test_msa_fmax_w.c (7531B)
1/* 2 * Test program for MSA instruction FMAX.W 3 * 4 * Copyright (C) 2019 Wave Computing, Inc. 5 * Copyright (C) 2019 Aleksandar Markovic <amarkovic@wavecomp.com> 6 * 7 * This program is free software: you can redistribute it and/or modify 8 * it under the terms of the GNU General Public License as published by 9 * the Free Software Foundation, either version 2 of the License, or 10 * (at your option) any later version. 11 * 12 * This program is distributed in the hope that it will be useful, 13 * but WITHOUT ANY WARRANTY; without even the implied warranty of 14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 15 * GNU General Public License for more details. 16 * 17 * You should have received a copy of the GNU General Public License 18 * along with this program. If not, see <https://www.gnu.org/licenses/>. 19 * 20 */ 21 22#include <sys/time.h> 23#include <stdint.h> 24 25#include "../../../../include/wrappers_msa.h" 26#include "../../../../include/test_inputs_128.h" 27#include "../../../../include/test_utils_128.h" 28 29#define TEST_COUNT_TOTAL ( \ 30 (PATTERN_INPUTS_SHORT_COUNT) * (PATTERN_INPUTS_SHORT_COUNT) + \ 31 (RANDOM_INPUTS_SHORT_COUNT) * (RANDOM_INPUTS_SHORT_COUNT)) 32 33 34int32_t main(void) 35{ 36 char *isa_ase_name = "MSA"; 37 char *group_name = "Float Max Min"; 38 char *instruction_name = "FMAX.W"; 39 int32_t ret; 40 uint32_t i, j; 41 struct timeval start, end; 42 double elapsed_time; 43 44 uint64_t b128_result[TEST_COUNT_TOTAL][2]; 45 uint64_t b128_expect[TEST_COUNT_TOTAL][2] = { 46 { 0xffffffffffffffffULL, 0xffffffffffffffffULL, }, /* 0 */ 47 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 48 { 0xaaaaaaaaaaaaaaaaULL, 0xaaaaaaaaaaaaaaaaULL, }, 49 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 50 { 0xccccccccccccccccULL, 0xccccccccccccccccULL, }, 51 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 52 { 0xe38e38e38e38e38eULL, 0x38e38e38e38e38e3ULL, }, 53 { 0x1c71c71c71c71c71ULL, 0xc71c71c71c71c71cULL, }, 54 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, /* 8 */ 55 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 56 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 57 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 58 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 59 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 60 { 0x0000000000000000ULL, 0x38e38e3800000000ULL, }, 61 { 0x1c71c71c71c71c71ULL, 0x000000001c71c71cULL, }, 62 { 0xaaaaaaaaaaaaaaaaULL, 0xaaaaaaaaaaaaaaaaULL, }, /* 16 */ 63 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 64 { 0xaaaaaaaaaaaaaaaaULL, 0xaaaaaaaaaaaaaaaaULL, }, 65 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 66 { 0xaaaaaaaaaaaaaaaaULL, 0xaaaaaaaaaaaaaaaaULL, }, 67 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 68 { 0xaaaaaaaa8e38e38eULL, 0x38e38e38aaaaaaaaULL, }, 69 { 0x1c71c71c71c71c71ULL, 0xaaaaaaaa1c71c71cULL, }, 70 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, /* 24 */ 71 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 72 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 73 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 74 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 75 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 76 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 77 { 0x5555555571c71c71ULL, 0x5555555555555555ULL, }, 78 { 0xccccccccccccccccULL, 0xccccccccccccccccULL, }, /* 32 */ 79 { 0x0000000000000000ULL, 0x0000000000000000ULL, }, 80 { 0xaaaaaaaaaaaaaaaaULL, 0xaaaaaaaaaaaaaaaaULL, }, 81 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 82 { 0xccccccccccccccccULL, 0xccccccccccccccccULL, }, 83 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 84 { 0xcccccccc8e38e38eULL, 0x38e38e38ccccccccULL, }, 85 { 0x1c71c71c71c71c71ULL, 0xc71c71c71c71c71cULL, }, 86 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, /* 40 */ 87 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 88 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 89 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 90 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 91 { 0x3333333333333333ULL, 0x3333333333333333ULL, }, 92 { 0x3333333333333333ULL, 0x38e38e3833333333ULL, }, 93 { 0x3333333371c71c71ULL, 0x3333333333333333ULL, }, 94 { 0xe38e38e38e38e38eULL, 0x38e38e38e38e38e3ULL, }, /* 48 */ 95 { 0x0000000000000000ULL, 0x38e38e3800000000ULL, }, 96 { 0xaaaaaaaa8e38e38eULL, 0x38e38e38aaaaaaaaULL, }, 97 { 0x5555555555555555ULL, 0x5555555555555555ULL, }, 98 { 0xcccccccc8e38e38eULL, 0x38e38e38ccccccccULL, }, 99 { 0x3333333333333333ULL, 0x38e38e3833333333ULL, }, 100 { 0xe38e38e38e38e38eULL, 0x38e38e38e38e38e3ULL, }, 101 { 0x1c71c71c71c71c71ULL, 0x38e38e381c71c71cULL, }, 102 { 0x1c71c71c71c71c71ULL, 0xc71c71c71c71c71cULL, }, /* 56 */ 103 { 0x1c71c71c71c71c71ULL, 0x000000001c71c71cULL, }, 104 { 0x1c71c71c71c71c71ULL, 0xaaaaaaaa1c71c71cULL, }, 105 { 0x5555555571c71c71ULL, 0x5555555555555555ULL, }, 106 { 0x1c71c71c71c71c71ULL, 0xc71c71c71c71c71cULL, }, 107 { 0x3333333371c71c71ULL, 0x3333333333333333ULL, }, 108 { 0x1c71c71c71c71c71ULL, 0x38e38e381c71c71cULL, }, 109 { 0x1c71c71c71c71c71ULL, 0xc71c71c71c71c71cULL, }, 110 { 0x886ae6cc28625540ULL, 0x4b670b5efe7bb00cULL, }, /* 64 */ 111 { 0x886ae6cc4d93c708ULL, 0x4b670b5e153f52fcULL, }, 112 { 0x886ae6cc28625540ULL, 0x4b670b5eab2b2514ULL, }, 113 { 0x704f164d5e31e24eULL, 0x4b670b5ea942e2a0ULL, }, 114 { 0x886ae6cc4d93c708ULL, 0x4b670b5e153f52fcULL, }, 115 { 0xfbbe00634d93c708ULL, 0x12f7bb1a153f52fcULL, }, 116 { 0xac5aaeaa4d93c708ULL, 0x27d8c6ff153f52fcULL, }, 117 { 0x704f164d5e31e24eULL, 0x12f7bb1a153f52fcULL, }, 118 { 0x886ae6cc28625540ULL, 0x4b670b5eab2b2514ULL, }, /* 72 */ 119 { 0xac5aaeaa4d93c708ULL, 0x27d8c6ff153f52fcULL, }, 120 { 0xac5aaeaab9cf8b80ULL, 0x27d8c6ffab2b2514ULL, }, 121 { 0x704f164d5e31e24eULL, 0x27d8c6ffa942e2a0ULL, }, 122 { 0x704f164d5e31e24eULL, 0x4b670b5ea942e2a0ULL, }, 123 { 0x704f164d5e31e24eULL, 0x12f7bb1a153f52fcULL, }, 124 { 0x704f164d5e31e24eULL, 0x27d8c6ffa942e2a0ULL, }, 125 { 0x704f164d5e31e24eULL, 0x8df188d8a942e2a0ULL, }, 126}; 127 128 reset_msa_registers(); 129 130 gettimeofday(&start, NULL); 131 132 for (i = 0; i < PATTERN_INPUTS_SHORT_COUNT; i++) { 133 for (j = 0; j < PATTERN_INPUTS_SHORT_COUNT; j++) { 134 do_msa_FMAX_W(b128_pattern[i], b128_pattern[j], 135 b128_result[PATTERN_INPUTS_SHORT_COUNT * i + j]); 136 } 137 } 138 139 for (i = 0; i < RANDOM_INPUTS_SHORT_COUNT; i++) { 140 for (j = 0; j < RANDOM_INPUTS_SHORT_COUNT; j++) { 141 do_msa_FMAX_W(b128_random[i], b128_random[j], 142 b128_result[((PATTERN_INPUTS_SHORT_COUNT) * 143 (PATTERN_INPUTS_SHORT_COUNT)) + 144 RANDOM_INPUTS_SHORT_COUNT * i + j]); 145 } 146 } 147 148 gettimeofday(&end, NULL); 149 150 elapsed_time = (end.tv_sec - start.tv_sec) * 1000.0; 151 elapsed_time += (end.tv_usec - start.tv_usec) / 1000.0; 152 153 ret = check_results_128(isa_ase_name, group_name, instruction_name, 154 TEST_COUNT_TOTAL, elapsed_time, 155 &b128_result[0][0], &b128_expect[0][0]); 156 157 return ret; 158}