diff options
| author | Jonathan Deakin <jonathan.deakin@arm.com> | 2024-01-24 09:15:38 +0000 |
|---|---|---|
| committer | Radu Salavat <radu.salavat@arm.com> | 2024-04-15 13:52:31 +0000 |
| commit | a668f9f8a4eab405df0fe8dd58e7d9425bcf9640 (patch) | |
| tree | db16e6af9289897557a58755b88d2c337dcb8650 /src/core/NEON/kernels/arm_gemm/quantized.hpp | |
| parent | 34bdffb288d6367cb6dca652ebed60c450854039 (diff) | |
| download | ComputeLibrary-a668f9f8a4eab405df0fe8dd58e7d9425bcf9640.tar.gz | |
Add s8f32 kernels and dynamic QuantizationInfo
- Add support for QASYMM_SIGNED*QASYMM8_SIGNED->F32 in
CpuGemmLowpMatrixMultiplyCore
- Add s8f32 kernel using existing s8->s32 kernels with a new
DequantizeFloat OutputStage, the structure is similar to Requantize32
but the opposite way around.
- Add SME s8f32 kernels with integrated support for DequantizeFloat.
- Add scale to CpuGemmLowpOffsetContributionKernel.
- Add virtual dequantize scale to gemm_common, only implemented for
gemm_interleaved.
- Update year to 2024 in generate_build_files.
- Add dynamic flag to QuantizationInfo which signals to operators that
it can change after configuration
- Add support for dynamic quantization in NEGEMMLowpMatrixMultiplyCore
- Add dynamic quantization fixture by extending
GEMMLowpGenericMatrixMultiplyCoreValidationFixture
- Add GEMMLowpDequantizedMatrixMultiplyValidationFixture
- Store k (number of cols of A) rather than k_offset in the offset
contribution kernels so that we can recompute it when the other
offsets change
relates to: ONCPUML-1444 MLINFSW-439
Co-authored-by: Milos Puzovic <Milos.Puzovic@arm.com>
Co-authored-by: David Mansell <David.Mansell@arm.com>
Change-Id: I58a3acf2c09289a303e52eea6b336a696a5bc8da
Signed-off-by: Jonathan Deakin <jonathan.deakin@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11022
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/quantized.hpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/quantized.hpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/quantized.hpp b/src/core/NEON/kernels/arm_gemm/quantized.hpp index 31dd65b397..bc64fd967b 100644 --- a/src/core/NEON/kernels/arm_gemm/quantized.hpp +++ b/src/core/NEON/kernels/arm_gemm/quantized.hpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019, 2023 Arm Limited. + * Copyright (c) 2019, 2023-2024 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -45,4 +45,8 @@ template<typename T> void row_sums_indirect(size_t num_strings, const unsigned int *string_lengths, IndirectInputArg<T> A_arg, size_t M, int32_t *output_ptr, const Requantize32 *qp); +void dequantize_block_32(const DequantizeFloat &qp, unsigned int width, unsigned int height, + const int32_t* input, unsigned int in_stride, float *output, unsigned int out_stride, + const float *row_bias, bool not_first_pass, const Activation &act); + } // namespace arm_gemm |