ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 13:11:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Clean DTYPES conditions in CMake (#974)

Browse Source 
* Add a condition to build fp8 instances

* simplified buffer_load/store

* add bfp8/fp8

* fixed

* remove all f8/bf8 condition include folder

* fixed cmake conditions

* fixed DTYPES=fp16/bfp16

* fix

* fixed buffer_load

* fixed buffer_store

* fix

* clean example cmake files

* fixed ci

* fixed cit

---------

Co-authored-by: Rostyslav Geyyer <rosty.geyyer@amd.com>
Co-authored-by: Jing Zhang <jizha@amd.com>
This commit is contained in:
zjing14
2023-10-18 11:14:14 -05:00
committed by GitHub
parent 1cc36ba5fb
commit bf435140dc
37 changed files with 558 additions and 710 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
include/ck/tensor_operation/gpu/element/unary_element_wise_operation.hpp
View File

@@ -113,7 +113,6 @@ struct PassThrough
}
#endif
#if defined CK_ENABLE_FP8
template <>
__host__ __device__ void operator()<f8_t, f8_t>(f8_t& y, const f8_t& x) const
{
@@ -143,9 +142,7 @@ struct PassThrough
{
y = type_convert<f8_t>(x);
}
#endif
#if defined CK_ENABLE_BF8
template <>
__host__ __device__ void operator()<bf8_t, bf8_t>(bf8_t& y, const bf8_t& x) const
{
@@ -175,7 +172,6 @@ struct PassThrough
{
y = ck::type_convert<bf8_t>(x);
}
#endif
};
struct UnaryConvert
@@ -204,7 +200,6 @@ struct ConvertBF16RTN
}
};
#if defined CK_ENABLE_FP8
struct ConvertF8SR
{
// convert to fp8 using stochastic rounding (SR)
@@ -221,7 +216,6 @@ struct ConvertF8SR
y = f8_convert_sr<Y>(x);
}
};
#endif
struct Scale
{