ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 13:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix wmma gemm int8; add grouped conv int8 example (#716)

Browse Source
This commit is contained in:
Haocong WANG
2023-05-30 20:18:53 +08:00
committed by GitHub
parent 1344a0f25b
commit 6eef0755c9
3 changed files with 31 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
include/ck/tensor_operation/gpu/warp/wmma_gemm.hpp
View File

@@ -262,12 +262,12 @@ struct wmma_type<WmmaInstr::wmma_i32_16x16x16_iu8,
template <index_t MPerWmma,
index_t NPerWmma,
bool neg_a,
bool neg_b,
bool clamp,
class FloatA,
class FloatB,
class FloatC>
class FloatC,
bool neg_a = false,
bool neg_b = false,
bool clamp = false>
__device__ void run(const FloatA& a, const FloatB& b, FloatC& reg_c) const
{
if constexpr(wave_size == 32)