From 7b4d547800d3ea49e7e6d9f497ec2766411cb948 Mon Sep 17 00:00:00 2001
From: Gian Marco <gianmarco.iodice@arm.com>
Date: Wed, 10 Jan 2018 15:56:30 +0000
Subject: COMPMID-816 - Optimizing CLGEMMLowpMatrixMultiplyCore - Part1

The performance improvements have been reported at the following
confluence page:

https://confluence.arm.com/display/MLENG/GEMMLowp+performance%3A+ACL+18.02

Config3 of McVail looks improved by 29x

Change-Id: I8b203c0b75fc368f85cea863b7eed398fab3e79a
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115783
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
---
 src/core/CL/CLKernelLibrary.cpp | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'src/core/CL/CLKernelLibrary.cpp')

diff --git a/src/core/CL/CLKernelLibrary.cpp b/src/core/CL/CLKernelLibrary.cpp
index 22a328bcaf..6695881d09 100644
--- a/src/core/CL/CLKernelLibrary.cpp
+++ b/src/core/CL/CLKernelLibrary.cpp
@@ -235,7 +235,8 @@ const std::map<std::string, std::string> CLKernelLibrary::_kernel_program_map =
     { "gemm_transpose1x4", "gemm.cl" },
     { "gemmlowp_matrix_a_reduction", "gemmlowp.cl" },
     { "gemmlowp_matrix_b_reduction", "gemmlowp.cl" },
-    { "gemmlowp_mm", "gemmlowp.cl" },
+    { "gemmlowp_mm_bifrost", "gemmlowp.cl" },
+    { "gemmlowp_mm_midgard", "gemmlowp.cl" },
     { "gemmlowp_mm_interleaved_transposed", "gemmlowp.cl" },
     { "gemmlowp_offset_contribution", "gemmlowp.cl" },
     { "gemmlowp_output_stage_quantize_down", "gemmlowp.cl" },
-- 
cgit v1.2.1