haraldwolff/CLBlast
1
0
Fork 0
mirror of https://github.com/CNugteren/CLBlast.git synced 2024-07-07 12:23:46 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fixed an issue with computing the GFLOPS numbers for the xGEMM performance tests for non-square matrices

Browse source
This commit is contained in:
cnugteren 2016-05-08 10:06:06 +02:00
parent ed2904a344
commit 1acb31896c
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
test/routines/level3/xgemm.h
View file

@ -153,10 +153,10 @@ class TestXgemm {
// Describes how to compute performance metrics
static size_t GetFlops(const Arguments<T> &args) {
return 2 * args.m * args.n * args.m;
return 2 * args.m * args.n * args.k;
}
static size_t GetBytes(const Arguments<T> &args) {
return (args.m*args.m + args.m*args.n + 2*args.m*args.n) * sizeof(T);
return (args.m*args.k + args.k*args.n + 2*args.m*args.n) * sizeof(T);
}
};