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>
diff --git a/tests/validation/reference/QuantizationLayer.cpp b/tests/validation/reference/QuantizationLayer.cpp
index 2766537..b76263b 100644
--- a/tests/validation/reference/QuantizationLayer.cpp
+++ b/tests/validation/reference/QuantizationLayer.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2017-2020 Arm Limited.
+ * Copyright (c) 2017-2020, 2024 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -80,6 +80,15 @@
dst[i] = quantize_qasymm16((src[i]), qinfo, rounding_policy);
}
break;
+ case DataType::F32:
+#if defined(_OPENMP)
+ #pragma omp parallel for
+#endif /* _OPENMP */
+ for(int i = 0; i < src.num_elements(); ++i)
+ {
+ dst[i] = dequantize_s32((src[i]), qinfo);
+ }
+ break;
default:
ARM_COMPUTE_ERROR("Unsupported output data type");
}
@@ -127,6 +136,7 @@
template SimpleTensor<uint8_t> quantization_layer(const SimpleTensor<float> &src, DataType output_data_type, const QuantizationInfo &quantization_info);
template SimpleTensor<uint16_t> quantization_layer(const SimpleTensor<half> &src, DataType output_data_type, const QuantizationInfo &quantization_info);
template SimpleTensor<uint16_t> quantization_layer(const SimpleTensor<float> &src, DataType output_data_type, const QuantizationInfo &quantization_info);
+template SimpleTensor<float> quantization_layer(const SimpleTensor<int32_t> &src, DataType output_data_type, const QuantizationInfo &quantization_info);
} // namespace reference
} // namespace validation
} // namespace test