_mm512_min_psADD TO COMPARE ADDED TO COMPARE
Intel 64-bit (64 bits)/ AVX512
View official documentation
View Félix Cloutier's documentation
Purpose:
Compare packed single-precision (32-bit) floating-point elements in "a" and "b", and store packed minimum values in "dst". [min_float_note]
Result:
__m512
Example:
#include <immintrin.h>
#include <stdio.h>
int main() {
__m512 a = _mm512_set_ps(5.5f, 3.2f, 8.7f, 2.1f, 4.9f, 1.3f, 7.8f, 0.5f, 9.0f, 6.3f, 4.2f, 3.7f, 6.6f, 5.1f, 2.8f, 7.0f);
__m512 b = _mm512_set_ps(2.2f, 4.6f, 3.3f, 6.8f, 5.1f, 7.9f, 0.2f, 3.0f, 8.1f, 5.7f, 2.9f, 6.0f, 4.0f, 3.6f, 7.2f, 5.4f);
__m512 r = _mm512_min_ps(a, b);
float* p = (float*)&r;
for (int i = 0; i < 16; i++) {
printf("%f ", p[i]);
}
return 0;
}Prototypes
Assembly Instruction:
vminps
Usage:
__m512 result =
_mm512_min_ps(
__m512 a, __m512 b
)
Performance Metrics:
📊 Unlock Performance Insights
Get access to detailed performance metrics including latency, throughput, and CPU-specific benchmarks for this intrinsic.
SIMD Intrinsics Summary
| SIMD Engines: | 6 |
| C Intrinsics: | 10444 |
| NEON: | 4353 |
| AVX2: | 405 |
| AVX512: | 4717 |
| SSE4.2: | 598 |
| VSX: | 192 |
| IBM-Z: | 179 |