From c1c4bc5d209280e4ec9be5c0a26f7c94077a6b20 Mon Sep 17 00:00:00 2001 From: Cedric Nugteren Date: Mon, 3 Oct 2016 19:32:01 +0200 Subject: Re-organised GEMM direct kernel and added faster fall-back version for incomplete rectangles --- src/tuning/kernels/xgemm_direct.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'src/tuning/kernels') diff --git a/src/tuning/kernels/xgemm_direct.cpp b/src/tuning/kernels/xgemm_direct.cpp index c6948ef5..204e0be4 100644 --- a/src/tuning/kernels/xgemm_direct.cpp +++ b/src/tuning/kernels/xgemm_direct.cpp @@ -35,6 +35,7 @@ class TuneXgemmDirect { #include "../src/kernels/common.opencl" #include "../src/kernels/level3/xgemm_direct_part1.opencl" #include "../src/kernels/level3/xgemm_direct_part2.opencl" + #include "../src/kernels/level3/xgemm_direct_part3.opencl" ; } -- cgit v1.2.3