From 3ecf9fefa6f6299a0736599f150d4791cc8345d9 Mon Sep 17 00:00:00 2001 From: Giorgio Arena Date: Wed, 28 Apr 2021 16:11:51 +0100 Subject: Remove OpenCL padding: CLReductionOperationKernel Change the parallel implementation across the X, now every thread computes one row Add missing test for MEAN_SUM Make reduction on any axis != 0 work with num_channels > 1 Resolve COMPMID-3917 Signed-off-by: Giorgio Arena Change-Id: Ib0f99540104e3c253bcd1ea637833db533f5e76e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5522 Comments-Addressed: Arm Jenkins Reviewed-by: Manuel Bottini Reviewed-by: Gian Marco Iodice Tested-by: Arm Jenkins --- src/core/CL/cl_kernels/helpers_asymm.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'src/core/CL/cl_kernels/helpers_asymm.h') diff --git a/src/core/CL/cl_kernels/helpers_asymm.h b/src/core/CL/cl_kernels/helpers_asymm.h index 27878cde36..562c5d3236 100644 --- a/src/core/CL/cl_kernels/helpers_asymm.h +++ b/src/core/CL/cl_kernels/helpers_asymm.h @@ -425,9 +425,22 @@ QUANTIZE_IMPL(uchar, 1) QUANTIZE_IMPL(char, 1) QUANTIZE_IMPL(uint, 1) QUANTIZE_IMPL(int, 1) +QUANTIZE_IMPL(uchar, 2) +QUANTIZE_IMPL(char, 2) +QUANTIZE_IMPL(uint, 2) +QUANTIZE_IMPL(int, 2) +QUANTIZE_IMPL(uchar, 3) +QUANTIZE_IMPL(char, 3) +QUANTIZE_IMPL(uint, 3) +QUANTIZE_IMPL(int, 3) QUANTIZE_IMPL(uchar, 4) QUANTIZE_IMPL(ushort, 4) QUANTIZE_IMPL(short, 4) +QUANTIZE_IMPL(int, 4) +QUANTIZE_IMPL(uchar, 8) +QUANTIZE_IMPL(char, 8) +QUANTIZE_IMPL(uint, 8) +QUANTIZE_IMPL(int, 8) QUANTIZE_IMPL(uchar, 16) QUANTIZE_IMPL(char, 16) QUANTIZE_IMPL(ushort, 16) @@ -439,9 +452,22 @@ DEQUANTIZE_IMPL(uchar, 1) DEQUANTIZE_IMPL(char, 1) DEQUANTIZE_IMPL(uint, 1) DEQUANTIZE_IMPL(int, 1) +DEQUANTIZE_IMPL(uchar, 2) +DEQUANTIZE_IMPL(char, 2) +DEQUANTIZE_IMPL(uint, 2) +DEQUANTIZE_IMPL(int, 2) +DEQUANTIZE_IMPL(uchar, 3) +DEQUANTIZE_IMPL(char, 3) +DEQUANTIZE_IMPL(uint, 3) +DEQUANTIZE_IMPL(int, 3) DEQUANTIZE_IMPL(uchar, 4) DEQUANTIZE_IMPL(ushort, 4) DEQUANTIZE_IMPL(short, 4) +DEQUANTIZE_IMPL(int, 4) +DEQUANTIZE_IMPL(uchar, 8) +DEQUANTIZE_IMPL(char, 8) +DEQUANTIZE_IMPL(uint, 8) +DEQUANTIZE_IMPL(int, 8) DEQUANTIZE_IMPL(uchar, 16) DEQUANTIZE_IMPL(char, 16) DEQUANTIZE_IMPL(ushort, 16) -- cgit v1.2.1