ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-06 15:54:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Permute elements in a vector

Browse Source
This commit is contained in:
Rostyslav Geyyer
2025-02-13 23:08:19 +00:00
parent 99e771a466
commit bec4968e48
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
include/ck/utility/type_convert.hpp
View File

@@ -962,7 +962,8 @@ inline __host__ __device__ f4x2_t f4_convert_sr(float2_t x, float scale = 1.0f)
f4x2_t f4x2_array[4];
} value{0};
printf("%f, %f\n", x[0], x[1]);
value.bitwise = __builtin_amdgcn_cvt_scalef32_sr_pk_fp4_f32(value.bitwise, x, rng, scale, 0);
value.bitwise = __builtin_amdgcn_cvt_scalef32_sr_pk_fp4_f32(
value.bitwise, float2_t{x[1], x[0]}, rng, scale, 0);
return value.f4x2_array[0];
#else
union