ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-05 14:11:29 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix pk_int4 cast and add pk_int4 dtype in ck tile (#1854)

Browse Source 
* Fix pk_int4 cast and add pk_int4 dtype in ck tile

* fixes

* Improvements

* fix typo
This commit is contained in:
Bartłomiej Kocot
2025-02-04 10:32:07 +01:00
committed by GitHub
parent 9c5b2f3936
commit 9ee69dd297
12 changed files with 406 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
test/ck_tile/CMakeLists.txt
View File

@@ -2,3 +2,4 @@ add_subdirectory(image_to_column)
add_subdirectory(gemm)
add_subdirectory(batched_gemm)
add_subdirectory(grouped_gemm)
add_subdirectory(data_type)

4
test/ck_tile/data_type/CMakeLists.txt Normal file
View File

@@ -0,0 +1,4 @@
# Currently ck_tile is only built on gfx9
if(GPU_TARGETS MATCHES "gfx9")
add_gtest_executable(test_ck_tile_pk_int4 test_pk_int4.cpp)
endif()

65
test/ck_tile/data_type/test_pk_int4.cpp Normal file
View File

@@ -0,0 +1,65 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
#include "gtest/gtest.h"
#include <hip/hip_runtime.h>
#include "ck_tile/core.hpp"
using ck_tile::bf16_t;
using ck_tile::bf16x2_t;
using ck_tile::fp16x2_t;
using ck_tile::fp32x2_t;
using ck_tile::half_t;
using ck_tile::pk_int4_t;
TEST(PackedInt4, ConvertToFloat)
{
#ifdef CK_TILE_USE_PK4_LAYOUT_SHUFFLE
constexpr float first_input_val = 7.f;
constexpr float second_input_val = -1.f;
#else
constexpr float first_input_val = -1.f;
constexpr float second_input_val = 7.f;
#endif
uint8_t data = 0b11110111; // {-1, 7}
pk_int4_t in = ck_tile::bit_cast<int8_t>(data);
fp32x2_t out = ck_tile::pk_int4_t_to_fp32x2_t(in);
EXPECT_EQ(out.x, first_input_val);
EXPECT_EQ(out.y, second_input_val);
}
TEST(PackedInt4, ConvertToHalf)
{
#ifdef CK_TILE_USE_PK4_LAYOUT_SHUFFLE
const half_t first_input_val = ck_tile::type_convert<half_t>(7.f);
const half_t second_input_val = ck_tile::type_convert<half_t>(-1.f);
#else
const half_t first_input_val = ck_tile::type_convert<half_t>(-1.f);
const half_t second_input_val = ck_tile::type_convert<half_t>(7.f);
#endif
uint8_t data = 0b11110111; // {-1, 7}
pk_int4_t in = ck_tile::bit_cast<int8_t>(data);
fp16x2_t out = ck_tile::pk_int4_t_to_halfx2_t(in);
EXPECT_EQ(out.x, first_input_val);
EXPECT_EQ(out.y, second_input_val);
}
TEST(PackedInt4, ConvertToBHalf)
{
#ifdef CK_TILE_USE_PK4_LAYOUT_SHUFFLE
const bf16_t first_input_val = ck_tile::type_convert<bf16_t>(7.f);
const bf16_t second_input_val = ck_tile::type_convert<bf16_t>(-1.f);
#else
const bf16_t first_input_val = ck_tile::type_convert<bf16_t>(-1.f);
const bf16_t second_input_val = ck_tile::type_convert<bf16_t>(7.f);
#endif
uint8_t data = 0b11110111; // {-1, 7}
pk_int4_t in = ck_tile::bit_cast<int8_t>(data);
bf16x2_t out = ck_tile::pk_int4_t_to_bfloat16x2_t(in);
EXPECT_EQ(out.x, first_input_val);
EXPECT_EQ(out.y, second_input_val);
}