From 93b75e0c072c3cc5654fcdf6aed1068b40012081 Mon Sep 17 00:00:00 2001 From: Michele Di Giorgio Date: Mon, 21 Jun 2021 12:00:43 +0100 Subject: Port NEGEMM to memory injecting interface (Part 1) - Start porting NEGEMM to the new API - Port NEGEMMInterleave4x4Kernel to the new API - Port NEGEMMMatrixAdditionKernel to the new API - Port NEGEMMTranspose1xWKernel to the new API - Remove padding from NEGEMMMatrixAdditionKernel - Remove unused INESimpleKernel and ICPPSimpleKernel Partially resolves: COMPMID-4402 Change-Id: I63edadddfe00a54586e5384d6a0211db25ae9042 Signed-off-by: Michele Di Giorgio Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5857 Reviewed-by: Georgios Pinitas Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins --- src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp') diff --git a/src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp b/src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp index b95bdd4ca5..6bcf59ee96 100644 --- a/src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp +++ b/src/core/NEON/kernels/NEGEMMLowpMatrixMultiplyKernel.cpp @@ -686,7 +686,7 @@ void inline matrix_multiply_s8(Iterator &ina, Iterator &inb, Iterator &out, int const auto width_out = static_cast(out_info.dimension(0)); const auto height_out = static_cast(out_info.dimension(1)); const size_t out_stride = out_info.strides_in_bytes()[1] / out_info.element_size(); - // The implementation assumes that the matrix A and Matrix B have been reshaped respectively with NEGEMMInterleave4x4 and NEGEMMTranspose1xW + // The implementation assumes that the matrix A and Matrix B have been reshaped respectively with CpuGemmInterleave4x4 and CpuGemmTranspose1xW // The reshaping of the matrices helps to have a cache friendly implementation and helps to avoid the data re-arrangements needed for computing 16x4 elements per iteration // All the values needed for computing a single 4x4 block will be read from consecutive memory positions execute_window_loop(window, [&](const Coordinates & id) -- cgit v1.2.1