[rocm-libraries] ROCm/rocm-libraries#5445 (commit 2cdbf8b)

[CK_TILE] Support for CompV4 pipeline in Stream-K GEMM
 (#5445)

## Motivation
This PR is extending the pipeline support for Stream-K GEMM by adding
the CompV4 pipeline. Additional pipelines will be added in subsequent
PRs.

## Technical Details

- Enable the CompV4 pipeline by adding an option to set DoubleSMemBuffer
to true if the CompV4 pipeline has been selected as it requires double
buffered shared memory
- Addition of CompV4 pipeline into the extended tests: kernel instances
mirror the existing CompV3/Mem configurations (same layout permutations,
data types, and tile sizes) with the pipeline type set to CompV4.
- Addition of CompV4 pipeline into smoke tests (generated using Tile
Engine)

## Test Plan
These were tested using the existing smoke and extended tests.

## Test Result
All tests passed
## Submission Checklist

- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_bf16_nonpersistent_compv4.cpp

@@ -0,0 +1,18 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKBf16NonPersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKBf16NonPersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKBf16NonPersistentCompV4,
+                 KernelTypesStreamKBf16NonPersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_bf16_persistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKBf16PersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKBf16PersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKBf16PersistentCompV4, KernelTypesStreamKBf16PersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_bf8_nonpersistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKBf8NonPersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKBf8NonPersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKBf8NonPersistentCompV4, KernelTypesStreamKBf8NonPersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_bf8_persistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKBf8PersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKBf8PersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKBf8PersistentCompV4, KernelTypesStreamKBf8PersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_fp16_nonpersistent_compv4.cpp

@@ -0,0 +1,18 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKFp16NonPersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKFp16NonPersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKFp16NonPersistentCompV4,
+                 KernelTypesStreamKFp16NonPersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_fp16_persistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKFp16PersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKFp16PersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKFp16PersistentCompV4, KernelTypesStreamKFp16PersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_fp8_nonpersistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKFp8NonPersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKFp8NonPersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKFp8NonPersistentCompV4, KernelTypesStreamKFp8NonPersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME

test/ck_tile/gemm_streamk/extended_tests/test_gemm_streamk_fp8_persistent_compv4.cpp

@@ -0,0 +1,17 @@
+// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
+// SPDX-License-Identifier: MIT
+
+#include "test_gemm_streamk_common_includes.hpp"
+
+template <typename Tuple>
+class TestCkTileStreamKFp8PersistentCompV4 : public TestCkTileStreamK<Tuple>
+{
+};
+
+#define TEST_SUITE_NAME TestCkTileStreamKFp8PersistentCompV4
+
+TYPED_TEST_SUITE(TestCkTileStreamKFp8PersistentCompV4, KernelTypesStreamKFp8PersistentCompV4);
+
+#include "test_gemm_streamk_extended_cases.inc"
+
+#undef TEST_SUITE_NAME