ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 10:59:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

This commit contains implementation of max pool2d for f8 type (#1506)

Browse Source 
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>

[ROCm/composable_kernel commit: 6834e5ee74]
This commit is contained in:
Mateusz Ozga
2024-09-16 10:15:06 +02:00
committed by GitHub
parent db557ada8b
commit d7326fb525
4 changed files with 47 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
library/src/tensor_operation_instance/gpu/max_pool_bwd/CMakeLists.txt
View File

@@ -2,5 +2,6 @@ set(DEVICE_MAXPOOL_BWD_INSTANCES)
list(APPEND DEVICE_MAXPOOL_BWD_INSTANCES device_max_pool_bwd_f16_instance.cpp
device_max_pool_bwd_bf16_instance.cpp
device_max_pool_bwd_f32_instance.cpp
device_max_pool_bwd_f8_instance.cpp
device_max_pool_bwd_int8_instance.cpp)
add_instance_library(device_max_pool_bwd_instance ${DEVICE_MAXPOOL_BWD_INSTANCES})

20
library/src/tensor_operation_instance/gpu/max_pool_bwd/device_max_pool_bwd_f8_instance.cpp Normal file
View File

@@ -0,0 +1,20 @@
// SPDX-License-Identifier: MIT
// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
#include "max_pool_bwd_instance_common.hpp"
namespace ck {
namespace tensor_operation {
namespace device {
namespace instance {
void add_device_maxpool_bwd_f8_instances(
std::vector<std::unique_ptr<DeviceMaxPoolBwd<F8, I32, F8>>>& instances)
{
add_device_operation_instances(instances, device_maxpool_bwd_instances<F8, I32, F8>{});
}
} // namespace instance
} // namespace device
} // namespace tensor_operation
} // namespace ck