diff options
author | Manuel Bottini <manuel.bottini@arm.com> | 2021-06-17 17:18:45 +0100 |
---|---|---|
committer | Manuel Bottini <manuel.bottini@arm.com> | 2021-06-22 17:03:54 +0000 |
commit | ae58bdf3b58739e105a24e3640d0245e81cea5ee (patch) | |
tree | e993b8768c3eff364a7c706db411c799fa86bfe0 /arm_compute/runtime/NEON/functions/NEQLSTMLayer.h | |
parent | 2db3a9955ef22be4be8ccd5a45bc0973ef80e42a (diff) | |
download | ComputeLibrary-ae58bdf3b58739e105a24e3640d0245e81cea5ee.tar.gz |
Port NEGEMMLowp Part 1
Details:
Port NEGEMMLowpQuantizeDownInt32ScaleKernel to CpuGemmLowpQuantizeDownInt32ScaleKernel
Port NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel to CpuGemmLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel
Port NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel to CpuGemmLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel
Port NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel to CpuGemmLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel
Port NEGEMMLowpOutputStage functions to CpuGemmLowpOutputStage operators
Partially Resolves: COMPMID-4403
Change-Id: I6d5f45e43f35d731d564ed3b5c0e804d2a318fb1
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5833
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEQLSTMLayer.h')
-rw-r--r-- | arm_compute/runtime/NEON/functions/NEQLSTMLayer.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEQLSTMLayer.h b/arm_compute/runtime/NEON/functions/NEQLSTMLayer.h index 7c2e9bc5a1..77adffd543 100644 --- a/arm_compute/runtime/NEON/functions/NEQLSTMLayer.h +++ b/arm_compute/runtime/NEON/functions/NEQLSTMLayer.h @@ -54,7 +54,7 @@ class NEGEMMLowpMatrixAReductionKernel; * -# @ref NEArithmeticSubtraction Elementwise subtraction * -# @ref NECopy Copy kernel for copying output_state_out to output * -# @ref NEGEMMLowpMatrixMultiplyCore Quantized matrix multiplication core. Accumulators are 32-bit integers - * -# @ref NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint Convert 32-bit integers into QSYMM16 + * -# @ref NEGEMMLowpOutputStage Convert 32-bit integers into QSYMM16 * -# @ref NEGEMMLowpMatrixAReductionKernel For precomputing effective biases to use * -# @ref NEPixelWiseMultiplication Elementwise multiplication * -# @ref NETranspose Transpose function for reshaping the weights |