From a668f9f8a4eab405df0fe8dd58e7d9425bcf9640 Mon Sep 17 00:00:00 2001 From: Jonathan Deakin Date: Wed, 24 Jan 2024 09:15:38 +0000 Subject: 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 Co-authored-by: David Mansell Change-Id: I58a3acf2c09289a303e52eea6b336a696a5bc8da Signed-off-by: Jonathan Deakin Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11022 Reviewed-by: Gunes Bayir Comments-Addressed: Arm Jenkins Tested-by: Arm Jenkins Benchmark: Arm Jenkins --- Android.bp | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'Android.bp') diff --git a/Android.bp b/Android.bp index c84e9e56ed..6cc85f1928 100644 --- a/Android.bp +++ b/Android.bp @@ -331,6 +331,7 @@ cc_library_static { "src/core/NEON/kernels/arm_gemm/gemm_int8.cpp", "src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp", "src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp", + "src/core/NEON/kernels/arm_gemm/gemm_s8fp32.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp", "src/core/NEON/kernels/arm_gemm/interleave-8way.cpp", @@ -1302,6 +1303,9 @@ cc_library_static { "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_1VLx4VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_2VLx2VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_4VLx1VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_1VLx4VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_2VLx2VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_4VLx1VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_1VLx4VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_2VLx2VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_4VLx1VL/generic.cpp", -- cgit v1.2.1