dsputil_mmx.c

ffmpeg移植到symbian的全部源代码

    MOVQ_ZERO(mm7);
    i = 4;
    do {
        asm volatile(
                "movq   (%2), %%mm0     \n\t"
                "movq   8(%2), %%mm1    \n\t"
                "movq   16(%2), %%mm2   \n\t"
                "movq   24(%2), %%mm3   \n\t"
                "movq   %0, %%mm4       \n\t"
                "movq   %1, %%mm6       \n\t"
                "movq   %%mm4, %%mm5    \n\t"
                "punpcklbw %%mm7, %%mm4 \n\t"
                "punpckhbw %%mm7, %%mm5 \n\t"
                "paddsw %%mm4, %%mm0    \n\t"
                "paddsw %%mm5, %%mm1    \n\t"
                "movq   %%mm6, %%mm5    \n\t"
                "punpcklbw %%mm7, %%mm6 \n\t"
                "punpckhbw %%mm7, %%mm5 \n\t"
                "paddsw %%mm6, %%mm2    \n\t"
                "paddsw %%mm5, %%mm3    \n\t"
                "packuswb %%mm1, %%mm0  \n\t"
                "packuswb %%mm3, %%mm2  \n\t"
                "movq   %%mm0, %0       \n\t"
                "movq   %%mm2, %1       \n\t"
                :"+m"(*pix), "+m"(*(pix+line_size))
                :"r"(p)
                :"memory");
        pix += line_size*2;
        p += 16;
    } while (--i);
}

static void put_pixels4_mmx(uint8_t *block, const uint8_t *pixels, int line_size, int h)
{
    asm volatile(
         "lea (%3, %3), %%"REG_a"       \n\t"
         ASMALIGN(3)
         "1:                            \n\t"
         "movd (%1), %%mm0              \n\t"
         "movd (%1, %3), %%mm1          \n\t"
         "movd %%mm0, (%2)              \n\t"
         "movd %%mm1, (%2, %3)          \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "movd (%1), %%mm0              \n\t"
         "movd (%1, %3), %%mm1          \n\t"
         "movd %%mm0, (%2)              \n\t"
         "movd %%mm1, (%2, %3)          \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "subl $4, %0                   \n\t"
         "jnz 1b                        \n\t"
         : "+g"(h), "+r" (pixels),  "+r" (block)
         : "r"((x86_reg)line_size)
         : "%"REG_a, "memory"
        );
}

static void put_pixels8_mmx(uint8_t *block, const uint8_t *pixels, int line_size, int h)
{
    asm volatile(
         "lea (%3, %3), %%"REG_a"       \n\t"
         ASMALIGN(3)
         "1:                            \n\t"
         "movq (%1), %%mm0              \n\t"
         "movq (%1, %3), %%mm1          \n\t"
         "movq %%mm0, (%2)              \n\t"
         "movq %%mm1, (%2, %3)          \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "movq (%1), %%mm0              \n\t"
         "movq (%1, %3), %%mm1          \n\t"
         "movq %%mm0, (%2)              \n\t"
         "movq %%mm1, (%2, %3)          \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "subl $4, %0                   \n\t"
         "jnz 1b                        \n\t"
         : "+g"(h), "+r" (pixels),  "+r" (block)
         : "r"((x86_reg)line_size)
         : "%"REG_a, "memory"
        );
}

static void put_pixels16_mmx(uint8_t *block, const uint8_t *pixels, int line_size, int h)
{
    asm volatile(
         "lea (%3, %3), %%"REG_a"       \n\t"
         ASMALIGN(3)
         "1:                            \n\t"
         "movq (%1), %%mm0              \n\t"
         "movq 8(%1), %%mm4             \n\t"
         "movq (%1, %3), %%mm1          \n\t"
         "movq 8(%1, %3), %%mm5         \n\t"
         "movq %%mm0, (%2)              \n\t"
         "movq %%mm4, 8(%2)             \n\t"
         "movq %%mm1, (%2, %3)          \n\t"
         "movq %%mm5, 8(%2, %3)         \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "movq (%1), %%mm0              \n\t"
         "movq 8(%1), %%mm4             \n\t"
         "movq (%1, %3), %%mm1          \n\t"
         "movq 8(%1, %3), %%mm5         \n\t"
         "movq %%mm0, (%2)              \n\t"
         "movq %%mm4, 8(%2)             \n\t"
         "movq %%mm1, (%2, %3)          \n\t"
         "movq %%mm5, 8(%2, %3)         \n\t"
         "add %%"REG_a", %1             \n\t"
         "add %%"REG_a", %2             \n\t"
         "subl $4, %0                   \n\t"
         "jnz 1b                        \n\t"
         : "+g"(h), "+r" (pixels),  "+r" (block)
         : "r"((x86_reg)line_size)
         : "%"REG_a, "memory"
        );
}

static void put_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
{
    asm volatile(
         "1:                            \n\t"
         "movdqu (%1), %%xmm0           \n\t"
         "movdqu (%1,%3), %%xmm1        \n\t"
         "movdqu (%1,%3,2), %%xmm2      \n\t"
         "movdqu (%1,%4), %%xmm3        \n\t"
         "movdqa %%xmm0, (%2)           \n\t"
         "movdqa %%xmm1, (%2,%3)        \n\t"
         "movdqa %%xmm2, (%2,%3,2)      \n\t"
         "movdqa %%xmm3, (%2,%4)        \n\t"
         "subl $4, %0                   \n\t"
         "lea (%1,%3,4), %1             \n\t"
         "lea (%2,%3,4), %2             \n\t"
         "jnz 1b                        \n\t"
         : "+g"(h), "+r" (pixels),  "+r" (block)
         : "r"((x86_reg)line_size), "r"((x86_reg)3L*line_size)
         : "memory"
        );
}

static void avg_pixels16_sse2(uint8_t *block, const uint8_t *pixels, int line_size, int h)
{
    asm volatile(
         "1:                            \n\t"
         "movdqu (%1), %%xmm0           \n\t"
         "movdqu (%1,%3), %%xmm1        \n\t"
         "movdqu (%1,%3,2), %%xmm2      \n\t"
         "movdqu (%1,%4), %%xmm3        \n\t"
         "pavgb  (%2), %%xmm0           \n\t"
         "pavgb  (%2,%3), %%xmm1        \n\t"
         "pavgb  (%2,%3,2), %%xmm2      \n\t"
         "pavgb  (%2,%4), %%xmm3        \n\t"
         "movdqa %%xmm0, (%2)           \n\t"
         "movdqa %%xmm1, (%2,%3)        \n\t"
         "movdqa %%xmm2, (%2,%3,2)      \n\t"
         "movdqa %%xmm3, (%2,%4)        \n\t"
         "subl $4, %0                   \n\t"
         "lea (%1,%3,4), %1             \n\t"
         "lea (%2,%3,4), %2             \n\t"
         "jnz 1b                        \n\t"
         : "+g"(h), "+r" (pixels),  "+r" (block)
         : "r"((x86_reg)line_size), "r"((x86_reg)3L*line_size)
         : "memory"
        );
}

static void clear_blocks_mmx(DCTELEM *blocks)
{
    asm volatile(
                "pxor %%mm7, %%mm7              \n\t"
                "mov $-128*6, %%"REG_a"         \n\t"
                "1:                             \n\t"
                "movq %%mm7, (%0, %%"REG_a")    \n\t"
                "movq %%mm7, 8(%0, %%"REG_a")   \n\t"
                "movq %%mm7, 16(%0, %%"REG_a")  \n\t"
                "movq %%mm7, 24(%0, %%"REG_a")  \n\t"
                "add $32, %%"REG_a"             \n\t"
                " js 1b                         \n\t"
                : : "r" (((uint8_t *)blocks)+128*6)
                : "%"REG_a
        );
}

static void add_bytes_mmx(uint8_t *dst, uint8_t *src, int w){
    x86_reg i=0;
    asm volatile(
        "jmp 2f                         \n\t"
        "1:                             \n\t"
        "movq  (%1, %0), %%mm0          \n\t"
        "movq  (%2, %0), %%mm1          \n\t"
        "paddb %%mm0, %%mm1             \n\t"
        "movq %%mm1, (%2, %0)           \n\t"
        "movq 8(%1, %0), %%mm0          \n\t"
        "movq 8(%2, %0), %%mm1          \n\t"
        "paddb %%mm0, %%mm1             \n\t"
        "movq %%mm1, 8(%2, %0)          \n\t"
        "add $16, %0                    \n\t"
        "2:                             \n\t"
        "cmp %3, %0                     \n\t"
        " js 1b                         \n\t"
        : "+r" (i)
        : "r"(src), "r"(dst), "r"((x86_reg)w-15)
    );
    for(; i<w; i++)
        dst[i+0] += src[i+0];
}

static void add_bytes_l2_mmx(uint8_t *dst, uint8_t *src1, uint8_t *src2, int w){
    x86_reg i=0;
    asm volatile(
        "jmp 2f                         \n\t"
        "1:                             \n\t"
        "movq   (%2, %0), %%mm0         \n\t"
        "movq  8(%2, %0), %%mm1         \n\t"
        "paddb  (%3, %0), %%mm0         \n\t"
        "paddb 8(%3, %0), %%mm1         \n\t"
        "movq %%mm0,  (%1, %0)          \n\t"
        "movq %%mm1, 8(%1, %0)          \n\t"
        "add $16, %0                    \n\t"
        "2:                             \n\t"
        "cmp %4, %0                     \n\t"
        " js 1b                         \n\t"
        : "+r" (i)
        : "r"(dst), "r"(src1), "r"(src2), "r"((x86_reg)w-15)
    );
    for(; i<w; i++)
        dst[i] = src1[i] + src2[i];
}

#define H263_LOOP_FILTER \
        "pxor %%mm7, %%mm7              \n\t"\
        "movq  %0, %%mm0                \n\t"\
        "movq  %0, %%mm1                \n\t"\
        "movq  %3, %%mm2                \n\t"\
        "movq  %3, %%mm3                \n\t"\
        "punpcklbw %%mm7, %%mm0         \n\t"\
        "punpckhbw %%mm7, %%mm1         \n\t"\
        "punpcklbw %%mm7, %%mm2         \n\t"\
        "punpckhbw %%mm7, %%mm3         \n\t"\
        "psubw %%mm2, %%mm0             \n\t"\
        "psubw %%mm3, %%mm1             \n\t"\
        "movq  %1, %%mm2                \n\t"\
        "movq  %1, %%mm3                \n\t"\
        "movq  %2, %%mm4                \n\t"\
        "movq  %2, %%mm5                \n\t"\
        "punpcklbw %%mm7, %%mm2         \n\t"\
        "punpckhbw %%mm7, %%mm3         \n\t"\
        "punpcklbw %%mm7, %%mm4         \n\t"\
        "punpckhbw %%mm7, %%mm5         \n\t"\
        "psubw %%mm2, %%mm4             \n\t"\
        "psubw %%mm3, %%mm5             \n\t"\
        "psllw $2, %%mm4                \n\t"\
        "psllw $2, %%mm5                \n\t"\
        "paddw %%mm0, %%mm4             \n\t"\
        "paddw %%mm1, %%mm5             \n\t"\
        "pxor %%mm6, %%mm6              \n\t"\
        "pcmpgtw %%mm4, %%mm6           \n\t"\
        "pcmpgtw %%mm5, %%mm7           \n\t"\
        "pxor %%mm6, %%mm4              \n\t"\
        "pxor %%mm7, %%mm5              \n\t"\
        "psubw %%mm6, %%mm4             \n\t"\
        "psubw %%mm7, %%mm5             \n\t"\
        "psrlw $3, %%mm4                \n\t"\
        "psrlw $3, %%mm5                \n\t"\
        "packuswb %%mm5, %%mm4          \n\t"\
        "packsswb %%mm7, %%mm6          \n\t"\
        "pxor %%mm7, %%mm7              \n\t"\
        "movd %4, %%mm2                 \n\t"\
        "punpcklbw %%mm2, %%mm2         \n\t"\
        "punpcklbw %%mm2, %%mm2         \n\t"\
        "punpcklbw %%mm2, %%mm2         \n\t"\
        "psubusb %%mm4, %%mm2           \n\t"\
        "movq %%mm2, %%mm3              \n\t"\
        "psubusb %%mm4, %%mm3           \n\t"\
        "psubb %%mm3, %%mm2             \n\t"\
        "movq %1, %%mm3                 \n\t"\
        "movq %2, %%mm4                 \n\t"\
        "pxor %%mm6, %%mm3              \n\t"\
        "pxor %%mm6, %%mm4              \n\t"\
        "paddusb %%mm2, %%mm3           \n\t"\
        "psubusb %%mm2, %%mm4           \n\t"\
        "pxor %%mm6, %%mm3              \n\t"\
        "pxor %%mm6, %%mm4              \n\t"\
        "paddusb %%mm2, %%mm2           \n\t"\
        "packsswb %%mm1, %%mm0          \n\t"\
        "pcmpgtb %%mm0, %%mm7           \n\t"\
        "pxor %%mm7, %%mm0              \n\t"\
        "psubb %%mm7, %%mm0             \n\t"\
        "movq %%mm0, %%mm1              \n\t"\
        "psubusb %%mm2, %%mm0           \n\t"\
        "psubb %%mm0, %%mm1             \n\t"\
        "pand %5, %%mm1                 \n\t"\
        "psrlw $2, %%mm1                \n\t"\
        "pxor %%mm7, %%mm1              \n\t"\
        "psubb %%mm7, %%mm1             \n\t"\
        "movq %0, %%mm5                 \n\t"\
        "movq %3, %%mm6                 \n\t"\
        "psubb %%mm1, %%mm5             \n\t"\