youngkingdom/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

CUTLASS 2.10 updates (#622)

Browse Source 
Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
This commit is contained in:
ANIKET SHIVAM
2022-09-12 18:26:30 -07:00
committed by GitHub
parent beae168f90
commit e773429f7e
96 changed files with 8365 additions and 1667 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/util/include/cutlass/util/reference/device/gemm_planar_complex.h
View File

@ -183,7 +183,7 @@ __global__ void GemmPlanarComplex(
ComplexC d_ij;
d_ij.real() = convert_op(result.real());
d_ij.imag() = convert_op(result.imag());;
d_ij.imag() = convert_op(result.imag());
tensor_d.at(coord) = d_ij;
}

2
tools/util/include/cutlass/util/reference/host/gemm_planar_complex.h
View File

@ -172,7 +172,7 @@ void GemmPlanarComplex(
complex<ScalarType> result = alpha * acc + beta * src;
d_ij.real() = convert_op(result.real());
d_ij.imag() = convert_op(result.imag());;
d_ij.imag() = convert_op(result.imag());
tensor_d.at(coord) = d_ij;
}