vminnm_f16ADD TO COMPARE ADDED TO COMPARE
Arm 64-bit (64 bits)/ NEON
View official documentation
Purpose:
Floating-point Minimum Number (vector). This instruction compares corresponding vector elements in the two source SIMD&FP registers, writes the smaller of the two floating-point values into a vector, and writes the vector to the destination SIMD&FP register.
Result:
float16x4_t
Example:
#include <arm_neon.h>
#include <stdio.h>
int main() {
float16_t dataA[4] = {
0.1, -0.2, 0.3, -0.4
};
float16_t dataB[4] = {
-0.1, 0.2, -0.3, 0.4
};
float16x4_t a = vld1_f16(dataA);
float16x4_t b = vld1_f16(dataB);
float16x4_t result = vminnm_f16(a, b);
float16_t output[4];
vst1_f16(output, result);
printf("Results: ");
for (int i = 0; i < 4; i++) {
printf("%.1f ", output[i]);
}
printf("\n");
return 0;
}Prototypes
Assembly Instruction:
FMINNM
Usage:
float16x4_t result =
vminnm_f16(
float16x4_t a, float16x4_t 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 |