diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2022-07-28 17:44:00 +0100 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2022-08-01 20:13:56 +0000 |
| commit | 9b921be1ff7283050eb39d9ce1b10b5c8bfc1300 (patch) | |
| tree | 0cb274a6c529717b8ef987aa3e270647927e9d89 /src/cpu/kernels/add/generic/neon/integer.cpp | |
| parent | 385dad2bffecbf395aa9aad257809de81c727ac7 (diff) | |
| download | ComputeLibrary-9b921be1ff7283050eb39d9ce1b10b5c8bfc1300.tar.gz | |
Optimize add layer by considering the input tensors as 1D array
Resolves: COMPMID-5108
Change-Id: I544f8160fbe5b4ffbef348d1fbd3dd626a6e1bdb
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8002
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/cpu/kernels/add/generic/neon/integer.cpp')
| -rw-r--r-- | src/cpu/kernels/add/generic/neon/integer.cpp | 17 |
1 files changed, 16 insertions, 1 deletions
diff --git a/src/cpu/kernels/add/generic/neon/integer.cpp b/src/cpu/kernels/add/generic/neon/integer.cpp index 62c19e66b1..ffead03474 100644 --- a/src/cpu/kernels/add/generic/neon/integer.cpp +++ b/src/cpu/kernels/add/generic/neon/integer.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -42,5 +42,20 @@ void add_s32_neon(const ITensor *src0, const ITensor *src1, ITensor *dst, const { return add_same_neon<int32_t>(src0, src1, dst, policy, window); } + +void add_u8_neon_as_1d_array(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window) +{ + return add_same_neon_as_1d_array<uint8_t>(src0, src1, dst, policy, window); +} + +void add_s16_neon_as_1d_array(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window) +{ + return add_same_neon_as_1d_array<int16_t>(src0, src1, dst, policy, window); +} + +void add_s32_neon_as_1d_array(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window) +{ + return add_same_neon_as_1d_array<int32_t>(src0, src1, dst, policy, window); +} } } // namespace arm_compute |