_mm_abs_epi16ADD TO COMPARE ADDED TO COMPARE
Intel 64-bit (64 bits)/ SSE4.2
View official documentation
Purpose:
Compute the absolute value of packed signed 16-bit integers in a, and store the unsigned results in output.
Result:
A 128-bit vector of 8 x 16-bit signed integers that hold the absolute values of the input elements.
Example:
#include <tmmintrin.h>
#include <stdio.h>
int main() {
int16_t a_data[8] = {
-10, 20, -30, 40, -50, 60, -70, 80
};
__m128i a = _mm_loadu_si128((__m128i*)a_data);
__m128i result = _mm_abs_epi16(a);
int16_t result_data[8];
_mm_storeu_si128((__m128i*)result_data, result);
for (int i = 0; i < 8; ++i) {
printf("%d ", result_data[i]);
}
printf("\n");
return 0;
}Prototypes
Assembly Instruction:
pabsw
Usage:
__m128i result =
_mm_abs_epi16(
__m128i a
)
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 |