diff options
| author | Michalis Spyrou <michalis.spyrou@arm.com> | 2020-06-23 17:25:43 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-06-25 13:14:06 +0000 |
| commit | 173ba9bbb19ea83f951318d9989e440768b4de8f (patch) | |
| tree | 840a28e1cc4d0adf47097c8ab27092531c8e0958 /arm_compute/runtime/NEON/functions/NELSTMLayer.h | |
| parent | 0f954eb6c8bf2f6c8600c56f21fec6aa9ebf082e (diff) | |
| download | ComputeLibrary-173ba9bbb19ea83f951318d9989e440768b4de8f.tar.gz | |
COMPMID-3373: Async support to NEArithmetic* kernels/functions (Pt. 1)
Added support on NEArithmeticAddition and NEArithmeticSubtraction
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Change-Id: Ifa805f8455ef6eff1ee627752dc1c7fe9740ec47
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3451
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NELSTMLayer.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NELSTMLayer.h | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/arm_compute/runtime/NEON/functions/NELSTMLayer.h b/arm_compute/runtime/NEON/functions/NELSTMLayer.h index 64845115b8..b9b581c484 100644 --- a/arm_compute/runtime/NEON/functions/NELSTMLayer.h +++ b/arm_compute/runtime/NEON/functions/NELSTMLayer.h @@ -25,13 +25,13 @@ #define ARM_COMPUTE_NELSTMLAYER_H #include "arm_compute/core/NEON/kernels/NEActivationLayerKernel.h" -#include "arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h" -#include "arm_compute/core/NEON/kernels/NEArithmeticSubtractionKernel.h" #include "arm_compute/core/NEON/kernels/NECopyKernel.h" #include "arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h" #include "arm_compute/core/Types.h" #include "arm_compute/runtime/NEON/functions/NEArithmeticAddition.h" +#include "arm_compute/runtime/NEON/functions/NEArithmeticAddition.h" +#include "arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h" #include "arm_compute/runtime/NEON/functions/NEConcatenateLayer.h" #include "arm_compute/runtime/NEON/functions/NEFullyConnectedLayer.h" #include "arm_compute/runtime/NEON/functions/NEGEMM.h" @@ -149,7 +149,7 @@ private: MemoryGroup _memory_group; NEFullyConnectedLayer _fully_connected_input_gate; NEArithmeticAddition _accum_input_gate1; - NEArithmeticSubtractionKernel _subtract_input_gate; + NEArithmeticSubtraction _subtract_input_gate; NEPixelWiseMultiplicationKernel _pixelwise_mul_input_gate; NEActivationLayer _activation_input_gate; NEFullyConnectedLayer _fully_connected_forget_gate; @@ -159,8 +159,8 @@ private: NEFullyConnectedLayer _fully_connected_cell_state; NEGEMM _gemm_cell_state1; NETransposeKernel _transpose_cell_state; - NEArithmeticAdditionKernel _accum_cell_state1; - NEArithmeticAdditionKernel _accum_cell_state2; + NEArithmeticAddition _accum_cell_state1; + NEArithmeticAddition _accum_cell_state2; NEPixelWiseMultiplicationKernel _pixelwise_mul_cell_state1; NEActivationLayer _activation_cell_state; NEActivationLayer _cell_clip; @@ -182,16 +182,16 @@ private: NEConcatenateLayer _concat_weights_output; NEMeanStdDevNormalizationLayer _mean_std_norm_input_gate; NEPixelWiseMultiplicationKernel _pixelwise_mul_input_gate_coeff; - NEArithmeticAdditionKernel _accum_input_gate_bias; + NEArithmeticAddition _accum_input_gate_bias; NEMeanStdDevNormalizationLayer _mean_std_norm_forget_gate; NEPixelWiseMultiplicationKernel _pixelwise_mul_forget_gate_coeff; - NEArithmeticAdditionKernel _accum_forget_gate_bias; + NEArithmeticAddition _accum_forget_gate_bias; NEMeanStdDevNormalizationLayer _mean_std_norm_cell_gate; NEPixelWiseMultiplicationKernel _pixelwise_mul_cell_gate_coeff; - NEArithmeticAdditionKernel _accum_cell_gate_bias; + NEArithmeticAddition _accum_cell_gate_bias; NEMeanStdDevNormalizationLayer _mean_std_norm_output_gate; NEPixelWiseMultiplicationKernel _pixelwise_mul_output_gate_coeff; - NEArithmeticAdditionKernel _accum_output_gate_bias; + NEArithmeticAddition _accum_output_gate_bias; Tensor _input_gate_out1; Tensor _input_gate_out2; Tensor _input_gate_out3; |