From 82833b80b1a28ff32fe3c3b2f4996fa21a08bbbc Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Tue, 30 Jan 2018 12:14:24 +0000 Subject: COMPMID-765 : NEON Wrapper initial traits and overloads Change-Id: Iea4c4732d19e8cf9b245ac2a9f75b2aa70a5839e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118149 Reviewed-by: Michele DiGiorgio Reviewed-by: Anthony Barbier Tested-by: Jenkins --- arm_compute/core/NEON/wrapper/intrinsics/load.h | 68 +++++++++++++++++++++++++ 1 file changed, 68 insertions(+) create mode 100644 arm_compute/core/NEON/wrapper/intrinsics/load.h (limited to 'arm_compute/core/NEON/wrapper/intrinsics/load.h') diff --git a/arm_compute/core/NEON/wrapper/intrinsics/load.h b/arm_compute/core/NEON/wrapper/intrinsics/load.h new file mode 100644 index 0000000000..9629f2b4e0 --- /dev/null +++ b/arm_compute/core/NEON/wrapper/intrinsics/load.h @@ -0,0 +1,68 @@ +/* + * Copyright (c) 2018 ARM Limited. + * + * SPDX-License-Identifier: MIT + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in all + * copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ +#ifndef __ARM_COMPUTE_WRAPPER_LOAD_H__ +#define __ARM_COMPUTE_WRAPPER_LOAD_H__ + +#include "arm_compute/core/NEON/wrapper/traits.h" + +#include + +namespace arm_compute +{ +namespace wrapper +{ +#define VLOAD_IMPL(stype, vtype, postfix) \ + inline vtype vload(const stype *ptr) \ + { \ + return vld1_##postfix(ptr); \ + } + +VLOAD_IMPL(uint8_t, uint8x8_t, u8) +VLOAD_IMPL(int8_t, int8x8_t, s8) +VLOAD_IMPL(uint16_t, uint16x4_t, u16) +VLOAD_IMPL(int16_t, int16x4_t, s16) +VLOAD_IMPL(uint32_t, uint32x2_t, u32) +VLOAD_IMPL(int32_t, int32x2_t, s32) +//VLOAD_IMPL(uint64_t, uint64x1_t, u64) +//VLOAD_IMPL(int64_t, int64x1_t, s64) +VLOAD_IMPL(float, float32x2_t, f32) + +#define VLOADQ_IMPL(stype, vtype, postfix) \ + inline vtype vloadq(const stype *ptr) \ + { \ + return vld1q_##postfix(ptr); \ + } + +VLOADQ_IMPL(uint8_t, uint8x16_t, u8) +VLOADQ_IMPL(int8_t, int8x16_t, s8) +VLOADQ_IMPL(uint16_t, uint16x8_t, u16) +VLOADQ_IMPL(int16_t, int16x8_t, s16) +VLOADQ_IMPL(uint32_t, uint32x4_t, u32) +VLOADQ_IMPL(int32_t, int32x4_t, s32) +//VLOAD_IMPL(uint64_t, uint64x1_t, u64) +//VLOAD_IMPL(int64_t, int64x1_t, s64) +VLOADQ_IMPL(float, float32x4_t, f32) +} +} +#endif /* __ARM_COMPUTE_WRAPPER_LOAD_H__ */ -- cgit v1.2.1