共1条
1/1 1 跳转至页
ARM NEON 优化举例

累加数组内起始元素到制定个数元素的累加和:
uint32_t vector_add_of_n(uint32_t *ptr, uint32_t nitems)
{
uint32_t result, *i;
uint32x2_t vec64a, vec64b;
uint32x4_t vec128 = vdupq_n_u32(0);
for (i = ptr; i 15) + 1) 1;
}
彩色转灰度:(C)
void reference_convert (uint8_t * __restrict dest, uint8_t * __restrict src, int n)
{
int i;
for (i=0; i8);
}
}
void neon_convert (uint8_t * __restrict dest, uint8_t * __restrict src, int n)
{
int i;
uint8x8_t **c = vdup_n_u8 (77);
uint8x8_t gfac = vdup_n_u8 (151);
uint8x8_t bfac = vdup_n_u8 (28);
n/=8;
for (i=0; i
关键词: 优化 举例
共1条
1/1 1 跳转至页