mirror of
https://github.com/ROCm/ROCm.git
synced 2026-01-10 15:18:11 -05:00
Compare commits
8 Commits
docs/5.7.0
...
rocm-5.7.1
| Author | SHA1 | Date | |
|---|---|---|---|
|
365b31728d | ||
|
|
b6c71018a6 | ||
|
|
54177e8b96 | ||
|
|
74f4f86c92 | ||
|
|
74d8f95afb | ||
|
|
50ad3847e5 | ||
|
|
444efec642 | ||
|
|
7d22b96c5d |
5
.gitignore
vendored
5
.gitignore
vendored
@@ -16,3 +16,8 @@ _readthedocs/
|
||||
docs/contributing.md
|
||||
docs/release.md
|
||||
docs/CHANGELOG.md
|
||||
|
||||
# auto-generated files
|
||||
docs/deploy/linux/installer/install.md
|
||||
docs/deploy/linux/os-native/install.md
|
||||
docs/deploy/linux/quick_start.md
|
||||
|
||||
@@ -3,19 +3,16 @@
|
||||
|
||||
version: 2
|
||||
|
||||
build:
|
||||
os: ubuntu-22.04
|
||||
tools:
|
||||
python: "3.10"
|
||||
apt_packages:
|
||||
- "doxygen"
|
||||
- "graphviz" # For dot graphs in doxygen
|
||||
sphinx:
|
||||
configuration: docs/conf.py
|
||||
|
||||
formats: [htmlzip, pdf]
|
||||
|
||||
python:
|
||||
install:
|
||||
- requirements: docs/sphinx/requirements.txt
|
||||
|
||||
sphinx:
|
||||
configuration: docs/conf.py
|
||||
|
||||
formats: []
|
||||
build:
|
||||
os: ubuntu-20.04
|
||||
tools:
|
||||
python: "3.8"
|
||||
|
||||
684
.wordlist.txt
684
.wordlist.txt
@@ -1,686 +1,122 @@
|
||||
AAC
|
||||
# building
|
||||
matchers
|
||||
# file_reorg
|
||||
FHS
|
||||
incrementing
|
||||
Filesystem
|
||||
filesystem
|
||||
rocm
|
||||
# gpu_aware_mpi
|
||||
DMA
|
||||
GDR
|
||||
HCA
|
||||
MPI
|
||||
MVAPICH
|
||||
Mellanox's
|
||||
NIC
|
||||
OFED
|
||||
OSU
|
||||
OpenFabrics
|
||||
PeerDirect
|
||||
RDMA
|
||||
UCX
|
||||
ib_core
|
||||
# isv_deployment_win
|
||||
ABI
|
||||
ACE
|
||||
ACEs
|
||||
AccVGPR
|
||||
AccVGPRs
|
||||
# linear algebra
|
||||
LAPACK
|
||||
MMA
|
||||
backends
|
||||
cuSOLVER
|
||||
cuSPARSE
|
||||
# mi200_performance_counters
|
||||
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
|
||||
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
|
||||
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
|
||||
preq
|
||||
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
|
||||
tagram
|
||||
tg
|
||||
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
|
||||
# openmp
|
||||
ICV
|
||||
Multithreaded
|
||||
# tuning_guides
|
||||
BMC
|
||||
DGEMM
|
||||
HPCG
|
||||
HPL
|
||||
IOPM
|
||||
# windows
|
||||
SKU
|
||||
SKUs
|
||||
PowerShell
|
||||
UAC
|
||||
# pytorch_install
|
||||
kdb
|
||||
precompiled
|
||||
# gpu_os_support
|
||||
HWE
|
||||
el
|
||||
# using_gpu_sanitizer
|
||||
LSAN
|
||||
deallocation
|
||||
detections
|
||||
tracebacks
|
||||
workgroup
|
||||
|
||||
67
CHANGELOG.md
67
CHANGELOG.md
@@ -1,4 +1,4 @@
|
||||
# Release Notes
|
||||
# Changelog
|
||||
<!-- Do not edit this file! This file is autogenerated with -->
|
||||
<!-- tools/autotag/tag_script.py -->
|
||||
|
||||
@@ -11,7 +11,70 @@
|
||||
|
||||
<!-- spellcheck-disable -->
|
||||
|
||||
The release notes for the ROCm platform.
|
||||
The changelog for the ROCm platform.
|
||||
|
||||
-------------------
|
||||
|
||||
## ROCm 5.7.1
|
||||
<!-- markdownlint-disable first-line-h1 -->
|
||||
<!-- markdownlint-disable no-duplicate-header -->
|
||||
|
||||
### What's New in This Release
|
||||
|
||||
### ROCm Libraries
|
||||
|
||||
#### rocBLAS
|
||||
A new functionality rocblas-gemm-tune and an environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH are added to rocBLAS in the ROCm 5.7.1 release.
|
||||
|
||||
*rocblas-gemm-tune* is used to find the best-performing GEMM kernel for each GEMM problem set. It has a command line interface, which mimics the --yaml input used by rocblas-bench. To generate the expected --yaml input, profile logging can be used, by setting the environment variable ROCBLAS_LAYER4.
|
||||
|
||||
For more information on rocBLAS logging, see Logging in rocBLAS, in the [API Reference Guide](https://rocm.docs.amd.com/projects/rocBLAS/en/docs-5.7.1/API_Reference_Guide.html#logging-in-rocblas).
|
||||
|
||||
An example input file: Expected output (note selected GEMM idx may differ): Where the far right values (solution_index) are the indices of the best-performing kernels for those GEMMs in the rocBLAS kernel library. These indices can be directly used in future GEMM calls. See rocBLAS/samples/example_user_driven_tuning.cpp for sample code of directly using kernels via their indices.
|
||||
|
||||
If the output is stored in a file, the results can be used to override default kernel selection with the kernels found, by setting the environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH, where points to the stored file.
|
||||
|
||||
For more details, refer to the [rocBLAS Programmer's Guide.](https://rocm.docs.amd.com/projects/rocBLAS/en/latest/Programmers_Guide.html#rocblas-gemm-tune)
|
||||
|
||||
#### HIP 5.7.1 (for ROCm 5.7.1)
|
||||
|
||||
ROCm 5.7.1 is a point release with several bug fixes in the HIP runtime.
|
||||
|
||||
### Fixed defects
|
||||
The *hipPointerGetAttributes* API returns the correct HIP memory type as *hipMemoryTypeManaged* for managed memory.
|
||||
|
||||
|
||||
|
||||
### Library Changes in ROCM 5.7.1
|
||||
|
||||
| Library | Version |
|
||||
|---------|---------|
|
||||
| hipBLAS | [1.1.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.7.1) |
|
||||
| hipCUB | [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.7.1) |
|
||||
| hipFFT | [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.7.1) |
|
||||
| hipSOLVER | 1.8.1 ⇒ [1.8.2](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.7.1) |
|
||||
| hipSPARSE | [2.3.8](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.7.1) |
|
||||
| MIOpen | [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.7.1) |
|
||||
| rocALUTION | [2.1.11](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.7.1) |
|
||||
| rocBLAS | [3.1.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.7.1) |
|
||||
| rocFFT | [1.0.24](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.7.1) |
|
||||
| rocm-cmake | [0.10.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.7.1) |
|
||||
| rocPRIM | [2.13.1](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.7.1) |
|
||||
| rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.7.1) |
|
||||
| rocSOLVER | [3.23.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.7.1) |
|
||||
| rocSPARSE | [2.5.4](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.7.1) |
|
||||
| rocThrust | [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.7.1) |
|
||||
| rocWMMA | [1.2.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.7.1) |
|
||||
| Tensile | [4.38.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.7.1) |
|
||||
|
||||
#### hipSOLVER 1.8.2
|
||||
|
||||
hipSOLVER 1.8.2 for ROCm 5.7.1
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Fixed conflicts between the hipsolver-dev and -asan packages by excluding
|
||||
hipsolver_module.f90 from the latter
|
||||
|
||||
-------------------
|
||||
|
||||
|
||||
478
RELEASE.md
478
RELEASE.md
@@ -15,469 +15,63 @@ The release notes for the ROCm platform.
|
||||
|
||||
-------------------
|
||||
|
||||
## ROCm 5.7.0
|
||||
## ROCm 5.7.1
|
||||
<!-- markdownlint-disable first-line-h1 -->
|
||||
<!-- markdownlint-disable no-duplicate-header -->
|
||||
|
||||
### Release Highlights for ROCm v5.7
|
||||
### What's New in This Release
|
||||
|
||||
ROCm 5.7.0 includes many new features. These include: a new library (hipTensor), and optimizations for rocRAND and MIVisionX. Address sanitizer for host and device code (GPU) is now available as a beta. Note that ROCm 5.7.0 is EOS for MI50. 5.7 versions of ROCm are the last major release in the ROCm 5 series. This release is Linux-only.
|
||||
### ROCm Libraries
|
||||
|
||||
Important: The next major ROCm release (ROCm 6.0) will not be backward compatible with the ROCm 5 series. Changes will include: splitting LLVM packages into more manageable sizes, changes to the HIP runtime API, splitting rocRAND and hipRAND into separate packages, and reorganizing our file structure.
|
||||
#### rocBLAS
|
||||
A new functionality rocblas-gemm-tune and an environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH are added to rocBLAS in the ROCm 5.7.1 release.
|
||||
|
||||
#### AMD Instinct™ MI50 End of Support Notice
|
||||
*rocblas-gemm-tune* is used to find the best-performing GEMM kernel for each GEMM problem set. It has a command line interface, which mimics the --yaml input used by rocblas-bench. To generate the expected --yaml input, profile logging can be used, by setting the environment variable ROCBLAS_LAYER4.
|
||||
|
||||
AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively gfx906 GPUs) will enter maintenance mode starting Q3 2023.
|
||||
For more information on rocBLAS logging, see Logging in rocBLAS, in the [API Reference Guide](https://rocm.docs.amd.com/projects/rocBLAS/en/docs-5.7.1/API_Reference_Guide.html#logging-in-rocblas).
|
||||
|
||||
As outlined in [5.6.0](https://rocm.docs.amd.com/en/docs-5.6.0/release.html), ROCm 5.7 will be the final release for gfx906 GPUs to be in a fully supported state.
|
||||
An example input file: Expected output (note selected GEMM idx may differ): Where the far right values (solution_index) are the indices of the best-performing kernels for those GEMMs in the rocBLAS kernel library. These indices can be directly used in future GEMM calls. See rocBLAS/samples/example_user_driven_tuning.cpp for sample code of directly using kernels via their indices.
|
||||
|
||||
- ROCm 6.0 release will show MI50s as "under maintenance" mode for [Linux](./about/release/linux_support) and [Windows](./about/release/windows_support)
|
||||
If the output is stored in a file, the results can be used to override default kernel selection with the kernels found, by setting the environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH, where points to the stored file.
|
||||
|
||||
- No new features and performance optimizations will be supported for the gfx906 GPUs beyond this major release (ROCm 5.7).
|
||||
For more details, refer to the [rocBLAS Programmer's Guide.](https://rocm.docs.amd.com/projects/rocBLAS/en/latest/Programmers_Guide.html#rocblas-gemm-tune)
|
||||
|
||||
- Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (EOM (End of Maintenance) will be aligned with the closest ROCm release).
|
||||
#### HIP 5.7.1 (for ROCm 5.7.1)
|
||||
|
||||
- Bug fixes during the maintenance will be made to the next ROCm point release.
|
||||
ROCm 5.7.1 is a point release with several bug fixes in the HIP runtime.
|
||||
|
||||
- Bug fixes will not be backported to older ROCm releases for gfx906.
|
||||
### Fixed defects
|
||||
The *hipPointerGetAttributes* API returns the correct HIP memory type as *hipMemoryTypeManaged* for managed memory.
|
||||
|
||||
- Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM.
|
||||
|
||||
#### Feature Updates
|
||||
|
||||
##### Non-hostcall HIP Printf
|
||||
|
||||
**Current behavior**
|
||||
|
||||
The current version of HIP printf relies on hostcalls, which, in turn, rely on PCIe atomics. However, PCle atomics are unavailable in some environments, and, as a result, HIP-printf does not work in those environments. Users may see the following error from runtime (with AMD_LOG_LEVEL 1 and above),
|
||||
|
||||
```
|
||||
Pcie atomics not enabled, hostcall not supported
|
||||
```
|
||||
**Workaround**
|
||||
|
||||
The ROCm 5.7 release introduces an alternative to the current hostcall-based implementation that leverages an older OpenCL-based printf scheme, which does not rely on hostcalls/PCIe atomics.
|
||||
Note: This option is less robust than hostcall-based implementation and is intended to be a workaround when hostcalls do not work.
|
||||
|
||||
The printf variant is now controlled via a new compiler option -mprintf-kind=<value>. This is supported only for HIP programs and takes the following values,
|
||||
|
||||
- “hostcall” – This currently available implementation relies on hostcalls, which require the system to support PCIe atomics. It is the default scheme.
|
||||
|
||||
- “buffered” – This implementation leverages the older printf scheme used by OpenCL; it relies on a memory buffer where printf arguments are stored during the kernel execution, and then the runtime handles the actual printing once the kernel finishes execution.
|
||||
|
||||
**NOTE**: With the new workaround,
|
||||
|
||||
- The printf buffer is fixed size and non-circular. After the buffer is filled, calls to printf will not result in additional output.
|
||||
|
||||
- The printf call returns either 0 (on success) or -1 (on failure, due to full buffer), unlike the hostcall scheme that returns the number of characters printed.
|
||||
|
||||
##### Beta Release of LLVM Address Sanitizer (ASAN) with the GPU
|
||||
|
||||
The ROCm v5.7 release introduces the beta release of LLVM Address Sanitizer (ASAN) with the GPU. The LLVM Address Sanitizer provides a process that allows developers to detect runtime addressing errors in applications and libraries. The detection is achieved using a combination of compiler-added instrumentation and runtime techniques, including function interception and replacement.
|
||||
Until now, the LLVM Address Sanitizer process was only available for traditional purely CPU applications. However, ROCm has extended this mechanism to additionally allow the detection of some addressing errors on the GPU in heterogeneous applications. Ideally, developers should treat heterogeneous HIP and OpenMP applications like pure CPU applications. However, this simplicity has not been achieved yet.
|
||||
|
||||
Refer to the documentation on LLVM Address Sanitizer with the GPU at [LLVM Address Sanitizer User Guide](understand/using_gpu_sanitizer.md).
|
||||
|
||||
**Note**: The beta release of LLVM Address Sanitizer for ROCm is currently tested and validated on Ubuntu 20.04.
|
||||
|
||||
#### Fixed Defects
|
||||
|
||||
The following defects are fixed in ROCm v5.7,
|
||||
|
||||
- Test hangs observed in HMM RCCL
|
||||
|
||||
- NoGpuTst test of Catch2 fails with Docker
|
||||
|
||||
- Failures observed with non-HMM HIP directed catch2 tests with XNACK+
|
||||
|
||||
- Multiple test failures and test hangs observed in hip-directed catch2 tests with xnack+
|
||||
|
||||
#### HIP 5.7.0
|
||||
|
||||
##### Optimizations
|
||||
|
||||
##### Added
|
||||
|
||||
- Added `meta_group_size`/`rank` for getting the number of tiles and rank of a tile in the partition
|
||||
|
||||
- Added new APIs supporting Windows only, under development on Linux
|
||||
|
||||
- `hipMallocMipmappedArray` for allocating a mipmapped array on the device
|
||||
|
||||
- `hipFreeMipmappedArray` for freeing a mipmapped array on the device
|
||||
|
||||
- `hipGetMipmappedArrayLevel` for getting a mipmap level of a HIP mipmapped array
|
||||
|
||||
- `hipMipmappedArrayCreate` for creating a mipmapped array
|
||||
|
||||
- `hipMipmappedArrayDestroy` for destroy a mipmapped array
|
||||
|
||||
- `hipMipmappedArrayGetLevel` for getting a mipmapped array on a mipmapped level
|
||||
|
||||
##### Changed
|
||||
|
||||
##### Fixed
|
||||
|
||||
##### Known Issues
|
||||
|
||||
- HIP memory type enum values currently don't support equivalent value to `cudaMemoryTypeUnregistered`, due to HIP functionality backward compatibility.
|
||||
- HIP API `hipPointerGetAttributes` could return invalid value in case the input memory pointer was not allocated through any HIP API on device or host.
|
||||
|
||||
##### Upcoming changes for HIP in ROCm 6.0 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
|
||||
|
||||
- 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
|
||||
|
||||
### Library Changes in ROCM 5.7.0
|
||||
### Library Changes in ROCM 5.7.1
|
||||
|
||||
| Library | Version |
|
||||
|---------|---------|
|
||||
| hipBLAS | ⇒ [1.1.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.7.0) |
|
||||
| hipCUB | ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.7.0) |
|
||||
| hipFFT | ⇒ [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.7.0) |
|
||||
| hipSOLVER | ⇒ [1.8.1](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.7.0) |
|
||||
| hipSPARSE | ⇒ [2.3.8](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.7.0) |
|
||||
| MIOpen | ⇒ [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.7.0) |
|
||||
| rccl | ⇒ [2.17.1-1](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.7.0) |
|
||||
| rocALUTION | ⇒ [2.1.11](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.7.0) |
|
||||
| rocBLAS | ⇒ [3.1.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.7.0) |
|
||||
| rocFFT | ⇒ [1.0.24](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.7.0) |
|
||||
| rocm-cmake | ⇒ [0.10.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.7.0) |
|
||||
| rocPRIM | ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.7.0) |
|
||||
| rocRAND | ⇒ [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.7.0) |
|
||||
| rocSOLVER | ⇒ [3.23.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.7.0) |
|
||||
| rocSPARSE | ⇒ [2.5.4](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.7.0) |
|
||||
| rocThrust | ⇒ [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.7.0) |
|
||||
| rocWMMA | ⇒ [1.2.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.7.0) |
|
||||
| Tensile | ⇒ [4.38.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.7.0) |
|
||||
| hipBLAS | [1.1.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.7.1) |
|
||||
| hipCUB | [2.13.1](https://github.com/ROCmSoftwarePlatform/hipCUB/releases/tag/rocm-5.7.1) |
|
||||
| hipFFT | [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.7.1) |
|
||||
| hipSOLVER | 1.8.1 ⇒ [1.8.2](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.7.1) |
|
||||
| hipSPARSE | [2.3.8](https://github.com/ROCmSoftwarePlatform/hipSPARSE/releases/tag/rocm-5.7.1) |
|
||||
| MIOpen | [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.7.1) |
|
||||
| rocALUTION | [2.1.11](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.7.1) |
|
||||
| rocBLAS | [3.1.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.7.1) |
|
||||
| rocFFT | [1.0.24](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.7.1) |
|
||||
| rocm-cmake | [0.10.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.7.1) |
|
||||
| rocPRIM | [2.13.1](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.7.1) |
|
||||
| rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.7.1) |
|
||||
| rocSOLVER | [3.23.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.7.1) |
|
||||
| rocSPARSE | [2.5.4](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.7.1) |
|
||||
| rocThrust | [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.7.1) |
|
||||
| rocWMMA | [1.2.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.7.1) |
|
||||
| Tensile | [4.38.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.7.1) |
|
||||
|
||||
#### hipBLAS 1.1.0
|
||||
#### hipSOLVER 1.8.2
|
||||
|
||||
hipBLAS 1.1.0 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- updated documentation requirements
|
||||
|
||||
##### Dependencies
|
||||
|
||||
- dependency rocSOLVER now depends on rocSPARSE
|
||||
|
||||
#### hipCUB 2.13.1
|
||||
|
||||
hipCUB 2.13.1 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- CUB backend references CUB and Thrust version 2.0.1.
|
||||
- Fixed `DeviceSegmentedReduce::ArgMin` and `DeviceSegmentedReduce::ArgMax` by returning the segment-relative index instead of the absolute one.
|
||||
- Fixed `DeviceSegmentedReduce::ArgMin` for inputs where the segment minimum is smaller than the value returned for empty segments. An equivalent fix is applied to `DeviceSegmentedReduce::ArgMax`.
|
||||
|
||||
##### Known Issues
|
||||
|
||||
- `debug_synchronous` no longer works on CUDA platform. `CUB_DEBUG_SYNC` should be used to enable those checks.
|
||||
- `DeviceReduce::Sum` does not compile on CUDA platform for mixed extended-floating-point/floating-point InputT and OutputT types.
|
||||
- `DeviceHistogram::HistogramEven` fails on CUDA platform for `[LevelT, SampleIteratorT] = [int, int]`.
|
||||
- `DeviceHistogram::MultiHistogramEven` fails on CUDA platform for `[LevelT, SampleIteratorT] = [int, int/unsigned short/float/double]` and `[LevelT, SampleIteratorT] = [float, double]`.
|
||||
|
||||
#### hipFFT 1.0.12
|
||||
|
||||
hipFFT 1.0.12 for ROCm 5.7.0
|
||||
|
||||
##### 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 1.8.1
|
||||
|
||||
hipSOLVER 1.8.1 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- Changed hipsolver-test sparse input data search paths to be relative to the test executable
|
||||
|
||||
#### hipSPARSE 2.3.8
|
||||
|
||||
hipSPARSE 2.3.8 for ROCm 5.7.0
|
||||
|
||||
##### Improved
|
||||
|
||||
- Fix compilation failures when using cusparse 12.1.0 backend
|
||||
- Fix compilation failures when using cusparse 12.0.0 backend
|
||||
- Fix compilation failures when using cusparse 10.1 (non-update versions) as backend
|
||||
- Minor improvements
|
||||
|
||||
#### MIOpen 2.19.0
|
||||
|
||||
MIOpen 2.19.0 for ROCm 5.7.0
|
||||
|
||||
##### 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
|
||||
hipSOLVER 1.8.2 for ROCm 5.7.1
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Fix 3d convolution Host API bug
|
||||
- [HOTFIX][MI200][FP16] Disabled ConvHipImplicitGemmBwdXdlops when FP16_ALT is required.
|
||||
|
||||
#### RCCL 2.17.1-1
|
||||
|
||||
RCCL 2.17.1-1 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- Compatibility with NCCL 2.17.1-1
|
||||
- Performance tuning for some collective operations
|
||||
|
||||
##### Added
|
||||
|
||||
- Minor improvements to MSCCL codepath
|
||||
- NCCL_NCHANNELS_PER_PEER support
|
||||
- Improved compilation performance
|
||||
- Support for gfx94x
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Potential race-condition during ncclSocketClose()
|
||||
|
||||
#### rocALUTION 2.1.11
|
||||
|
||||
rocALUTION 2.1.11 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- Added support for gfx940, gfx941 and gfx942
|
||||
|
||||
##### Improved
|
||||
|
||||
- Fixed OpenMP runtime issue with Windows toolchain
|
||||
|
||||
#### rocBLAS 3.1.0
|
||||
|
||||
rocBLAS 3.1.0 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- yaml lock step argument scanning for rocblas-bench and rocblas-test clients. See Programmers Guide for details.
|
||||
- rocblas-gemm-tune is used to find the best performing GEMM kernel for each of a given set of GEMM problems.
|
||||
|
||||
##### Fixed
|
||||
|
||||
- make offset calculations for rocBLAS functions 64 bit safe. Fixes for very large leading dimensions or increments potentially causing overflow:
|
||||
- Level 1: axpy, copy, rot, rotm, scal, swap, asum, dot, iamax, iamin, nrm2
|
||||
- Level 2: gemv, symv, hemv, trmv, ger, syr, her, syr2, her2, trsv
|
||||
- Level 3: gemm, symm, hemm, trmm, syrk, herk, syr2k, her2k, syrkx, herkx, trsm, trtri, dgmm, geam
|
||||
- General: set_vector, get_vector, set_matrix, get_matrix
|
||||
- Related fixes: internal scalar loads with > 32bit offsets
|
||||
- fix in-place functionality for all trtri sizes
|
||||
|
||||
##### Changed
|
||||
|
||||
- dot when using rocblas_pointer_mode_host is now synchronous to match legacy BLAS as it stores results in host memory
|
||||
- enhanced reporting of installation issues caused by runtime libraries (Tensile)
|
||||
- standardized internal rocblas C++ interface across most functions
|
||||
|
||||
##### Deprecated
|
||||
|
||||
- Removal of __STDC_WANT_IEC_60559_TYPES_EXT__ define in future release
|
||||
|
||||
##### Dependencies
|
||||
|
||||
- optional use of AOCL BLIS 4.0 on Linux for clients
|
||||
- optional build tool only dependency on python psutil
|
||||
|
||||
#### rocFFT 1.0.24
|
||||
|
||||
rocFFT 1.0.24 for ROCm 5.7.0
|
||||
|
||||
##### Optimizations
|
||||
|
||||
- Improved performance of complex forward/inverse 1D FFTs (2049 <= length <= 131071) that use Bluestein's algorithm.
|
||||
|
||||
##### Added
|
||||
|
||||
- Implemented a solution map version converter and finish the first conversion from ver.0 to ver.1. Where version 1 removes some incorrect kernels (sbrc/sbcr using half_lds)
|
||||
|
||||
##### Changed
|
||||
|
||||
- Moved rocfft_rtc_helper executable to lib/rocFFT directory on Linux.
|
||||
- Moved library kernel cache to lib/rocFFT directory.
|
||||
|
||||
#### rocm-cmake 0.10.0
|
||||
|
||||
rocm-cmake 0.10.0 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- Added ROCMTest module
|
||||
- ROCMCreatePackage: Added support for ASAN packages
|
||||
|
||||
#### rocPRIM 2.13.1
|
||||
|
||||
rocPRIM 2.13.1 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- Deprecated configuration `radix_sort_config` for device-level radix sort as it no longer matches the algorithm's parameters. New configuration `radix_sort_config_v2` is preferred instead.
|
||||
- Removed erroneous implementation of device-level `inclusive_scan` and `exclusive_scan`. The prior default implementation using lookback-scan now is the only available implementation.
|
||||
- The benchmark metric indicating the bytes processed for `exclusive_scan_by_key` and `inclusive_scan_by_key` has been changed to incorporate the key type. Furthermore, the benchmark log has been changed such that these algorithms are reported as `scan` and `scan_by_key` instead of `scan_exclusive` and `scan_inclusive`.
|
||||
- Deprecated configurations `scan_config` and `scan_by_key_config` for device-level scans, as they no longer match the algorithm's parameters. New configurations `scan_config_v2` and `scan_by_key_config_v2` are preferred instead.
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Fixed build issue caused by missing header in `thread/thread_search.hpp`.
|
||||
|
||||
#### rocRAND 2.10.17
|
||||
|
||||
rocRAND 2.10.17 for ROCm 5.7.0
|
||||
|
||||
##### 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, "Parallel random numbers: as easy as 1, 2, 3".
|
||||
|
||||
##### Changed
|
||||
|
||||
- Python 2.7 is no longer officially supported.
|
||||
|
||||
#### rocSOLVER 3.23.0
|
||||
|
||||
rocSOLVER 3.23.0 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- LU factorization without pivoting for block tridiagonal matrices:
|
||||
- GEBLTTRF_NPVT now supports interleaved\_batched format
|
||||
- Linear system solver without pivoting for block tridiagonal matrices:
|
||||
- GEBLTTRS_NPVT now supports interleaved\_batched format
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Fixed stack overflow in sparse tests on Windows
|
||||
|
||||
##### Changed
|
||||
|
||||
- Changed rocsolver-test sparse input data search paths to be relative to the test executable
|
||||
- Changed build scripts to default to compressed debug symbols in Debug builds
|
||||
|
||||
#### rocSPARSE 2.5.4
|
||||
|
||||
rocSPARSE 2.5.4 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- Added more mixed precisions for SpMV, (matrix: float, vectors: double, calculation: double) and (matrix: rocsparse_float_complex, vectors: rocsparse_double_complex, calculation: rocsparse_double_complex)
|
||||
- Added support for gfx940, gfx941 and gfx942
|
||||
|
||||
##### Improved
|
||||
|
||||
- Fixed a bug in csrsm and bsrsm
|
||||
|
||||
##### Known Issues
|
||||
|
||||
In csritlu0, the algorithm rocsparse_itilu0_alg_sync_split_fusion has some accuracy issues to investigate with XNACK enabled. The fallback is rocsparse_itilu0_alg_sync_split.
|
||||
|
||||
#### rocThrust 2.18.0
|
||||
|
||||
rocThrust 2.18.0 for ROCm 5.7.0
|
||||
|
||||
##### Fixed
|
||||
|
||||
- `lower_bound`, `upper_bound`, and `binary_search` failed to compile for certain types.
|
||||
- Fixed issue where `transform_iterator` would not compile with `__device__`-only operators.
|
||||
|
||||
##### Changed
|
||||
|
||||
- Updated `docs` directory structure to match the standard of [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core).
|
||||
- Removed references to and workarounds for deprecated hcc
|
||||
|
||||
#### rocWMMA 1.2.0
|
||||
|
||||
rocWMMA 1.2.0 for ROCm 5.7.0
|
||||
|
||||
##### Changed
|
||||
|
||||
- Fixed a bug with synchronization
|
||||
- Updated rocWMMA cmake versioning
|
||||
|
||||
#### Tensile 4.38.0
|
||||
|
||||
Tensile 4.38.0 for ROCm 5.7.0
|
||||
|
||||
##### Added
|
||||
|
||||
- Added support for FP16 Alt Round Near Zero Mode (this feature allows the generation of alternate kernels with intermediate rounding instead of truncation)
|
||||
- Added user-driven solution selection feature
|
||||
|
||||
##### Optimizations
|
||||
|
||||
- Enabled LocalSplitU with MFMA for I8 data type
|
||||
- Optimized K mask code in mfmaIter
|
||||
- Enabled TailLoop code in NoLoadLoop to prefetch global/local read
|
||||
- Enabled DirectToVgpr in TailLoop for NN, TN, and TT matrix orientations
|
||||
- Optimized DirectToLds test cases to reduce the test duration
|
||||
|
||||
##### Changed
|
||||
|
||||
- Removed DGEMM NT custom kernels and related test cases
|
||||
- Changed noTailLoop logic to apply noTailLoop only for NT
|
||||
- Changed the range of AssertFree0ElementMultiple and Free1
|
||||
- Unified aStr, bStr generation code in mfmaIter
|
||||
|
||||
##### Fixed
|
||||
|
||||
- Fixed LocalSplitU mismatch issue for SGEMM
|
||||
- Fixed BufferStore=0 and Ldc != Ldd case
|
||||
- Fixed mismatch issue with TailLoop + MatrixInstB > 1
|
||||
- Fixed conflicts between the hipsolver-dev and -asan packages by excluding
|
||||
hipsolver_module.f90 from the latter
|
||||
|
||||
@@ -12,7 +12,7 @@ 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-5.7.0"
|
||||
<default revision="refs/tags/rocm-5.7.1"
|
||||
remote="roc-github"
|
||||
sync-c="true"
|
||||
sync-j="4" />
|
||||
|
||||
@@ -1,3 +0,0 @@
|
||||
# 404 - Page Not Found
|
||||
|
||||
Return [home](./index) or use the sidebar navigation to get back on track.
|
||||
@@ -5,6 +5,7 @@ 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, license name, and link to the license terms.
|
||||
The table is ordered to follow ROCm's manifest file.
|
||||
|
||||
<!-- spellcheck-disable -->
|
||||
| Component | License |
|
||||
|
||||
24
docs/conf.py
24
docs/conf.py
@@ -5,9 +5,27 @@
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html
|
||||
|
||||
import shutil
|
||||
import jinja2
|
||||
import os
|
||||
|
||||
from rocm_docs import ROCmDocs
|
||||
|
||||
# Environement to process Jinja templates.
|
||||
jinja_env = jinja2.Environment(loader=jinja2.FileSystemLoader("."))
|
||||
|
||||
# Jinja templates to render out.
|
||||
templates = [
|
||||
"./deploy/linux/quick_start.md.jinja",
|
||||
"./deploy/linux/installer/install.md.jinja",
|
||||
"./deploy/linux/os-native/install.md.jinja"
|
||||
]
|
||||
|
||||
# Render templates and output files without the last extension.
|
||||
# For example: 'install.md.jinja' becomes 'install.md'.
|
||||
for template in templates:
|
||||
rendered = jinja_env.get_template(template).render()
|
||||
with open(os.path.splitext(template)[0], 'w') as file:
|
||||
file.write(rendered)
|
||||
|
||||
shutil.copy2('../CONTRIBUTING.md','./contributing.md')
|
||||
shutil.copy2('../RELEASE.md','./release.md')
|
||||
@@ -27,8 +45,8 @@ latex_elements = {
|
||||
project = "ROCm Documentation"
|
||||
author = "Advanced Micro Devices, Inc."
|
||||
copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved."
|
||||
version = "5.7.0"
|
||||
release = "5.7.0"
|
||||
version = "5.7.1"
|
||||
release = "5.7.1"
|
||||
|
||||
setting_all_article_info = True
|
||||
all_article_info_os = ["linux", "windows"]
|
||||
@@ -92,7 +110,7 @@ article_pages = [
|
||||
|
||||
external_toc_path = "./sphinx/_toc.yml"
|
||||
|
||||
docs_core = ROCmDocs("ROCm 5.7.0 Documentation Home")
|
||||
docs_core = ROCmDocs("ROCm 5.7.1 Documentation Home")
|
||||
docs_core.setup()
|
||||
|
||||
external_projects_current_project = "rocm"
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 32 KiB |
@@ -1,3 +1,5 @@
|
||||
{%- import "deploy/linux/linux.template.jinja" as linux %}
|
||||
<!-- markdownlint-disable no-duplicate-header blanks-around-headings no-multiple-blanks -->
|
||||
# Installation with install script
|
||||
|
||||
Prior to beginning, please ensure you have the [prerequisites](../prerequisites)
|
||||
@@ -15,98 +17,48 @@ it via {ref}`hip_visible_devices`.
|
||||
To download and install the `amdgpu-install` script on the system, use the
|
||||
following commands based on your distribution.
|
||||
|
||||
::::::{tab-set}
|
||||
:::::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
{% call(family) linux.for_family_in(linux.supported_family) %}
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu 20.04
|
||||
:sync: ubuntu-20.04
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
sudo apt update
|
||||
wget https://repo.radeon.com/amdgpu-install/5.7/ubuntu/focal/amdgpu-install_5.7.50700-1_all.deb
|
||||
sudo apt install ./amdgpu-install_5.7.50700-1_all.deb
|
||||
wget https://repo.radeon.com/amdgpu-install/{{ family.amdgpu_version }}/ubuntu/{{ version.release }}/amdgpu-install_{{ family.amdgpu_install_version }}_all.deb
|
||||
sudo apt install ./amdgpu-install_{{ family.amdgpu_install_version }}_all.deb
|
||||
```
|
||||
{%- endcall -%}
|
||||
{%- elif os.tag == "rhel" %}
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
:::
|
||||
:::{tab-item} Ubuntu 22.04
|
||||
:sync: ubuntu-22.04
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
sudo apt update
|
||||
wget https://repo.radeon.com/amdgpu-install/5.7/ubuntu/jammy/amdgpu-install_5.7.50700-1_all.deb
|
||||
sudo apt install ./amdgpu-install_5.7.50700-1_all.deb
|
||||
sudo yum install https://repo.radeon.com/amdgpu-install/{{ family.amdgpu_version }}/rhel/{{ version.number }}/amdgpu-install-{{ family.amdgpu_install_version }}.{{ version.release | trim("rh") }}.noarch.rpm
|
||||
```
|
||||
{%- endcall -%}
|
||||
{%- elif os.tag == "sle" %}
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
:::
|
||||
::::
|
||||
:::::
|
||||
:::::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} RHEL 8.7
|
||||
:sync: RHEL-8.7
|
||||
:sync: RHEL-8
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
sudo yum install https://repo.radeon.com/amdgpu-install/5.7/rhel/8.7/amdgpu-install-5.7.50700-1.el8.noarch.rpm
|
||||
sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/{{ family.amdgpu_version }}/sle/{{ version.number }}/amdgpu-install-{{ family.amdgpu_install_version }}.noarch.rpm
|
||||
```
|
||||
{%- endcall -%}
|
||||
{%- endif %}
|
||||
|
||||
:::
|
||||
:::{tab-item} RHEL 8.8
|
||||
:sync: RHEL-8.8
|
||||
:sync: RHEL-8
|
||||
|
||||
```shell
|
||||
sudo yum install https://repo.radeon.com/amdgpu-install/5.7/rhel/8.8/amdgpu-install-5.7.50700-1.el8.noarch.rpm
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} RHEL 9.1
|
||||
:sync: RHEL-9.1
|
||||
:sync: RHEL-9
|
||||
|
||||
```shell
|
||||
sudo yum install https://repo.radeon.com/amdgpu-install/5.7/rhel/9.1/amdgpu-install-5.7.50700-1.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/5.7/rhel/9.2/amdgpu-install-5.7.50700-1.el9.noarch.rpm
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
:::::
|
||||
:::::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} SLES 15.4
|
||||
:sync: SLES-15.4
|
||||
|
||||
```shell
|
||||
sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/5.7/sle/15.4/amdgpu-install-5.7.50700-1.noarch.rpm
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} SLES 15.5
|
||||
:sync: SLES-15.5
|
||||
|
||||
```shell
|
||||
sudo zypper --no-gpg-checks install https://repo.radeon.com/amdgpu-install/5.7/sle/15.5/amdgpu-install-5.7.50700-1.noarch.rpm
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
:::::
|
||||
::::::
|
||||
{%- endcall -%}
|
||||
{%- endcall %}
|
||||
|
||||
## Use cases
|
||||
|
||||
@@ -191,9 +143,9 @@ 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 5.5.3, 5.6.1 and 5.7
|
||||
**Example:** If you want to install ROCm releases 5.5.3, 5.6.1 and {{ linux.supported_family[0].rocm_version }}
|
||||
simultaneously, you are required to download the installer from the latest ROCm
|
||||
release 5.7.
|
||||
release {{ linux.supported_family[0].rocm_version }}.
|
||||
|
||||
### Add Required Repositories
|
||||
|
||||
@@ -203,50 +155,37 @@ automatically adds the required repositories for the latest release.
|
||||
|
||||
Run the following commands based on your distribution to add the repositories:
|
||||
|
||||
::::::{tab-set}
|
||||
:::::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
{% call(family) linux.for_family_in(linux.supported_family) %}
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu 20.04
|
||||
:sync: ubuntu-20.04
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
for ver in 5.5.3 5.6.1 5.7; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] https://repo.radeon.com/rocm/apt/$ver focal main" | sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
for ver in 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] https://repo.radeon.com/rocm/apt/$ver {{ version.release }} main" | sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
done
|
||||
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt update
|
||||
```
|
||||
{%- endcall -%}
|
||||
{%- elif os.tag == "rhel" %}
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
:::
|
||||
:::{tab-item} Ubuntu 22.04
|
||||
:sync: ubuntu-22.04
|
||||
|
||||
```shell
|
||||
for ver in 5.5.3 5.6.1 5.7; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] https://repo.radeon.com/rocm/apt/$ver jammy main" | sudo tee /etc/apt/sources.list.d/rocm.list
|
||||
done
|
||||
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' | sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt update
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
:::::
|
||||
:::::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} RHEL 8
|
||||
:sync: RHEL-8
|
||||
|
||||
```shell
|
||||
for ver in 5.5.3 5.6.1 5.7; do
|
||||
for ver in 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
|
||||
[ROCm-$ver]
|
||||
name=ROCm$ver
|
||||
baseurl=https://repo.radeon.com/rocm/rhel8/$ver/main
|
||||
baseurl=https://repo.radeon.com/rocm/{{ version.release }}/$ver/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
@@ -255,34 +194,10 @@ EOF
|
||||
done
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} RHEL 9
|
||||
:sync: RHEL-9
|
||||
|
||||
{%- endcall -%}
|
||||
{%- elif os.tag == "sle" %}
|
||||
```shell
|
||||
for ver in 5.5.3 5.6.1 5.7; do
|
||||
sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
|
||||
[ROCm-$ver]
|
||||
name=ROCm$ver
|
||||
baseurl=https://repo.radeon.com/rocm/rhel9/$ver/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
done
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
:::::
|
||||
:::::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
```shell
|
||||
for ver in 5.5.3 5.6.1 5.7; do
|
||||
for ver in 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
sudo tee --append /etc/zypp/repos.d/rocm.repo <<EOF
|
||||
name=rocm
|
||||
baseurl=https://repo.radeon.com/rocm/zyp/$ver/main
|
||||
@@ -293,26 +208,27 @@ EOF
|
||||
done
|
||||
sudo zypper ref
|
||||
```
|
||||
{%- endif %}
|
||||
|
||||
:::::
|
||||
::::::
|
||||
{%- endcall -%}
|
||||
{%- endcall %}
|
||||
|
||||
### Install packages
|
||||
|
||||
Use the installer script as given below:
|
||||
|
||||
```none
|
||||
```shell
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease=<release-number-1>
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease=<release-number-2>
|
||||
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 5.7, will be installed as its latest
|
||||
driver, associated with the ROCm release {{ linux.supported_family[0].rocm_version }}, will be installed as its latest
|
||||
release in the list.
|
||||
|
||||
```none
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease=5.7
|
||||
```shell
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease={{ linux.supported_family[0].rocm_version }}
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease=5.6.1
|
||||
sudo amdgpu-install --usecase=rocm --rocmrelease=5.5.3
|
||||
```
|
||||
120
docs/deploy/linux/linux.template.jinja
Normal file
120
docs/deploy/linux/linux.template.jinja
Normal file
@@ -0,0 +1,120 @@
|
||||
{%- set supported_family = ([
|
||||
{
|
||||
"tag": "instinct",
|
||||
"name": "Select OS",
|
||||
"amdgpu_version": "5.7.1",
|
||||
"amdgpu_install_version": "5.7.50701-1",
|
||||
"rocm_version": "5.7.1",
|
||||
"rocm_install_version": "5.7.50701-1",
|
||||
}
|
||||
]) -%}
|
||||
|
||||
{%- set supported_os = ([
|
||||
{
|
||||
"tag": "ubuntu",
|
||||
"name": "Ubuntu",
|
||||
"shortname" : "Ubuntu",
|
||||
"version": [
|
||||
{
|
||||
"number": "22.04",
|
||||
"release": "jammy"
|
||||
},
|
||||
{
|
||||
"number": "20.04",
|
||||
"release": "focal"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"tag": "rhel",
|
||||
"name": "Red Hat Enterprise Linux",
|
||||
"shortname" : "RHEL",
|
||||
"version": [
|
||||
{
|
||||
"number": "8.8",
|
||||
"release": "rhel8"
|
||||
},
|
||||
{
|
||||
"number": "8.7",
|
||||
"release": "rhel8"
|
||||
},
|
||||
{
|
||||
"number": "8.6",
|
||||
"release": "rhel8"
|
||||
},
|
||||
{
|
||||
"number": "9.2",
|
||||
"release": "rhel9"
|
||||
},
|
||||
{
|
||||
"number": "9.1",
|
||||
"release": "rhel9"
|
||||
},
|
||||
]
|
||||
},
|
||||
{
|
||||
"tag": "sle",
|
||||
"name": "SUSE Linux Enterprise Server",
|
||||
"shortname" : "SLES",
|
||||
"version": [
|
||||
{
|
||||
"number": "15.5"
|
||||
},
|
||||
{
|
||||
"number": "15.4"
|
||||
},
|
||||
]
|
||||
}
|
||||
]) -%}
|
||||
|
||||
{%- macro for_family_in(supported_family) %}
|
||||
::::::::{tab-set}
|
||||
{%- for family in supported_family %}
|
||||
:::::::{tab-item} {{ family.name }}
|
||||
:sync: {{ family.tag }}
|
||||
{{ caller(family) }}
|
||||
|
||||
:::::::
|
||||
{%- endfor %}
|
||||
::::::::
|
||||
{%- endmacro -%}
|
||||
|
||||
{%- macro for_os_in(supported_os) %}
|
||||
::::::{tab-set}
|
||||
{%- for os in supported_os %}
|
||||
:::::{tab-item} {{ os.name }}
|
||||
:sync: {{ os.tag }}
|
||||
{{ caller(os) }}
|
||||
|
||||
:::::
|
||||
{%- endfor %}
|
||||
::::::
|
||||
{%- endmacro -%}
|
||||
|
||||
{%- macro for_version_in(os) %}
|
||||
::::{tab-set}
|
||||
{%- for version in os.version %}
|
||||
:::{tab-item} {{ os.shortname }} {{ version.number }}
|
||||
:sync: {{ os.tag }}-{{ version.number }}
|
||||
{{ caller(version) }}
|
||||
|
||||
:::
|
||||
{%- endfor %}
|
||||
::::
|
||||
{%- endmacro -%}
|
||||
|
||||
{%- macro install(os, argument) %}
|
||||
```shell
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
sudo apt install {{ argument }}
|
||||
{%- elif os.tag == "rhel" %}
|
||||
sudo yum install {{ argument }}
|
||||
{%- elif os.tag == "sle" %}
|
||||
sudo zypper install {{ argument }}
|
||||
{%- endif %}
|
||||
```
|
||||
{%- endmacro -%}
|
||||
|
||||
{%- macro header_anchor(family, os) -%}
|
||||
({{ caller() | lower | replace('#', '') | trim | replace(' ', '-')}}-{{ family.tag }}-{{ os.tag }})= {{ caller() }}
|
||||
{%- endmacro -%}
|
||||
@@ -1,3 +1,5 @@
|
||||
{%- import "deploy/linux/linux.template.jinja" as linux %}
|
||||
<!-- markdownlint-disable no-duplicate-header blanks-around-headings no-multiple-blanks -->
|
||||
# Installation (Linux)
|
||||
|
||||
```{warning}
|
||||
@@ -19,10 +21,9 @@ installed version by using the multi-version ROCm packages.
|
||||
|
||||
## Step by Step Instructions
|
||||
|
||||
::::::{tab-set}
|
||||
:::::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
::::{rubric} 1. Download and convert the package signing key
|
||||
::::
|
||||
|
||||
@@ -53,39 +54,22 @@ section.
|
||||
```
|
||||
|
||||
To add the AMDGPU repository, follow these steps:
|
||||
{% call(version) linux.for_version_in(os) %}
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu 20.04
|
||||
:sync: ubuntu-20.04
|
||||
```{important}
|
||||
Instructions for {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
ver={{ linux.supported_family[0].amdgpu_version }}
|
||||
|
||||
# amdgpu repository for focal
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$ver/ubuntu focal main" \
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$ver/ubuntu {{ version.release }} main" \
|
||||
| sudo tee /etc/apt/sources.list.d/amdgpu.list
|
||||
sudo apt update
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} Ubuntu 22.04
|
||||
:sync: ubuntu-22.04
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
# amdgpu repository for jammy
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/amdgpu/$ver/ubuntu jammy main" \
|
||||
| sudo tee /etc/apt/sources.list.d/amdgpu.list
|
||||
sudo apt update
|
||||
# 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
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
{%- endcall %}
|
||||
|
||||
Install the kernel mode driver and reboot the system using the following
|
||||
commands:
|
||||
@@ -100,38 +84,23 @@ sudo reboot
|
||||
|
||||
To add the ROCm repository, use the following steps:
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu 20.04
|
||||
:sync: ubuntu-20.04
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# ROCm repositories for focal
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 5.7; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$ver focal main" \
|
||||
# ROCm repositories for {{ version.release }}
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$ver {{ version.release }} main" \
|
||||
| sudo tee --append /etc/apt/sources.list.d/rocm.list
|
||||
done
|
||||
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' \
|
||||
| sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt update
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} Ubuntu 22.04
|
||||
:sync: ubuntu-22.04
|
||||
|
||||
```shell
|
||||
# ROCm repositories for jammy
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 5.7; do
|
||||
echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/$ver jammy main" \
|
||||
| sudo tee --append /etc/apt/sources.list.d/rocm.list
|
||||
done
|
||||
echo -e 'Package: *\nPin: release o=repo.radeon.com\nPin-Priority: 600' \
|
||||
| sudo tee /etc/apt/preferences.d/rocm-pin-600
|
||||
sudo apt update
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
{%- endcall %}
|
||||
|
||||
::::{rubric} 4. Install packages
|
||||
::::
|
||||
@@ -151,13 +120,9 @@ For a comprehensive list of meta-packages, refer to
|
||||
- Sample Multi-version installation
|
||||
|
||||
```shell
|
||||
sudo apt install rocm-hip-sdk5.7 rocm-hip-sdk5.6.1 rocm-hip-sdk5.5.3
|
||||
sudo apt install rocm-hip-sdk{{ linux.supported_family[0].rocm_version }} rocm-hip-sdk5.6.1 rocm-hip-sdk5.5.3
|
||||
```
|
||||
|
||||
:::::
|
||||
:::::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
{%- elif os.tag == "rhel" %}
|
||||
::::{rubric} 1. Add the AMDGPU Stack Repository and Install the Kernel-mode Driver
|
||||
::::
|
||||
|
||||
@@ -165,20 +130,20 @@ For a comprehensive list of meta-packages, refer to
|
||||
If you have a version of the kernel-mode driver installed, you may skip this
|
||||
section.
|
||||
```
|
||||
{% call(version) linux.for_version_in(os) %}
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} RHEL 8.7
|
||||
:sync: RHEL-8.7
|
||||
:sync: RHEL-8
|
||||
```{important}
|
||||
Instructions for {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
ver={{ linux.supported_family[0].amdgpu_version }}
|
||||
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/8.7/main/x86_64/
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/{{ version.number }}/main/x86_64/
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
@@ -186,76 +151,7 @@ gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} RHEL 8.8
|
||||
:sync: RHEL-8.8
|
||||
:sync: RHEL-8
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/8.8/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 9.1
|
||||
:sync: RHEL-9.1
|
||||
:sync: RHEL-9
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/9.1/main/x86_64/
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} RHEL 9.2
|
||||
:sync: RHEL-9.2
|
||||
:sync: RHEL-9
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/rhel/9.2/main/x86_64/
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
{%- endcall %}
|
||||
Install the kernel mode driver and reboot the system using the following
|
||||
commands:
|
||||
|
||||
@@ -274,7 +170,7 @@ To add the ROCm repository, use the following steps, based on your distribution:
|
||||
:sync: RHEL-8
|
||||
|
||||
```shell
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 5.7; do
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
|
||||
[ROCm-$ver]
|
||||
name=ROCm$ver
|
||||
@@ -285,6 +181,7 @@ gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
done
|
||||
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
@@ -293,7 +190,7 @@ sudo yum clean all
|
||||
:sync: RHEL-9
|
||||
|
||||
```shell
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 5.7; do
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
sudo tee --append /etc/yum.repos.d/rocm.repo <<EOF
|
||||
[ROCm-$ver]
|
||||
name=ROCm$ver
|
||||
@@ -328,13 +225,9 @@ For a comprehensive list of meta-packages, refer to
|
||||
- Sample Multi-version installation
|
||||
|
||||
```shell
|
||||
sudo yum install rocm-hip-sdk5.7 rocm-hip-sdk5.6.1
|
||||
sudo yum install rocm-hip-sdk{{ linux.supported_family[0].rocm_version }} rocm-hip-sdk5.6.1
|
||||
```
|
||||
|
||||
:::::
|
||||
:::::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
{%- elif os.tag == "sle" %}
|
||||
::::{rubric} 1. Add the AMDGPU Repository and Install the Kernel-mode Driver
|
||||
::::
|
||||
|
||||
@@ -342,48 +235,27 @@ For a comprehensive list of meta-packages, refer to
|
||||
If you have a version of the kernel-mode driver installed, you may skip this
|
||||
section.
|
||||
```
|
||||
{% call(version) linux.for_version_in(os) %}
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} SLES 15.4
|
||||
:sync: SLES-15.4
|
||||
```{important}
|
||||
Instructions for {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
ver={{ linux.supported_family[0].amdgpu_version }}
|
||||
|
||||
sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/sle/15.4/main/x86_64
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/sle/{{ version.number }}/main/x86_64
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
sudo zypper ref
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} SLES 15.5
|
||||
:sync: SLES-15.5
|
||||
|
||||
```shell
|
||||
# version
|
||||
ver=5.7
|
||||
|
||||
sudo tee /etc/zypp/repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$ver/sle/15.5/main/x86_64
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
sudo zypper ref
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
{%- endcall %}
|
||||
|
||||
Install the kernel mode driver and reboot the system using the following
|
||||
commands:
|
||||
@@ -399,7 +271,7 @@ sudo reboot
|
||||
To add the ROCm repository, use the following steps:
|
||||
|
||||
```shell
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 5.7; do
|
||||
for ver in 5.3.3 5.4.6 5.5.3 5.6.1 {{ linux.supported_family[0].rocm_version }}; do
|
||||
sudo tee --append /etc/zypp/repos.d/rocm.repo <<EOF
|
||||
[ROCm-$ver]
|
||||
name=ROCm$ver
|
||||
@@ -431,14 +303,12 @@ For a comprehensive list of meta-packages, refer to
|
||||
- Sample Multi-version installation
|
||||
|
||||
```shell
|
||||
sudo zypper --gpg-auto-import-keys install rocm-hip-sdk5.7 rocm-hip-sdk5.6.1
|
||||
sudo zypper --gpg-auto-import-keys install rocm-hip-sdk{{ linux.supported_family[0].rocm_version }} rocm-hip-sdk5.6.1
|
||||
```
|
||||
|
||||
:::::
|
||||
::::::
|
||||
{%- endif %}
|
||||
{%- endcall %}
|
||||
|
||||
(post-install-actions-linux)=
|
||||
|
||||
## Post-install Actions and Verification Process
|
||||
|
||||
The post-install actions listed here are optional and depend on your use case,
|
||||
@@ -468,7 +338,7 @@ but are generally useful. Verification of the install is advised.
|
||||
2. Add binary paths to the `PATH` environment variable.
|
||||
|
||||
```shell
|
||||
export PATH=$PATH:/opt/rocm-5.7/bin:/opt/rocm-5.7/opencl/bin
|
||||
export PATH=$PATH:/opt/rocm-{{ linux.supported_family[0].rocm_version }}/bin:/opt/rocm-{{ linux.supported_family[0].rocm_version }}/opencl/bin
|
||||
|
||||
```
|
||||
|
||||
@@ -512,31 +382,18 @@ by both commands, the installation is considered successful:
|
||||
|
||||
To ensure the packages are installed successfully, use the following commands:
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
```shell
|
||||
sudo apt list --installed
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
{%- elif os.tag == "rhel" %}
|
||||
```shell
|
||||
sudo yum list installed
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
{%- elif os.tag == "sle" %}
|
||||
```shell
|
||||
sudo zypper search --installed-only
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
{%- endif %}
|
||||
{%- endcall %}
|
||||
@@ -57,6 +57,28 @@ sudo apt update
|
||||
:sync: RHEL
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} RHEL 8.6
|
||||
:sync: RHEL-8.6
|
||||
:sync: RHEL-8
|
||||
|
||||
```shell
|
||||
# version
|
||||
version=5.7
|
||||
|
||||
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<EOF
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/$version/rhel/8.6/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 8.7
|
||||
:sync: RHEL-8.7
|
||||
:sync: RHEL-8
|
||||
|
||||
@@ -116,16 +116,12 @@ sudo crb enable
|
||||
|
||||
Add the perl languages repository.
|
||||
|
||||
```{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
|
||||
zypper addrepo https://download.opensuse.org/repositories/devel:languages:perl/SLE_15_SP4/devel:languages:perl.repo
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
@@ -1,342 +0,0 @@
|
||||
# Quick Start (Linux)
|
||||
|
||||
## Add Repositories
|
||||
|
||||
::::::{tab-set}
|
||||
:::::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
|
||||
::::{rubric} 1. Download and convert the package signing key
|
||||
::::
|
||||
|
||||
```shell
|
||||
# Make the directory if it doesn't exist yet.
|
||||
# This location is recommended by the distribution maintainers.
|
||||
sudo mkdir --parents --mode=0755 /etc/apt/keyrings
|
||||
# Download the key, convert the signing-key to a full
|
||||
# keyring required by apt and store in the keyring directory
|
||||
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
|
||||
gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
|
||||
```
|
||||
|
||||
::::{rubric} 2. Add the repositories
|
||||
::::
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu 20.04
|
||||
:sync: ubuntu-20.04
|
||||
|
||||
```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/5.7/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/5.7 focal main
|
||||
EOF
|
||||
```
|
||||
|
||||
:::
|
||||
:::{tab-item} Ubuntu 22.04
|
||||
:sync: ubuntu-22.04
|
||||
|
||||
```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/5.7/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/5.7 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
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
::::{rubric} 3. Update the list of packages
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo apt update
|
||||
```
|
||||
|
||||
:::::
|
||||
|
||||
:::::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
::::{rubric} 1. Add the repositories
|
||||
::::
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} RHEL 8.7
|
||||
:sync: RHEL-8.7
|
||||
|
||||
```shell
|
||||
# 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/5.7/rhel/8.7/main/x86_64
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
# Add the rocm repository for RHEL 8
|
||||
sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
|
||||
[rocm]
|
||||
name=rocm
|
||||
baseurl=https://repo.radeon.com/rocm/rhel8/5.7/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} RHEL 8.8
|
||||
:sync: RHEL-8.8
|
||||
|
||||
```shell
|
||||
# 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/5.7/rhel/8.8/main/x86_64
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
# Add the rocm repository for RHEL 8
|
||||
sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
|
||||
[rocm]
|
||||
name=rocm
|
||||
baseurl=https://repo.radeon.com/rocm/rhel8/5.7/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} RHEL 9.1
|
||||
:sync: RHEL-9.1
|
||||
|
||||
```shell
|
||||
# Add the amdgpu module repository for RHEL 9.1
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/5.7/rhel/9.1/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/rhel9/5.7/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/5.7/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/rhel9/5.7/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
::::{rubric} 2. Clean cached files from enabled repositories
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo yum clean all
|
||||
```
|
||||
|
||||
:::::
|
||||
|
||||
:::::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
::::{rubric} 1. Add the repositories
|
||||
::::
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} SLES 15.4
|
||||
:sync: SLES-15.4
|
||||
|
||||
```shell
|
||||
|
||||
# Add the amdgpu module repository for SLES 15.4
|
||||
sudo tee /etc/zypp/repos.d/amdgpu.repo <<'EOF'
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/5.7/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/5.7/sle/15.5/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
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
::::{rubric} 2. Update the new repository
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo zypper ref
|
||||
```
|
||||
|
||||
:::::
|
||||
::::::
|
||||
|
||||
## Install Drivers
|
||||
|
||||
Install the `amdgpu-dkms` kernel module, aka driver, on your system.
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
|
||||
```shell
|
||||
sudo apt install amdgpu-dkms
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
```shell
|
||||
sudo yum install amdgpu-dkms
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
```shell
|
||||
sudo zypper install amdgpu-dkms
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
## Install ROCm Runtimes
|
||||
|
||||
Install the `rocm-hip-libraries` meta-package. This contains dependencies for most
|
||||
common ROCm applications.
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} Ubuntu
|
||||
:sync: ubuntu
|
||||
|
||||
```console shell
|
||||
sudo apt install rocm-hip-libraries
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} Red Hat Enterprise Linux
|
||||
:sync: RHEL
|
||||
|
||||
```console shell
|
||||
sudo yum install rocm-hip-libraries
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} SUSE Linux Enterprise Server
|
||||
:sync: SLES
|
||||
|
||||
```console shell
|
||||
sudo zypper install rocm-hip-libraries
|
||||
```
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
## Reboot the system
|
||||
|
||||
Loading the new driver requires a reboot of the system.
|
||||
|
||||
```shell
|
||||
sudo reboot
|
||||
```
|
||||
161
docs/deploy/linux/quick_start.md.jinja
Normal file
161
docs/deploy/linux/quick_start.md.jinja
Normal file
@@ -0,0 +1,161 @@
|
||||
{%- import "deploy/linux/linux.template.jinja" as linux %}
|
||||
<!-- markdownlint-disable no-duplicate-header blanks-around-headings no-multiple-blanks -->
|
||||
# Quick Start (Linux)
|
||||
|
||||
## Add Repositories
|
||||
{% call(family) linux.for_family_in(linux.supported_family) %}
|
||||
|
||||
{%- if family.tag == "instinct" %}
|
||||
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
|
||||
{%- if os.tag == "ubuntu" %}
|
||||
::::{rubric} 1. Download and convert the package signing key
|
||||
::::
|
||||
|
||||
```shell
|
||||
# Make the directory if it doesn't exist yet.
|
||||
# This location is recommended by the distribution maintainers.
|
||||
sudo mkdir --parents --mode=0755 /etc/apt/keyrings
|
||||
# Download the key, convert the signing-key to a full
|
||||
# keyring required by apt and store in the keyring directory
|
||||
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
|
||||
gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null
|
||||
```
|
||||
|
||||
::::{rubric} 2. Add the repositories
|
||||
::::
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# Kernel driver repository for {{ version.release }}
|
||||
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/{{ family.amdgpu_version }}/ubuntu {{ version.release }} main
|
||||
EOF
|
||||
# ROCm repository for {{ version.release }}
|
||||
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 {{ version.release }} 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
|
||||
```
|
||||
|
||||
{%- endcall %}
|
||||
|
||||
::::{rubric} 3. Update the list of packages
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo apt update
|
||||
```
|
||||
{%- elif os.tag == "rhel" %}
|
||||
::::{rubric} 1. Add the repositories
|
||||
::::
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# Add the amdgpu module repository for RHEL {{ version.number }}
|
||||
sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/{{ family.amdgpu_version }}/rhel/{{ version.number }}/main/x86_64
|
||||
enabled=1
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
# Add the rocm repository for {{ version.release | upper }}
|
||||
sudo tee /etc/yum.repos.d/rocm.repo <<'EOF'
|
||||
[rocm]
|
||||
name=rocm
|
||||
baseurl=https://repo.radeon.com/rocm/{{ version.release }}/latest/main
|
||||
enabled=1
|
||||
priority=50
|
||||
gpgcheck=1
|
||||
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
|
||||
EOF
|
||||
```
|
||||
|
||||
{%- endcall %}
|
||||
|
||||
::::{rubric} 2. Clean cached files from enabled repositories
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo yum clean all
|
||||
```
|
||||
{%- elif os.tag == "sle" %}
|
||||
::::{rubric} 1. Add the repositories
|
||||
::::
|
||||
{%- call(version) linux.for_version_in(os) %}
|
||||
|
||||
```{important}
|
||||
Instructions for {{ family.name }}, {{ os.name }} {{ version.number }}
|
||||
```
|
||||
|
||||
```shell
|
||||
# Add the amdgpu module repository for SLES {{ version.number }}
|
||||
sudo tee /etc/zypp/repos.d/amdgpu.repo <<'EOF'
|
||||
[amdgpu]
|
||||
name=amdgpu
|
||||
baseurl=https://repo.radeon.com/amdgpu/{{ family.amdgpu_version }}/sle/{{ version.number }}/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
|
||||
```
|
||||
|
||||
{%- endcall %}
|
||||
|
||||
::::{rubric} 2. Update the new repository
|
||||
::::
|
||||
|
||||
```shell
|
||||
sudo zypper ref
|
||||
```
|
||||
{%- endif %}
|
||||
{%- endcall -%}
|
||||
{%- endif %}
|
||||
{%- endcall %}
|
||||
|
||||
## Install drivers
|
||||
|
||||
Install the `amdgpu-dkms` kernel module, aka driver, on your system.
|
||||
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
{{ linux.install(os, "amdgpu-dkms")}}
|
||||
{%- endcall %}
|
||||
|
||||
## Install ROCm runtimes
|
||||
|
||||
Install the `rocm-hip-libraries` meta-package. This contains dependencies for most
|
||||
common ROCm applications.
|
||||
|
||||
{%- call(os) linux.for_os_in(linux.supported_os) %}
|
||||
{{ linux.install(os, "rocm-hip-libraries")}}
|
||||
{%- endcall %}
|
||||
|
||||
## Reboot the system
|
||||
|
||||
Loading the new driver requires a reboot of the system.
|
||||
|
||||
```shell
|
||||
sudo reboot
|
||||
```
|
||||
@@ -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 the 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:
|
||||
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:
|
||||
|
||||
- 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 the MIGraphX 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 MIGraphX's 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 the MIGraphX C++ or Python API to generate `.mxr` file. Refer to {numref}`image018` for an example.
|
||||
Alternatively, you can use MIGraphX's 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
|
||||
|
||||
@@ -3,6 +3,14 @@
|
||||
:::::{grid} 1 1 2 2
|
||||
:gutter: 1
|
||||
|
||||
:::{grid-item-card} ROCm using Radeon
|
||||
:link: {doc}`ROCm using Radeon <radeon:index>`
|
||||
:link-type: url
|
||||
ROCm and PyTorch installation processes to pair with the Radeon RX 7900 XTX GPU or the Radeon PRO W7900 GPU,
|
||||
and get started on a fully-functional environment for AI and ML development.
|
||||
|
||||
:::
|
||||
|
||||
:::{grid-item-card} Tuning Guides
|
||||
:link: tuning_guides/index
|
||||
:link-type: doc
|
||||
|
||||
@@ -59,16 +59,7 @@ 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 <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
|
||||
---
|
||||
align: center
|
||||
---
|
||||
Installation Matrix from Pytorch
|
||||
```
|
||||
[https://pytorch.org/get-started/locally/](https://pytorch.org/get-started/locally/). For the correct wheels command, you must select 'Linux', 'Python', 'pip', and 'ROCm' in the matrix.
|
||||
|
||||
To install PyTorch using the wheels package, follow these installation steps:
|
||||
|
||||
@@ -299,7 +290,7 @@ 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 Docker Hub or installing an official
|
||||
prebuilt PyTorch Docker image from AMD ROCm DockerHub 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.
|
||||
|
||||
@@ -17,6 +17,7 @@ tools, and APIs that enable GPU programming from low-level kernel to end-user ap
|
||||
|
||||
- {doc}`/deploy/linux/index`
|
||||
- {doc}`/deploy/docker`
|
||||
- {doc}`Deploy ROCm using Radeon <radeon:index>`
|
||||
|
||||
:::
|
||||
::::
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
# Docker
|
||||
@@ -57,8 +57,8 @@ 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 |
|
||||
| 5.7 | 1.17.2 | 22.9 |
|
||||
| 5.6.x | 1.17.2 | 22.9 |
|
||||
| 5.7.x | 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).
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
# Docker Image Support Matrix
|
||||
|
||||
The software support matrices for ROCm container releases is listed.
|
||||
|
||||
## ROCm 5.6
|
||||
|
||||
### PyTorch
|
||||
|
||||
#### `Ubuntu+ rocm5.6_internal_testing +169530b`
|
||||
|
||||
* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
|
||||
* [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)
|
||||
* [Torchvision 0.15.1](https://github.com/pytorch/vision/tree/v0.15.1)
|
||||
* [Tensorboard 2.12.0](https://github.com/tensorflow/tensorboard/tree/2.12.0)
|
||||
* [MAGMA](https://bitbucket.org/icl/magma/src/master/)
|
||||
* [UCX 1.10.0](https://github.com/openucx/ucx/tree/v1.10.0)
|
||||
* [OMPI 4.0.3](https://github.com/open-mpi/ompi/tree/v4.0.3)
|
||||
* [OFED 5.4.3](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)
|
||||
|
||||
#### `CentOS7+ rocm5.6_internal_testing +169530b`
|
||||
|
||||
* [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)
|
||||
* [Torchvision 0.15.1](https://github.com/pytorch/vision/tree/v0.15.1)
|
||||
* [Tensorboard 2.12.0](https://github.com/tensorflow/tensorboard/tree/2.12.0)
|
||||
* [MAGMA](https://bitbucket.org/icl/magma/src/master/)
|
||||
|
||||
#### `1.13 +bfeb431`
|
||||
|
||||
* [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)
|
||||
* [Torchvision 0.14.0](https://github.com/pytorch/vision/tree/v0.14.0)
|
||||
* [Tensorboard 2.12.0](https://github.com/tensorflow/tensorboard/tree/2.12.0)
|
||||
* [MAGMA](https://bitbucket.org/icl/magma/src/master/)
|
||||
* [UCX 1.10.0](https://github.com/openucx/ucx/tree/v1.10.0)
|
||||
* [OMPI 4.0.3](https://github.com/open-mpi/ompi/tree/v4.0.3)
|
||||
* [OFED 5.4.3](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)
|
||||
|
||||
#### `1.12 +05d5d04`
|
||||
|
||||
* [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)
|
||||
* [Torchvision 0.13.1](https://github.com/pytorch/vision/tree/v0.13.1)
|
||||
* [Tensorboard 2.12.0](https://github.com/tensorflow/tensorboard/tree/2.12.0)
|
||||
* [MAGMA](https://bitbucket.org/icl/magma/src/master/)
|
||||
* [UCX 1.10.0](https://github.com/openucx/ucx/tree/v1.10.0)
|
||||
* [OMPI 4.0.3](https://github.com/open-mpi/ompi/tree/v4.0.3)
|
||||
* [OFED 5.4.3](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)
|
||||
|
||||
### TensorFlow
|
||||
|
||||
#### `tensorflow_develop-upstream-QA-rocm56 +c88a9f4`
|
||||
|
||||
* [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)
|
||||
* [OMPI 4.0.7](https://github.com/open-mpi/ompi/tree/v4.0.7)
|
||||
* [Horovod 0.27.0](https://github.com/horovod/horovod/tree/v0.27.0)
|
||||
* [Tensorboard 2.12.0](https://github.com/tensorflow/tensorboard/tree/2.12.0)
|
||||
|
||||
#### `r2.11-rocm-enhanced +5be4141`
|
||||
|
||||
* [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)
|
||||
* [OMPI 4.0.7](https://github.com/open-mpi/ompi/tree/v4.0.7)
|
||||
* [Horovod 0.27.0](https://github.com/horovod/horovod/tree/v0.27.0)
|
||||
* [Tensorboard 2.11.2](https://github.com/tensorflow/tensorboard/tree/2.11.2)
|
||||
|
||||
#### `r2.10-rocm-enhanced +72789a3`
|
||||
|
||||
* [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)
|
||||
* [OMPI 4.0.7](https://github.com/open-mpi/ompi/tree/v4.0.7)
|
||||
* [Horovod 0.27.0](https://github.com/horovod/horovod/tree/v0.27.0)
|
||||
* [Tensorboard 2.10.1](https://github.com/tensorflow/tensorboard/tree/2.10.1)
|
||||
112
docs/release/docker_image_support_matrix.rst
Normal file
112
docs/release/docker_image_support_matrix.rst
Normal file
@@ -0,0 +1,112 @@
|
||||
******************************************************************
|
||||
Docker image support matrix
|
||||
******************************************************************
|
||||
|
||||
AMD validates and publishes `PyTorch <https://hub.docker.com/r/rocm/pytorch>`_ and `TensorFlow <https://hub.docker.com/r/rocm/tensorflow>`_
|
||||
containers on dockerhub. The following tags, and associated inventories, are validated with ROCm 5.7.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: PyTorch
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: Ubuntu 20.04
|
||||
|
||||
Tag: `rocm/pytorch:rocm5.7_ubuntu20.04_py3.9_pytorch_staging <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_ubuntu20.04_py3.9_pytorch_2.0.1/images/sha256-4dd86046e5f777f53ae40a75ecfc76a5e819f01f3b2d40eacbb2db95c2f971d4)>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `Torch 2.1.0 <https://github.com/ROCmSoftwarePlatform/pytorch/tree/rocm5.7_internal_testing>`_
|
||||
* `Apex 0.1 <https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1>`_
|
||||
* `Torchvision 0.16.0 <https://github.com/pytorch/vision/tree/release/0.16>`_
|
||||
* `Tensorboard 2.14.0 <https://github.com/tensorflow/tensorboard/tree/2.14>`_
|
||||
* `MAGMA <https://bitbucket.org/icl/magma/src/master/>`_
|
||||
* `UCX 1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
|
||||
* `OMPI 4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
|
||||
* `OFED 5.4.3 <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>`_
|
||||
|
||||
|
||||
Tag: `Ubuntu rocm/pytorch:rocm5.7_ubuntu20.04_py3.9_pytorch_1.12.1 <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_ubuntu20.04_py3.9_pytorch_1.12.1/images/sha256-e67db9373c045a7b6defd43cc3d067e7d49fd5d380f3f8582d2fb219c1756e1f>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `Torch 1.12.1 <https://github.com/ROCmSoftwarePlatform/pytorch/tree/release/1.12>`_
|
||||
* `Apex 0.1 <https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1>`_
|
||||
* `Torchvision 0.13.1 <https://github.com/pytorch/vision/tree/v0.13.1>`_
|
||||
* `Tensorboard 2.14.0 <https://github.com/tensorflow/tensorboard/tree/2.14>`_
|
||||
* `MAGMA <https://bitbucket.org/icl/magma/src/master/>`_
|
||||
* `UCX 1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
|
||||
* `OMPI 4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
|
||||
* `OFED 5.4.3 <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>`_
|
||||
|
||||
Tag: `Ubuntu rocm/pytorch:rocm5.7_ubuntu20.04_py3.9_pytorch_1.13.1 <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_ubuntu20.04_py3.9_pytorch_1.13.1/images/sha256-ed99d159026093d2aaf5c48c1e4b0911508773430377051372733f75c340a4c1>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `Torch 1.12.1 <https://github.com/ROCmSoftwarePlatform/pytorch/tree/release/1.13>`_
|
||||
* `Apex 0.1 <https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1>`_
|
||||
* `Torchvision 0.14.0 <https://github.com/pytorch/vision/tree/v0.14.0>`_
|
||||
* `Tensorboard 2.12.0 <https://github.com/tensorflow/tensorboard/tree/2.12.0>`_
|
||||
* `MAGMA <https://bitbucket.org/icl/magma/src/master/>`_
|
||||
* `UCX 1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
|
||||
* `OMPI 4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
|
||||
* `OFED 5.4.3 <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>`_
|
||||
|
||||
Tag: `Ubuntu rocm/pytorch:rocm5.7_ubuntu20.04_py3.9_pytorch_2.0.1 <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_ubuntu20.04_py3.9_pytorch_2.0.1/images/sha256-4dd86046e5f777f53ae40a75ecfc76a5e819f01f3b2d40eacbb2db95c2f971d4>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `Torch 2.0.1 <https://github.com/ROCmSoftwarePlatform/pytorch/tree/release/2.0>`_
|
||||
* `Apex 0.1 <https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1>`_
|
||||
* `Torchvision 0.15.2 <https://github.com/pytorch/vision/tree/release/0.15>`_
|
||||
* `Tensorboard 2.14.0 <https://github.com/tensorflow/tensorboard/tree/2.14>`_
|
||||
* `MAGMA <https://bitbucket.org/icl/magma/src/master/>`_
|
||||
* `UCX 1.10.0 <https://github.com/openucx/ucx/tree/v1.10.0>`_
|
||||
* `OMPI 4.0.3 <https://github.com/open-mpi/ompi/tree/v4.0.3>`_
|
||||
* `OFED 5.4.3 <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>`_
|
||||
|
||||
.. tab-item:: CentOS 7
|
||||
|
||||
Tag: `rocm/pytorch:rocm5.7_centos7_py3.9_pytorch_staging <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_centos7_py3.9_pytorch_staging/images/sha256-92240cdf0b4aa7afa76fc78be995caa19ee9c54b5c9f1683bdcac28cedb58d2b>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/yum/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `Torch 2.1.0 <https://github.com/ROCmSoftwarePlatform/pytorch/tree/rocm5.7_internal_testing>`_
|
||||
* `Apex 0.1 <https://github.com/ROCmSoftwarePlatform/apex/tree/v0.1>`_
|
||||
* `Torchvision 0.16.0 <https://github.com/pytorch/vision/tree/release/0.16>`_
|
||||
* `MAGMA <https://bitbucket.org/icl/magma/src/master/>`_
|
||||
|
||||
.. tab-item:: TensorFlow
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: Ubuntu 20.04
|
||||
|
||||
Tag: `rocm5.7-tf2.12-dev <https://hub.docker.com/layers/rocm/tensorflow/rocm5.7-tf2.12-dev/images/sha256-e0ac4d49122702e5167175acaeb98a79b9500f585d5e74df18facf6b52ce3e59>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `tensorflow-rocm 2.12.1 <https://pypi.org/project/tensorflow-rocm/2.12.1.570/>`_
|
||||
* `Tensorboard 2.12.3 <https://github.com/tensorflow/tensorboard/tree/2.12>`_
|
||||
|
||||
Tag: `rocm5.7-tf2.13-dev <https://hub.docker.com/layers/rocm/tensorflow/rocm5.7-tf2.13-dev/images/sha256-6f995539eebc062aac2b53db40e2b545192d8b032d0deada8c24c6651a7ac332>`_
|
||||
|
||||
* Inventory:
|
||||
|
||||
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
|
||||
* `Python 3.9 <https://www.python.org/downloads/release/python-3918/>`_
|
||||
* `tensorflow-rocm 2.13.0 <https://pypi.org/project/tensorflow-rocm/2.13.0.570/>`_
|
||||
* `Tensorboard 2.13.0 <https://github.com/tensorflow/tensorboard/tree/2.13>`_
|
||||
@@ -5,6 +5,7 @@ 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 |
|
||||
|
||||
@@ -21,3 +21,4 @@ the compatibility combinations that are currently supported.
|
||||
| 5.6.0 | 5.4.3, 5.5.1 |
|
||||
| 5.6.1 | 5.7.0 |
|
||||
| 5.7.0 | 5.5.0, 5.6.1 |
|
||||
| 5.7.1 | 5.5.0, 5.6.1 |
|
||||
|
||||
@@ -2,8 +2,6 @@
|
||||
|
||||
| Version | Release Date |
|
||||
| ------- | ------------ |
|
||||
| [5.7.0](https://rocm.docs.amd.com/en/docs-5.7.0/) | Sep 15, 2023 |
|
||||
| [5.6.1](https://rocm.docs.amd.com/en/docs-5.6.1/) | Aug 29, 2023 |
|
||||
| [5.6.0](https://rocm.docs.amd.com/en/docs-5.6.0/) | Jun 28, 2023 |
|
||||
| [5.5.1](https://rocm.docs.amd.com/en/docs-5.5.1/) | May 24, 2023 |
|
||||
| [5.5.0](https://rocm.docs.amd.com/en/docs-5.5.0/) | May 1, 2023 |
|
||||
|
||||
@@ -19,6 +19,14 @@ ROCm supports programming models, such as OpenMP and OpenCL, and includes all ne
|
||||
compilers, debuggers, and libraries. ROCm is fully integrated into machine learning (ML) frameworks,
|
||||
such as PyTorch and TensorFlow.
|
||||
|
||||
## ROCm on Radeon
|
||||
|
||||
Starting with ROCm™ 5.7 on Linux®, researchers and developers working with Machine Learning (ML) models and algorithms can tap into the parallel computing power of the AMD desktop GPUs based on the RDNA™ 3 architecture.
|
||||
|
||||
A client solution built on powerful high-end AMD GPUs provides a local, private and often cost-effective workflow to develop ROCm and train ML (PyTorch) for the users who previously relied solely on cloud-based solutions.
|
||||
|
||||
For information about how to install ROCm on AMD desktop GPUs based on the RDNA™ 3 architecture, see {doc}`Use ROCm on Radeon <radeon:index>`. For more information about supported AMD Radeon™ desktop GPUs, see {doc}`Radeon Compatibility Matrices <radeon:compatibility>`.
|
||||
|
||||
## ROCm on Windows
|
||||
|
||||
Starting with ROCm 5.5, the HIP SDK brings a subset of ROCm to developers on Windows.
|
||||
|
||||
@@ -81,7 +81,7 @@ subtrees:
|
||||
subtrees:
|
||||
- entries:
|
||||
- file: release/user_kernel_space_compat_matrix
|
||||
- file: release/docker_image_support_matrix
|
||||
- file: release/docker_image_support_matrix.rst
|
||||
- file: release/3rd_party_support_matrix
|
||||
- file: release/licensing
|
||||
|
||||
@@ -102,7 +102,7 @@ subtrees:
|
||||
- entries:
|
||||
- file: reference/gpu_libraries/linear_algebra
|
||||
subtrees:
|
||||
- entries:
|
||||
- entries:
|
||||
- title: rocBLAS
|
||||
url: ${project:rocblas}
|
||||
- title: hipBLAS
|
||||
|
||||
@@ -1,2 +1 @@
|
||||
rocm-docs-core==1.8.0
|
||||
sphinx-reredirects
|
||||
rocm-docs-core==0.26.0
|
||||
|
||||
@@ -4,103 +4,105 @@
|
||||
#
|
||||
# pip-compile requirements.in
|
||||
#
|
||||
accessible-pygments==0.0.5
|
||||
accessible-pygments==0.0.3
|
||||
# via pydata-sphinx-theme
|
||||
alabaster==1.0.0
|
||||
alabaster==0.7.13
|
||||
# via sphinx
|
||||
babel==2.16.0
|
||||
babel==2.11.0
|
||||
# via
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
beautifulsoup4==4.12.3
|
||||
beautifulsoup4==4.11.2
|
||||
# via pydata-sphinx-theme
|
||||
breathe==4.35.0
|
||||
breathe==4.34.0
|
||||
# via rocm-docs-core
|
||||
certifi==2024.8.30
|
||||
certifi==2023.7.22
|
||||
# via requests
|
||||
cffi==1.17.1
|
||||
cffi==1.15.1
|
||||
# via
|
||||
# cryptography
|
||||
# pynacl
|
||||
charset-normalizer==3.3.2
|
||||
charset-normalizer==2.1.1
|
||||
# via requests
|
||||
click==8.1.7
|
||||
click==8.1.3
|
||||
# via sphinx-external-toc
|
||||
cryptography==43.0.1
|
||||
cryptography==41.0.3
|
||||
# via pyjwt
|
||||
deprecated==1.2.14
|
||||
deprecated==1.2.13
|
||||
# via pygithub
|
||||
docutils==0.21.2
|
||||
docutils==0.19
|
||||
# via
|
||||
# breathe
|
||||
# myst-parser
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
fastjsonschema==2.20.0
|
||||
fastjsonschema==2.16.3
|
||||
# via rocm-docs-core
|
||||
gitdb==4.0.11
|
||||
gitdb==4.0.10
|
||||
# via gitpython
|
||||
gitpython==3.1.43
|
||||
gitpython==3.1.30
|
||||
# via rocm-docs-core
|
||||
idna==3.10
|
||||
idna==3.4
|
||||
# via requests
|
||||
imagesize==1.4.1
|
||||
# via sphinx
|
||||
jinja2==3.1.4
|
||||
jinja2==3.1.2
|
||||
# via
|
||||
# myst-parser
|
||||
# sphinx
|
||||
markdown-it-py==3.0.0
|
||||
markdown-it-py==2.2.0
|
||||
# via
|
||||
# mdit-py-plugins
|
||||
# myst-parser
|
||||
markupsafe==2.1.5
|
||||
markupsafe==2.1.2
|
||||
# via jinja2
|
||||
mdit-py-plugins==0.4.2
|
||||
mdit-py-plugins==0.3.4
|
||||
# via myst-parser
|
||||
mdurl==0.1.2
|
||||
# via markdown-it-py
|
||||
myst-parser==4.0.0
|
||||
myst-parser==1.0.0
|
||||
# via rocm-docs-core
|
||||
packaging==24.1
|
||||
packaging==23.0
|
||||
# via
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
pycparser==2.22
|
||||
pycparser==2.21
|
||||
# via cffi
|
||||
pydata-sphinx-theme==0.15.4
|
||||
pydata-sphinx-theme==0.13.3
|
||||
# via
|
||||
# rocm-docs-core
|
||||
# sphinx-book-theme
|
||||
pygithub==2.4.0
|
||||
pygithub==1.58.1
|
||||
# via rocm-docs-core
|
||||
pygments==2.18.0
|
||||
pygments==2.15.0
|
||||
# via
|
||||
# accessible-pygments
|
||||
# pydata-sphinx-theme
|
||||
# sphinx
|
||||
pyjwt[crypto]==2.9.0
|
||||
pyjwt[crypto]==2.6.0
|
||||
# via pygithub
|
||||
pynacl==1.5.0
|
||||
# via pygithub
|
||||
pyyaml==6.0.2
|
||||
pytz==2022.7.1
|
||||
# via babel
|
||||
pyyaml==6.0
|
||||
# via
|
||||
# myst-parser
|
||||
# rocm-docs-core
|
||||
# sphinx-external-toc
|
||||
requests==2.32.3
|
||||
requests==2.31.0
|
||||
# via
|
||||
# pygithub
|
||||
# sphinx
|
||||
rocm-docs-core==1.8.0
|
||||
rocm-docs-core==0.26.0
|
||||
# via -r requirements.in
|
||||
smmap==5.0.1
|
||||
smmap==5.0.0
|
||||
# via gitdb
|
||||
snowballstemmer==2.2.0
|
||||
# via sphinx
|
||||
soupsieve==2.6
|
||||
soupsieve==2.4
|
||||
# via beautifulsoup4
|
||||
sphinx==8.0.2
|
||||
sphinx==5.3.0
|
||||
# via
|
||||
# breathe
|
||||
# myst-parser
|
||||
@@ -111,40 +113,31 @@ sphinx==8.0.2
|
||||
# sphinx-design
|
||||
# sphinx-external-toc
|
||||
# sphinx-notfound-page
|
||||
# sphinx-reredirects
|
||||
sphinx-book-theme==1.1.3
|
||||
sphinx-book-theme==1.0.1
|
||||
# via rocm-docs-core
|
||||
sphinx-copybutton==0.5.2
|
||||
sphinx-copybutton==0.5.1
|
||||
# via rocm-docs-core
|
||||
sphinx-design==0.6.1
|
||||
sphinx-design==0.4.1
|
||||
# via rocm-docs-core
|
||||
sphinx-external-toc==1.0.1
|
||||
sphinx-external-toc==0.3.1
|
||||
# via rocm-docs-core
|
||||
sphinx-notfound-page==1.0.4
|
||||
sphinx-notfound-page==0.8.3
|
||||
# via rocm-docs-core
|
||||
sphinx-reredirects==0.1.5
|
||||
# via -r requirements.in
|
||||
sphinxcontrib-applehelp==2.0.0
|
||||
sphinxcontrib-applehelp==1.0.4
|
||||
# via sphinx
|
||||
sphinxcontrib-devhelp==2.0.0
|
||||
sphinxcontrib-devhelp==1.0.2
|
||||
# via sphinx
|
||||
sphinxcontrib-htmlhelp==2.1.0
|
||||
sphinxcontrib-htmlhelp==2.0.1
|
||||
# via sphinx
|
||||
sphinxcontrib-jsmath==1.0.1
|
||||
# via sphinx
|
||||
sphinxcontrib-qthelp==2.0.0
|
||||
sphinxcontrib-qthelp==1.0.3
|
||||
# via sphinx
|
||||
sphinxcontrib-serializinghtml==2.0.0
|
||||
sphinxcontrib-serializinghtml==1.1.5
|
||||
# via sphinx
|
||||
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
|
||||
typing-extensions==4.5.0
|
||||
# via pydata-sphinx-theme
|
||||
urllib3==1.26.13
|
||||
# via requests
|
||||
wrapt==1.14.1
|
||||
# via deprecated
|
||||
|
||||
@@ -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 atomic operations operate as completers for ``CAS`` (Compare and Swap), ``FetchADD``, ``SWAP`` atomics. The atomic operations are initiated by the
|
||||
The new PCIe AtomicOps operate as completers for ``CAS`` (Compare and Swap), ``FetchADD``, ``SWAP`` atomics. The AtomicsOps 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 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.
|
||||
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.
|
||||
|
||||
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.
|
||||
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.
|
||||
|
||||
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.
|
||||
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.
|
||||
|
||||
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).
|
||||
|
||||
@@ -69,7 +69,7 @@ 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
|
||||
|
||||
@@ -77,7 +77,7 @@ 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.
|
||||
|
||||
@@ -116,5 +116,30 @@ 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.
|
||||
|
||||
For more information, you can review
|
||||
`Overview of Changes to PCI Express 3.0 <https://www.mindshare.com/files/resources/PCIe%203-0.pdf>`_.
|
||||
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
|
||||
|
||||
@@ -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 the CMake HIP language support will require CMake 3.21 or higher.
|
||||
to make use of CMake's 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 related facilities.
|
||||
to get an overview of CMake's 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 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
|
||||
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
|
||||
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 the following CMake commands:
|
||||
This project can then be configured with for eg.
|
||||
|
||||
- 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 the CMake option ``-D GPU_TARGETS="gfx1032;gfx1035"``.
|
||||
AMD ROCm. It can be set to eg. ``-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-and-forget fashion for quick assembly using graphical front-ends. This is
|
||||
a setup'n'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 Integration (CI) pipelines. CMake has condensed existing practice
|
||||
Continuous Intergration (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>`_
|
||||
|
||||
@@ -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. |
|
||||
|
||||
@@ -81,7 +81,7 @@ The command processor counters are further classified into fetcher and compute.
|
||||
| `spi_ra_lds_cu_full_csn` | CUs | Sum of CU where LDS cannot take csn wave when not fits |
|
||||
| `spi_ra_bar_cu_full_csn[∗]` | CUs | Sum of CU where BARRIER cannot take csn wave when not fits |
|
||||
| `spi_ra_bulky_cu_full_csn[∗]` | CUs | Sum of CU where BULKY cannot take csn wave when not fits |
|
||||
| `spi_ra_tglim_cu_full_csn[∗]` | Cycles | Cycles where csn wants to req but all CUs are at `tg_limit` |
|
||||
| `spi_ra_tglim_cu_full_csn[∗]` | Cycles | Cycles where csn wants to req but all CUs are at tg_limit |
|
||||
| `spi_ra_wvlim_cu_full_csn[∗]` | Cycles | Number of clocks csn is stalled due to WAVE LIMIT |
|
||||
| `spi_vwc_csc_wr` | Cycles | Number of clocks to write CSC waves to VGPRs (need to multiply this value by 4) |
|
||||
| `spi_swc_csc_wr` | Cycles | Number of clocks to write CSC waves to SGPRs (need to multiply this value by 4) |
|
||||
@@ -288,9 +288,9 @@ The vector L1 cache subsystem counters are further classified into texture addre
|
||||
| `tcp_gate_en2` | Cycles | Number of cycles vL1D core clocks are turned on |
|
||||
| `tcp_td_tcp_stall_cycles` | Cycles | Number of cycles TD stalls vL1D |
|
||||
| `tcp_tcr_tcp_stall_cycles` | Cycles | Number of cycles TCR stalls vL1D |
|
||||
| `tcp_read_tagconflict_stall_cycles` | Cycles | Number of cycles tag RAM conflict stalls on a Read |
|
||||
| `tcp_write_tagconflict_stall_cycles` | Cycles | Number of cycles tag RAM conflict stalls on a Write |
|
||||
| `tcp_atomic_tagconflict_stall_cycles` | Cycles | Number of cycles tag RAM conflict stalls on an Atomic |
|
||||
| `tcp_read_tagconflict_stall_cycles` | Cycles | Number of cycles tagram conflict stalls on a Read |
|
||||
| `tcp_write_tagconflict_stall_cycles` | Cycles | Number of cycles tagram conflict stalls on a Write |
|
||||
| `tcp_atomic_tagconflict_stall_cycles` | Cycles | Number of cycles tagram conflict stalls on an Atomic |
|
||||
| `tcp_pending_stall_cycles` | Cycles | Number of cycles vL1D cache is stalled due to data pending from L2 Cache |
|
||||
| `tcp_ta_tcp_state_read` | Req | Number of wavefront instruction requests to vL1D |
|
||||
| `tcp_volatile[∗]` | Req | Number of L1 volatile pixels/buffers from TA |
|
||||
@@ -347,7 +347,7 @@ The vector L1 cache subsystem counters are further classified into texture addre
|
||||
| `tcc_CC_req` |Req | Number of CC requests |
|
||||
| `tcc_RW_req` |Req | Number of RW requests |
|
||||
| `tcc_probe` |Req | Number of L2 Cache probe requests |
|
||||
| `tcc_probe_all[∗]` |Req | Number of external probe requests with `EA_TCC_preq_all== 1` |
|
||||
| `tcc_probe_all[∗]` |Req | Number of external probe requests with EA_TCC_preq_all== 1 |
|
||||
| `tcc_read_req` |Req | Number of L2 Cache Read requests |
|
||||
| `tcc_write_req` |Req | Number of L2 Cache Write requests |
|
||||
| `tcc_atomic_req` |Req | Number of L2 Cache Atomic requests |
|
||||
|
||||
@@ -17,16 +17,16 @@
|
||||
- Run this for 5.6.0 (change for whatever version you require)
|
||||
- `GITHUB_ACCESS_TOKEN=my_token_here`
|
||||
|
||||
To generate the changelog from 5.0.0 up to and including 5.6.0:
|
||||
To generate the changelog from 5.0.0 up to and including 5.7.1:
|
||||
|
||||
```sh
|
||||
python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --do-previous --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.6 5.6.0
|
||||
python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --do-previous --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.7 5.7.1
|
||||
```
|
||||
|
||||
To generate the changelog only for 5.6.0:
|
||||
To generate the changelog only for 5.7.1:
|
||||
|
||||
```sh
|
||||
python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.6 5.6.0
|
||||
python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.7 5.7.1
|
||||
```
|
||||
|
||||
### Notes
|
||||
|
||||
36
tools/autotag/templates/rocm_changes/5.7.1.md
Normal file
36
tools/autotag/templates/rocm_changes/5.7.1.md
Normal file
@@ -0,0 +1,36 @@
|
||||
<!-- markdownlint-disable first-line-h1 -->
|
||||
<!-- markdownlint-disable no-duplicate-header -->
|
||||
|
||||
### What's New in This Release
|
||||
|
||||
#### Installing all GPU Address sanitizer packages with a single command
|
||||
|
||||
ROCm 5.7.1 simplifies the installation steps for the optional Address Sanitizer (ASan) packages. This release provides the meta package *rocm-ml-sdk-asan* for ease of ASan installation. The following command can be used to install all ASan packages rather than installing each package separately,
|
||||
|
||||
sudo apt-get install rocm-ml-sdk-asan
|
||||
|
||||
For more detailed information about using the GPU AddressSanitizer, refer to the [user guide](https://rocm.docs.amd.com/en/docs-5.7.1/understand/using_gpu_sanitizer.html)
|
||||
|
||||
### ROCm Libraries
|
||||
|
||||
#### rocBLAS
|
||||
A new functionality rocblas-gemm-tune and an environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH are added to rocBLAS in the ROCm 5.7.1 release.
|
||||
|
||||
*rocblas-gemm-tune* is used to find the best-performing GEMM kernel for each GEMM problem set. It has a command line interface, which mimics the --yaml input used by rocblas-bench. To generate the expected --yaml input, profile logging can be used, by setting the environment variable ROCBLAS_LAYER4.
|
||||
|
||||
For more information on rocBLAS logging, see Logging in rocBLAS, in the [API Reference Guide](https://rocm.docs.amd.com/projects/rocBLAS/en/docs-5.7.1/API_Reference_Guide.html#logging-in-rocblas).
|
||||
|
||||
An example input file: Expected output (note selected GEMM idx may differ): Where the far right values (solution_index) are the indices of the best-performing kernels for those GEMMs in the rocBLAS kernel library. These indices can be directly used in future GEMM calls. See rocBLAS/samples/example_user_driven_tuning.cpp for sample code of directly using kernels via their indices.
|
||||
|
||||
If the output is stored in a file, the results can be used to override default kernel selection with the kernels found, by setting the environment variable ROCBLAS_TENSILE_GEMM_OVERRIDE_PATH, where points to the stored file.
|
||||
|
||||
For more details, refer to the [rocBLAS Programmer's Guide.](https://rocm.docs.amd.com/projects/rocBLAS/en/latest/Programmers_Guide.html#rocblas-gemm-tune)
|
||||
|
||||
#### HIP 5.7.1 (for ROCm 5.7.1)
|
||||
|
||||
ROCm 5.7.1 is a point release with several bug fixes in the HIP runtime.
|
||||
|
||||
### Fixed defects
|
||||
The *hipPointerGetAttributes* API returns the correct HIP memory type as *hipMemoryTypeManaged* for managed memory.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user