commit 1d25ed54a948639d1894c8b021940df70005d519
author Gian Marco <gianmarco.iodice@arm.com> Sat Dec 16 19:33:50 2017 +0000
committer Anthony Barbier <anthony.barbier@arm.com> Fri Nov 02 16:42:33 2018 +0000
tree 96a29126c5b61299d64496fad7f6844412ab2cca
parent 57b20109108a90113d29d21ce7d3c873ff19749c

COMPMID-759 - CLGEMM optimization for McVail benchmarks

This patch introduces an optimization for CLGEMM on Bifrost
architectures which can bring to 40% of FMA utilization on
config 3 of McVail. The new CLGEMM does not require any reshape of
matrix A and matrix B.

This patch also adds the auto-config in CLConvolutionLayer and CLGEMM
and extends the interface for NEGEMM and CLGEMM.

Change-Id: Ibb354eda45e9ca64b14a99700fb21dff5989dda9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113716
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>

arm_compute/runtime/CL/functions/CLConvolutionLayer.h

diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index a8a04a0..3fe6604 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -138,10 +138,9 @@
     CLTensor _gemm_output;
     CLTensor _tmp_output;
 
-    bool _append_bias;
-    bool _is_fully_connected_convolution;
     bool _are_weights_reshaped;
     bool _is_quantized;
+    bool _is_interleaved_transposed;
 };
 }
 #endif /* __ARM_COMPUTE_CLCONVOLUTIONLAYER_H__ */