derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
main
TheRock/rocm-libraries/shared/rocroller/test/unit/GEMMJammedTest.cpp
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

344 lines
8.3 KiB
C++
Raw Permalink Blame History

// Copyright Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#ifdef ROCROLLER_USE_HIP
#include <hip/hip_ext.h>
#include <hip/hip_runtime.h>
#endif /* ROCROLLER_USE_HIP */
#include "GEMMTestBase.hpp"
namespace GEMMTests
{
using namespace rocRoller;
namespace SolutionParams = rocRoller::Parameters::Solution;
// ========================================================================
// GEMMJammedTestSuite
// ========================================================================
class GEMMJammedTestSuite : public BaseGEMMContextFixture<>
{
};
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_2x2)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 2 * gemm.wavefrontSize;
gemm.workgroupSizeY = 4;
gemm.loadPathA = SolutionParams::LoadPath::BufferToVGPR;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
gemm.fuseLoops = false;
basicGEMM<Half>(gemm);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_2x1)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 128;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 2 * gemm.wavefrontSize;
gemm.workgroupSizeY = 4;
gemm.betaInFma = false;
gemm.transA = "T";
gemm.transB = "N";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b64"), 18);
EXPECT_EQ(countSubstring(generatedCode, "ds_read_b128"), 8);
EXPECT_EQ(countSubstring(generatedCode, "buffer_store_dwordx4"), 8);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_2x1_UnrollK)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 128;
gemm.macK = 16;
gemm.unrollK = 2;
gemm.waveK = 8;
gemm.workgroupSizeX = 2 * gemm.wavefrontSize;
gemm.workgroupSizeY = 4;
gemm.transA = "T";
gemm.transB = "N";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b64"), 22);
EXPECT_EQ(countSubstring(generatedCode, "ds_read_b128"), 8);
EXPECT_EQ(countSubstring(generatedCode, "buffer_store_dwordx4"), 8);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_1x2)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 128;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 4 * gemm.wavefrontSize;
gemm.workgroupSizeY = 2;
gemm.transA = "T";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b64"), 18);
EXPECT_EQ(countSubstring(generatedCode, "ds_read_b128"), 8);
EXPECT_EQ(countSubstring(generatedCode, "buffer_store_dwordx4"), 8);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_1x2_UnrollK)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 128;
gemm.macK = 16;
gemm.unrollK = 4;
gemm.waveK = 8;
gemm.workgroupSizeX = 4 * gemm.wavefrontSize;
gemm.workgroupSizeY = 2;
gemm.transA = "T";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b64"), 26);
EXPECT_EQ(countSubstring(generatedCode, "ds_read_b128"), 8);
EXPECT_EQ(countSubstring(generatedCode, "buffer_store_dwordx4"), 8);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_1x8)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 4 * gemm.wavefrontSize;
gemm.workgroupSizeY = 1;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
basicGEMM<Half>(gemm);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_1x8_UnrollK)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.unrollK = 2;
gemm.waveK = 8;
gemm.workgroupSizeX = 4 * gemm.wavefrontSize;
gemm.workgroupSizeY = 1;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
basicGEMM<Half>(gemm);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_2x4)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 2 * gemm.wavefrontSize;
gemm.workgroupSizeY = 2;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b128"), 3);
EXPECT_EQ(countSubstring(generatedCode, "v_pack_b32_f16"), 152);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_2x4_UnrollK)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.unrollK = 2;
gemm.prefetchInFlight = 2;
gemm.prefetchLDSFactor = 2;
gemm.prefetchMixMemOps = true;
gemm.waveK = 8;
gemm.workgroupSizeX = 2 * gemm.wavefrontSize;
gemm.workgroupSizeY = 2;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b128"), 9);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_4x2)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.waveK = 8;
gemm.workgroupSizeX = 1 * gemm.wavefrontSize;
gemm.workgroupSizeY = 4;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
gemm.transB = "N";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b128"), 3);
}
TEST_P(GEMMJammedTestSuite, GPU_GEMM_Jammed_4x2_UnrollK)
{
REQUIRE_ARCH_CAP(GPUCapability::HasMFMA);
GEMMProblem gemm;
gemm.m = 256;
gemm.n = 512;
gemm.k = 64;
gemm.macM = 128;
gemm.macN = 256;
gemm.macK = 16;
gemm.unrollK = 4;
gemm.waveK = 8;
gemm.workgroupSizeX = 1 * gemm.wavefrontSize;
gemm.workgroupSizeY = 4;
gemm.storePath = SolutionParams::StorePath::VGPRToGlobalMemoryWithBuffer;
gemm.transB = "N";
basicGEMM<Half>(gemm);
std::string generatedCode = m_context->instructions()->toString();
EXPECT_EQ(countSubstring(generatedCode, "ds_write_b128"), 15);
}
INSTANTIATE_TEST_SUITE_P(GEMMJammedTest, GEMMJammedTestSuite, currentGPUISA());
} // namespace GEMMTests
Reference in new issue View Git Blame Copy Permalink