cmake list

.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)
 
 ### 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

@@ -373,10 +373,9 @@ include_directories(BEFORE
 
 SET(BUILD_DEV ON CACHE BOOL "BUILD_DEV")
 if(BUILD_DEV)
-    add_compile_options(-Werror -Weverything)
+    add_compile_options(-Werror)
+    add_compile_options(-Weverything)
 endif()
-#add flags to reduce the size of binaries
-add_compile_options(-Oz -flto=thin)
 message("CMAKE_CXX_FLAGS: ${CMAKE_CXX_FLAGS}")
 
 add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND} --output-on-failure -C ${CMAKE_CFG_INTDIR})

Config.cmake.in

 @PACKAGE_INIT@
 
-set(_composable_kernel_supported_components device_operations utility)
+set(_composable_kernel_supported_components device_other_operations device_gemm_operations device_conv_operations device_mha_operations device_contraction_operations device_reduction_operations utility)
 
 foreach(_comp ${composable_kernel_FIND_COMPONENTS})
 	if(NOT _comp IN_LIST _composable_kernel_supported_components)

Dockerfile

@@ -111,7 +111,7 @@ ENV compiler_commit=$compiler_commit
 RUN sh -c "echo compiler version = '$compiler_version'"
 RUN sh -c "echo compiler commit = '$compiler_commit'"
 
-RUN if [ "$compiler_version" = "amd-stg-open" ] && [ "$compiler_commit" = "" ]; then \
+RUN if [ "$compiler_version" != "" ] && [ "$compiler_commit" = "" ]; then \
         git clone -b "$compiler_version" https://github.com/RadeonOpenCompute/llvm-project.git && \
         cd llvm-project && mkdir build && cd build && \
         cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \
@@ -119,7 +119,7 @@ RUN if [ "$compiler_version" = "amd-stg-open" ] && [ "$compiler_commit" = "" ];
     else echo "using the release compiler"; \
     fi
 
-RUN if [ "$compiler_version" = "amd-stg-open" ] && [ "$compiler_commit" != "" ]; then \
+RUN if [ "$compiler_version" != "" ] && [ "$compiler_commit" != "" ]; then \
         git clone -b "$compiler_version" https://github.com/RadeonOpenCompute/llvm-project.git && \
         cd llvm-project && git checkout "$compiler_commit" && echo "checking out commit $compiler_commit" && mkdir build && cd build && \
         cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \

Jenkinsfile

 def rocmnode(name) {
-    return 'rocmtest && miopen && ' + name
+    return '(rocmtest || miopen) && ' + name
 }
 
 def show_node_info() {
@@ -84,7 +84,7 @@ def build_compiler(){
         compiler = '/opt/rocm/bin/hipcc'
     }
     else{
-        if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){
+        if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
             compiler = "/llvm-project/build/bin/clang++"
         }
         else{
@@ -293,7 +293,7 @@ def buildHipClangJob(Map conf=[:]){
             dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
         }
         def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' "
-        if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){
+        if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
             dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
         }
 
@@ -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 - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
             withDockerContainer(image: image, args: dockerOpts + ' -v=/var/jenkins/:/var/jenkins') {
                 timeout(time: 5, unit: 'HOURS')
                 {
@@ -348,14 +348,14 @@ def runCKProfiler(Map conf=[:]){
             dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
         }
         def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' "
-        if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){
+        if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
             dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
         }
 
         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 - ${variant}", account: 'ROCm', repo: 'composable_kernel') {
             try {
                 (retimage, image) = getDockerImage(conf)
                 withDockerContainer(image: image, args: dockerOpts) {
@@ -479,7 +479,7 @@ def Build_CK(Map conf=[:]){
             dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
         }
         def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' "
-        if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){
+        if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
             dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
         }
 
@@ -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)
         }
@@ -657,7 +657,8 @@ 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=
-                                              0 19 * * * % BUILD_DOCKER=true;DL_KERNELS=true;COMPILER_VERSION=amd-stg-open;COMPILER_COMMIT=;USE_SCCACHE=false''' : ""
+                                              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''' : ""
 
 pipeline {
     agent none
@@ -679,15 +680,15 @@ pipeline {
         string(
             name: 'COMPILER_VERSION', 
             defaultValue: '', 
-            description: 'Specify which version of compiler to use: release, amd-stg-open, or leave blank (default).')
+            description: 'Specify which version of compiler to use: release, amd-stg-open, amd-mainline-open, or leave blank (default).')
         string(
             name: 'COMPILER_COMMIT', 
             defaultValue: '', 
-            description: 'Specify which commit of compiler branch to use: leave blank to use the latest commit, or use 5541927df00eabd6a110180170eca7785d436ee3 (default) commit of amd-stg-open branch.')
+            description: 'Specify which commit of compiler branch to use: leave blank to use the latest commit (default), or use some specific commit of llvm-project branch.')
         string(
             name: 'BUILD_COMPILER', 
-            defaultValue: 'hipcc', 
-            description: 'Specify whether to build CK with hipcc (default) or with clang.')
+            defaultValue: 'clang', 
+            description: 'Specify whether to build CK with hipcc or with clang (default).')
         booleanParam(
             name: "RUN_FULL_QA",
             defaultValue: false,
@@ -767,8 +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="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """ 
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -783,8 +791,12 @@ pipeline {
                     }
                     agent{ label rocmnode("gfx908 || gfx90a") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx908;gfx90a" """
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${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="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """ 
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -799,8 +811,12 @@ pipeline {
                     }
                     agent{ label rocmnode("navi21") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1030" -DDL_KERNELS=ON """ 
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${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="${build_compiler()}" \
+                                           -DCMAKE_CXX_FLAGS=" -O3 " .. && make -j """
                     }
                     steps{
                         Build_CK_and_Reboot(setup_args: setup_args, config_targets: "install", no_reboot:true, build_type: 'Release', execute_cmd: execute_args, prefixpath: '/usr/local')
@@ -815,8 +831,12 @@ pipeline {
                     }
                     agent{ label rocmnode("navi32") }
                     environment{
-                        setup_args = """ -DCMAKE_INSTALL_PREFIX=../install -DGPU_TARGETS="gfx1101" -DDL_KERNELS=ON """
-                        execute_args = """ cd ../client_example && rm -rf build && mkdir build && cd build && cmake -D CMAKE_PREFIX_PATH="${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

@@ -71,7 +71,7 @@ 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/01_gemm/CMakeLists.txt

 add_executable(client_gemm gemm.cpp)
-target_link_libraries(client_gemm PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm PRIVATE composable_kernel::device_other_operations composable_kernel::device_gemm_operations)

client_example/02_gemm_add_add_fastgelu/CMakeLists.txt

 add_custom_target(client_gemm_fastgelu_examples)
 
 add_executable(client_gemm_add_add_fastgelu gemm_add_add_fastgelu.cpp)
-target_link_libraries(client_gemm_add_add_fastgelu PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_add_fastgelu PRIVATE composable_kernel::device_gemm_operations)
 
 add_executable(client_gemm_add_fastgelu gemm_add_fastgelu.cpp)
-target_link_libraries(client_gemm_add_fastgelu PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_fastgelu PRIVATE composable_kernel::device_gemm_operations)
 
 add_executable(client_gemm_fastgelu gemm_fastgelu.cpp)
-target_link_libraries(client_gemm_fastgelu PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_fastgelu PRIVATE composable_kernel::device_gemm_operations)
 
 add_dependencies(client_gemm_fastgelu_examples client_gemm_add_add_fastgelu client_gemm_add_fastgelu
                  client_gemm_fastgelu)
@@ -15,13 +15,13 @@ add_dependencies(client_gemm_fastgelu_examples client_gemm_add_add_fastgelu clie
 add_custom_target(client_gemm_fastgelu_generic_examples)
 
 add_executable(client_gemm_add_add_fastgelu_generic gemm_add_add_fastgelu_generic.cpp)
-target_link_libraries(client_gemm_add_add_fastgelu_generic PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_add_fastgelu_generic composable_kernel::device_gemm_operations)
 
 add_executable(client_gemm_add_fastgelu_generic gemm_add_fastgelu_generic.cpp)
-target_link_libraries(client_gemm_add_fastgelu_generic PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_fastgelu_generic PRIVATE composable_kernel::device_gemm_operations)
 
 add_executable(client_gemm_fastgelu_generic gemm_fastgelu_generic.cpp)
-target_link_libraries(client_gemm_fastgelu_generic PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_fastgelu_generic PRIVATE composable_kernel::device_gemm_operations)
 
 add_dependencies(client_gemm_fastgelu_generic_examples client_gemm_add_add_fastgelu_generic 
                  client_gemm_add_fastgelu_generic client_gemm_fastgelu_generic)

client_example/03_gemm_layernorm/CMakeLists.txt

 add_executable(client_gemm_add_add_layernorm_naive gemm_add_add_layernorm_naive.cpp)
-target_link_libraries(client_gemm_add_add_layernorm_naive PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_add_layernorm_naive PRIVATE composable_kernel::device_gemm_operations composable_kernel::device_other_operations)
 
 add_executable(client_gemm_add_relu_add_layernorm_welford gemm_add_relu_add_layernorm_welford.cpp)
-target_link_libraries(client_gemm_add_relu_add_layernorm_welford PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_add_relu_add_layernorm_welford PRIVATE composable_kernel::device_gemm_operations composable_kernel::device_other_operations)

client_example/04_contraction/CMakeLists.txt

 add_executable(client_contraction_scale_fp32 contraction_scale_fp32.cpp)
-target_link_libraries(client_contraction_scale_fp32 PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_contraction_scale_fp32 PRIVATE composable_kernel::device_other_operations composable_kernel::device_contraction_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_contraction_bilinear_fp32 contraction_bilinear_fp32.cpp)
-target_link_libraries(client_contraction_bilinear_fp32 PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_contraction_bilinear_fp32 PRIVATE composable_kernel::device_other_operations composable_kernel::device_contraction_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_contraction_scale_fp64 contraction_scale_fp64.cpp)
-target_link_libraries(client_contraction_scale_fp64 PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_contraction_scale_fp64 PRIVATE composable_kernel::device_other_operations composable_kernel::device_contraction_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_contraction_bilinear_fp64 contraction_bilinear_fp64.cpp)
-target_link_libraries(client_contraction_bilinear_fp64 PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_contraction_bilinear_fp64 PRIVATE composable_kernel::device_other_operations composable_kernel::device_contraction_operations composable_kernel::device_gemm_operations)
 
 add_executable(contraction_g1m2n3k1_add_xdl_fp16 contraction_g1m2n3k1_add_xdl_fp16.cpp)
-target_link_libraries(contraction_g1m2n3k1_add_xdl_fp16 PRIVATE composable_kernel::device_operations)
+target_link_libraries(contraction_g1m2n3k1_add_xdl_fp16 PRIVATE composable_kernel::device_other_operations composable_kernel::device_contraction_operations composable_kernel::device_gemm_operations)
 

client_example/05_layernorm/CMakeLists.txt

 add_executable(client_layernorm2d_fwd layernorm2d_fwd.cpp)
-target_link_libraries(client_layernorm2d_fwd PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_layernorm2d_fwd PRIVATE composable_kernel::device_other_operations)
 
 add_executable(client_layernorm4d_fwd layernorm4d_fwd.cpp)
-target_link_libraries(client_layernorm4d_fwd PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_layernorm4d_fwd PRIVATE composable_kernel::device_other_operations)

client_example/06_softmax/CMakeLists.txt

 add_executable(client_softmax4d softmax4d.cpp)
-target_link_libraries(client_softmax4d PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_softmax4d PRIVATE composable_kernel::device_other_operations composable_kernel::device_reduction_operations)

client_example/07_grouped_convnd_fwd/CMakeLists.txt

 add_executable(client_grouped_conv2d_fwd grouped_conv2d_fwd.cpp)
-target_link_libraries(client_grouped_conv2d_fwd PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_grouped_conv2d_fwd PRIVATE composable_kernel::device_conv_operations)
 
 add_executable(client_grouped_conv1d_fwd grouped_conv1d_fwd.cpp)
-target_link_libraries(client_grouped_conv1d_fwd PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_grouped_conv1d_fwd PRIVATE composable_kernel::device_conv_operations)

client_example/08_fused_attention/CMakeLists.txt

 add_executable(client_fused_attention fused_attention.cpp)
-target_link_libraries(client_fused_attention PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_fused_attention PRIVATE composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_fused_attention_bias fused_attention_bias.cpp)
-target_link_libraries(client_fused_attention_bias PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_fused_attention_bias PRIVATE composable_kernel::device_other_operations composable_kernel::device_gemm_operations)

client_example/09_quantization/CMakeLists.txt

 if(DTYPES MATCHES "int8" OR NOT DEFINED DTYPES)
 add_executable(client_conv2d_fwd_bias_tanh_perchannel_quantization conv2d_fwd_bias_tanh_perchannel_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_bias_tanh_perchannel_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_bias_tanh_perchannel_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_conv2d_fwd_bias_relu_perchannel_quantization conv2d_fwd_bias_relu_perchannel_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_bias_relu_perchannel_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_bias_relu_perchannel_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_conv2d_fwd_bias_tanh_perlayer_quantization conv2d_fwd_bias_tanh_perlayer_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_bias_tanh_perlayer_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_bias_tanh_perlayer_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_conv2d_fwd_bias_relu_perlayer_quantization conv2d_fwd_bias_relu_perlayer_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_bias_relu_perlayer_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_bias_relu_perlayer_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_conv2d_fwd_perchannel_quantization conv2d_fwd_perchannel_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_perchannel_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_perchannel_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_conv2d_fwd_perlayer_quantization conv2d_fwd_perlayer_quantization.cpp)
-target_link_libraries(client_conv2d_fwd_perlayer_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_conv2d_fwd_perlayer_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 
 add_executable(client_gemm_quantization gemm_quantization.cpp)
-target_link_libraries(client_gemm_quantization PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_gemm_quantization PRIVATE composable_kernel::device_conv_operations composable_kernel::device_other_operations composable_kernel::device_gemm_operations)
 endif()

client_example/10_grouped_convnd_bwd_data/CMakeLists.txt

 add_executable(client_grouped_conv2d_bwd_data grouped_conv2d_bwd_data.cpp)
-target_link_libraries(client_grouped_conv2d_bwd_data PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_grouped_conv2d_bwd_data PRIVATE composable_kernel::device_conv_operations)
 
 add_executable(client_grouped_conv3d_bwd_data grouped_conv3d_bwd_data.cpp)
-target_link_libraries(client_grouped_conv3d_bwd_data PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_grouped_conv3d_bwd_data PRIVATE composable_kernel::device_conv_operations)
 
 add_executable(client_grouped_conv3d_bwd_data_input_fp16_comp_bf8f8 grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp)
-target_link_libraries(client_grouped_conv3d_bwd_data_input_fp16_comp_bf8f8 PRIVATE composable_kernel::device_operations)
+target_link_libraries(client_grouped_conv3d_bwd_data_input_fp16_comp_bf8f8 PRIVATE composable_kernel::device_conv_operations)