diff options
author | Francesco Petrogalli <francesco.petrogalli@arm.com> | 2022-06-30 10:22:01 +0000 |
---|---|---|
committer | Francesco Petrogalli <francesco.petrogalli@arm.com> | 2022-07-19 09:26:27 +0000 |
commit | 553f6953fe3bdfad53c11c25f305a16d79d83b24 (patch) | |
tree | 73642b948b79662096f593458c6138d2f7f48ec6 /src/cpu/operators/CpuGemm.h | |
parent | 99c46475daf277aa53e6747f9e41209f418fed33 (diff) | |
download | ComputeLibrary-553f6953fe3bdfad53c11c25f305a16d79d83b24.tar.gz |
[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>
Diffstat (limited to 'src/cpu/operators/CpuGemm.h')
-rw-r--r-- | src/cpu/operators/CpuGemm.h | 24 |
1 files changed, 21 insertions, 3 deletions
diff --git a/src/cpu/operators/CpuGemm.h b/src/cpu/operators/CpuGemm.h index 334ab6c647..b37ab73485 100644 --- a/src/cpu/operators/CpuGemm.h +++ b/src/cpu/operators/CpuGemm.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -101,11 +101,29 @@ public: static Status validate(const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *d, float alpha, float beta, const GEMMInfo &gemm_info = GEMMInfo()); + /** Indicates whether or not there is an optimal assembly implementation that can be used to process the given parameters. + * + * This method has the same use of @ref + * NEGEMMConvolutionLayer::has_opt_impl, with the only caveat that + * the value of arm_gemm::WeightFormat need to be passed via the + * parameter gemm_info. + */ + static Status has_opt_impl(arm_gemm::WeightFormat &weight_format, const ITensorInfo *a, const ITensorInfo *b, const ITensorInfo *c, const ITensorInfo *d, + const GEMMInfo &gemm_info = GEMMInfo()); + // Inherited methods overridden: - void run(ITensorPack &tensors) override; - void prepare(ITensorPack &constants) override; + void run(ITensorPack &tensors) override; + void prepare(ITensorPack &constants) override; experimental::MemoryRequirements workspace() const override; + /** Indicates if the convolution executes in variable weights mode. + * + * When ACL executes convolution in variable weights mode, it does + * not perform any processing of the weights tensor. Instead, it + * utilizes the data as it is given by the user. + */ + bool isVarWeightsKernel() const; + private: enum AuxTensorIdx { |