From 4ee8b1599dbaf7634d25607fa5ac96ba3dc6b0f2 Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Fri, 16 Jul 2021 16:16:43 +0100 Subject: Update GEMM assembly kernels - Introduce Fp32 kernels with internal calculations in Bfloat16 when fast_mode is enabled - Improve kernel selection heuristics Signed-off-by: Georgios Pinitas Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965 Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins --- src/runtime/NEON/functions/NEConvolutionLayer.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/runtime/NEON/functions/NEConvolutionLayer.cpp') diff --git a/src/runtime/NEON/functions/NEConvolutionLayer.cpp b/src/runtime/NEON/functions/NEConvolutionLayer.cpp index 1022e397d0..e88bd3b5d4 100644 --- a/src/runtime/NEON/functions/NEConvolutionLayer.cpp +++ b/src/runtime/NEON/functions/NEConvolutionLayer.cpp @@ -67,7 +67,7 @@ void NEConvolutionLayer::configure(ITensor *input, const ITensor *weights, const case ConvolutionMethod::GEMM: { auto f = std::make_unique(_memory_manager); - f->configure(input, weights, biases, output, conv_info, weights_info, dilation, act_info); + f->configure(input, weights, biases, output, conv_info, weights_info, dilation, act_info, enable_fast_math); _function = std::move(f); break; } -- cgit v1.2.1