[ONCPUML-951] Variable weight support for Convolution.
API changes for NEGEMMConvolutionLayer and CpuGemmConv2d
Built with:
scons neon=1 opencl=0 os=linux arch=armv8.2-a multi_isa=1 \
build=native -j32 Werror=false validation_tests=1 build_dir=opt \
standalone=1 asserts=1 experimental_fixed_format_kernels=1 .
Tested with:
./build/opt/tests/arm_compute_validation
Hardware where the test executable was run:
Neoverse N1
Test coverage:
* NEGEMMConvolutionLayer, CpuGemmConv2d
* NHWC (the only one supported by the fixed-format kernels)
* F16, F32
* Shapes: RunSmall
Change-Id: I4fd3e495a7cbf61210ea02d37440ba9652934e99
Signed-off-by: Francesco Petrogalli <francesco.petrogalli@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7632
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/runtime/NEON/functions/NEGEMMConvolutionLayer.cpp b/src/runtime/NEON/functions/NEGEMMConvolutionLayer.cpp
index c780d63..13635c6 100644
--- a/src/runtime/NEON/functions/NEGEMMConvolutionLayer.cpp
+++ b/src/runtime/NEON/functions/NEGEMMConvolutionLayer.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2017-2021 Arm Limited.
+ * Copyright (c) 2017-2022 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -58,6 +58,7 @@
const Size2D &dilation, const ActivationLayerInfo &act_info, bool enable_fast_math, unsigned int num_groups)
{
ARM_COMPUTE_ERROR_ON_NULLPTR(input, weights, output);
+
_impl->weights = weights;
_impl->op = std::make_unique<cpu::CpuGemmConv2d>();
_impl->op->configure(input->info(), weights->info(), (biases != nullptr ? biases->info() : nullptr), output->info(), conv_info, weights_info, dilation, act_info, enable_fast_math, num_groups);
@@ -79,6 +80,13 @@
return cpu::CpuGemmConv2d::validate(input, weights, biases, output, conv_info, weights_info, dilation, act_info, enable_fast_math, num_groups);
}
+Status NEGEMMConvolutionLayer::has_opt_impl(arm_gemm::WeightFormat &expected_weight_format, const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *dst,
+ const PadStrideInfo &conv_info,
+ const WeightsInfo &weights_info, const Size2D &dilation, const ActivationLayerInfo &act_info, const bool enable_fast_math)
+{
+ return cpu::CpuGemmConv2d::has_opt_impl(expected_weight_format, src, weights, biases, dst, conv_info, weights_info, dilation, act_info, enable_fast_math);
+}
+
void NEGEMMConvolutionLayer::run()
{
prepare();