ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-17 19:40:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Refactor f8_t, add bf8_t (#792)

Browse Source 
* Refactor f8_t to add bf8_t

* Add check_err impl for f8_t

* Update fp8 test

* Format

* Revert the fix

* Update vector_type implementation

* Add bf8 test

* Add bf8, use BitInt types

* Add bf8 conversion methods

* Update type_convert for fp8/bf8

* Add check_err fp8/bf8 support

* Add subnorm fp8 tests

* Add subnorm bf8 tests

* Fix conversion

* Add bf8 cmake bindings

* Add macros to enable build with disabled fp8/bf8

* Remove is_native method

* Update flag combination for mixed precision instances

* Add more flag checks

* Add another flag to a client example

* Add type traits, decouple f8/bf8 casting

* Clean up

* Decouple fp8 and bf8 flags

* Remove more redundant flags

* Remove leftover comments

[ROCm/composable_kernel commit: 62d4af7449]
This commit is contained in:
Rostyslav Geyyer
2023-09-12 17:04:27 -05:00
committed by GitHub
parent e885110f62
commit 2e227b8581
23 changed files with 739 additions and 172 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
client_example/20_splitk_gemm/CMakeLists.txt
View File

@@ -1,2 +1,4 @@
add_executable(client_splitK_gemm splitK_gemm_fp16_f8.cpp)
target_link_libraries(client_splitK_gemm PRIVATE composable_kernel::device_operations)
if((DTYPES MATCHES "fp8" AND DTYPES MATCHES "fp16") OR NOT DEFINED DTYPES)
add_executable(client_splitK_gemm splitK_gemm_fp16_f8.cpp)
target_link_libraries(client_splitK_gemm PRIVATE composable_kernel::device_operations)
endif()