See http://codearcana.com/posts/2013/05/18/achieving-maximum-memory-bandwidth.html for the usage of stream loads/writes. Or section 6.1, page 47 of https://akkadia.org/drepper/cpumemory.pdf .
| 109 | // for the usage of stream loads/writes. Or section 6.1, page 47 of |
| 110 | // https://akkadia.org/drepper/cpumemory.pdf . |
| 111 | static void StreamRead(void* src, void* dst, size_t size) { |
| 112 | auto simd = static_cast<VectorType*>(src); |
| 113 | VectorType a, b, c, d; |
| 114 | (void)dst; |
| 115 | |
| 116 | memset(&a, 0, sizeof(a)); |
| 117 | memset(&b, 0, sizeof(b)); |
| 118 | memset(&c, 0, sizeof(c)); |
| 119 | memset(&d, 0, sizeof(d)); |
| 120 | |
| 121 | for (size_t i = 0; i < size / sizeof(VectorType); i += 4) { |
| 122 | VectorStreamLoadAsm(simd[i], a); |
| 123 | VectorStreamLoadAsm(simd[i + 1], b); |
| 124 | VectorStreamLoadAsm(simd[i + 2], c); |
| 125 | VectorStreamLoadAsm(simd[i + 3], d); |
| 126 | } |
| 127 | |
| 128 | auto result = a + b + c + d; |
| 129 | benchmark::DoNotOptimize(result); |
| 130 | } |
| 131 | |
| 132 | static void StreamWrite(void* src, void* dst, size_t size) { |
| 133 | auto simd = static_cast<VectorType*>(dst); |
nothing calls this directly
no test coverage detected