static void yuv2yuvX_sse3(const int16_t *filter, int filterSize,
const int16_t **src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset)
{
if(((int)dest) & 15){
yuv2yuvX_mmxext(filter, filterSize, src, dest, dstW, dither, offset);
return;
}
if (offset) {
__asm__ volatile("movq (%0), %%xmm3\n\t"
"movdqa %%xmm3, %%xmm4\n\t"
"psrlq $24, %%xmm3\n\t"
"psllq $40, %%xmm4\n\t"
"por %%xmm4, %%xmm3\n\t"
:: "r"(dither)
);
} else {
static void yuv2yuvX_sse3(const int16_t *filter, int filterSize,
const int16_t **src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset)
{
if(((uintptr_t)dest) & 15){
yuv2yuvX_mmxext(filter, filterSize, src, dest, dstW, dither, offset);
return;
}
filterSize--;
#define MAIN_FUNCTION \
"pxor %%xmm0, %%xmm0 \n\t" \
"punpcklbw %%xmm0, %%xmm3 \n\t" \
"movd %4, %%xmm1 \n\t" \
"punpcklwd %%xmm1, %%xmm1 \n\t" \
"punpckldq %%xmm1, %%xmm1 \n\t" \
"punpcklqdq %%xmm1, %%xmm1 \n\t" \
"psllw $3, %%xmm1 \n\t" \
"paddw %%xmm1, %%xmm3 \n\t" \
"psraw $4, %%xmm3 \n\t" \
"movdqa %%xmm3, %%xmm4 \n\t" \
"movdqa %%xmm3, %%xmm7 \n\t" \
"movl %3, %%ecx \n\t" \
"mov %0, %%"FF_REG_d" \n\t"\
"mov (%%"FF_REG_d"), %%"FF_REG_S" \n\t"\
".p2align 4 \n\t" /* FIXME Unroll? */\
"1: \n\t"\
"movddup 8(%%"FF_REG_d"), %%xmm0 \n\t" /* filterCoeff */\
"movdqa (%%"FF_REG_S", %%"FF_REG_c", 2), %%xmm2 \n\t" /* srcData */\
"movdqa 16(%%"FF_REG_S", %%"FF_REG_c", 2), %%xmm5 \n\t" /* srcData */\
"add $16, %%"FF_REG_d" \n\t"\
"mov (%%"FF_REG_d"), %%"FF_REG_S" \n\t"\
"test %%"FF_REG_S", %%"FF_REG_S" \n\t"\
"pmulhw %%xmm0, %%xmm2 \n\t"\
"pmulhw %%xmm0, %%xmm5 \n\t"\
"paddw %%xmm2, %%xmm3 \n\t"\
"paddw %%xmm5, %%xmm4 \n\t"\
" jnz 1b \n\t"\
"psraw $3, %%xmm3 \n\t"\
"psraw $3, %%xmm4 \n\t"\
"packuswb %%xmm4, %%xmm3 \n\t"\
"movntdq %%xmm3, (%1, %%"FF_REG_c") \n\t"\
"add $16, %%"FF_REG_c" \n\t"\
"cmp %2, %%"FF_REG_c" \n\t"\
"movdqa %%xmm7, %%xmm3 \n\t" \
"movdqa %%xmm7, %%xmm4 \n\t" \
"mov %0, %%"FF_REG_d" \n\t"\
"mov (%%"FF_REG_d"), %%"FF_REG_S" \n\t"\
"jb 1b \n\t"
if (offset) {
__asm__ volatile(
"movq %5, %%xmm3 \n\t"
"movdqa %%xmm3, %%xmm4 \n\t"
"psrlq $24, %%xmm3 \n\t"
"psllq $40, %%xmm4 \n\t"
"por %%xmm4, %%xmm3 \n\t"
MAIN_FUNCTION
:: "g" (filter),
"r" (dest-offset), "g" ((x86_reg)(dstW+offset)), "m" (offset),
"m"(filterSize), "m"(((uint64_t *) dither)[0])
: XMM_CLOBBERS("%xmm0" , "%xmm1" , "%xmm2" , "%xmm3" , "%xmm4" , "%xmm5" , "%xmm7" ,)
"%"FF_REG_d, "%"FF_REG_S, "%"FF_REG_c
);
} else {
