapper header files are placed in the old location (
-`/opt/rocm-xxx/<component>/include`) with a warning message to include files
-from the new location (`/opt/rocm-xxx/include`) as shown in the example below.
+`/opt/rocm-<ver>/<component>/include`) with a warning message to include files
+from the new location (`/opt/rocm-<ver>/include`) as shown in the example below.
 
 ```cpp
 #pragma message "This file is deprecated. Use file from include path /opt/rocm-ver/include/ and prefix with hip."
-#include "hip/hip_runtime.h"
+#include <hip/hip_runtime.h>
 ```
 
-The deprecation plan for backward compatibility wrapper header files is as
-follows
+- Starting at ROCm 5.2 release, the deprecation for backward compatibility wrapper header files is: `#pragma` message announcing `#warning`.
+- Starting from ROCm 6.0 (tentatively) backward compatibility for wrapper header files will be removed, and the `#pragma` message will be announcing `#error`.
 
-- `#pragma` message announcing deprecation – ROCm v5.2 release.
-- `#pragma` message changed to `#warning` – Future release, tentatively ROCm
-  v5.5.
-- `#warning` changed to `#error` – Future release, tentatively ROCm v5.6.
-- Backward compatibility wrappers removed – Future release, tentatively ROCm
-  v6.0.
+### Executable Files
 
-### Executable files
-
-Executable files are available in the `/opt/rocm-xxx/bin` folder. For backward
-compatibility, the old library location (`/opt/rocm-xxx/<component>/bin`) has a
+Executable files are available in the `/opt/rocm-<ver>/bin` folder. For backward
+compatibility, the old library location (`/opt/rocm-<ver>/<component>/bin`) has a
 soft link to the library at the new location. Soft links will be removed in a
 future release, tentatively ROCm v6.0.
 
@@ -113,10 +103,10 @@ $ ls -l /opt/rocm/hip/bin/
 lrwxrwxrwx 1 root root   24 Jan 1 23:32 hipcc -> ../../bin/hipcc
 ```
 
-### Library files
+### Library Files
 
-Library files are available in the `/opt/rocm-xxx/lib` folder. For backward
-compatibility, the old library location (`/opt/rocm-xxx/<component>/lib`) has a
+Library files are available in the `/opt/rocm-<ver>/lib` folder. For backward
+compatibility, the old library location (`/opt/rocm-<ver>/<component>/lib`) has a
 soft link to the library at the new location. Soft links will be removed in a
 future release, tentatively ROCm v6.0.
 
@@ -126,11 +116,11 @@ drwxr-xr-x 4 root root 4096 Jan 1 10:45 cmake
 lrwxrwxrwx 1 root root   24 Jan 1 23:32 libamdhip64.so -> ../../lib/libamdhip64.so
 ```
 
-### CMake Config files
+### CMake Config Files
 
 All CMake configuration files are available in the
-`/opt/rocm-xxx/lib/cmake/<component>` folder. For backward compatibility, the
-old CMake locations (`/opt/rocm-xxx/<component>/lib/cmake`) consist of a soft
+`/opt/rocm-<ver>/lib/cmake/<component>` folder. For backward compatibility, the
+old CMake locations (`/opt/rocm-<ver>/<component>/lib/cmake`) consist of a soft
 link to the new CMake config. Soft links will be removed in a future release,
 tentatively ROCm v6.0.
 
@@ -139,10 +129,10 @@ $ ls -l /opt/rocm/hip/lib/cmake/hip/
 lrwxrwxrwx 1 root root 42 Jan 1 23:32 hip-config.cmake -> ../../../../lib/cmake/hip/hip-config.cmake
 ```
 
-## Changes required in applications using ROCm
+## Changes Required in Applications Using ROCm
 
 Applications using ROCm are advised to use the new file paths. As the old files
-will be deprecated in a future release. Application have to make sure to include
+will be deprecated in a future release. Applications have to make sure to include
 correct header file and use correct search paths.
 
 1. `#include<header_file.h>` needs to be changed to
@@ -158,10 +148,18 @@ correct header file and use correct search paths.
    `VAR2=/opt/rocm/hsa` needs to be changed to `VAR2=/opt/rocm`
 
 3. Any reference to `/opt/rocm/<component>/bin` or `/opt/rocm/<component>/lib`
-   needs to be changed to `/opt/rocm/bin` and `/opt/rocm/lib/` respectively.
+   needs to be changed to `/opt/rocm/bin` and `/opt/rocm/lib/`, respectively.
 
-## References
+## Changes in Versioning Specifications
 
-{ref}`ROCm deprecation warning <5_4_0_filesystem_reorg_deprecation_notice>`
+In order to better manage ROCm dependencies specification and allow smoother releases of ROCm while avoiding dependency conflicts, the ROCm platform shall adhere to the following scheme when numbering and incrementing ROCm files versions:
 
-[Linux File System Standard](https://refspecs.linuxfoundation.org/fhs.shtml)
+rocm-\<ver\>, where \<ver\> = \<x.y.z\>
+
+x.y.z denote: MAJOR.MINOR.PATCH
+
+z: PATCH - increment z when implementing backward compatible bug fixes.
+
+y: MINOR - increment y when implementing minor changes that add functionality but are still backward compatible.
+
+x: MAJOR - increment x when implementing major changes that are not backward compatible.

tools/autotag/tag_script.py

@@ -81,7 +81,6 @@ class TaggingArgs(argparse.Namespace):
     def exclude(self) -> List[str]:
         """Get the excluded libraries plus defaults."""
         defaults = [
-            "AMDMIGraphX",
             "MIOpenGEMM",
             "MIOpenKernels",
             "MIOpenTensile",
@@ -236,9 +235,21 @@ def run_tagging():
     )
 
     # Find all the math libraries and their remotes.
-    names_and_remotes = list(
-        (entry.get("name"), entry.get("remote")) for entry in manifest_tree.findall(".//project[@groups='mathlibs']")
-    )
+    included_names = [
+        "rocm-cmake",
+        "MIOpen",
+        "AMDMIGraphX",
+        "rocprofiler"
+    ]
+    included_groups = [
+        "mathlibs"
+    ]
+    projects = [ ]
+    for project in manifest_tree.iterfind(".//project"):
+        include = str(project.get("name")) in included_names
+        if (project.get("name") in included_names) or (project.get("groups") in included_groups):
+            projects.append(project)
+    names_and_remotes = list((entry.get("name"), entry.get("remote")) for entry in projects)
 
     # Get all the relevant ROCm releases, and only the last version if not doing previous.
     minimum_version = "5.0.0" if args.previous else args.version
@@ -249,12 +260,17 @@ def run_tagging():
     for (version, release) in releases.items():
         for (_, library) in release.libraries.items():
             # Parse the changelog for each library and each version
-            success = PROCESSORS[library.name](
-                library,
-                TEMPLATES[library.name],
-                args.previous,
-                Version(version) < Version(args.version)
-            )
+            try:
+                success = PROCESSORS[library.name](
+                    library,
+                    TEMPLATES[library.name],
+                    args.previous,
+                    Version(version) < Version(args.version)
+                )
+            except Exception as e:
+                success = False
+                print(f"Exception parsing {library.name} for ROCm {version}")
+                print(e)
             if not success:
                 print(f"Error processing {library.name} for ROCm {version}")
                 failed.append((version, library.name))

tools/autotag/templates/changelog.jinja

@@ -32,15 +32,15 @@ The release notes for the ROCm platform.
 | Library | Version |
 |---------|---------|
 {%- for lib_name, lib in release.libraries | dictsort %}
-{%- if rocm_ver_by_lib_ver[lib_name][lib.lib_version] == version %}
+{%- if rocm_ver_by_lib_ver[lib_name][lib.lib_version] == version and lib.lib_version %}
 | {{ lib_name }} | {{prev_lib_ver[lib_name][lib.lib_version]}} ⇒ [{{ lib.lib_version }}]({{ lib.release_url }}) |
-{%- else %}
+{%- elif lib.lib_version %}
 | {{ lib_name }} | [{{ lib.lib_version }}]({{ lib.release_url }}) |
 {%- endif %}
 {%- endfor %}
 
 {%- for lib_name, lib in release.libraries | dictsort %}
-{%- if rocm_ver_by_lib_ver[lib_name][lib.lib_version] == version %}
+{%- if rocm_ver_by_lib_ver[lib_name][lib.lib_version] == version and lib.lib_version%}
 
 #### {{lib_name}} {{lib.lib_version}}
 

tools/autotag/templates/rocm_changes/5.4.0.md

@@ -95,8 +95,6 @@ The `hipcc` and `hipconfig` Perl scripts are deprecated. In a future release, co
 >
 > There will be a transition period where the Perl scripts and compiled binaries are available  before the scripts are removed. There will be no functional difference between the Perl scripts and their compiled binary counterpart. No user action is required. Once these are available, users can optionally switch to `hipcc.bin` and `hipconfig.bin`. The `hipcc`/`hipconfig` soft link will be assimilated to point from `hipcc`/`hipconfig` to the respective compiled binaries as the default option.
 
-(5_4_0_filesystem_reorg_deprecation_notice)=
-
 ##### Linux Filesystem Hierarchy Standard for ROCm
 
 ROCm packages have adopted the Linux foundation filesystem hierarchy standard in this release to ensure ROCm components follow open source conventions for Linux-based distributions. While moving to a new filesystem hierarchy, ROCm ensures backward compatibility with its 5.1 version or older filesystem hierarchy. See below for a detailed explanation of the new filesystem hierarchy and backward compatibility.

tools/autotag/templates/rocm_changes/5.5.0.md

@@ -26,6 +26,29 @@ The following hipcc changes are implemented in this release:
   - `hipCommander` at <https://github.com/ROCm-Developer-Tools/hip-tests/tree/develop/samples/1_Utils/hipCommander>
 
   Note that the samples will continue to be available in previous release branches.
+- Removal of gcnarch from hipDeviceProp_t structure
+- Addition of new fields in hipDeviceProp_t structure
+  - maxTexture1D
+  - maxTexture2D
+  - maxTexture1DLayered
+  - maxTexture2DLayered
+  - sharedMemPerMultiprocessor
+  - deviceOverlap
+  - asyncEngineCount
+  - surfaceAlignment
+  - unifiedAddressing
+  - computePreemptionSupported
+  - hostRegisterSupported
+  - uuid
+- Removal of deprecated code
+  - hip-hcc codes from hip code tree
+- Correct hipArray usage in HIP APIs such as hipMemcpyAtoH and hipMemcpyHtoA
+- HIPMEMCPY_3D fields correction to avoid truncation of "size_t" to "unsigned int" inside hipMemcpy3D()
+- Renaming of 'memoryType' in hipPointerAttribute_t structure to 'type'
+- Correct hipGetLastError to return the last error instead of last API call's return code
+- Update hipExternalSemaphoreHandleDesc to add "unsigned int reserved[16]"
+- Correct handling of flag values in hipIpcOpenMemHandle for hipIpcMemLazyEnablePeerAccess
+- Remove hiparray* and make it opaque with hipArray_t
 
 ##### New HIP APIs in This Release
 
@@ -280,7 +303,3 @@ When user applications call `ncclCommAbort` to destruct communicators and then c
 communicators repeatedly, subsequent communicators may fail to initialize.
 
 This issue is under investigation and will be resolved in a future release.
-
-#### Failures In HIP Directed Tests
-
-Multiple HIP directed tests fail.

tools/autotag/templates/rocm_changes/5.5.1.md

@@ -2,9 +2,22 @@
 <!-- markdownlint-disable no-duplicate-header -->
 ### What's New in This Release
 
+#### HIP SDK for Windows
+
+AMD is pleased to announce the availability of the HIP SDK for Windows as part
+of the ROCm platform. The
+[HIP SDK OS and GPU support page](https://rocm.docs.amd.com/en/docs-5.5.1/release/windows_support.html)
+lists the versions of Windows and GPUs validated by AMD. HIP SDK features on
+Windows are described in detail in our
+[What is ROCm?](https://rocm.docs.amd.com/en/docs-5.5.1/rocm.html#rocm-on-windows)
+page and differs from the Linux feature set. Visit
+[Quick Start](https://rocm.docs.amd.com/en/docs-5.5.1/deploy/windows/quick_start.html#)
+page to get started. Known issues are tracked on
+[GitHub](https://github.com/RadeonOpenCompute/ROCm/issues?q=is%3Aopen+label%3A5.5.1+label%3A%22Verified+Issue%22+label%3AWindows).
+
 #### HIP API Change
 
-The following HIP API is updated in the ROCm v5.5.1 release,
+The following HIP API is updated in the ROCm 5.5.1 release:
 
 ##### `hipDeviceSetCacheConfig`