amd/blis
1
0
Fork 0
mirror of https://github.com/amd/blis.git synced 2026-05-11 17:50:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Vectorized and parallelized zdscal routine

Browse Source 
- Implemented optimized intrinsic kernel for zdscalv for the cases where AVX2 is supported.
- Also added multithreaded support for the same.
- The optimal number of threads is being calculated on the basis of input size.

AMD-Internal: [CPUPL-2602]
Change-Id: I4d05c3b1cc365a7770703286a89c6dce3875c067
This commit is contained in:
Arnav Sharma
2022-09-29 23:32:10 +05:30
committed by Arnav Sharma
parent 9c292b79e2
commit 90f915d3a9
4 changed files with 403 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
frame/include/bli_gentfunc_macro_defs.h
View File

@@ -159,8 +159,8 @@ GENTFUNCR2( dcomplex, double, z, d, blasname, blisname )
\
GENTFUNCSCAL( scomplex, scomplex, c, , blasname, blisname ) \
GENTFUNCSCAL( dcomplex, dcomplex, z, , blasname, blisname ) \
GENTFUNCSCAL( scomplex, float, c, s, blasname, blisname ) \
GENTFUNCSCAL( dcomplex, double, z, d, blasname, blisname )
GENTFUNCSCAL( scomplex, float, c, s, blasname, blisname )
// GENTFUNCSCAL( dcomplex, double, z, d, blasname, blisname )
#define INSERT_GENTFUNCSCAL_BLAS( blasname, blisname ) \