Merge branch 'develop' into amd-develop

.github/ISSUE_TEMPLATE/config.yml

+blank_issues_enabled: true

.github/ISSUE_TEMPLATE/issue_report.yml

+name: Issue Report
+description: File a report for ROCm related issues on Linux and Windows. For issues pertaining to documentation or non-bug related, please open a blank issue located below.
+title: "[Issue]: "
+
+body:
+- type: markdown
+  attributes:
+    value: |
+      Thank you for taking the time to fill out this report!
+
+      You can acquire your OS, CPU, GPU (for filling out this report) with the following commands:
+
+      Linux:
+        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)";
+        
+      Windows:
+         (Get-WmiObject Win32_OperatingSystem).Version
+         (Get-WmiObject win32_Processor).Name
+         (Get-WmiObject win32_VideoController).Name
+- type: textarea
+  attributes:
+    label: Problem Description
+    description: Describe the issue you encountered.
+  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: dropdown
+  attributes:
+    label: GPU
+    description: What GPU(s) did you encounter the issue on (you can select multiple GPUs from the list)
+    multiple: true
+    options:
+        - AMD Instinct MI300X
+        - AMD Instinct MI300A
+        - AMD Instinct MI300
+        - AMD Instinct MI250X
+        - AMD Instinct MI250
+        - AMD Instinct MI210
+        - AMD Instinct MI100
+        - AMD Instinct MI50
+        - AMD Instinct MI25
+        - AMD Radeon Pro V620
+        - AMD Radeon Pro VII
+        - AMD Radeon RX 7900 XTX
+        - AMD Radeon VII
+        - AMD Radeon Pro W7900
+        - AMD Radeon Pro W7800
+        - AMD Radeon Pro W6800
+        - AMD Radeon Pro W6600
+        - AMD Radeon Pro W5500
+        - AMD Radeon RX 7900 XT
+        - AMD Radeon RX 7600
+        - AMD Radeon RX 6950 XT
+        - AMD Radeon RX 6900 XT
+        - AMD Radeon RX 6800 XT
+        - AMD Radeon RX 6800
+        - AMD Radeon RX 6750
+        - AMD Radeon RX 6700 XT
+        - AMD Radeon RX 6700
+        - AMD Radeon RX 6650 XT
+        - AMD Radeon RX 6600 XT
+        - AMD Radeon RX 6600
+        - Other
+  validations:
+    required: true
+- type: input
+  attributes:
+    label: Other
+    description: If you selected Other, please specify
+- type: dropdown
+  attributes:
+    label: ROCm Version
+    description: What version(s) of ROCm did you encounter the issue on?
+    multiple: true
+    options:
+        - ROCm 6.0.0
+        - ROCm 5.7.1
+        - ROCm 5.7.0
+        - ROCm 5.6.1
+        - ROCm 5.6.0
+        - ROCm 5.5.1
+        - ROCm 5.5.0
+  validations:
+    required: true
+- type: dropdown
+  attributes:
+    label: ROCm Component
+    description: (Optional) If this issue relates to a specific ROCm component, it can be mentioned here.
+    multiple: true
+    options:
+        - Other
+        - AMD Common Language Runtime
+        - AMD MIGraphX
+        - AMD System Management Interface
+        - amdgpu KCL/autoconf
+        - amdgpu Kernel-mode GPU Driver
+        - amdgpu-install
+        - AOMP
+        - AOMP Extras
+        - AqlProfile
+        - build-infra
+        - chelsio
+        - clang-ocl
+        - Composable Kernel
+        - dkms
+        - docker / ROCm-docker
+        - flang
+        - gpuburn
+        - half
+        - HIP
+        - HIP Examples
+        - hipBLAS
+        - hipBLASLt
+        - HIPCC
+        - hipCUB
+        - hip-examples-private
+        - hipFFT
+        - hipfort
+        - HIPIFY
+        - hipRAND
+        - hipSOLVER
+        - hipSPARSE
+        - hipSPARSELt
+        - hipTensor
+        - hip-tests
+        - HSA Runtime
+        - infrastructure
+        - jenkins-utils
+        - libdrm
+        - Linux BPI packaging framework
+        - llvm-project
+        - Mesa
+        - meta
+        - MIOpen
+        - MIVisionX
+        - ml-framework-ci
+        - MLSEQA_TestRepo
+        - OpenCL API C++ Bindings
+        - OpenCL API Headers
+        - OpenCL Conformance Test Suite
+        - OpenCL ICD Loader
+        - perftest-p2p
+        - prototype
+        - RCCL
+        - rccl-rdma-sharp-plugins
+        - rocALUTION
+        - rocBLAS
+        - ROCdbgapi
+        - ROCdebug-agent
+        - rocFFT
+        - ROCgdb
+        - ROCK
+        - ROCm Documentation/Website
+        - ROCm Data Center Tool
+        - ROCm Examples
+        - ROCm for Windows
+        - ROCm Performance Primitives
+        - ROCm System Management Interface Library
+        - ROCm Thrust
+        - ROCm Validation Suite
+        - rocm_bandwidth_test
+        - rocm-cmake
+        - rocm-core
+        - rocm-docs-core
+        - rocminfo
+        - rocMLIR
+        - rocmtools
+        - rocPRIM
+        - rocprofiler
+        - rocRAND
+        - ROCR-Runtime
+        - rocSOLVER
+        - rocSPARSE
+        - roctracer
+        - ROCT-Thunk-Interface
+        - rocWMMA
+        - Tensile
+        - umr
+        - ibv_rc_pingpong-amd
+        - mellanox
+        - mpitest
+        - Pytorch
+        - Tensorflow
+        - APEX
+        - torchvision
+        - Magma
+- type: textarea
+  attributes:
+    label: Steps to Reproduce
+    description: (Optional) Detailed steps to reproduce the issue.
+  validations:
+    required: false
+    
+- type: textarea
+  attributes:
+    label: (Optional for Linux users) Output of /opt/rocm/bin/rocminfo --support
+    description: The output of rocminfo --support could help to better address the problem.
+  validations:
+    required: false
+
+- type: textarea
+  attributes:
+    label: Additional Information
+    description: (Optional) Any additional information that is relevant, e.g. relevant environment variables, dockerfiles, log files, dmesg output (on Linux), etc.
+  validations:
+    required: false

.github/dependabot.yml

@@ -10,3 +10,9 @@ updates:
     open-pull-requests-limit: 10
     schedule:
       interval: "daily"
+    labels:
+      - "documentation"
+      - "dependencies"
+      - "ci:docs-only"
+    reviewers:
+      - "samjwu"

.gitignore

@@ -54,5 +54,4 @@ _images/
 _static/
 _templates/
 _toc.yml
-docBin/
 _doxygen/

.readthedocs.yaml

@@ -3,11 +3,6 @@
 
 version: 2
 
-build:
-   os: ubuntu-22.04
-   tools:
-      python: "3.8"
-
 sphinx:
    configuration: docs/conf.py
 
@@ -16,3 +11,8 @@ formats: [htmlzip, pdf, epub]
 python:
    install:
    - requirements: docs/sphinx/requirements.txt
+
+build:
+   os: ubuntu-22.04
+   tools:
+      python: "3.8"

CHANGELOG.md

@@ -19,6 +19,7 @@ None
 - Support for NHWGC (2D and 3D) grouped convolution backward weight (#769 #804)
 - Support for bf16/f32/f16 and NHWGC (2D and 3D) grouped convolution backward data (#757 #799)
 - Support for Batched Gemm DL (#732)
+- Introduce wrapper sublibrary (limited functionality). (#1071, #1098)
 
 ### Changes
  - Changed the grouped convolution API to maintain consistency with other convolution kernels (#817)

CITATION.cff

@@ -59,9 +59,9 @@ authors:
     family-names: Zhou
   - given-names: Jianfeng
     family-names: Yan
-repository-code: 'https://github.com/ROCmSoftwarePlatform/composable_kernel'
+repository-code: 'https://github.com/ROCm/composable_kernel'
 abstract: Composable Kernel (CK) library aims to provide a programming model for writing performance critical kernels for Machine Learning workloads across multiple architectures including GPUs, CPUs, etc, through general purpose kernel progarmming languages, like HIP C++.
 keywords:
   - 'CK, Composable Kernel, Tensor Coordinate Transformation'
 license: MIT
-license-url: https://github.com/ROCmSoftwarePlatform/composable_kernel/blob/7fc3ed761aa35709d87c8fbbe41dd368648b3541/LICENSE
+license-url: https://github.com/ROCm/composable_kernel/blob/7fc3ed761aa35709d87c8fbbe41dd368648b3541/LICENSE

CMakeLists.txt

@@ -146,6 +146,33 @@ if(${hip_VERSION_FLAT} GREATER 500723302)
    add_compile_options(-fno-offload-uniform-block)
 endif()
 
+#
+# Seperate linking jobs from compiling
+# Too many concurrent linking jobs can break the build
+# Copied from LLVM
+set(CK_PARALLEL_LINK_JOBS "" CACHE STRING
+  "Define the maximum number of concurrent link jobs (Ninja only).")
+if(CMAKE_GENERATOR MATCHES "Ninja")
+  if(CK_PARALLEL_LINK_JOBS)
+    set_property(GLOBAL APPEND PROPERTY JOB_POOLS link_job_pool=${CK_PARALLEL_LINK_JOBS})
+    set(CMAKE_JOB_POOL_LINK link_job_pool)
+  endif()
+elseif(CK_PARALLEL_LINK_JOBS)
+  message(WARNING "Job pooling is only available with Ninja generators.")
+endif()
+# Similar for compiling
+set(CK_PARALLEL_COMPILE_JOBS "" CACHE STRING
+  "Define the maximum number of concurrent compile jobs (Ninja only).")
+if(CMAKE_GENERATOR MATCHES "Ninja")
+  if(CK_PARALLEL_COMPILE_JOBS)
+    set_property(GLOBAL APPEND PROPERTY JOB_POOLS compile_job_pool=${CK_PARALLEL_COMPILE_JOBS})
+    set(CMAKE_JOB_POOL_COMPILE compile_job_pool)
+  endif()
+elseif(CK_PARALLEL_COMPILE_JOBS)
+  message(WARNING "Job pooling is only available with Ninja generators.")
+endif()
+
+
 option(USE_BITINT_EXTENSION_INT4, "Whether to enable clang's BitInt extension to provide int4 data type." OFF)
 option(USE_OPT_NAVI3X, "Whether to enable LDS cumode and Wavefront32 mode for NAVI3X silicons." OFF)
 

Dockerfile

 FROM ubuntu:20.04
 ARG DEBIAN_FRONTEND=noninteractive
-ARG ROCMVERSION=5.7
+ARG ROCMVERSION=6.0
 ARG compiler_version=""
 ARG compiler_commit=""
 
@@ -16,8 +16,8 @@ RUN apt-get install -y --allow-unauthenticated apt-utils wget gnupg2 curl
 ENV APT_KEY_DONT_WARN_ON_DANGEROUS_USAGE=DontWarn
 RUN curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor -o /etc/apt/trusted.gpg.d/rocm-keyring.gpg
 
-RUN wget https://repo.radeon.com/amdgpu-install/5.7/ubuntu/focal/amdgpu-install_5.7.50700-1_all.deb  --no-check-certificate
-RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --allow-unauthenticated ./amdgpu-install_5.7.50700-1_all.deb
+RUN wget https://repo.radeon.com/amdgpu-install/6.0/ubuntu/focal/amdgpu-install_6.0.60000-1_all.deb  --no-check-certificate
+RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --allow-unauthenticated ./amdgpu-install_6.0.60000-1_all.deb
 
 RUN wget -qO - http://repo.radeon.com/rocm/rocm.gpg.key | apt-key add - && \
     sh -c "echo deb [arch=amd64 signed-by=/etc/apt/trusted.gpg.d/rocm-keyring.gpg] $DEB_ROCM_REPO focal main > /etc/apt/sources.list.d/rocm.list" && \

Jenkinsfile

@@ -33,7 +33,7 @@ def runShell(String command){
 
 def getDockerImageName(){
     def img
-    if (params.ROCMVERSION != "6.0"){
+    if (params.ROCMVERSION != "6.1"){
        if (params.COMPILER_VERSION == "") {
            img = "${env.CK_DOCKERHUB}:ck_ub20.04_rocm${params.ROCMVERSION}"
        }
@@ -302,7 +302,7 @@ def buildHipClangJob(Map conf=[:]){
         def retimage
         (retimage, image) = getDockerImage(conf)
 
-        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
+        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
             withDockerContainer(image: image, args: dockerOpts + ' -v=/var/jenkins/:/var/jenkins') {
                 timeout(time: 5, unit: 'HOURS')
                 {
@@ -355,7 +355,7 @@ def runCKProfiler(Map conf=[:]){
         def variant = env.STAGE_NAME
         def retimage
 
-        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
+        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
             try {
                 (retimage, image) = getDockerImage(conf)
                 withDockerContainer(image: image, args: dockerOpts) {
@@ -487,7 +487,7 @@ def Build_CK(Map conf=[:]){
         def retimage
         def navi_node = 0
 
-        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
+        gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
             try {
                 (retimage, image) = getDockerImage(conf)
                 withDockerContainer(image: image, args: dockerOpts) {
@@ -553,7 +553,7 @@ def Build_CK(Map conf=[:]){
                         sh """#!/bin/bash
                             rm -rf "${params.hipTensor_branch}".zip
                             rm -rf hipTensor-"${params.hipTensor_branch}"
-                            wget https://github.com/ROCmSoftwarePlatform/hipTensor/archive/refs/heads/"${params.hipTensor_branch}".zip
+                            wget https://github.com/ROCm/hipTensor/archive/refs/heads/"${params.hipTensor_branch}".zip
                             unzip -o "${params.hipTensor_branch}".zip
                         """
                         dir("hipTensor-${params.hipTensor_branch}"){
@@ -605,7 +605,7 @@ def process_results(Map conf=[:]){
     def variant = env.STAGE_NAME
     def retimage
 
-    gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCmSoftwarePlatform', repo: 'composable_kernel') {
+    gitStatusWrapper(credentialsId: "${status_wrapper_creds}", gitHubContext: "Jenkins - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
         try {
             (retimage, image) = getDockerImage(conf)
         }
@@ -655,8 +655,8 @@ def process_results(Map conf=[:]){
 }
 
 //launch develop branch daily at 23:00 UT in FULL_QA mode and at 19:00 UT with latest staging compiler version
-CRON_SETTINGS = BRANCH_NAME == "develop" ? '''0 23 * * * % RUN_FULL_QA=true;ROCMVERSION=5.7;COMPILER_VERSION=
-                                              0 21 * * * % ROCMVERSION=5.7;COMPILER_VERSION=;COMPILER_COMMIT=
+CRON_SETTINGS = BRANCH_NAME == "develop" ? '''0 23 * * * % RUN_FULL_QA=true;ROCMVERSION=6.0;COMPILER_VERSION=
+                                              0 21 * * * % ROCMVERSION=6.0;COMPILER_VERSION=;COMPILER_COMMIT=
                                               0 19 * * * % BUILD_DOCKER=true;DL_KERNELS=true;COMPILER_VERSION=amd-stg-open;COMPILER_COMMIT=;USE_SCCACHE=false
                                               0 17 * * * % BUILD_DOCKER=true;DL_KERNELS=true;COMPILER_VERSION=amd-mainline-open;COMPILER_COMMIT=;USE_SCCACHE=false''' : ""
 
@@ -675,8 +675,8 @@ pipeline {
             description: "Force building docker image (default: false), set to true if docker image needs to be updated.")
         string(
             name: 'ROCMVERSION', 
-            defaultValue: '5.7', 
-            description: 'Specify which ROCM version to use: 5.7 (default).')
+            defaultValue: '6.0', 
+            description: 'Specify which ROCM version to use: 6.0 (default).')
         string(
             name: 'COMPILER_VERSION', 
             defaultValue: '', 
@@ -703,8 +703,8 @@ pipeline {
             description: "Use the CK build to verify hipTensor build and tests (default: ON)")
         string(
             name: 'hipTensor_branch',
-            defaultValue: 'develop',
-            description: 'Specify which branch of hipTensor to use (default: develop)')
+            defaultValue: 'mainline',
+            description: 'Specify which branch of hipTensor to use (default: mainline)')
         booleanParam(
             name: "USE_SCCACHE",
             defaultValue: true,
@@ -768,8 +768,15 @@ pipeline {
                     }
                     agent{ label rocmnode("gfx908 || gfx90a") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942" -DCMAKE_EXE_LINKER_FLAGS=" -L ${env.WORKSPACE}/script -T hip_fatbin_insert " """
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ 
+                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install \
+                                         -DGPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942" \
+                                         -DCMAKE_EXE_LINKER_FLAGS=" -L ${env.WORKSPACE}/script -T hip_fatbin_insert " \
+                                         -DCMAKE_CXX_FLAGS=" -O3 " """
+                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && \
+                                           cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" \
+                                           -DGPU_TARGETS="gfx908;gfx90a;gfx940;gfx941;gfx942" \
+                                           -DCMAKE_CXX_COMPILER="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """ 
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -784,8 +791,12 @@ pipeline {
                     }
                     agent{ label rocmnode("gfx908 || gfx90a") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a" """
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx908;gfx90a" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """ 
+                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a" -DCMAKE_CXX_FLAGS=" -O3 " """
+                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && \
+                                           cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" \
+                                           -DGPU_TARGETS="gfx908;gfx90a" \
+                                           -DCMAKE_CXX_COMPILER="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """ 
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -800,8 +811,12 @@ pipeline {
                     }
                     agent{ label rocmnode("navi21") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1030" -DDL_KERNELS=ON """ 
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx1030" -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """
+                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1030" -DDL_KERNELS=ON -DCMAKE_CXX_FLAGS=" -O3 " """ 
+                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && \
+                                           cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" \
+                                           -DGPU_TARGETS="gfx1030" \
+                                           -DCMAKE_CXX_COMPILER="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -816,8 +831,12 @@ pipeline {
                     }
                     agent{ label rocmnode("navi32") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1101" -DDL_KERNELS=ON """
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" -DGPU_TARGETS="gfx1101" -DDL_KERNELS=ON -D CMAKE_CXX_COMPILER="${build_compiler()}" .. && make -j """
+                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1101" -DDL_KERNELS=ON -DCMAKE_CXX_FLAGS=" -O3 " """
+                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && \
+                                           cmake -DCMAKE_PREFIX_PATH="${env.WORKSPACE}/install;/opt/rocm" \
+                                           -DGPU_TARGETS="gfx1101" \
+                                           -DCMAKE_CXX_COMPILER="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')

README.md

@@ -32,7 +32,6 @@ python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
 ```
 
 You can find a list of our developers and contributors on our [Contributors](/CONTRIBUTORS.md) page.
-page.
 
 ```note
 If you use CK, cite us as follows:
@@ -71,7 +70,7 @@ Docker images are available on [DockerHub](https://hub.docker.com/r/rocm/composa
 3. Clone CK source code from the GitHub repository and start the build:
 
     ```bash
-    git clone https://github.com/ROCmSoftwarePlatform/composable_kernel.git && \
+    git clone https://github.com/ROCm/composable_kernel.git && \
     cd composable_kernel && \
     mkdir build && \
     cd build

client_example/23_grouped_convnd_fwd_scaleadd_scaleadd_relu/grouped_conv_fwd_scaleadd_scaleadd_relu.inc

@@ -16,6 +16,7 @@
 using InLayout             = ck::tensor_layout::convolution::NDHWGC;
 using WeiLayout            = ck::tensor_layout::convolution::GKZYXC;
 using OutLayout            = ck::tensor_layout::convolution::NDHWGK;
+using BiasLayout           = ck::tensor_layout::convolution::G_K;
 using PassThrough          = ck::tensor_operation::element_wise::PassThrough;
 using ScaleAddScaleAddRelu = ck::tensor_operation::element_wise::ScaleAddScaleAddRelu;
 
@@ -64,6 +65,9 @@ int execute_conv_fwd_scaleadd_scaleadd_relu()
     std::array<ck::index_t, 6> out_lengths{G, N, K, Do, Ho, Wo};
     std::array<ck::index_t, 6> out_strides{
         K, Do * Ho * Wo * G * K, 1, Ho * Wo * G * K, Wo * G * K, G * K};
+    // Logical broadcast bias (we have to pass bias lengths in the same format as output - GNKDHW)
+    std::array<ck::index_t, 6> bias_lengths{G, 1, K, 1, 1, 1};
+    std::array<ck::index_t, 6> bias_strides{K, 0, 1, 0, 0, 0};
 
     std::array<ck::index_t, NumDimSpatial> filter_strides{1, 1, 1};
     std::array<ck::index_t, NumDimSpatial> filter_dilations{1, 1, 1};
@@ -74,13 +78,13 @@ int execute_conv_fwd_scaleadd_scaleadd_relu()
     SimpleDeviceMem wei(sizeof(WeiDataType) * G * K * Z * Y * X * C);
     SimpleDeviceMem out(sizeof(OutDataType) * N * Do * Ho * Wo * G * K);
     SimpleDeviceMem d0(sizeof(std::tuple_element_t<0, DDataTypes>) * N * Do * Ho * Wo * G * K);
-    SimpleDeviceMem d1(sizeof(std::tuple_element_t<1, DDataTypes>) * N * Do * Ho * Wo * G * K);
+    SimpleDeviceMem d1(sizeof(std::tuple_element_t<1, DDataTypes>) * G * K);
 
     using DeviceOp = ck::tensor_operation::device::DeviceGroupedConvFwdMultipleABD<
         NumDimSpatial,
         InLayout,
         WeiLayout,
-        ck::Tuple<OutLayout, OutLayout>,
+        ck::Tuple<OutLayout, BiasLayout>,
         OutLayout,
         InDataType,
         WeiDataType,
@@ -117,8 +121,8 @@ int execute_conv_fwd_scaleadd_scaleadd_relu()
                                         in_strides,
                                         wei_lengths,
                                         wei_strides,
-                                        {out_lengths, out_lengths},
-                                        {out_strides, out_strides},
+                                        {out_lengths, bias_lengths},
+                                        {out_strides, bias_strides},
                                         out_lengths,
                                         out_strides,
                                         filter_strides,
@@ -187,8 +191,8 @@ int execute_conv_fwd_scaleadd_scaleadd_relu()
                                         in_strides,
                                         wei_lengths,
                                         wei_strides,
-                                        {out_lengths, out_lengths},
-                                        {out_strides, out_strides},
+                                        {out_lengths, bias_lengths},
+                                        {out_strides, bias_strides},
                                         out_lengths,
                                         out_strides,
                                         filter_strides,

client_example/25_tensor_transforms/CMakeLists.txt

+add_executable(client_tensor_transform tensor_transform.cpp)
+target_link_libraries(client_tensor_transform PRIVATE composable_kernel::device_other_operations)
+add_executable(client_tensor_transform_using_wrapper tensor_transform_using_wrapper.cpp)
+target_link_libraries(client_tensor_transform_using_wrapper PRIVATE composable_kernel::device_other_operations)

example/64_tensor_transforms/tensor_transform_using_wrapper.cpp → client_example/25_tensor_transforms/tensor_transform_using_wrapper.cpp

@@ -9,7 +9,7 @@
 #include "ck/utility/tuple.hpp"
 #include "ck/utility/sequence.hpp"
 
-#include "tensor_transform_wrapper.hpp"
+#include "ck/wrapper/layout.hpp"
 
 using DataType = int;
 
@@ -17,7 +17,7 @@ template <typename Layout>
 void Print1d(const Layout& layout)
 {
     std::cout << "Print1d" << std::endl;
-    for(ck::index_t w = 0; w < ck::tensor_transform_wrapper::size(layout); w++)
+    for(ck::index_t w = 0; w < ck::wrapper::size(layout); w++)
     {
         std::cout << layout(ck::make_tuple(w)) << " ";
     }
@@ -28,9 +28,9 @@ template <typename Layout>
 void Print2d(const Layout& layout)
 {
     std::cout << "Print2d" << std::endl;
-    for(ck::index_t h = 0; h < ck::tensor_transform_wrapper::size<0>(layout); h++)
+    for(ck::index_t h = 0; h < ck::wrapper::size<0>(layout); h++)
     {
-        for(ck::index_t w = 0; w < ck::tensor_transform_wrapper::size<1>(layout); w++)
+        for(ck::index_t w = 0; w < ck::wrapper::size<1>(layout); w++)
         {
             std::cout << layout(ck::make_tuple(h, w)) << " ";
         }
@@ -43,15 +43,11 @@ template <typename Layout>
 void Print3dCustom(const Layout& layout)
 {
     std::cout << "Print3dCustom" << std::endl;
-    for(ck::index_t d = 0;
-        d < ck::tensor_transform_wrapper::size<0>(ck::tensor_transform_wrapper::get<0>(layout));
-        d++)
+    for(ck::index_t d = 0; d < ck::wrapper::size<0>(ck::wrapper::get<0>(layout)); d++)
     {
-        for(ck::index_t h = 0;
-            h < ck::tensor_transform_wrapper::size<1>(ck::tensor_transform_wrapper::get<0>(layout));
-            h++)
+        for(ck::index_t h = 0; h < ck::wrapper::size<1>(ck::wrapper::get<0>(layout)); h++)
         {
-            for(ck::index_t w = 0; w < ck::tensor_transform_wrapper::size<1>(layout); w++)
+            for(ck::index_t w = 0; w < ck::wrapper::size<1>(layout); w++)
             {
                 std::cout << layout(ck::make_tuple(ck::make_tuple(d, h), w)) << " ";
             }
@@ -68,7 +64,7 @@ int main()
     // Basic descriptor 0, 1, 2, ... 30, 31 (compile-time descriptor)
     // (dims:4,8 strides:1,4)
     const auto shape_4x8       = ck::make_tuple(ck::Number<4>{}, ck::Number<8>{});
-    const auto layout_4x8_s1x4 = ck::tensor_transform_wrapper::make_layout(shape_4x8);
+    const auto layout_4x8_s1x4 = ck::wrapper::make_layout(shape_4x8);
     std::cout << "dims:4,8 strides:1,4" << std::endl;
     Print2d(layout_4x8_s1x4);
     using Cord1x1Type                = ck::Tuple<ck::Number<1>, ck::Number<1>>;
@@ -77,10 +73,9 @@ int main()
 
     // Basic descriptor 0, 1, 8, 9, 16, 17, ... 30, 31 (runtime descriptor)
     // dims:4,(2,4) strides:2,(1,8)
-    const auto shape_4x2x4    = ck::make_tuple(4, ck::make_tuple(2, 4));
-    const auto strides_s2x1x8 = ck::make_tuple(2, ck::make_tuple(1, 8));
-    const auto layout_4x2x4_s2x1x8 =
-        ck::tensor_transform_wrapper::make_layout(shape_4x2x4, strides_s2x1x8);
+    const auto shape_4x2x4         = ck::make_tuple(4, ck::make_tuple(2, 4));
+    const auto strides_s2x1x8      = ck::make_tuple(2, ck::make_tuple(1, 8));
+    const auto layout_4x2x4_s2x1x8 = ck::wrapper::make_layout(shape_4x2x4, strides_s2x1x8);
 
     std::cout << "dims:4,(2,4) strides:2,(1,8)" << std::endl;
     Print2d(layout_4x2x4_s2x1x8);
@@ -92,7 +87,7 @@ int main()
     const auto strides_s1x4x2x8 = ck::make_tuple(ck::make_tuple(ck::Number<1>{}, ck::Number<4>{}),
                                                  ck::make_tuple(ck::Number<2>{}, ck::Number<8>{}));
     static const auto layout_2x2x2x4_s1x4x2x8 =
-        ck::tensor_transform_wrapper::make_layout(shape_2x2x2x4, strides_s1x4x2x8);
+        ck::wrapper::make_layout(shape_2x2x2x4, strides_s1x4x2x8);
 
     std::cout << "dims:(2,2),(2,4) strides:(1,4),(2,8)" << std::endl;
     Print2d(layout_2x2x2x4_s1x4x2x8);
@@ -108,7 +103,7 @@ int main()
         ck::make_tuple(ck::make_tuple(ck::Number<1>{}, ck::Number<4>{}), ck::Number<2>{}),
         ck::Number<8>{});
     static const auto layout_2x2x2x4_s1x4x2x8_nested =
-        ck::tensor_transform_wrapper::make_layout(shape_2x2x2x4_nested, strides_s1x4x2x8_nested);
+        ck::wrapper::make_layout(shape_2x2x2x4_nested, strides_s1x4x2x8_nested);
 
     std::cout << "dims:((2,2),2),4 strides:((1,4),2),8" << std::endl;
     Print1d(layout_2x2x2x4_s1x4x2x8_nested);

dev-requirements.txt

-ROCmSoftwarePlatform/rocm-recipes
+ROCm/rocm-recipes
 RadeonOpenCompute/rocm-cmake@04f694df2a8dc9d7e35fa4dee4ba5fa407ec04f8 --build
-danmar/cppcheck@2.9
\ No newline at end of file
+danmar/cppcheck@2.9

docs/conf.py

@@ -4,23 +4,34 @@
 # list see the documentation:
 # https://www.sphinx-doc.org/en/master/usage/configuration.html
 
-import subprocess
+import re
 
 from rocm_docs import ROCmDocs
 
+html_theme_options = {"flavor": "list"}
 
-name = "Composable Kernel"
-get_version = r'sed -n -e "s/^rocm_setup_version(.* \([0-9\.]\{1,\}\).*/\1/p" ../CMakeLists.txt'
-version = subprocess.getoutput(get_version)
-if len(version) > 0:
-    name = f"{name} {version}"
+with open('../CMakeLists.txt', encoding='utf-8') as f:
+    match = re.search(r'.*set\(version ([0-9.]+)[^0-9.]+', f.read())
+    if not match:
+        raise ValueError("VERSION not found!")
+    version_number = match[1]
+left_nav_title = f"Composable Kernel {version_number} Documentation"
+
+# for PDF output on Read the Docs
+project = "Composable Kernel Documentation"
+author = "Advanced Micro Devices, Inc."
+copyright = "Copyright (c) 2023 Advanced Micro Devices, Inc. All rights reserved."
+version = version_number
+release = version_number
 
 external_toc_path = "./sphinx/_toc.yml"
 
-docs_core = ROCmDocs(f"{name} Documentation")
-docs_core.run_doxygen(doxygen_root="doxygen", doxygen_path="doxygen/docBin/xml")
+docs_core = ROCmDocs(left_nav_title)
+docs_core.run_doxygen(doxygen_root="doxygen", doxygen_path="doxygen/xml")
 docs_core.setup()
 
+external_projects_current_project = "composable_kernel"
+
 mathjax3_config = {
 'tex': {
     'macros': {

docs/doxygen/Doxyfile

@@ -58,7 +58,7 @@ PROJECT_LOGO           =
 # entered, it will be relative to the location where doxygen was started. If
 # left blank the current directory will be used.
 
-OUTPUT_DIRECTORY       = docBin
+OUTPUT_DIRECTORY       = .
 
 # If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub-
 # directories (in 2 levels) under the output directory of each output format and
@@ -778,7 +778,9 @@ WARN_LOGFILE           =
 INPUT                  = ../../include/ck/tensor_operation/gpu/grid \
                          ../../include/ck/tensor_operation/gpu/block \
                          ../../include/ck/tensor_operation/gpu/thread \
-                         ../../library/include/ck/library/utility
+                         ../../library/include/ck/library/utility \
+                         ../../include/ck/wrapper
+
 
 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses

docs/index.rst

@@ -34,6 +34,7 @@ Current CK library are structured into 4 layers:
 * "Templated Tile Operators" layer
 * "Templated Kernel and Invoker" layer
 * "Instantiated Kernel and Invoker" layer
+* "Wrapper for tensor transform operations"
 * "Client API" layer
 
 .. image:: data/ck_layer.png
@@ -50,6 +51,7 @@ The following is a list of CK documents in the suggested reading order:
 
    tutorial_hello_world
    dockerhub
+   wrapper
    Supported_Primitives_Guide
    API_Reference_Guide
    Contributors_Guide

docs/sphinx/_toc.yml.in

@@ -5,6 +5,6 @@ defaults:
   maxdepth: 6
 root: index
 subtrees:
-  - caption: About
-    entries:
-      - file: license
+- caption: About
+  entries:
+    - file: license