From 1d25ed54a948639d1894c8b021940df70005d519 Mon Sep 17 00:00:00 2001 From: Gian Marco Date: Sat, 16 Dec 2017 19:33:50 +0000 Subject: 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 Reviewed-by: Michalis Spyrou Reviewed-by: Anthony Barbier --- arm_compute/runtime/CL/functions/CLConvolutionLayer.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to '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 a8a04a0bbf..3fe6604db9 100644 --- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h +++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h @@ -138,10 +138,9 @@ private: 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__ */ -- cgit v1.2.1