github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-01-09 14:48:06 -05:00
Code Issues Packages Projects Releases Wiki Activity

merge conflicts & remove linux install

Browse Source
This commit is contained in:
Lisa Delaney
2023-10-25 13:15:47 -06:00
parent b0caf52156 37db70c914
commit f0f4fa15b4
28 changed files with 6050 additions and 2575 deletions
Download Patch File Download Diff File Expand all files Collapse all files

76
.github/ISSUE_TEMPLATE/0_issue_report.yml vendored Normal file
View File

@@ -0,0 +1,76 @@
name: Issue Report
description: File a report for something not working correctly.
title: "[Issue]: "
body:
- type: markdown
attributes:
value: |
Thank you for taking the time to fill out this report!
On a Linux system, you can acquire your OS, CPU, GPU, and ROCm version (for filling out this report) with the following commands:
echo "OS:" && cat /etc/os-release | grep -E "^(NAME=|VERSION=)";
echo "CPU: " && cat /proc/cpuinfo | grep "model name" | sort --unique;
echo "GPU:" && /opt/rocm/bin/rocminfo | grep -E "^\s*(Name|Marketing Name)";
echo "ROCm in /opt:" && ls -1 /opt | grep -E "rocm-";
- type: textarea
attributes:
label: Problem Description
description: Describe the issue you encountered.
placeholder: "The steps to reproduce can be included here, or in the dedicated section further below."
validations:
required: true
- type: input
attributes:
label: Operating System
description: What is the name and version number of the OS?
placeholder: "e.g. Ubuntu 22.04.3 LTS (Jammy Jellyfish)"
validations:
required: true
- type: input
attributes:
label: CPU
description: What CPU did you encounter the issue on?
placeholder: "e.g. AMD Ryzen 9 5900HX with Radeon Graphics"
validations:
required: true
- type: input
attributes:
label: GPU
description: What GPU(s) did you encounter the issue on?
placeholder: "e.g. MI200"
validations:
required: true
- type: input
attributes:
label: ROCm Version
description: What version(s) of ROCm did you encounter the issue on?
placeholder: "e.g. 5.7.0"
validations:
required: true
- type: input
attributes:
label: ROCm Component
description: (Optional) If this issue relates to a specific ROCm component, it can be mentioned here.
placeholder: "e.g. rocBLAS"
- type: textarea
attributes:
label: Steps to Reproduce
description: (Optional) Detailed steps to reproduce the issue.
placeholder: Please also include what you expected to happen, and what actually did, at the failing step(s).
validations:
required: false
- type: textarea
attributes:
label: Output of /opt/rocm/bin/rocminfo --support
description: The output of rocminfo --support will help to better address the problem.
placeholder: |
ROCk module is loaded
=====================
HSA System Attributes
=====================
[...]
validations:
required: true

32
.github/ISSUE_TEMPLATE/1_feature_request.yml vendored Normal file
View File

@@ -0,0 +1,32 @@
name: Feature Suggestion
description: Suggest an additional functionality, or new way of handling an existing functionality.
title: "[Feature]: "
body:
- type: markdown
attributes:
value: |
Thank you for taking the time to make a suggestion!
- type: textarea
attributes:
label: Suggestion Description
description: Describe your suggestion.
validations:
required: true
- type: input
attributes:
label: Operating System
description: (Optional) If this is for a specific OS, you can mention it here.
placeholder: "e.g. Ubuntu"
- type: input
attributes:
label: GPU
description: (Optional) If this is for a specific GPU or GPU family, you can mention it here.
placeholder: "e.g. MI200"
- type: input
attributes:
label: ROCm Component
description: (Optional) If this issue relates to a specific ROCm component, it can be mentioned here.
placeholder: "e.g. rocBLAS"

5
.github/ISSUE_TEMPLATE/config.yml vendored Normal file
View File

@@ -0,0 +1,5 @@
blank_issues_enabled: false
contact_links:
- name: ROCm Community Discussions
url: https://github.com/RadeonOpenCompute/ROCm/discussions
about: Please ask and answer questions here for anything ROCm.

2
.gitignore vendored
View File

@@ -15,4 +15,4 @@ _readthedocs/
# avoid duplicating contributing.md due to conf.py # avoid duplicating contributing.md due to conf.py
docs/CHANGELOG.md docs/CHANGELOG.md
docs/contribute/index.md docs/contribute/index.md
docs/about/release-notes.md docs/about/release-notes.md

2
.readthedocs.yaml
View File

@@ -6,7 +6,7 @@ version: 2
sphinx: sphinx:
configuration: docs/conf.py configuration: docs/conf.py
formats: [htmlzip, pdf, epub] formats: [htmlzip, pdf]
python: python:
install: install:

89
CHANGELOG.md
View File

@@ -1,4 +1,4 @@
# Release Notes # Changelog
<!-- Do not edit this file! This file is autogenerated with --> <!-- Do not edit this file! This file is autogenerated with -->
<!-- tools/autotag/tag_script.py --> <!-- tools/autotag/tag_script.py -->
@@ -11,7 +11,70 @@
<!-- spellcheck-disable --> <!-- 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
------------------- -------------------
@@ -31,7 +94,7 @@ AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively gfx906
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. 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.
* ROCm 6.0 release will show MI50s as "under maintenance" mode for [Linux](./compatibility/linux-support.md) and [Windows](./compatibility/windows-support.md) * ROCm 6.0 release will show MI50s as "under maintenance" for [Linux](../about/compatibility/linux-support.md) and [Windows](../about/compatibility/windows-support.md)
* No new features and performance optimizations will be supported for the gfx906 GPUs beyond this major release (ROCm 5.7). * No new features and performance optimizations will be supported for the gfx906 GPUs beyond this major release (ROCm 5.7).
@@ -41,7 +104,7 @@ As outlined in [5.6.0](https://rocm.docs.amd.com/en/docs-5.6.0/release.html), RO
* Bug fixes will not be backported to older ROCm releases for gfx906. * Bug fixes will not be backported to older ROCm releases for gfx906.
* Distribution and operating system updates will continue as per the ROCm release cadence for gfx906 GPUs until EOM. * Distribution and operating system updates will continue per the ROCm release cadence for gfx906 GPUs until EOM.
#### Feature updates #### Feature updates
@@ -79,7 +142,7 @@ The ROCm 5.7 release introduces the beta release of LLVM AddressSanitizer (ASan)
Until now, the LLVM ASan 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. Until now, the LLVM ASan 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.
<!-- TODO: Fix the link to be able to work at every files --> <!-- TODO: Fix the link to be able to work at every files -->
Refer to the documentation on LLVM ASan with the GPU at [LLVM AddressSanitizer User Guide](../conceptual/using-gpu-sanitizer.md). Refer to the documentation on LLVM ASan with the GPU at [LLVM AddressSanitizer user guide](../conceptual/using-gpu-sanitizer.md).
**Note**: The beta release of LLVM ASan for ROCm is currently tested and validated on Ubuntu 20.04. **Note**: The beta release of LLVM ASan for ROCm is currently tested and validated on Ubuntu 20.04.
@@ -242,7 +305,7 @@ MIGraphX 2.7 for ROCm 5.7.0
- Bumped version of half library to 5.6.0 - Bumped version of half library to 5.6.0
- Bumped CI to support rocm 5.6 - Bumped CI to support rocm 5.6
- Make building tests optional - Make building tests optional
- replace np.bool with bool as per numpy request - replace np.bool with bool per numpy request
##### Removed ##### Removed
@@ -528,7 +591,7 @@ ROCm 5.6 consists of several AI software ecosystem improvements to our fast-grow
* Ongoing software enhancements for LLMs, ensuring full compliance with the HuggingFace unit test suite * Ongoing software enhancements for LLMs, ensuring full compliance with the HuggingFace unit test suite
* OpenAI Triton, CuPy, HIP Graph support, and many other library performance enhancements * OpenAI Triton, CuPy, HIP Graph support, and many other library performance enhancements
* Improved ROCm deployment and development tools, including CPU-GPU (rocGDB) debugger, profiler, and docker containers * Improved ROCm deployment and development tools, including CPU-GPU (rocGDB) debugger, profiler, and docker containers
* New pseudorandom generators are available in rocRAND. Added support for half-precision transforms in hipFFT/rocFFT. Added LU refactorization and linear system solver for sparse matrices in rocSOLVER. * New pseudorandom generators are available in rocRAND. Added support for half-precision transforms in hipFFT/rocFFT. Added LU refactorization and linear system solver for sparse matrices in rocSOLVER.
### OS and GPU support changes ### OS and GPU support changes
@@ -538,7 +601,7 @@ ROCm 5.6 consists of several AI software ecosystem improvements to our fast-grow
* Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance \[EOM])(will be aligned with the closest ROCm release) * Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance \[EOM])(will be aligned with the closest ROCm release)
* Bug fixes during the maintenance will be made to the next ROCm point release * Bug fixes during the maintenance will be made to the next ROCm point release
* Bug fixes will not be back ported to older ROCm releases for this SKU * Bug fixes will not be back ported to older ROCm releases for this SKU
* Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM. * Distro / Operating system updates will continue per the ROCm release cadence for gfx906 GPUs till EOM.
### AMDSMI CLI 23.0.0.4 ### AMDSMI CLI 23.0.0.4
@@ -1038,7 +1101,7 @@ Applications requiring to update the stack size can use hipDeviceSetLimit API.
The following hipcc changes are implemented in this release: The following hipcc changes are implemented in this release:
* `hipcc` will not implicitly link to `libpthread` and `librt`, as they are no longer a link time dependence for HIP programs.  Applications that depend on these libraries must explicitly link to them. * `hipcc` will not implicitly link to `libpthread` and `librt`, as they are no longer a link time dependence for HIP programs. Applications that depend on these libraries must explicitly link to them.
* `-use-staticlib` and `-use-sharedlib` options are deprecated. * `-use-staticlib` and `-use-sharedlib` options are deprecated.
##### Future changes ##### Future changes
@@ -3657,7 +3720,7 @@ This release introduces a new ROCm C++ library for accelerating mixed-precision
rocWMMA is released as a header library and includes test and sample projects to validate and illustrate example usages of the C++ API. GEMM matrix multiplication is used as primary validation given the heavy precedent for the library. However, the usage portfolio is growing significantly and demonstrates different ways rocWMMA may be consumed. rocWMMA is released as a header library and includes test and sample projects to validate and illustrate example usages of the C++ API. GEMM matrix multiplication is used as primary validation given the heavy precedent for the library. However, the usage portfolio is growing significantly and demonstrates different ways rocWMMA may be consumed.
For more information, refer to For more information, refer to
[Communication Libraries](./reference/library-index.md) [Communication Libraries](../reference/library-index.md)
#### OpenMP enhancements in this release #### OpenMP enhancements in this release
@@ -4753,9 +4816,9 @@ The resolution includes a compiler change, which emits the required metadata by
Note: Note:
This fix may lead to breakage in some OpenMP offload use cases, which use print inside a target region and result in an abort in device code. The issue will be fixed in a future release. This fix may lead to breakage in some OpenMP offload use cases, which use print inside a target region and result in an abort in device code. The issue will be fixed in a future release.
Compatibility Matrix Updates to the [Deep-learning guide](./how-to/deep-learning-rocm.md) Compatibility Matrix Updates to the [Deep-learning guide](../how-to/deep-learning-rocm.md)
The compatibility matrix in the [Deep-learning guide](./how-to/deep-learning-rocm.md) is updated for ROCm v5.0.2. The compatibility matrix in the [Deep-learning guide](../how-to/deep-learning-rocm.md) is updated for ROCm v5.0.2.
### Library Changes in ROCM 5.0.2 ### Library Changes in ROCM 5.0.2
@@ -5529,4 +5592,4 @@ Tensile 4.31.0 for ROCm 5.0.0
- Fix for Python 3.8: add case for Constant nodeType - Fix for Python 3.8: add case for Constant nodeType
- Fix architecture mapping for gfx1011 and gfx1012 - Fix architecture mapping for gfx1011 and gfx1012
- Fix PrintSolutionRejectionReason verbiage in KernelWriter.py - Fix PrintSolutionRejectionReason verbiage in KernelWriter.py
- Fix vgpr alignment problem when enabling flat buffer load - Fix vgpr alignment problem when enabling flat buffer load

460
RELEASE.md
View File

@@ -15,449 +15,61 @@ Welcome to the release notes for the ROCm platform.
------------------- -------------------
## ROCm 5.7.0 ## ROCm 5.7.1
<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable no-duplicate-header --> <!-- markdownlint-disable no-duplicate-header -->
### Release highlights for ROCm 5.7 ### 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](./compatibility/linux-support.md) and [Windows](./compatibility/windows-support.md) 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 and critical security patches will continue to be supported for the gfx906 GPUs until 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.
* Distribution and operating system updates will continue as per the ROCm release cadence for gfx906 GPUs until EOM. ### Library Changes in ROCM 5.7.1
#### 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 AddressSanitizer (ASan) with the GPU
The ROCm 5.7 release introduces the beta release of LLVM AddressSanitizer (ASan) with the GPU. The LLVM ASan 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 ASan 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 ASan with the GPU at [LLVM AddressSanitizer User Guide](../conceptual/using-gpu-sanitizer.md).
**Note**: The beta release of LLVM ASan 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 | Version | | Library | Version |
|---------|---------| |---------|---------|
| AMDMIGraphX | 2.5 ⇒ [2.7](https://github.com/ROCmSoftwarePlatform/AMDMIGraphX/releases/tag/rocm-5.7.0) | | hipBLAS | [1.1.0](https://github.com/ROCmSoftwarePlatform/hipBLAS/releases/tag/rocm-5.7.1) |
| hipBLAS | 0.54.0 ⇒ [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-5.7.1) |
| 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-5.7.1) |
| hipFFT | [1.0.12](https://github.com/ROCmSoftwarePlatform/hipFFT/releases/tag/rocm-5.7.0) | | hipSOLVER | 1.8.1 ⇒ [1.8.2](https://github.com/ROCmSoftwarePlatform/hipSOLVER/releases/tag/rocm-5.7.1) |
| hipSOLVER | 1.8.0 ⇒ [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-5.7.1) |
| hipSPARSE | 2.3.7 ⇒ [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-5.7.1) |
| MIOpen | [2.19.0](https://github.com/ROCmSoftwarePlatform/MIOpen/releases/tag/rocm-5.7.0) | | rocALUTION | [2.1.11](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.7.1) |
| rccl | 2.15.5 ⇒ [2.17.1-1](https://github.com/ROCmSoftwarePlatform/rccl/releases/tag/rocm-5.7.0) | | rocBLAS | [3.1.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.7.1) |
| rocALUTION | 2.1.9 ⇒ [2.1.11](https://github.com/ROCmSoftwarePlatform/rocALUTION/releases/tag/rocm-5.7.0) | | rocFFT | [1.0.24](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.7.1) |
| rocBLAS | 3.0.0 ⇒ [3.1.0](https://github.com/ROCmSoftwarePlatform/rocBLAS/releases/tag/rocm-5.7.0) | | rocm-cmake | [0.10.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.7.1) |
| rocFFT | 1.0.23 ⇒ [1.0.24](https://github.com/ROCmSoftwarePlatform/rocFFT/releases/tag/rocm-5.7.0) | | rocPRIM | [2.13.1](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.7.1) |
| rocm-cmake | 0.9.0 ⇒ [0.10.0](https://github.com/RadeonOpenCompute/rocm-cmake/releases/tag/rocm-5.7.0) | | rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.7.1) |
| rocPRIM | 2.13.0 ⇒ [2.13.1](https://github.com/ROCmSoftwarePlatform/rocPRIM/releases/tag/rocm-5.7.0) | | rocSOLVER | [3.23.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.7.1) |
| rocRAND | [2.10.17](https://github.com/ROCmSoftwarePlatform/rocRAND/releases/tag/rocm-5.7.0) | | rocSPARSE | [2.5.4](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.7.1) |
| rocSOLVER | 3.22.0 ⇒ [3.23.0](https://github.com/ROCmSoftwarePlatform/rocSOLVER/releases/tag/rocm-5.7.0) | | rocThrust | [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.7.1) |
| rocSPARSE | 2.5.2 ⇒ [2.5.4](https://github.com/ROCmSoftwarePlatform/rocSPARSE/releases/tag/rocm-5.7.0) | | rocWMMA | [1.2.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.7.1) |
| rocThrust | [2.18.0](https://github.com/ROCmSoftwarePlatform/rocThrust/releases/tag/rocm-5.7.0) | | Tensile | [4.38.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.7.1) |
| rocWMMA | 1.1.0 ⇒ [1.2.0](https://github.com/ROCmSoftwarePlatform/rocWMMA/releases/tag/rocm-5.7.0) |
| Tensile | 4.37.0 ⇒ [4.38.0](https://github.com/ROCmSoftwarePlatform/Tensile/releases/tag/rocm-5.7.0) |
#### AMDMIGraphX 2.7 #### hipSOLVER 1.8.2
MIGraphX 2.7 for ROCm 5.7.0 hipSOLVER 1.8.2 for ROCm 5.7.1
##### Added
- Enabled hipRTC to not require dev packages for migraphx runtime and allow the ROCm install to be in a different directory than it was during build time
- Add support for multi-target execution
- Added Dynamic Batch support with C++/Python APIs
- Add migraphx.create_argument to python API
- Added dockerfile example for Ubuntu 22.04
- Add TensorFlow supported ops in driver similar to exist onnx operator list
- Add a MIGRAPHX_TRACE_MATCHES_FOR env variable to filter the matcher trace
- Improved debugging by printing max,min,mean and stddev values for TRACE_EVAL = 2
- use fast_math flag instead of ENV flag for GELU
- Print message from driver if offload copy is set for compiled program
##### Optimizations
- Optimized for ONNX Runtime 1.14.0
- Improved compile times by only building for the GPU on the system
- Improve performance of pointwise/reduction kernels when using NHWC layouts
- Load specific version of the migraphx_py library
- Annotate functions with the block size so the compiler can do a better job of optimizing
- Enable reshape on nonstandard shapes
- Use half HIP APIs to compute max and min
- Added support for broadcasted scalars to unsqueeze operator
- Improved multiplies with dot operator
- Handle broadcasts across dot and concat
- Add verify namespace for better symbol resolution
##### Fixed ##### Fixed
- Resolved accuracy issues with FP16 resnet50 - Fixed conflicts between the hipsolver-dev and -asan packages by excluding
- Update cpp generator to handle inf from float hipsolver_module.f90 from the latter
- Fix assertion error during verify and make DCE work with tuples
- Fix convert operation for NaNs
- Fix shape typo in API test
- Fix compile warnings for shadowing variable names
- Add missing specialization for the `nullptr` for the hash function
##### Changed
- Bumped version of half library to 5.6.0
- Bumped CI to support rocm 5.6
- Make building tests optional
- replace np.bool with bool as per numpy request
##### Removed
- Removed int8x4 rocBlas calls due to deprecation
- removed std::reduce usage since not all OS&#39; support it
#### hipBLAS 1.1.0
hipBLAS 1.1.0 for ROCm 5.7.0
##### Changed
- updated documentation requirements
##### Dependencies
- dependency rocSOLVER now depends on rocSPARSE
#### 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
#### 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 &gt; 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 &lt;= length &lt;= 131071) that use Bluestein&#39;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&#39;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&#39;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`.
#### 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.
#### 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 &gt; 1

2
default.xml
View File

@@ -12,7 +12,7 @@ fetch="https://github.com/GPUOpen-ProfessionalCompute-Libraries/" />
fetch="https://github.com/GPUOpen-Tools/" /> fetch="https://github.com/GPUOpen-Tools/" />
<remote name="KhronosGroup" <remote name="KhronosGroup"
fetch="https://github.com/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" remote="roc-github"
sync-c="true" sync-c="true"
sync-j="4" /> sync-j="4" />

5595
docs/about/CHANGELOG.md Normal file
View File

File diff suppressed because it is too large Load Diff

4
docs/about/compatibility/3rd-party-support-matrix.md
View File

@@ -57,7 +57,7 @@ contemporary CUDA / NVIDIA HPC SDK alternatives.
| 5.3.x | 1.16 | 22.7 | | 5.3.x | 1.16 | 22.7 |
| 5.4.x | 1.16 | 22.9 | | 5.4.x | 1.16 | 22.9 |
| 5.5.x | 1.17 | 22.9 | | 5.5.x | 1.17 | 22.9 |
| 5.6 | 1.17.2 | 22.9 | | 5.6.x | 1.17.2 | 22.9 |
| 5.7 | 1.17.2 | 22.9 | | 5.7.x | 1.17.2 | 22.9 |
For the latest documentation of these libraries, refer to [API libraries](../../reference/library-index.md). For the latest documentation of these libraries, refer to [API libraries](../../reference/library-index.md).

88
docs/about/compatibility/docker-image-support-matrix.md
View File

@@ -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/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/)
#### `1.13 +bfeb431`
* [ROCm5.6](https://repo.radeon.com/rocm/apt/latest/)
* [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/latest/)
* [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/latest/)
* [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/latest/)
* [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/latest/)
* [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)

130
docs/about/compatibility/docker-image-support-matrix.rst Normal file
View File

@@ -0,0 +1,130 @@
******************************************************************
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 22.04
Tag: `rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1 <https://hub.docker.com/layers/rocm/pytorch/rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1/images/sha256-21df283b1712f3d73884b9bc4733919374344ceacb694e8fbc2c50bdd3e767ee>`_
* Inventory:
* `ROCm 5.7 <https://repo.radeon.com/rocm/apt/5.7/>`_
* `Python 3.10 <https://www.python.org/downloads/release/python-31013/>`_
* `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 0.15.0 <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:: 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>`_

23
docs/about/compatibility/linux-support.md
View File

@@ -64,13 +64,11 @@ The table below shows supported GPUs for Instinct™, Radeon Pro™ and Radeon
GPUs. Please click the tabs below to switch between GPU product lines. If a GPU GPUs. Please click the tabs below to switch between GPU product lines. If a GPU
is not listed on this table, the GPU is not officially supported by AMD. is not listed on this table, the GPU is not officially supported by AMD.
::::{tab-set} :::::{tab-set}
:::{tab-item} AMD Instinct™ ::::{tab-item} AMD Instinct™
:sync: instinct :sync: instinct
Use Driver Shipped with ROCm
| Product Name | Architecture | [LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) |Support | | Product Name | Architecture | [LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) |Support |
|:------------:|:------------:|:--------------------------------------------------------------------:|:-------:| |:------------:|:------------:|:--------------------------------------------------------------------:|:-------:|
| AMD Instinct™ MI250X | CDNA2 | gfx90a | ✅ | | AMD Instinct™ MI250X | CDNA2 | gfx90a | ✅ |
@@ -80,32 +78,29 @@ Use Driver Shipped with ROCm
| AMD Instinct™ MI50 | GCN5.1 | gfx906 | ✅ | | AMD Instinct™ MI50 | GCN5.1 | gfx906 | ✅ |
| AMD Instinct™ MI25 | GCN5.0 | gfx900 | ❌ | | AMD Instinct™ MI25 | GCN5.0 | gfx900 | ❌ |
::: ::::
:::{tab-item} Radeon Pro™ ::::{tab-item} Radeon Pro™
:sync: radeonpro :sync: radeonpro
[Use Radeon Pro Driver](https://www.amd.com/en/support/linux-drivers)
| Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Support| | Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Support|
|:----:|:------------:|:--------------------------------------------------------------------:|:-------:| |:----:|:------------:|:--------------------------------------------------------------------:|:-------:|
| AMD Radeon™ Pro W7900 | RDNA3 | gfx1100 | ✅ (Ubuntu 22.04 only)|
| AMD Radeon™ Pro W6800 | RDNA2 | gfx1030 | ✅ | | AMD Radeon™ Pro W6800 | RDNA2 | gfx1030 | ✅ |
| AMD Radeon™ Pro V620 | RDNA2 | gfx1030 | ✅ | | AMD Radeon™ Pro V620 | RDNA2 | gfx1030 | ✅ |
| AMD Radeon™ Pro VII | GCN5.1 | gfx906 | ✅ | | AMD Radeon™ Pro VII | GCN5.1 | gfx906 | ✅ |
::: ::::
:::{tab-item} Radeon™ ::::{tab-item} Radeon™
:sync: radeonpro :sync: radeonpro
[Use Radeon Pro Driver](https://www.amd.com/en/support/linux-drivers)
| Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Support| | Name | Architecture |[LLVM Target](https://www.llvm.org/docs/AMDGPUUsage.html#processors) | Support|
|:----:|:---------------:|:--------------------------------------------------------------------:|:-------:| |:----:|:---------------:|:--------------------------------------------------------------------:|:-------:|
| AMD Radeon™ RX 7900 XTX | RDNA3 | gfx1100 | ✅ (Ubuntu 22.04 only)|
| AMD Radeon™ VII | GCN5.1 | gfx906 | ✅ | | AMD Radeon™ VII | GCN5.1 | gfx906 | ✅ |
:::
:::: ::::
:::::
### Support status ### Support status

2
docs/about/compatibility/openmp.md
View File

@@ -22,7 +22,7 @@ The OpenMP toolchain is automatically installed as part of the standard ROCm
installation and is available under `/opt/rocm-{version}/llvm`. The installation and is available under `/opt/rocm-{version}/llvm`. The
sub-directories are: sub-directories are:
bin: Compilers (`flang` and `clang`) and other binaries. - bin: Compilers (`flang` and `clang`) and other binaries.
* examples: The usage section below shows how to compile and run these programs. * examples: The usage section below shows how to compile and run these programs.
* include: Header files. * include: Header files.

1
docs/about/compatibility/user-kernel-space-compat-matrix.md
View File

@@ -21,3 +21,4 @@ the compatibility combinations that are currently supported.
| 5.6.0 | 5.4.3, 5.5.1 | | 5.6.0 | 5.4.3, 5.5.1 |
| 5.6.1 | 5.7.0 | | 5.6.1 | 5.7.0 |
| 5.7.0 | 5.5.0, 5.6.1 | | 5.7.0 | 5.5.0, 5.6.1 |
| 5.7.1 | 5.5.0, 5.6.1 |

2
docs/about/compatibility/windows-support.md
View File

@@ -4,7 +4,7 @@
## Supported SKUs ## Supported SKUs
AMD ROCm™ Platform supports the following Windows SKU. AMD HIP SDK supports the following Windows variants.
| Distribution |Processor Architectures| Validated update | | Distribution |Processor Architectures| Validated update |
|---------------------|-----------------------|--------------------| |---------------------|-----------------------|--------------------|

3
docs/about/licensing.md
View File

@@ -4,7 +4,8 @@ ROCm™ is released by Advanced Micro Devices, Inc. and is licensed per componen
The following table is a list of ROCm components with links to their respective license The following table is a list of ROCm components with links to their respective license
terms. These components may include third party components subject to terms. These components may include third party components subject to
additional licenses. Please review individual repositories for more information. 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 shows ROCm components, the name of license, and link to the license terms.
The table is ordered to follow the ROCm manifest file. The table is ordered to follow the ROCm manifest file.
<!-- spellcheck-disable --> <!-- spellcheck-disable -->

28
docs/conf.py
View File

@@ -5,9 +5,25 @@
# https://www.sphinx-doc.org/en/master/usage/configuration.html # https://www.sphinx-doc.org/en/master/usage/configuration.html
import shutil import shutil
import jinja2
import os
from rocm_docs import ROCmDocs from rocm_docs import ROCmDocs
# Environement to process Jinja templates.
jinja_env = jinja2.Environment(loader=jinja2.FileSystemLoader("."))
# Jinja templates to render out.
templates = [
]
# 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','./contribute/index.md') shutil.copy2('../CONTRIBUTING.md','./contribute/index.md')
shutil.copy2('../RELEASE.md','./about/release-notes.md') shutil.copy2('../RELEASE.md','./about/release-notes.md')
@@ -15,14 +31,20 @@ shutil.copy2('../RELEASE.md','./about/release-notes.md')
shutil.copy2('../CHANGELOG.md','./about/CHANGELOG.md') shutil.copy2('../CHANGELOG.md','./about/CHANGELOG.md')
latex_engine = "xelatex" latex_engine = "xelatex"
latex_elements = {
"fontpkg": r"""
\usepackage{tgtermes}
\usepackage{tgheros}
\renewcommand\ttdefault{txtt}
"""
}
# configurations for PDF output by Read the Docs # configurations for PDF output by Read the Docs
project = "ROCm Documentation" project = "ROCm Documentation"
author = "Advanced Micro Devices, Inc." author = "Advanced Micro Devices, Inc."
copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved." copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved."
version = "5.7.0" version = "5.7.1"
release = "5.7.0" release = "5.7.1"
setting_all_article_info = True setting_all_article_info = True
all_article_info_os = ["linux", "windows"] all_article_info_os = ["linux", "windows"]
all_article_info_author = "" all_article_info_author = ""

2
docs/index.md
View File

@@ -46,7 +46,7 @@ ROCm compatibility information
* [Windows (GPU & OS)](./about/compatibility/windows-support.md) * [Windows (GPU & OS)](./about/compatibility/windows-support.md)
* [Third-party](./about/compatibility/3rd-party-support-matrix.md) * [Third-party](./about/compatibility/3rd-party-support-matrix.md)
* [User/kernel space](./about/compatibility/user-kernel-space-compat-matrix.md) * [User/kernel space](./about/compatibility/user-kernel-space-compat-matrix.md)
* [Docker](./about/compatibility/docker-image-support-matrix.md) * [Docker](./about/compatibility/docker-image-support-matrix.rst)
* [OpenMP](./about/compatibility/openmp.md) * [OpenMP](./about/compatibility/openmp.md)
::: :::

372
docs/install/linux/install-quick.md
View File

@@ -1,372 +0,0 @@
# Linux quick-start installation guide
For a quick summary on installing ROCm on Linux, follow the steps listed on this page. If you
want a more in-depth installation guide, see [Installing ROCm on Linux](./install.md).
## 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 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/latest/ubuntu jammy main
EOF
# ROCm repository for jammy
sudo tee /etc/apt/sources.list.d/rocm.list <<'EOF'
deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/debian jammy main
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
```
:::
:::{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/latest/ubuntu focal main
EOF
# ROCm repository for focal
sudo tee /etc/apt/sources.list.d/rocm.list <<'EOF'
deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/rocm/apt/debian focal main
EOF
```
:::
::::
::::{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 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/latest/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/latest/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/latest/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/latest/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/latest/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/latest/main
enabled=1
priority=50
gpgcheck=1
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
EOF
```
:::
:::{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/latest/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/latest/main
enabled=1
priority=50
gpgcheck=1
gpgkey=https://repo.radeon.com/rocm/rocm.gpg.key
EOF
```
:::
:::{tab-item} RHEL 8.6
:sync: RHEL-8.6
```shell
# Add the amdgpu module repository for RHEL 8.6
sudo tee /etc/yum.repos.d/amdgpu.repo <<'EOF'
[amdgpu]
name=amdgpu
baseurl=https://repo.radeon.com/amdgpu/latest/rhel/8.6/main/x86_64
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/latest/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 15.5
: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/latest/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
```
:::
:::{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/latest/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
```
:::
::::
::::{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 system reboot.
```shell
sudo reboot
```

1534
docs/install/linux/install.md
View File

File diff suppressed because it is too large Load Diff

101
docs/install/linux/package-manager-integration.md
View File

@@ -1,101 +0,0 @@
# Package manager integration
This section provides information about the required meta-packages for the
following AMD ROCm programming models:
* Heterogeneous-Computing Interface for Portability (HIP)
* OpenCL™
* OpenMP™
## ROCm package naming conventions
A meta-package is a grouping of related packages and dependencies used to
support a specific use case.
All meta-packages exist in both versioned and non-versioned forms.
* Non-versioned packages – For a single-version installation of the ROCm stack
* Versioned packages – For multi-version installations of the ROCm stack
![ROCm release package naming](../../data/install/linux/linux002.png "ROCm release package naming")
The preceding image demonstrates the single and multi-version ROCm packages' naming
structure, including examples for various Linux distributions. See terms below:
_Module_ - It is the part of the package that represents the name of the ROCm
component.
**Example:** The examples mentioned in the image represent the ROCm HIP module.
_Module version_ - It is the version of the library released in that package. It
should increase with a newer release.
_Release version_ - It shows the ROCm release version when the package was
released.
**Example:** `50400` points to the ROCm 5.4.0 release.
_Build id_ - It represents the Jenkins build number for that release.
_Arch_ - It shows the architecture for which the package was created.
_Distro_ - It describes the distribution for which the package was created. It is
valid only for rpm packages.
**Example:** `el8` represents RHEL 8.x packages.
## Components of ROCm programming models
The following image demonstrates the high-level layered architecture of ROCm
programming models and their meta-packages. All meta-packages are a combination
of required packages and libraries.
**Example:**
* `rocm-hip-runtime` is used to deploy on supported machines to execute HIP
applications.
* `rocm-hip-sdk` contains runtime components to deploy and execute HIP
applications.
![ROCm meta packages](../../data/install/linux/linux003.png "ROCm meta packages")
```{note}
`rocm-llvm` is not a meta-package but a single package that installs the ROCm
clang compiler files.
```
```{table} Meta-packages and Their Descriptions
:name: meta-package-desc
| **Meta-packages** | **Description** |
|:---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------:|
| `rocm-language-runtime` | The ROCm runtime |
| `rocm-hip-runtime` | Run HIP applications written for the AMD platform |
| `rocm-opencl-runtime` | Run OpenCL-based applications on the AMD platform |
| `rocm-hip-runtime-devel` | Develop applications on HIP or port from CUDA |
| `rocm-opencl-sdk` | Develop applications in OpenCL for the AMD platform |
| `rocm-hip-libraries` | HIP libraries optimized for the AMD platform |
| `rocm-hip-sdk` | Develop or port HIP applications and libraries for the AMD platform |
| `rocm-developer-tools` | Debug and profile HIP applications |
| `rocm-ml-sdk` | Develop and run machine-learning applications with optimized for AMD |
| `rocm-ml-libraries` | Key machine-learning libraries, specifically MIOpen |
| `rocm-openmp-sdk` | Develop OpenMP-based applications for the AMD platform |
| `rocm-openmp-runtime` | Run OpenMP-based applications for the AMD platform |
```
## Packages in ROCm programming models
This section discusses the available meta-packages and their packages. The
following image visualizes the meta-packages and their associated packages in a
ROCm programming model.
![Associated packages](../../data/install/linux/linux004.png "Associated packages")
* Meta-packages can include another meta-package.
* `rocm-core` package is common across all the meta-packages.
* Meta-packages and associated packages are represented in the same color.
```{note}
The preceding image is for informational purposes only, as the individual
packages in a meta-package are subject to change. Install meta-packages, and not
individual packages, to avoid conflicts.
```

10
docs/sphinx/_toc.yml.in
View File

@@ -11,16 +11,8 @@ subtrees:
- caption: Installation - caption: Installation
entries: entries:
- file: install/linux/install-quick.md
title: Quick start (Linux)
- file: install/windows/install-quick.md - file: install/windows/install-quick.md
title: Quick start (Windows) title: Quick start (Windows)
- file: install/linux/install.md
title: Linux install guide
subtrees:
- entries:
- file: install/linux/package-manager-integration.md
title: Package manager integration
- file: install/windows/install.md - file: install/windows/install.md
title: Windows install guide title: Windows install guide
subtrees: subtrees:
@@ -48,7 +40,7 @@ subtrees:
title: Third-party title: Third-party
- file: about/compatibility/user-kernel-space-compat-matrix.md - file: about/compatibility/user-kernel-space-compat-matrix.md
title: User/kernel space support title: User/kernel space support
- file: about/compatibility/docker-image-support-matrix.md - file: about/compatibility/docker-image-support-matrix.rst
title: Docker title: Docker
- file: about/compatibility/openmp.md - file: about/compatibility/openmp.md
title: OpenMP title: OpenMP

2
docs/sphinx/requirements.txt
View File

@@ -1,5 +1,5 @@
# #
# This file is autogenerated by pip-compile with Python 3.8 # This file is autogenerated by pip-compile with Python 3.10
# by the following command: # by the following command:
# #
# pip-compile requirements.in # pip-compile requirements.in

15
tools/autotag/README.md
View File

@@ -17,16 +17,23 @@
* Run this for 5.6.0 (change for whatever version you require) * Run this for 5.6.0 (change for whatever version you require)
* `GITHUB_ACCESS_TOKEN=my_token_here` * `GITHUB_ACCESS_TOKEN=my_token_here`
<<<<<<< HEAD
To generate the changelog from 5.0.0 up to and including 5.7.0: To generate the changelog from 5.0.0 up to and including 5.7.0:
```sh ```sh
python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --do-previous --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.7 5.7.0 python3 tag_script.py -t $GITHUB_ACCESS_TOKEN --no-release --no-pulls --do-previous --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.7 5.7.0
``` =======
To generate the changelog from 5.0.0 up to and including 5.7.1:
To generate the changelog only for 5.6.0:
```sh ```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 --do-previous --compile_file ../../CHANGELOG.md --branch release/rocm-rel-5.7 5.7.1
>>>>>>> roc-5.7.x
```
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-5.7 5.7.1
``` ```
### Notes ### Notes

2
tools/autotag/templates/rocm_changes/5.6.0.md
View File

@@ -19,7 +19,7 @@ ROCm 5.6 consists of several AI software ecosystem improvements to our fast-grow
* Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance \[EOM])(will be aligned with the closest ROCm release) * Bug fixes / critical security patches will continue to be supported for the gfx906 GPUs till Q2 2024 (End of Maintenance \[EOM])(will be aligned with the closest ROCm release)
* Bug fixes during the maintenance will be made to the next ROCm point release * Bug fixes during the maintenance will be made to the next ROCm point release
* Bug fixes will not be back ported to older ROCm releases for this SKU * Bug fixes will not be back ported to older ROCm releases for this SKU
* Distro / Operating system updates will continue as per the ROCm release cadence for gfx906 GPUs till EOM. * Distro / Operating system updates will continue per the ROCm release cadence for gfx906 GPUs till EOM.
### AMDSMI CLI 23.0.0.4 ### AMDSMI CLI 23.0.0.4

4
tools/autotag/templates/rocm_changes/5.7.0.md
View File

@@ -13,7 +13,7 @@ AMD Instinct MI50, Radeon Pro VII, and Radeon VII products (collectively gfx906
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. 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.
* ROCm 6.0 release will show MI50s as "under maintenance" mode for [Linux](./compatibility/linux-support.md) and [Windows](./compatibility/windows-support.md) * ROCm 6.0 release will show MI50s as "under maintenance" for [Linux](../about/compatibility/linux-support.md) and [Windows](../about/compatibility/windows-support.md)
* No new features and performance optimizations will be supported for the gfx906 GPUs beyond this major release (ROCm 5.7). * No new features and performance optimizations will be supported for the gfx906 GPUs beyond this major release (ROCm 5.7).
@@ -23,7 +23,7 @@ As outlined in [5.6.0](https://rocm.docs.amd.com/en/docs-5.6.0/release.html), RO
* Bug fixes will not be backported to older ROCm releases for gfx906. * Bug fixes will not be backported to older ROCm releases for gfx906.
* Distribution and operating system updates will continue as per the ROCm release cadence for gfx906 GPUs until EOM. * Distribution and operating system updates will continue per the ROCm release cadence for gfx906 GPUs until EOM.
#### Feature updates #### Feature updates

39
tools/autotag/templates/rocm_changes/5.7.1.md
View File

@@ -1,3 +1,4 @@
<<<<<<< HEAD
<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable no-duplicate-header --> <!-- markdownlint-disable no-duplicate-header -->
@@ -9,3 +10,41 @@ ROCm 5.7.1 is a point release with several bug fixes in the HIP runtime.
### Fixed defects ### Fixed defects
=======
<!-- 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.
>>>>>>> roc-5.7.x