From 131e34f582419419423c99cea63a46d596a5e818 Mon Sep 17 00:00:00 2001 From: pbhandar-amd <138039281+pbhandar-amd@users.noreply.github.com> Date: Fri, 11 Apr 2025 15:11:34 -0400 Subject: [PATCH 1/2] Update w6000-v620.md --- docs/how-to/system-optimization/w6000-v620.md | 31 ------------------- 1 file changed, 31 deletions(-) diff --git a/docs/how-to/system-optimization/w6000-v620.md b/docs/how-to/system-optimization/w6000-v620.md index 96465bc57..ec5cf9677 100644 --- a/docs/how-to/system-optimization/w6000-v620.md +++ b/docs/how-to/system-optimization/w6000-v620.md @@ -37,37 +37,6 @@ their full potential. - [RDNA 2 architecture](https://www.amd.com/system/files/documents/rdna2-explained-radeon-pro-W6000.pdf) ``` -## Workstation workloads - -Workstation workloads, much like those for HPC, have a unique set of -requirements: a blend of both graphics and compute, certification, stability and -others. - -The document covers specific software requirements and processes needed to use -these GPUs for Single Root I/O Virtualization (SR-IOV) and machine learning -tasks. - -The main purpose of this document is to help users utilize the RDNA™ 2 GPUs to -their full potential. - -```{list-table} - :header-rows: 1 - :stub-columns: 1 - - * - System Guide - - - Architecture reference - - - White papers - - * - [System settings](#system-settings) - - - [AMD RDNA 2 instruction set architecture](https://www.amd.com/system/files/TechDocs/rdna2-shader-instruction-set-architecture.pdf) - - - [RDNA 2 architecture](https://www.amd.com/content/dam/amd/en/documents/products/graphics/workstation/rdna2-explained-radeon-pro-W6000.pdf) - -``` - ## System settings This chapter reviews system settings that are required to configure the system From 686fcece1dcb4853363afc296945826bb13cbbf5 Mon Sep 17 00:00:00 2001 From: Pratik Basyal Date: Fri, 11 Apr 2025 15:12:57 -0400 Subject: [PATCH 2/2] PRE GA Day 640 update for resetting link and HPC application list (#367) * Links reset to point to latest from stg, internal, RTD, and develop * ROCm for HPC updated * GA prep changes --- RELEASE.md | 109 ++++++++++++++--------------- docs/how-to/rocm-for-hpc/index.rst | 21 ++---- docs/sphinx/_toc.yml.in | 4 +- 3 files changed, 63 insertions(+), 71 deletions(-) diff --git a/RELEASE.md b/RELEASE.md index 786c4ec83..3f1135b73 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -84,7 +84,7 @@ VP9 support is added to [rocDecode](https://github.com/ROCm/rocDecode) and [rocP ### Bitstream reader support added to rocDecode -The new bitstream reader feature has been added to [rocDecode](https://github.com/ROCm/rocDecode). It contains built-in stream file parsers, including an elementary stream file parser and an IVF container file parser. It enables decoding without the requirement for FFmpeg demuxer. The reader can parse AVC, HEVC, and AV1 elementary stream files, and AV1 IVF container files. See [Using the rocDecode bitstream reader APIs](https://rocm.docs.amd.com/projects/rocDecode/en/develop/how-to/using-rocDecode-bitstream.html) for more information. +The new bitstream reader feature has been added to [rocDecode](https://github.com/ROCm/rocDecode). It contains built-in stream file parsers, including an elementary stream file parser and an IVF container file parser. It enables decoding without the requirement for FFmpeg demuxer. The reader can parse AVC, HEVC, and AV1 elementary stream files, and AV1 IVF container files. See [Using the rocDecode bitstream reader APIs](https://rocm.docs.amd.com/projects/rocDecode/en/latest/how-to/using-rocDecode-bitstream.html) for more information. ### DLPack support added to rocAL @@ -154,7 +154,7 @@ ROCm documentation continues to be updated to provide clearer and more comprehen guide has been updated to feature the latest [ROCm/pytorch-training](https://hub.docker.com/layers/rocm/pytorch-training/v25.4/images/sha256-fa98a9aa69968e654466c06f05aaa12730db79b48b113c1ab4f7a5fe6920a20b) Docker image. -* A new topic, [Hardware atomics operation support](https://rocm-stg.amd.com/en/develop/reference/gpu-atomics-operation.html), discusses the support for atomic read-modify-write (atomicRMW) operations on gfx9, gfx10, gfx11, gfx12, MI100, MI200 and MI300 AMD GPUs. +* A new topic, [Hardware atomics operation support](https://rocm.docs.amd.com/en/latest/reference/gpu-atomics-operation.html), discusses the support for atomic read-modify-write (atomicRMW) operations on gfx9, gfx10, gfx11, gfx12, MI100, MI200 and MI300 AMD GPUs. * [LLM inference performance testing on AMD Instinct MI300X](https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/inference/vllm-benchmark.html?model=pyt_vllm_llama-3.1-8b) has been updated to feature the latest [ROCm/vLLM](https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.7.3_20250311/images/sha256-de0a2649b735f45b7ecab8813eb7b19778ae1f40591ca1196b07bc29c42ed4a3) @@ -170,11 +170,11 @@ ROCm documentation continues to be updated to provide clearer and more comprehen ## Operating system and hardware support changes -ROCm 6.4.0 adds support for Oracle Linux 9 operating system. Oracle Linux is supported only on AMD Instinct accelerators. For more information, see [Oracle Linux installation](https://rocm.docs.amd.com/projects/install-on-linux-internal/en/latest/install/install-methods/package-manager/package-manager-ol.html). +ROCm 6.4.0 adds support for Oracle Linux 9 operating system. Oracle Linux is supported only on AMD Instinct accelerators. For more information, see [Oracle Linux installation](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/install-methods/package-manager/package-manager-ol.html). ROCm 6.4.0 marks the end of support (EoS) for SLES 15 SP5. -ROCm 6.4.0 adds support for [AMD Radeon PRO W7800 48GB](https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7800-48gb.html) GPU for compute workloads. See [Supported GPUs](https://rocm.docs.amd.com/projects/install-on-linux-internal/en/latest/reference/system-requirements.html#supported-gpus) for more information. +ROCm 6.4.0 adds support for [AMD Radeon PRO W7800 48GB](https://www.amd.com/en/products/graphics/workstations/radeon-pro/w7800-48gb.html) GPU for compute workloads. See [Supported GPUs](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html#supported-gpus) for more information. See the [Compatibility matrix](../../docs/compatibility/compatibility-matrix.rst) @@ -205,47 +205,47 @@ Click {fab}`github` to go to the component's source code on GitHub. Libraries Machine learning and computer vision - Composable Kernel + Composable Kernel 1.1.0 ⇒ 1.1.0 - MIGraphX + MIGraphX 2.11.0 ⇒ 2.12.0 - MIOpen + MIOpen 3.3.0 ⇒ 3.4.0 - MIVisionX + MIVisionX 3.1.0 ⇒ 3.2.0 - rocAL + rocAL 2.1.0 ⇒ 2.2.0 - rocDecode + rocDecode 0.8.0 ⇒ 0.10.0 - rocJPEG + rocJPEG 0.6.0 ⇒ 0.8.0 - rocPyDecode + rocPyDecode 0.2.0 ⇒ 0.3.1 - RPP + RPP 1.9.1 ⇒ 1.9.10 @@ -254,7 +254,7 @@ Click {fab}`github` to go to the component's source code on GitHub. Communication - RCCL + RCCL 2.21.5 ⇒ 2.22.3 @@ -263,82 +263,82 @@ Click {fab}`github` to go to the component's source code on GitHub. Math - hipBLAS + hipBLAS 2.3.0 ⇒ 2.4.0 - hipBLASLt + hipBLASLt 0.10.0 ⇒ 0.12.0 - hipFFT + hipFFT 1.0.17 ⇒ 1.0.18 - hipfort + hipfort 0.5.1 ⇒ 0.6.0 - hipRAND + hipRAND 2.11.1 ⇒ 2.12.0 - hipSOLVER + hipSOLVER 2.3.0 ⇒ 2.4.0 - hipSPARSE + hipSPARSE 3.1.2 ⇒ 3.2.0 - hipSPARSELt + hipSPARSELt 0.2.2 ⇒ 0.2.3 - rocALUTION + rocALUTION 3.2.1 ⇒ 3.2.2 - rocBLAS + rocBLAS 4.3.0 ⇒ 4.4.0 - rocFFT + rocFFT 1.0.31 ⇒ 1.0.32 - rocRAND + rocRAND 3.2.0 ⇒ 3.3.0 - rocSOLVER + rocSOLVER 3.27.0 ⇒ 3.28.0 - rocSPARSE + rocSPARSE 3.3.0 ⇒ 3.4.0 - rocWMMA + rocWMMA 1.6.0 ⇒ 1.7.0 - Tensile + Tensile 4.42.0 ⇒ 4.43.0 @@ -347,22 +347,22 @@ Click {fab}`github` to go to the component's source code on GitHub. Primitives - hipCUB + hipCUB 3.3.0 ⇒ 3.4.0 - hipTensor + hipTensor 1.4.0 ⇒ 1.5.0 - rocPRIM + rocPRIM 3.3.0 ⇒ 3.4.0 - rocThrust + rocThrust 3.3.0 ⇒ 3.3.0 @@ -371,27 +371,27 @@ Click {fab}`github` to go to the component's source code on GitHub. Tools System management - AMD SMI + AMD SMI 24.7.1 ⇒ 25.3.0 - ROCm Data Center Tool + ROCm Data Center Tool 0.3.0 ⇒ 0.3.0 - rocminfo + rocminfo 1.0.0 - ROCm SMI + ROCm SMI 7.4.0 ⇒ 7.5.0 - ROCmValidationSuite + ROCmValidationSuite 1.1.0 @@ -400,38 +400,38 @@ Click {fab}`github` to go to the component's source code on GitHub. Performance - ROCm Bandwidth + ROCm Bandwidth Test 1.4.0 - ROCm Compute Profiler + ROCm Compute Profiler 3.0.0 ⇒ 3.1.0 - ROCm Systems Profiler + ROCm Systems Profiler 0.1.2 ⇒ 1.0.0 - ROCProfiler + ROCProfiler 2.0.0 ⇒ 2.0.0 - ROCprofiler-SDK + ROCprofiler-SDK 0.5.0 ⇒ 0.6.0 - ROCTracer + ROCTracer 4.1.0 ⇒ 4.1.0 @@ -441,32 +441,32 @@ Click {fab}`github` to go to the component's source code on GitHub. Development - HIPIFY + HIPIFY 18.0.0 ⇒ 19.0.0 - ROCdbgapi + ROCdbgapi 0.77.0 ⇒ 0.77.2 - ROCm CMake + ROCm CMake 0.14.0 - ROCm Debugger (ROCgdb) + ROCm Debugger (ROCgdb) 15.2 ⇒ 15.2 - ROCr Debug Agent + ROCr Debug Agent 2.0.3 ⇒ 2.0.4 Compilers - HIPCC + HIPCC 1.1.1 - llvm-project + llvm-project 18.0.0 ⇒ 19.0.0 @@ -491,12 +491,12 @@ Click {fab}`github` to go to the component's source code on GitHub. Runtimes - HIP + HIP 6.3.3 ⇒ 6.4.0 - ROCr Runtime + ROCr Runtime 1.14.0 ⇒ 1.15.0 @@ -1633,7 +1633,6 @@ Clang compilation failure with the error `fatal error: 'cmath' file not found` m ### ROCProfiler with rocprof might fail to initialize in some PyTorch applications In some PyTorch applications, the `HSA_TOOLS_LIB` environment variable might fail to initialize the ROCProfiler library with the `rocprof` tool. As a result of the issue, `--stats` and the counter collection commands might fail to trace the execution of the application and collect hardware component performance during kernel execution, respectively. The issue might have originated from a change in the PyTorch library, causing an overwrite in the `HSA_TOOLS_LIB` environment variable. This issue will be fixed in a future ROCm release. However, consider that ROCprofiler and `rocprof` are being phased out in favor of ROCprofiler-SDK in upcoming ROCm releases. For details, see [ROCm upcoming changes](#roctracer-rocprofiler-rocprof-and-rocprofv2-deprecation). - As a workaround, add the following to the command you are running: ``` diff --git a/docs/how-to/rocm-for-hpc/index.rst b/docs/how-to/rocm-for-hpc/index.rst index 9fc0a80f3..20785e923 100644 --- a/docs/how-to/rocm-for-hpc/index.rst +++ b/docs/how-to/rocm-for-hpc/index.rst @@ -93,6 +93,13 @@ Ubuntu versions. Publications of work done using this code or derivatives of this code should acknowledge this use. + * - + - `QUDA `_ + - Library designed for efficient lattice QCD computations on + accelerators. It includes optimized Dirac operators and a variety of + fermion solvers and conjugate gradient (CG) implementations, enhancing + performance and accuracy in lattice QCD simulations. + * - - `PIConGPU `_ - PIConGPU (Particle-in-cell on Graphics Processing Units) is an Open Source @@ -174,20 +181,6 @@ Ubuntu versions. help engineers and researchers analyze and optimize the performance of products and systems across various industries. - * - Computational chemistry - - `QUDA `_ - - Library designed for efficient lattice QCD computations on - accelerators. It includes optimized Dirac operators and a variety of - fermion solvers and conjugate gradient (CG) implementations, enhancing - performance and accuracy in lattice QCD simulations. - - * - Electronic structure - - `CP2K `_ - - CP2K is a quantum chemistry and solid state physics software package that can - perform atomistic simulations of solid state, liquid, molecular, periodic, material, - crystal, and biological systems. This AMD container, based on a released version - of CP2K, is an AMD beta version with ongoing optimizations. - * - Quantum Monte Carlo Simulation - `QMCPACK `_ - QMCPACK is an open-source production-level many-body ab initio Quantum diff --git a/docs/sphinx/_toc.yml.in b/docs/sphinx/_toc.yml.in index d7de00d0e..af0bd57c8 100644 --- a/docs/sphinx/_toc.yml.in +++ b/docs/sphinx/_toc.yml.in @@ -12,14 +12,14 @@ subtrees: - file: compatibility/compatibility-matrix.rst title: Compatibility matrix entries: - - url: https://rocm.docs.amd.com/projects/install-on-linux-internal/en/latest/reference/system-requirements.html + - url: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html title: Linux system requirements - url: https://rocm.docs.amd.com/projects/install-on-windows/en/${branch}/reference/system-requirements.html title: Windows system requirements - caption: Install entries: - - url: https://rocm.docs.amd.com/projects/install-on-linux-internal/en/latest/ + - url: https://rocm.docs.amd.com/projects/install-on-linux/en/latest/ title: ROCm on Linux - url: https://rocm.docs.amd.com/projects/install-on-windows/en/${branch}/ title: HIP SDK on Windows