diff options
| author | Jonathan Deakin <jonathan.deakin@arm.com> | 2023-01-12 11:41:14 +0000 |
|---|---|---|
| committer | Jonathan Deakin <jonathan.deakin@arm.com> | 2023-02-01 08:05:35 +0000 |
| commit | 464ed2087c2ce2d2e741cc1e1dc4bd49d06e7d26 (patch) | |
| tree | da07a18be246742773a729e264080d9a9b314d59 /src/runtime/NEON | |
| parent | 7594f989963724e127c3e28210d60fed590b0524 (diff) | |
| download | ComputeLibrary-464ed2087c2ce2d2e741cc1e1dc4bd49d06e7d26.tar.gz | |
Remove fixed format strides hack
- Remove hack in CpuGemmAssemblyDispatch.cpp which tried to guess
strides for fixed format kernels. Instead, expect that strides will
have been correctly set on weights externally
- Update fixed format test fixtures to set the strides
- If the fixed format uses fast math mode, then weights should be of
type BFLOAT16. Change the validation logic to accept this.
Resolves: [ONCPUML-1131]
Co-authored-by: Milos Puzovic <Milos.Puzovic@arm.com>
Change-Id: I0f18d8b86b0f639be25fd122fa06a591e90645f2
Signed-off-by: Jonathan Deakin <jonathan.deakin@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8985
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/NEON')
| -rw-r--r-- | src/runtime/NEON/functions/NEFullyConnectedLayer.cpp | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/src/runtime/NEON/functions/NEFullyConnectedLayer.cpp b/src/runtime/NEON/functions/NEFullyConnectedLayer.cpp index 4f858fb54b..919e5ed84f 100644 --- a/src/runtime/NEON/functions/NEFullyConnectedLayer.cpp +++ b/src/runtime/NEON/functions/NEFullyConnectedLayer.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2022 Arm Limited. + * Copyright (c) 2017-2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -69,7 +69,8 @@ void NEFullyConnectedLayer::configure(const ITensor *input, const ITensor *weigh weights->info(), biases != nullptr ? biases->info() : nullptr, output->info(), - fc_info)); + fc_info, + weights_info)); ARM_COMPUTE_LOG_PARAMS(input, weights, biases, output, fc_info); _impl->op = std::make_unique<cpu::CpuFullyConnected>(); @@ -96,9 +97,9 @@ Status NEFullyConnectedLayer::has_opt_impl(arm_compute::WeightFormat &expected_w } Status NEFullyConnectedLayer::validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, - FullyConnectedLayerInfo fc_info) + FullyConnectedLayerInfo fc_info, const WeightsInfo &weights_info) { - return cpu::CpuFullyConnected::validate(input, weights, biases, output, fc_info); + return cpu::CpuFullyConnected::validate(input, weights, biases, output, fc_info, weights_info); } void NEFullyConnectedLayer::run() |