1 /* 2 * Copyright (c) 2017-2020 Arm Limited. 3 * 4 * SPDX-License-Identifier: MIT 5 * 6 * Permission is hereby granted, free of charge, to any person obtaining a copy 7 * of this software and associated documentation files (the "Software"), to 8 * deal in the Software without restriction, including without limitation the 9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or 10 * sell copies of the Software, and to permit persons to whom the Software is 11 * furnished to do so, subject to the following conditions: 12 * 13 * The above copyright notice and this permission notice shall be included in all 14 * copies or substantial portions of the Software. 15 * 16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 22 * SOFTWARE. 23 */ 24 #pragma once 25 26 #ifdef __aarch64__ 27 28 #include "../std_transforms_fixed.hpp" 29 30 namespace arm_gemm { 31 32 // Actual kernel implementations 33 void a64_gemm_u16_asimd_8x12(const uint16_t *, const uint16_t *, uint32_t *, int, int, int); 34 35 class cls_a64_gemm_u16_8x12 { 36 public: 37 typedef uint16_t operand_type; 38 typedef uint32_t result_type; 39 40 typedef void (*kern_type)(const uint16_t *, const uint16_t *, uint32_t *, int, int, int); 41 42 /* Kernel blocking parameters */ out_width()43 static unsigned int out_width() { 44 return 12; 45 } 46 out_height()47 static unsigned int out_height() { 48 return 8; 49 } 50 k_unroll()51 static unsigned int k_unroll() { 52 return 1; 53 } 54 55 // Use the standard fixed size transforms. 56 StdTransformsFixed<operand_type, result_type, 8, 12> transforms = {}; 57 StdTransformsFixed<operand_type, result_type, 8, 12, 1, true> transforms_quantized = {}; 58 59 kern_type kernel = a64_gemm_u16_asimd_8x12; 60 cls_a64_gemm_u16_8x12(const CPUInfo *)61 cls_a64_gemm_u16_8x12(const CPUInfo *) { } 62 }; 63 64 } // namespace arm_gemm 65 66 #endif // __aarch64__ 67