From 05288a2b871ef99f544771621c3bba409b2f70df Mon Sep 17 00:00:00 2001 From: Gian Marco Date: Tue, 21 Nov 2017 10:57:50 +0000 Subject: COMPMID-697 - Rework GEMMLowp interface on OpenCL Reworked the interface of GemmLowp in order to make easy the integration in Android NN - Added support for different output stage - Added validation for both matrix multiplication and output stage - Added bounded relu support in the output stage - Added in32_t bias support - Added optimized path for vector by matrix case This rework is required for: - Convolution quantized - Fully connected quantized Change-Id: I512283d406099cf8c614dd89d0a97ed411143afc Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110625 Reviewed-by: Georgios Pinitas Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com --- src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp') diff --git a/src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp b/src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp index a8395a15cb..81094f8743 100644 --- a/src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp +++ b/src/core/NEON/kernels/NEGEMMLowpReductionKernel.cpp @@ -209,7 +209,7 @@ void NEGEMMLowpMatrixAReductionKernel::run(const Window &window, const ThreadInf uint32x4_t sum_row_u32 = vdupq_n_u32(0); uint32_t sum_row = 0; - const uint8_t *matrix_a = (in.ptr() + id.x() * _input->info()->strides_in_bytes()[1] + +id.y() * _input->info()->strides_in_bytes()[2]); + const uint8_t *matrix_a = (in.ptr() + id.x() * _input->info()->strides_in_bytes()[1] + id.y() * _input->info()->strides_in_bytes()[2]); #if __arm__ asm volatile("PLD [%0, #128*4]" ::"r"(matrix_a)); -- cgit v1.2.1