WIP

.azuredevops/components/HIP.yml

@@ -77,8 +77,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       componentName: clr
-      cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+      cmakeBuildDir: 'clr/build'
       extraBuildFlags: >-
         -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
         -DHIP_PLATFORM=amd
@@ -139,8 +138,7 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       componentName: clr
-      cmakeBuildDir: '$(Build.SourcesDirectory)/clr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/clr'
+      cmakeBuildDir: 'clr/build'
       extraBuildFlags: >-
         -DHIP_COMMON_DIR=$(Build.SourcesDirectory)/HIP
         -DHIP_PLATFORM=nvidia

.azuredevops/components/HIPIFY.yml

@@ -73,7 +73,6 @@ jobs:
     parameters:
       componentName: upstream-llvm
       cmakeBuildDir: $(Pipeline.Workspace)/llvm-project/llvm/build
-      cmakeSourceDir: $(Pipeline.Workspace)/llvm-project/llvm
       installDir: $(Pipeline.Workspace)/llvm
       extraBuildFlags: >-
         -DCMAKE_BUILD_TYPE=Release

.azuredevops/components/aomp.yml

@@ -118,7 +118,6 @@ jobs:
     parameters:
       componentName: extras
       cmakeBuildDir: '$(Build.SourcesDirectory)/aomp-extras/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/aomp-extras'
       installDir: '$(Build.BinariesDirectory)/llvm'
       extraBuildFlags: >-
         -DLLVM_DIR=$(Agent.BuildDirectory)/rocm/llvm
@@ -130,7 +129,6 @@ jobs:
     parameters:
       componentName: openmp
       cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/openmp/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/openmp'
       installDir: '$(Build.BinariesDirectory)/llvm'
       extraBuildFlags: >-
         -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"
@@ -157,7 +155,6 @@ jobs:
     parameters:
       componentName: offload
       cmakeBuildDir: '$(Build.SourcesDirectory)/llvm-project/offload/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm-project/offload'
       installDir: '$(Build.BinariesDirectory)/llvm'
       extraBuildFlags: >-
         -DCMAKE_PREFIX_PATH="$(Agent.BuildDirectory)/rocm;$(Build.BinariesDirectory)"

.azuredevops/components/hipSOLVER.yml

@@ -92,8 +92,7 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         componentName: external
-        cmakeBuildDir: '$(Build.SourcesDirectory)/deps/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/deps'
+        cmakeBuildDir: 'deps/build'
         installDir: '$(Pipeline.Workspace)/deps-install'
         extraBuildFlags: >-
           -DBUILD_BOOST=OFF

.azuredevops/components/llvm-project.yml

@@ -83,8 +83,7 @@ jobs:
         -DROCM_LLVM_BACKWARD_COMPAT_LINK=$(Build.BinariesDirectory)/llvm
         -DROCM_LLVM_BACKWARD_COMPAT_LINK_TARGET=./lib/llvm
         -GNinja
-      cmakeBuildDir: '$(Build.SourcesDirectory)/llvm/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/llvm'
+      cmakeBuildDir: 'llvm/build'
       installDir: '$(Build.BinariesDirectory)/llvm'
 # use llvm-lit to run unit tests for llvm, clang, and lld
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
@@ -122,8 +121,7 @@ jobs:
       extraBuildFlags: >-
         -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build"
         -DCMAKE_BUILD_TYPE=Release
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/device-libs/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/device-libs'
+      cmakeBuildDir: 'amd/device-libs/build'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       componentName: comgr
@@ -131,8 +129,7 @@ jobs:
         -DCMAKE_PREFIX_PATH="$(Build.SourcesDirectory)/llvm/build;$(Build.SourcesDirectory)/amd/device-libs/build"
         -DCOMGR_DISABLE_SPIRV=1
         -DCMAKE_BUILD_TYPE=Release
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/comgr/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/comgr'
+      cmakeBuildDir: 'amd/comgr/build'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/test.yml
     parameters:
       componentName: comgr
@@ -145,8 +142,7 @@ jobs:
       extraBuildFlags: >-
         -DCMAKE_BUILD_TYPE=Release
         -DHIPCC_BACKWARD_COMPATIBILITY=OFF
-      cmakeBuildDir: '$(Build.SourcesDirectory)/amd/hipcc/build'
-      cmakeSourceDir: '$(Build.SourcesDirectory)/amd/hipcc'
+      cmakeBuildDir: 'amd/hipcc/build'
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/manifest.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-upload.yml
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/artifact-links.yml

.azuredevops/components/rdc.yml

@@ -105,7 +105,6 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:
         cmakeBuildDir: $(Build.SourcesDirectory)/grpc/build
-        cmakeSourceDir: $(Build.SourcesDirectory)/grpc
         installDir: $(Build.SourcesDirectory)/bin
         extraBuildFlags: >-
           -DgRPC_INSTALL=ON

.azuredevops/components/rocAL.yml

@@ -125,7 +125,6 @@ jobs:
       parameters:
         componentName: PyBind11
         cmakeBuildDir: '$(Build.SourcesDirectory)/pybind11/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/pybind11'
         customInstallPath: false
         installEnabled: false
         extraBuildFlags: >-
@@ -142,7 +141,6 @@ jobs:
       parameters:
         componentName: RapidJSON
         cmakeBuildDir: '$(Build.SourcesDirectory)/rapidjson/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/rapidjson'
         customInstallPath: false
         installEnabled: false
         extraBuildFlags: >-
@@ -202,6 +200,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm/include/rocal
     pool:
       name: ${{ job.target }}_test_pool
+      demands: firstRenderDeviceAccess
     workspace:
       clean: all
     steps:

.azuredevops/components/rocDecode.yml

@@ -108,6 +108,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     pool:
       name: ${{ job.target }}_test_pool
+      demands: firstRenderDeviceAccess
     workspace:
       clean: all
     steps:

.azuredevops/components/rocJPEG.yml

@@ -114,6 +114,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     pool:
       name: ${{ job.target }}_test_pool
+      demands: firstRenderDeviceAccess
     workspace:
       clean: all
     steps:

.azuredevops/components/rocPRIM.yml

@@ -5,12 +5,6 @@ parameters:
 - name: checkoutRef
   type: string
   default: ''
-- name: sparseCheckout
-  type: boolean
-  default: false
-- name: sparseCheckoutDir
-  type: string
-  default: ''
 # set to true if doing full build of ROCm stack
 # and dependencies are pulled from same pipeline
 - name: aggregatePipeline
@@ -72,8 +66,6 @@ jobs:
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/checkout.yml
       parameters:
         checkoutRepo: ${{ parameters.checkoutRepo }}
-        sparseCheckout: ${{ parameters.sparseCheckout }}
-        sparseCheckoutDir: ${{ parameters.sparseCheckoutDir }}
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/dependencies-rocm.yml
       parameters:
         checkoutRef: ${{ parameters.checkoutRef }}

.azuredevops/components/rocPyDecode.yml

@@ -168,6 +168,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     pool:
       name: ${{ job.target }}_test_pool
+      demands: firstRenderDeviceAccess
     workspace:
       clean: all
     steps:

.azuredevops/components/rocSOLVER.yml

@@ -105,7 +105,6 @@ jobs:
           -DLAPACKE=OFF
           -GNinja
         cmakeBuildDir: '$(Build.SourcesDirectory)/lapack/build'
-        cmakeSourceDir: '$(Build.SourcesDirectory)/lapack'
         installDir: '$(Pipeline.Workspace)/deps-install'
     - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
       parameters:

.azuredevops/components/rocprofiler-systems.yml

@@ -167,6 +167,7 @@ jobs:
       value: $(Agent.BuildDirectory)/rocm
     pool:
       name: ${{ job.target }}_test_pool
+      demands: firstRenderDeviceAccess
     workspace:
       clean: all
     steps:

.azuredevops/dependencies/grpc.yml

@@ -38,7 +38,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       cmakeBuildDir: $(Agent.BuildDirectory)/grpc/build
-      cmakeSourceDir: $(Agent.BuildDirectory)/grpc
       extraBuildFlags: >-
         -DgRPC_INSTALL=ON
         -DgRPC_BUILD_TESTS=OFF

.azuredevops/dependencies/gtest.yml

@@ -38,7 +38,6 @@ jobs:
   - template: ${{ variables.CI_TEMPLATE_PATH }}/steps/build-cmake.yml
     parameters:
       cmakeBuildDir: $(Agent.BuildDirectory)/googletest/build
-      cmakeSourceDir: $(Agent.BuildDirectory)/googletest
       extraBuildFlags: >-
         -DGTEST_FORCE_SHARED_CRT=ON
         -DCMAKE_DEBUG_POSTFIX=d

.azuredevops/templates/steps/build-cmake.yml

@@ -10,10 +10,10 @@ parameters:
   default: ''
 - name: cmakeBuildDir
   type: string
-  default: $(Agent.BuildDirectory)/s/build
+  default: 'build'
 - name: cmakeSourceDir
   type: string
-  default: $(Agent.BuildDirectory)/s
+  default: '..'
 - name: customBuildTarget
   type: string
   default: ''
@@ -46,7 +46,7 @@ steps:
     ${{ if eq(parameters.customInstallPath, true) }}:
       cmakeArgs: -DCMAKE_INSTALL_PREFIX=${{ parameters.installDir }} ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
     ${{ else }}:
-      cmakeArgs: ${{ parameters.extraBuildFlags }} ${{ parameters.cmakeSourceDir }}
+      cmakeArgs: ${{ parameters.extraBuildFlags }} ..
 - ${{ if parameters.printDiskSpace }}:
   - script: df -h
     displayName: Disk space before build

.azuredevops/templates/steps/checkout.yml

@@ -4,12 +4,6 @@ parameters:
 - name: checkoutRepo
   type: string
   default: 'self'
-- name: sparseCheckout
-  type: boolean
-  default: false
-- name: sparseCheckoutDir
-  type: string
-  default: ''
 # submodule download behaviour
 # change to 'recursive' for repos with submodules
 - name: submoduleBehaviour
@@ -21,13 +15,3 @@ steps:
     clean: true
     submodules: ${{ parameters.submoduleBehaviour }}
     retryCountOnTaskFailure: 3
-    fetchFilter: blob:none
-    ${{ if eq(parameters.sparseCheckout, true) }}:
-      sparseCheckoutDirectories: ${{ parameters.sparseCheckoutDir }}
-      path: sparse
-  - ${{ if eq(parameters.sparseCheckout, true) }}:
-    - task: Bash@3
-      displayName: Symlink sparse checkout
-      inputs:
-        targetType: inline
-        script: ln -s $(Agent.BuildDirectory)/sparse/${{ parameters.sparseCheckoutDir }} $(Agent.BuildDirectory)/s

.azuredevops/templates/steps/docker-container.yml

@@ -106,7 +106,6 @@ parameters:
   type: object
   default:
     - gfx90a
-    - gfx942
 
 steps:
 # these steps should only be run if there was a failure or warning

.wordlist.txt

@@ -34,7 +34,6 @@ Autocast
 BARs
 BLAS
 BMC
-BabelStream
 Blit
 Blockwise
 Bluefield
@@ -139,7 +138,6 @@ GDR
 GDS
 GEMM
 GEMMs
-GFLOPS
 GFortran
 GFXIP
 Gemma
@@ -643,7 +641,6 @@ hipSPARSELt
 hipTensor
 hipamd
 hipblas
-hipcc
 hipcub
 hipfft
 hipfort

docs/conf.py

@@ -51,8 +51,6 @@ article_pages = [
     {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/install", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/system-health-check", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/training/index", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/train-a-model", "os": ["linux"]},
@@ -69,6 +67,7 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/inference/index", "os": ["linux"]},
+    {"file": "how-to/rocm-for-ai/inference/install", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/hugging-face-models", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/llm-inference-frameworks", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/vllm-benchmark", "os": ["linux"]},

docs/how-to/rocm-for-ai/inference/install.rst

@@ -30,7 +30,7 @@ ROCm supports multiple :doc:`installation methods <rocm-install-on-linux:install
 
 * :doc:`Using the AMDGPU installer <rocm-install-on-linux:install/amdgpu-install>`
 
-* :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`
+* :ref:`Multi-version installation <rocm-install-on-linux:installation-types>`.
 
 .. grid:: 1
 
@@ -59,8 +59,4 @@ images with the framework pre-installed.
 
 * :doc:`JAX for ROCm <rocm-install-on-linux:install/3rd-party/jax-install>`
 
-Next steps
-==========
-
-After installing ROCm and your desired ML libraries -- and before running AI workloads -- conduct system health benchmarks
-to test the optimal performance of your AMD hardware. See :doc:`system-health-check` to get started.
+The sections that follow in :doc:`Training a model <../training/train-a-model>` are geared for a ROCm with PyTorch installation.

docs/how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst

@@ -62,52 +62,47 @@ PyTorch inference performance testing
       {% endfor %}
    {% endfor %}
 
-   System validation
-   =================
+   Getting started
+   ===============
 
-   Before running AI workloads, it's important to validate that your AMD hardware is configured
-   correctly and performing optimally.
+   Use the following procedures to reproduce the benchmark results on an
+   MI300X series accelerator with the prebuilt PyTorch Docker image.
 
-   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
-   might hang until the periodic balancing is finalized. For more information,
-   see the :ref:`system validation steps <rocm-for-ai-system-optimization>`.
+   .. _pytorch-benchmark-get-started:
 
-   .. code-block:: shell
+   1. Disable NUMA auto-balancing.
 
-      # disable automatic NUMA balancing
-      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
-      # check if NUMA balancing is disabled (returns 0 if disabled)
-      cat /proc/sys/kernel/numa_balancing
-      0
+      To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+      might hang until the periodic balancing is finalized. For more information,
+      see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
 
-   To test for optimal performance, consult the recommended :ref:`System health benchmarks
-   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-   system's configuration.
+      .. code-block:: shell
 
-   Pull the Docker image
-   =====================
+         # disable automatic NUMA balancing
+         sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+         # check if NUMA balancing is disabled (returns 0 if disabled)
+         cat /proc/sys/kernel/numa_balancing
+         0
 
    .. container:: model-doc pyt_chai1_inference
 
-      Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue/images/sha256-b736a4239ab38a9d0e448af6d4adca83b117debed00bfbe33846f99c4540f79b>`_ from Docker Hub.
+      2. Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue/images/sha256-b736a4239ab38a9d0e448af6d4adca83b117debed00bfbe33846f99c4540f79b>`_ from Docker Hub.
 
-      .. code-block:: shell
+         .. code-block:: shell
 
-         docker pull rocm/pytorch:rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue
+            docker pull rocm/pytorch:rocm6.2.3_ubuntu22.04_py3.10_pytorch_release_2.3.0_triton_llvm_reg_issue
 
-      .. note::
+         .. note::
 
-         The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.
+            The Chai-1 benchmark uses a specifically selected Docker image using ROCm 6.2.3 and PyTorch 2.3.0 to address an accuracy issue.
 
    .. container:: model-doc pyt_clip_inference
 
-      Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/latest/images/sha256-05b55983e5154f46e7441897d0908d79877370adca4d1fff4899d9539d6c4969>`_ from Docker Hub.
+      2. Use the following command to pull the `ROCm PyTorch Docker image <https://hub.docker.com/layers/rocm/pytorch/latest/images/sha256-05b55983e5154f46e7441897d0908d79877370adca4d1fff4899d9539d6c4969>`_ from Docker Hub.
 
-      .. code-block:: shell
+         .. code-block:: shell
 
-         docker pull rocm/pytorch:latest
-
-   .. _pytorch-benchmark-get-started:
+            docker pull rocm/pytorch:latest
 
    Benchmarking
    ============

docs/how-to/rocm-for-ai/inference/vllm-benchmark.rst

@@ -111,37 +111,35 @@ vLLM inference performance testing
    For information on experimental features and known issues related to ROCm optimization efforts on vLLM,
    see the developer's guide at `<https://github.com/ROCm/vllm/blob/main/docs/dev-docker/README.md>`__.
 
-   System validation
-   =================
+   Getting started
+   ===============
 
-   Before running AI workloads, it's important to validate that your AMD hardware is configured
-   correctly and performing optimally.
+   Use the following procedures to reproduce the benchmark results on an
+   MI300X accelerator with the prebuilt vLLM Docker image.
 
-   To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
-   might hang until the periodic balancing is finalized. For more information,
-   see the :ref:`system validation steps <rocm-for-ai-system-optimization>`.
+   .. _vllm-benchmark-get-started:
 
-   .. code-block:: shell
+   1. Disable NUMA auto-balancing.
 
-      # disable automatic NUMA balancing
-      sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
-      # check if NUMA balancing is disabled (returns 0 if disabled)
-      cat /proc/sys/kernel/numa_balancing
-      0
+      To optimize performance, disable automatic NUMA balancing. Otherwise, the GPU
+      might hang until the periodic balancing is finalized. For more information,
+      see :ref:`AMD Instinct MI300X system optimization <mi300x-disable-numa>`.
 
-   To test for optimal performance, consult the recommended :ref:`System health benchmarks
-   <rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-   system's configuration.
+      .. code-block:: shell
 
-   Pull the Docker image
-   =====================
+         # disable automatic NUMA balancing
+         sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
+         # check if NUMA balancing is disabled (returns 0 if disabled)
+         cat /proc/sys/kernel/numa_balancing
+         0
 
-   Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
-   Use the following command to pull the Docker image from Docker Hub.
+   2. Download the `ROCm vLLM Docker image <{{ unified_docker.docker_hub_url }}>`_.
 
-   .. code-block:: shell
+      Use the following command to pull the Docker image from Docker Hub.
 
-      docker pull {{ unified_docker.pull_tag }}
+      .. code-block:: shell
+
+         docker pull {{ unified_docker.pull_tag }}
 
    Benchmarking
    ============

docs/how-to/rocm-for-ai/system-health-check.rst

@@ -1,104 +0,0 @@
-.. meta::
-   :description: System health checks with RVS, RCCL tests, BabelStream, and TransferBench to validate AMD hardware performance running AI workloads.
-   :keywords: gpu, accelerator, system, health, validation, bench, perf, performance, rvs, rccl, babel, mi300x, mi325x, flops, bandwidth, rbt, training, inference
-
-.. _rocm-for-ai-system-health-bench:
-
-************************
-System health benchmarks
-************************
-
-Before running AI workloads, it is important to validate that your AMD hardware is configured correctly and is performing optimally. This topic outlines several system health benchmarks you can use to test key aspects like GPU compute capabilities (FLOPS), memory bandwidth, and interconnect performance. Many of these tests are part of the ROCm Validation Suite (RVS).
-
-ROCm Validation Suite (RVS) tests
-=================================
-
-RVS provides a collection of tests, benchmarks, and qualification tools, each
-targeting a specific subsystem of the system under test. It includes tests for
-GPU stress and memory bandwidth.
-
-.. _healthcheck-install-rvs:
-
-Install ROCm Validation Suite
------------------------------
-
-To get started, install RVS. For example, on an Ubuntu system with ROCm already
-installed, run the following command:
-
-.. code-block:: shell
-
-   sudo apt update
-   sudo apt install rocm-validation-suite
-
-See the `ROCm Validation Suite installation instructions <https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/latest/install/installation.html>`_,
-and `System validation tests <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/system-validation.html#system-validation-tests>`_
-in the Instinct documentation for more detailed instructions.
-
-Benchmark, stress, and qualification tests
-------------------------------------------
-
-The GPU stress test runs various GEMM computations as workloads to stress the GPU FLOPS performance and check whether it
-meets the configured target GFLOPS.
-
-Run the benchmark, stress, and qualification tests included with RVS. See the `Benchmark, stress, qualification
-<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/system-validation.html#benchmark-stress-qualification>`_
-section of the Instinct documentation for usage instructions.
-
-BabelStream test
-----------------
-
-BabelStream is a synthetic GPU benchmark based on the STREAM benchmark for
-CPUs, measuring memory transfer rates to and from global device memory.
-BabelStream tests are included with the RVS package as part of the `BABEL module
-<https://rocm.docs.amd.com/projects/ROCmValidationSuite/en/latest/conceptual/rvs-modules.html#babel-benchmark-test-babel-module>`_.
-
-For more information, see `Performance benchmarking
-<https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/performance-bench.html#babelstream-benchmarking-results>`_
-in the Instinct documentation.
-
-RCCL tests
-==========
-
-The ROCm Communication Collectives Library (RCCL) enables efficient multi-GPU
-communication. The `<https://github.com/ROCm/rccl-tests>`__ suite benchmarks
-the performance and verifies the correctness of these collective operations.
-This helps ensure optimal scaling for multi-accelerator tasks.
-
-1. To get started, build RCCL-tests using the official instructions in the README at
-   `<https://github.com/ROCm/rccl-tests?tab=readme-ov-file#build>`__ or use the
-   following commands:
-
-   .. code-block:: shell
-
-      git clone https://github.com/ROCm/rccl-tests.git
-      cd rccl-tests
-      make
-
-2. Run the suggested RCCL tests -- see `RCCL benchmarking
-   <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/performance-bench.html#rccl-benchmarking-results>`_
-   in the Instinct performance benchmarking documentation for instructions.
-
-TransferBench test
-==================
-
-TransferBench is a standalone utility for benchmarking simultaneous data
-transfer performance between various devices in the system, including
-CPU-to-GPU and GPU-to-GPU (peer-to-peer). This helps identify potential
-bottlenecks in data movement between the host system and the GPUs, or between
-GPUs, which can impact end-to-end latency.
-
-.. _healthcheck-install-transferbench:
-
-1. To get started, use the instructions in the `TransferBench documentation
-   <https://rocm.docs.amd.com/projects/TransferBench/en/latest/install/install.html#install-transferbench>`_
-   or use the following commands:
-
-   .. code:: shell
-
-      git clone https://github.com/ROCm/TransferBench.git
-      cd TransferBench
-      CC=hipcc make
-
-2. Run the suggested TransferBench tests -- see `TransferBench benchmarking
-   <https://instinct.docs.amd.com/projects/system-acceptance/en/latest/mi300x/performance-bench.html#transferbench-benchmarking-results>`_
-   in the Instinct performance benchmarking documentation for instructions.

docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst

@@ -79,18 +79,11 @@ across different input sequences. Support for packed input format is planned for
 System validation
 =================
 
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
 before starting training.
 
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
 Environment setup
 =================
 
@@ -182,8 +175,8 @@ with RDMA, skip ahead to :ref:`amd-maxtext-download-docker`.
 
 .. _amd-maxtext-download-docker:
 
-Pull the Docker image
----------------------
+Download the Docker image
+-------------------------
 
 1. Use the following command to pull the Docker image from Docker Hub.
 

docs/how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst

@@ -103,18 +103,11 @@ popular AI models.
 System validation
 =================
 
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
 before starting training.
 
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
 .. _mi300x-amd-megatron-lm-training:
 
 Environment setup

docs/how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry.rst

@@ -34,18 +34,11 @@ for MPT-30B with access to detailed logs and performance metrics.
 System validation
 =================
 
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
 before starting training.
 
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
 Getting started
 ===============
 

docs/how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst

@@ -77,18 +77,11 @@ popular AI models.
 System validation
 =================
 
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
+If you have already validated your system settings, including NUMA
+auto-balancing, skip this step. Otherwise, complete the :ref:`system validation
+and optimization steps <train-a-model-system-validation>` to set up your system
 before starting training.
 
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
 This Docker image is optimized for specific model configurations outlined
 below. Performance can vary for other training workloads, as AMD 
 doesn’t validate configurations and run conditions outside those described.

docs/how-to/rocm-for-ai/training/index.rst

@@ -21,12 +21,8 @@ In this guide, you'll learn about:
 
 - Training a model
 
-  - :doc:`With Megatron-LM <benchmark-docker/megatron-lm>`
+  - :doc:`Train a model with Megatron-LM <benchmark-docker/megatron-lm>`
 
-  - :doc:`With PyTorch <benchmark-docker/pytorch-training>`
-
-  - :doc:`With JAX MaxText <benchmark-docker/jax-maxtext>`
-
-  - :doc:`With LLM Foundry <benchmark-docker/mpt-llm-foundry>`
+  - :doc:`Train a model with PyTorch <benchmark-docker/pytorch-training>`
 
 - :doc:`Scaling model training <scale-model-training>`

docs/how-to/rocm-for-ai/training/prerequisite-system-validation.rst

@@ -5,13 +5,12 @@
    :keywords: ROCm, AI, LLM, train, megatron, Llama, tutorial, docker, torch, pytorch, jax
 
 .. _train-a-model-system-validation:
-.. _rocm-for-ai-system-optimization:
 
-**********************************************************
-Prerequisite system validation before running AI workloads
-**********************************************************
+**********************************************
+Prerequisite system validation before training
+**********************************************
 
-Complete the following system validation and optimization steps to set up your system before starting training and inference.
+Complete the following system validation and optimization steps to set up your system before starting training.
 
 Disable NUMA auto-balancing
 ---------------------------
@@ -27,8 +26,7 @@ the output is ``1``, run the following command to disable NUMA auto-balancing.
 
    sudo sh -c 'echo 0 > /proc/sys/kernel/numa_balancing'
 
-See `Disable NUMA auto-balancing <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html#disable-numa-auto-balancing>`_
-in the Instinct documentation for more information.
+See :ref:`mi300x-disable-numa` for more information.
 
 Hardware verification with ROCm
 -------------------------------
@@ -44,8 +42,7 @@ Run the command:
 
    rocm-smi --setperfdeterminism 1900
 
-See `Hardware verfication for ROCm <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html#hardware-verification-with-rocm>`_
-in the Instinct documentation for more information.
+See :ref:`mi300x-hardware-verification-with-rocm` for more information.
 
 RCCL Bandwidth Test for multi-node setups
 -----------------------------------------

docs/how-to/system-debugging.md

@@ -0,0 +1,68 @@
+---
+myst:
+  html_meta:
+    "description": "Learn more about common system-level debugging measures for ROCm."
+    "keywords": "env, var, sys, PCIe, troubleshooting, admin, error"
+---
+
+# System debugging
+
+## ROCm language and system-level debug, flags, and environment variables
+
+Kernel options to avoid: the Ethernet port getting renamed every time you change graphics cards, `net.ifnames=0 biosdevname=0`
+
+## ROCr error code
+
+* 2 Invalid Dimension
+* 4 Invalid Group Memory
+* 8 Invalid (or Null) Code
+* 32 Invalid Format
+* 64 Group is too large
+* 128 Out of VGPRs
+* 0x80000000 Debug Options
+
+## Command to dump firmware version and get Linux kernel version
+
+`sudo cat /sys/kernel/debug/dri/1/amdgpu_firmware_info`
+
+`uname -a`
+
+## Debug flags
+
+Debug messages when developing/debugging base ROCm driver. You could enable the printing from `libhsakmt.so` by setting an environment variable, `HSAKMT_DEBUG_LEVEL`. Available debug levels are 3-7. The higher level you set, the more messages will print.
+
+* `export HSAKMT_DEBUG_LEVEL=3` : Only pr_err() prints.
+
+* `export HSAKMT_DEBUG_LEVEL=4` : pr_err() and pr_warn() print.
+
+* `export HSAKMT_DEBUG_LEVEL=5` : We currently do not implement “notice”. Setting to 5 is same as setting to 4.
+
+* `export HSAKMT_DEBUG_LEVEL=6` : pr_err(), pr_warn(), and pr_info print.
+
+* `export HSAKMT_DEBUG_LEVEL=7` : Everything including pr_debug prints.
+
+## ROCr level environment variables for debug
+
+`HSA_ENABLE_SDMA=0`
+
+`HSA_ENABLE_INTERRUPT=0`
+
+`HSA_SVM_GUARD_PAGES=0`
+
+`HSA_DISABLE_CACHE=1`
+
+## Turn off page retry on GFX9/Vega devices
+
+`sudo -s`
+
+`echo 1 > /sys/module/amdkfd/parameters/noretry`
+
+## HIP environment variables 3.x
+
+### OpenCL debug flags
+
+`AMD_OCL_WAIT_COMMAND=1 (0 = OFF, 1 = On)`
+
+## PCIe-debug
+
+For information on how to debug and profile HIP applications, see {doc}`hip:how-to/debugging`

docs/index.md

@@ -42,6 +42,7 @@ ROCm documentation is organized into the following categories:
 * [Use ROCm for HPC](./how-to/rocm-for-hpc/index.rst)
 * [System optimization](./how-to/system-optimization/index.rst)
 * [AMD Instinct MI300X performance validation and tuning](./how-to/tuning-guides/mi300x/index.rst)
+* [System debugging](./how-to/system-debugging.md)
 * [Use advanced compiler features](./conceptual/compiler-topics.md)
 * [Set the number of CUs](./how-to/setting-cus)
 * [Troubleshoot BAR access limitation](./how-to/Bar-Memory.rst)

docs/sphinx/_toc.yml.in

@@ -36,10 +36,6 @@ subtrees:
     title: Use ROCm for AI
     subtrees:
     - entries:
-      - file: how-to/rocm-for-ai/install.rst
-        title: Installation
-      - file: how-to/rocm-for-ai/system-health-check.rst
-        title: System health benchmarks
       - file: how-to/rocm-for-ai/training/index.rst
         title: Training
         subtrees:
@@ -74,6 +70,8 @@ subtrees:
         title: Inference
         subtrees:
         - entries:
+          - file: how-to/rocm-for-ai/inference/install.rst
+            title: Installation
           - file: how-to/rocm-for-ai/inference/hugging-face-models.rst
             title: Run models from Hugging Face
           - file: how-to/rocm-for-ai/inference/llm-inference-frameworks.rst
@@ -109,6 +107,7 @@ subtrees:
     title: System optimization
   - file: how-to/gpu-performance/mi300x.rst
     title: AMD Instinct MI300X performance guides
+  - file: how-to/system-debugging.md
   - file: conceptual/compiler-topics.md
     title: Use advanced compiler features
     subtrees:
@@ -122,7 +121,7 @@ subtrees:
   - file: how-to/setting-cus
     title: Set the number of CUs
   - file: how-to/Bar-Memory.rst
-    title: Troubleshoot BAR access limitation
+    title: Troubleshoot BAR access limitation  
   - url: https://github.com/amd/rocm-examples
     title: ROCm examples