commit ff1fe3e32e25069fed750cdfe3046b7d8d5a2628
author Gian Marco Iodice <gianmarco.iodice@arm.com> Sat Jan 02 09:58:51 2021 +0000
committer Georgios Pinitas <georgios.pinitas@arm.com> Tue Jan 19 13:43:52 2021 +0000
tree 9c01379de63f6ab218c7890dc91b10ac8faac157
parent 6124390be4690ba06c404d56449f7e5d390cef53

Remove padding from direct convolution - OpenCL

- Refactor direct convolution for NHWC
- Remove old kernels for NHWC
- Change the heuristic in CLConvolutionLayer.cpp. The new direct
  convolution implementation is faster than FFT

Resolves COMPMID-3908

Change-Id: Iee15ce7b04e21847b6eaae5c6d3c1b18180e7efc
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4876
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

src/core/CL/cl_kernels/gemmlowp.cl

diff --git a/src/core/CL/cl_kernels/gemmlowp.cl b/src/core/CL/cl_kernels/gemmlowp.cl
index 50dda7e..ad92511 100644
--- a/src/core/CL/cl_kernels/gemmlowp.cl
+++ b/src/core/CL/cl_kernels/gemmlowp.cl
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2020 Arm Limited.
+ * Copyright (c) 2017-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -37,7 +37,6 @@
 
 #if defined(ARM_COMPUTE_OPENCL_DOT8_ENABLED) && defined(cl_arm_integer_dot_product_int8)
 
-/** Specialized macros to perform the dot product instruction between two vectors of size N [1,16]. These macros use the dot8 instruction */
 #define ARM_DOT1(a, b, c)                                                                                                                               \
     ({                                                                                                                                                  \
         ARM_DOT((VEC_DATA_TYPE(DATA_TYPE, 4))(a, (VEC_DATA_TYPE(DATA_TYPE, 3))0), (VEC_DATA_TYPE(DATA_TYPE, 4))(b, (VEC_DATA_TYPE(DATA_TYPE, 3))0), c); \