_m_pmullwADD TO COMPARE ADDED TO COMPARE
Intel 64-bit (64 bits)/ SSE4.2
View official documentation
View Félix Cloutier's documentation
Purpose:
Multiply the packed 16-bit integers in "a" and "b", producing intermediate 32-bit integers, and store the low 16 bits of the intermediate integers in "dst".
Result:
__m64
Example:
#include <mmintrin.h>
#include <stdio.h>
int main() {
__m64 a = _mm_set_pi16(1000, 2000, 3000, 4000);
__m64 b = _mm_set_pi16(2, 3, 4, 5);
__m64 r = _m_pmullw(a, b);
short *res = (short*)&r;
printf("%d %d %d %d\n", res[0], res[1], res[2], res[3]);
_mm_empty();
return 0;
}Prototypes
Assembly Instruction:
vpmullw
Usage:
__m64 result =
_m_pmullw(
__m64 a, __m64 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 |