Skip to content

GitLab

Commit 9b3a0d42 authored by Artur Wojcik's avatar Artur Wojcik
Browse files

Merge branch 'develop' into uif2-initial

parents 16e39ac5 ff24b537
Hide whitespace changes
Inline Side-by-side
Showing with 74 additions and 70 deletions
CMakeLists.txt
View file @ 9b3a0d42
...@@ -377,10 +377,9 @@ include_directories(BEFORE ...@@ -377,10 +377,9 @@ include_directories(BEFORE
SET(BUILD_DEV ON CACHE BOOL "BUILD_DEV") SET(BUILD_DEV ON CACHE BOOL "BUILD_DEV")
if(BUILD_DEV) if(BUILD_DEV)
add_compile_options(-Werror -Weverything) add_compile_options(-Werror)
add_compile_options(-Weverything)
endif() endif()
#add flags to reduce the size of binaries
add_compile_options(-Oz -flto=thin)
message("CMAKE_CXX_FLAGS: ${CMAKE_CXX_FLAGS}") message("CMAKE_CXX_FLAGS: ${CMAKE_CXX_FLAGS}")
add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND} --output-on-failure -C ${CMAKE_CFG_INTDIR}) add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND} --output-on-failure -C ${CMAKE_CFG_INTDIR})
......
Dockerfile
View file @ 9b3a0d42
...@@ -111,7 +111,7 @@ ENV compiler_commit=$compiler_commit ...@@ -111,7 +111,7 @@ ENV compiler_commit=$compiler_commit
RUN sh -c "echo compiler version = '$compiler_version'" RUN sh -c "echo compiler version = '$compiler_version'"
RUN sh -c "echo compiler commit = '$compiler_commit'" 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 && \ git clone -b "$compiler_version" https://github.com/RadeonOpenCompute/llvm-project.git && \
cd llvm-project && mkdir build && cd build && \ cd llvm-project && mkdir build && cd build && \
cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \ cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \
...@@ -119,7 +119,7 @@ RUN if [ "$compiler_version" = "amd-stg-open" ] && [ "$compiler_commit" = "" ]; ...@@ -119,7 +119,7 @@ RUN if [ "$compiler_version" = "amd-stg-open" ] && [ "$compiler_commit" = "" ];
else echo "using the release compiler"; \ else echo "using the release compiler"; \
fi fi
RUN if [ "$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 && \ git clone -b "$compiler_version" https://github.com/RadeonOpenCompute/llvm-project.git && \
cd llvm-project && git checkout "$compiler_commit" && echo "checking out commit $compiler_commit" && mkdir build && cd build && \ cd llvm-project && git checkout "$compiler_commit" && echo "checking out commit $compiler_commit" && mkdir build && cd build && \
cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \ cmake -DCMAKE_INSTALL_PREFIX=/opt/rocm/llvm -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=1 -DLLVM_TARGETS_TO_BUILD="AMDGPU;X86" -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_ENABLE_RUNTIMES="compiler-rt" ../llvm && \
......
Jenkinsfile
View file @ 9b3a0d42
...@@ -84,7 +84,7 @@ def build_compiler(){ ...@@ -84,7 +84,7 @@ def build_compiler(){
compiler = '/opt/rocm/bin/hipcc' compiler = '/opt/rocm/bin/hipcc'
} }
else{ else{
if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){ if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
compiler = "/llvm-project/build/bin/clang++" compiler = "/llvm-project/build/bin/clang++"
} }
else{ else{
...@@ -293,7 +293,7 @@ def buildHipClangJob(Map conf=[:]){ ...@@ -293,7 +293,7 @@ def buildHipClangJob(Map conf=[:]){
dockerOpts = dockerOpts + " --env HSA_XNACK=1 " dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
} }
def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' " def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' "
if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){ if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' " dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
} }
...@@ -348,7 +348,7 @@ def runCKProfiler(Map conf=[:]){ ...@@ -348,7 +348,7 @@ def runCKProfiler(Map conf=[:]){
dockerOpts = dockerOpts + " --env HSA_XNACK=1 " dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
} }
def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' " def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' "
if (params.COMPILER_VERSION == "amd-stg-open" || params.COMPILER_COMMIT != ""){ if (params.COMPILER_VERSION != "" || params.COMPILER_COMMIT != ""){
dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' " dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
} }
...@@ -479,7 +479,7 @@ def Build_CK(Map conf=[:]){ ...@@ -479,7 +479,7 @@ def Build_CK(Map conf=[:]){
dockerOpts = dockerOpts + " --env HSA_XNACK=1 " dockerOpts = dockerOpts + " --env HSA_XNACK=1 "
} }
def dockerArgs = "--build-arg PREFIX=${prefixpath} --build-arg compiler_version='${params.COMPILER_VERSION}' --build-arg compiler_commit='${params.COMPILER_COMMIT}' --build-arg ROCMVERSION='${params.ROCMVERSION}' " def dockerArgs = "--build-arg PREFIX=${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' " dockerOpts = dockerOpts + " --env HIP_CLANG_PATH='/llvm-project/build/bin' "
} }
...@@ -657,7 +657,8 @@ def process_results(Map 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 //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= 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 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 { pipeline {
agent none agent none
...@@ -679,15 +680,15 @@ pipeline { ...@@ -679,15 +680,15 @@ pipeline {
string( string(
name: 'COMPILER_VERSION', name: 'COMPILER_VERSION',
defaultValue: '', 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( string(
name: 'COMPILER_COMMIT', name: 'COMPILER_COMMIT',
defaultValue: '', 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( string(
name: 'BUILD_COMPILER', name: 'BUILD_COMPILER',
defaultValue: 'hipcc', defaultValue: 'clang',
description: 'Specify whether to build CK with hipcc (default) or with clang.') description: 'Specify whether to build CK with hipcc or with clang (default).')
booleanParam( booleanParam(
name: "RUN_FULL_QA", name: "RUN_FULL_QA",
defaultValue: false, defaultValue: false,
......
library/include/ck/library/tensor_operation_instance/gpu/grouped_convolution_forward_scaleadd_ab.hpp
View file @ 9b3a0d42
...@@ -23,19 +23,20 @@ using ScaleAdd = ck::tensor_operation::element_wise::ScaleAdd; ...@@ -23,19 +23,20 @@ using ScaleAdd = ck::tensor_operation::element_wise::ScaleAdd;
#ifdef CK_ENABLE_BF16 #ifdef CK_ENABLE_BF16
// grouped conv3d forward multi AB scaleadd, NDHWGC/GKZYXC/NDHWGK // grouped conv3d forward multi AB scaleadd, NDHWGC/GKZYXC/NDHWGK
void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances( // TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3, // void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
NDHWGC, // std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
GKZYXC, // NDHWGC,
ck::Tuple<>, // GKZYXC,
NDHWGK, // ck::Tuple<>,
ck::Tuple<BF16, BF16>, // NDHWGK,
ck::Tuple<BF16, BF16>, // ck::Tuple<BF16, BF16>,
ck::Tuple<>, // ck::Tuple<BF16, BF16>,
BF16, // ck::Tuple<>,
ScaleAdd, // BF16,
ScaleAdd, // ScaleAdd,
PassThrough>>>& instances); // ScaleAdd,
// PassThrough>>>& instances);
#endif #endif
#ifdef CK_ENABLE_FP16 #ifdef CK_ENABLE_FP16
...@@ -151,13 +152,15 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe ...@@ -151,13 +152,15 @@ struct DeviceOperationInstanceFactory<ck::tensor_operation::device::DeviceGroupe
} }
#endif #endif
#ifdef CK_ENABLE_BF16 #ifdef CK_ENABLE_BF16
if constexpr(is_same_v<InDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> && // TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
is_same_v<WeiDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> && // if constexpr(is_same_v<InDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
is_same_v<OutDataType, ck::bhalf_t> && is_same_v<ComputeType, ck::bhalf_t>) // is_same_v<WeiDataType, ck::Tuple<ck::bhalf_t, ck::bhalf_t>> &&
{ // is_same_v<OutDataType, ck::bhalf_t> && is_same_v<ComputeType,
add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances( // ck::bhalf_t>)
op_ptrs); // {
} // add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
// op_ptrs);
// }
#endif #endif
#ifdef CK_ENABLE_INT8 #ifdef CK_ENABLE_INT8
if constexpr(is_same_v<InDataType, ck::Tuple<int8_t, int8_t>> && if constexpr(is_same_v<InDataType, ck::Tuple<int8_t, int8_t>> &&
......
library/src/tensor_operation_instance/gpu/grouped_conv3d_fwd_scaleadd_ab/xdl/device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instance.cpp
View file @ 9b3a0d42
...@@ -9,42 +9,43 @@ namespace tensor_operation { ...@@ -9,42 +9,43 @@ namespace tensor_operation {
namespace device { namespace device {
namespace instance { namespace instance {
void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances( // TODO: Workaround for https://ontrack-internal.amd.com/browse/SWDEV-435347
std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3, // void add_device_grouped_conv3d_fwd_xdl_scaleadd_ab_ndhwgc_gkzyxc_ndhwgk_bf16_instances(
NDHWGC, // std::vector<std::unique_ptr<DeviceGroupedConvFwdMultipleABD<3,
GKZYXC, // NDHWGC,
ck::Tuple<>, // GKZYXC,
NDHWGK, // ck::Tuple<>,
ck::Tuple<BF16, BF16>, // NDHWGK,
ck::Tuple<BF16, BF16>, // ck::Tuple<BF16, BF16>,
ck::Tuple<>, // ck::Tuple<BF16, BF16>,
BF16, // ck::Tuple<>,
ScaleAdd, // BF16,
ScaleAdd, // ScaleAdd,
PassThrough>>>& instances) // ScaleAdd,
{ // PassThrough>>>& instances)
add_device_operation_instances( // {
instances, // add_device_operation_instances(
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3, // instances,
NDHWGC, // device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
GKZYXC, // NDHWGC,
NDHWGK, // GKZYXC,
ConvFwdDefault>{}); // NDHWGK,
add_device_operation_instances( // ConvFwdDefault>{});
instances, // add_device_operation_instances(
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3, // instances,
NDHWGC, // device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
GKZYXC, // NDHWGC,
NDHWGK, // GKZYXC,
ConvFwd1x1P0>{}); // NDHWGK,
add_device_operation_instances( // ConvFwd1x1P0>{});
instances, // add_device_operation_instances(
device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3, // instances,
NDHWGC, // device_grouped_conv_fwd_xdl_scaleadd_ab_bf16_instances<3,
GKZYXC, // NDHWGC,
NDHWGK, // GKZYXC,
ConvFwd1x1S1P0>{}); // NDHWGK,
} // ConvFwd1x1S1P0>{});
// }
} // namespace instance } // namespace instance
} // namespace device } // namespace device
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment