har0ke/FFmpeg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

avcodec/mips: [loongson] reoptimize h264_chroma_mc8_mmi v2.

Browse Source 
Reoptimize function ff_put_h264_chroma_mc8_mmi and ff_avg_h264_chroma_mc8_mmi.
Performance of h264 decoding improved about 5%(from 69fps to 73fps, tested on loongson 3A3000).

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
This commit is contained in:
Shiyou Yin 2018-08-31 21:56:05 +08:00 committed by Michael Niedermayer
parent df13b75aa1
commit f91237baf6
1 changed files with 456 additions and 290 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

378
libavcodec/mips/h264chroma_mmi.c
View File

@ -29,17 +29,95 @@
void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y)
{
const int A = (8 - x) * (8 - y);
const int B = x * (8 - y);
const int C = (8 - x) * y;
const int D = x * y;
const int E = B + C;
int A = 64, B, C, D, E;
double ftmp[10];
uint64_t tmp[1];
mips_reg addr[1];
DECLARE_VAR_ALL64;
if (D) {
if (!(x || y)) {
/* x=0, y=0, A=64 */
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
"mtc1 %[tmp0], %[ftmp4] \n\t"
"1: \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
"addi %[h], %[h], -0x04 \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp5], %[src], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp6], %[src], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp7], %[src], 0x00)
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"psllh %[ftmp1], %[ftmp2], %[ftmp4] \n\t"
"psllh %[ftmp2], %[ftmp3], %[ftmp4] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
"punpcklbh %[ftmp2], %[ftmp5], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp5], %[ftmp0] \n\t"
"psllh %[ftmp1], %[ftmp2], %[ftmp4] \n\t"
"psllh %[ftmp2], %[ftmp3], %[ftmp4] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
"punpcklbh %[ftmp2], %[ftmp6], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp6], %[ftmp0] \n\t"
"psllh %[ftmp1], %[ftmp2], %[ftmp4] \n\t"
"psllh %[ftmp2], %[ftmp3], %[ftmp4] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
"punpcklbh %[ftmp2], %[ftmp7], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp7], %[ftmp0] \n\t"
"psllh %[ftmp1], %[ftmp2], %[ftmp4] \n\t"
"psllh %[ftmp2], %[ftmp3], %[ftmp4] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[tmp0]"=&r"(tmp[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32)
: "memory"
);
} else {
if (x && y) {
/* x!=0, y!=0 */
D = x * y;
B = (x << 3) - D;
C = (y << 3) - D;
A = 64 - D - B - C;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
@ -50,11 +128,12 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"pshufh %[D], %[D], %[ftmp0] \n\t"
"1: \n\t"
PTR_ADDU "%[addr0], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
MMI_ULDC1(%[ftmp2], %[src], 0x01)
MMI_ULDC1(%[ftmp3], %[addr0], 0x00)
MMI_ULDC1(%[ftmp4], %[addr0], 0x01)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp3], %[src], 0x00)
MMI_ULDC1(%[ftmp4], %[src], 0x01)
"addi %[h], %[h], -0x02 \n\t"
"punpcklbh %[ftmp5], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp1], %[ftmp0] \n\t"
@ -85,10 +164,47 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"psrlh %[ftmp1], %[ftmp1], %[ftmp9] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp9] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x01 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
MMI_ULDC1(%[ftmp2], %[src], 0x01)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp3], %[src], 0x00)
MMI_ULDC1(%[ftmp4], %[src], 0x01)
"punpcklbh %[ftmp5], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp1], %[ftmp0] \n\t"
"punpcklbh %[ftmp7], %[ftmp2], %[ftmp0] \n\t"
"punpckhbh %[ftmp8], %[ftmp2], %[ftmp0] \n\t"
"pmullh %[ftmp5], %[ftmp5], %[A] \n\t"
"pmullh %[ftmp7], %[ftmp7], %[B] \n\t"
"paddh %[ftmp1], %[ftmp5], %[ftmp7] \n\t"
"pmullh %[ftmp6], %[ftmp6], %[A] \n\t"
"pmullh %[ftmp8], %[ftmp8], %[B] \n\t"
"paddh %[ftmp2], %[ftmp6], %[ftmp8] \n\t"
"punpcklbh %[ftmp5], %[ftmp3], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp3], %[ftmp0] \n\t"
"punpcklbh %[ftmp7], %[ftmp4], %[ftmp0] \n\t"
"punpckhbh %[ftmp8], %[ftmp4], %[ftmp0] \n\t"
"pmullh %[ftmp5], %[ftmp5], %[C] \n\t"
"pmullh %[ftmp7], %[ftmp7], %[D] \n\t"
"paddh %[ftmp3], %[ftmp5], %[ftmp7] \n\t"
"pmullh %[ftmp6], %[ftmp6], %[C] \n\t"
"pmullh %[ftmp8], %[ftmp8], %[D] \n\t"
"paddh %[ftmp4], %[ftmp6], %[ftmp8] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ftmp3] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp9] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp9] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
@ -96,8 +212,6 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[ftmp8]"=&f"(ftmp[8]), [ftmp9]"=&f"(ftmp[9]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[addr0]"=&r"(addr[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32),
@ -105,8 +219,11 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[C]"f"(C), [D]"f"(D)
: "memory"
);
} else if (E) {
const int step = C ? stride : 1;
} else {
if (x) {
/* x!=0, y==0 */
E = x << 3;
A = 64 - E;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
@ -116,9 +233,10 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"mtc1 %[tmp0], %[ftmp7] \n\t"
"1: \n\t"
PTR_ADDU "%[addr0], %[src], %[step] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
MMI_ULDC1(%[ftmp2], %[addr0], 0x00)
MMI_ULDC1(%[ftmp2], %[src], 0x01)
"addi %[h], %[h], -0x01 \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
"punpcklbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp4], %[ftmp1], %[ftmp0] \n\t"
@ -136,9 +254,7 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"psrlh %[ftmp1], %[ftmp1], %[ftmp7] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp7] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x01 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
@ -146,81 +262,136 @@ void ff_put_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[addr0]"=&r"(addr[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[step]"r"((mips_reg)step),
: [stride]"r"((mips_reg)stride),
[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A), [E]"f"(E)
: "memory"
);
} else {
/* x==0, y!=0 */
E = y << 3;
A = 64 - E;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
"pshufh %[A], %[A], %[ftmp0] \n\t"
"mtc1 %[tmp0], %[ftmp4] \n\t"
"pshufh %[E], %[E], %[ftmp0] \n\t"
"mtc1 %[tmp0], %[ftmp7] \n\t"
"1: \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp2], %[src], 0x00)
"addi %[h], %[h], -0x01 \n\t"
"punpcklbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp4], %[ftmp1], %[ftmp0] \n\t"
"punpcklbh %[ftmp5], %[ftmp2], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp2], %[ftmp0] \n\t"
"pmullh %[ftmp3], %[ftmp3], %[A] \n\t"
"pmullh %[ftmp5], %[ftmp5], %[E] \n\t"
"paddh %[ftmp1], %[ftmp3], %[ftmp5] \n\t"
"pmullh %[ftmp4], %[ftmp4], %[A] \n\t"
"pmullh %[ftmp6], %[ftmp6], %[E] \n\t"
"paddh %[ftmp2], %[ftmp4], %[ftmp6] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp7] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp7] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x02 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
[ftmp4]"=&f"(ftmp[4]),
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A)
: [stride]"r"((mips_reg)stride),
[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A), [E]"f"(E)
: "memory"
);
}
}
}
}
void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y)
{
const int A = (8 - x) * (8 - y);
const int B = x * (8 - y);
const int C = (8 - x) * y;
const int D = x * y;
const int E = B + C;
int A = 64, B, C, D, E;
double ftmp[10];
uint64_t tmp[1];
mips_reg addr[1];
DECLARE_VAR_ALL64;
if (D) {
if(!(x || y)){
/* x=0, y=0, A=64 */
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
"pshufh %[A], %[A], %[ftmp0] \n\t"
"mtc1 %[tmp0], %[ftmp4] \n\t"
"1: \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp5], %[src], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"punpcklbh %[ftmp2], %[ftmp5], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp5], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"addi %[h], %[h], -0x02 \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[tmp0]"=&r"(tmp[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A)
: "memory"
);
} else {
if(x && y) {
/* x!=0, y!=0 */
D = x * y;
B = (x << 3) - D;
C = (y << 3) - D;
A = 64 - D - B - C;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
@ -231,11 +402,12 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"pshufh %[D], %[D], %[ftmp0] \n\t"
"1: \n\t"
PTR_ADDU "%[addr0], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
MMI_ULDC1(%[ftmp2], %[src], 0x01)
MMI_ULDC1(%[ftmp3], %[addr0], 0x00)
MMI_ULDC1(%[ftmp4], %[addr0], 0x01)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp3], %[src], 0x00)
MMI_ULDC1(%[ftmp4], %[src], 0x01)
"addi %[h], %[h], -0x01 \n\t"
"punpcklbh %[ftmp5], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp1], %[ftmp0] \n\t"
@ -268,10 +440,8 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x01 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
@ -279,8 +449,6 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[ftmp8]"=&f"(ftmp[8]), [ftmp9]"=&f"(ftmp[9]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[addr0]"=&r"(addr[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32),
@ -288,9 +456,11 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[C]"f"(C), [D]"f"(D)
: "memory"
);
} else if (E) {
const int step = C ? stride : 1;
} else {
if(x) {
/* x!=0, y==0 */
E = x << 3;
A = 64 - E;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
@ -299,9 +469,10 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"mtc1 %[tmp0], %[ftmp7] \n\t"
"1: \n\t"
PTR_ADDU "%[addr0], %[src], %[step] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
MMI_ULDC1(%[ftmp2], %[addr0], 0x00)
MMI_ULDC1(%[ftmp2], %[src], 0x01)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
"addi %[h], %[h], -0x01 \n\t"
"punpcklbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp4], %[ftmp1], %[ftmp0] \n\t"
@ -321,9 +492,7 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x01 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
@ -331,69 +500,66 @@ void ff_avg_h264_chroma_mc8_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[addr0]"=&r"(addr[0]),
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[step]"r"((mips_reg)step),
: [stride]"r"((mips_reg)stride),
[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A), [E]"f"(E)
: "memory"
);
} else {
/* x==0, y!=0 */
E = y << 3;
A = 64 - E;
__asm__ volatile (
"xor %[ftmp0], %[ftmp0], %[ftmp0] \n\t"
"dli %[tmp0], 0x06 \n\t"
"pshufh %[A], %[A], %[ftmp0] \n\t"
"mtc1 %[tmp0], %[ftmp4] \n\t"
"pshufh %[E], %[E], %[ftmp0] \n\t"
"mtc1 %[tmp0], %[ftmp7] \n\t"
"1: \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_ULDC1(%[ftmp2], %[src], 0x00)
"addi %[h], %[h], -0x01 \n\t"
"punpcklbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp4], %[ftmp1], %[ftmp0] \n\t"
"punpcklbh %[ftmp5], %[ftmp2], %[ftmp0] \n\t"
"punpckhbh %[ftmp6], %[ftmp2], %[ftmp0] \n\t"
"pmullh %[ftmp3], %[ftmp3], %[A] \n\t"
"pmullh %[ftmp5], %[ftmp5], %[E] \n\t"
"paddh %[ftmp1], %[ftmp3], %[ftmp5] \n\t"
"pmullh %[ftmp4], %[ftmp4], %[A] \n\t"
"pmullh %[ftmp6], %[ftmp6], %[E] \n\t"
"paddh %[ftmp2], %[ftmp4], %[ftmp6] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp7] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp7] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
PTR_ADDU "%[src], %[src], %[stride] \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
MMI_ULDC1(%[ftmp1], %[src], 0x00)
"punpcklbh %[ftmp2], %[ftmp1], %[ftmp0] \n\t"
"punpckhbh %[ftmp3], %[ftmp1], %[ftmp0] \n\t"
"pmullh %[ftmp1], %[ftmp2], %[A] \n\t"
"pmullh %[ftmp2], %[ftmp3], %[A] \n\t"
"paddh %[ftmp1], %[ftmp1], %[ff_pw_32] \n\t"
"paddh %[ftmp2], %[ftmp2], %[ff_pw_32] \n\t"
"psrlh %[ftmp1], %[ftmp1], %[ftmp4] \n\t"
"psrlh %[ftmp2], %[ftmp2], %[ftmp4] \n\t"
"packushb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
MMI_LDC1(%[ftmp2], %[dst], 0x00)
"pavgb %[ftmp1], %[ftmp1], %[ftmp2] \n\t"
"addi %[h], %[h], -0x02 \n\t"
MMI_SDC1(%[ftmp1], %[dst], 0x00)
PTR_ADDU "%[src], %[src], %[stride] \n\t"
PTR_ADDU "%[dst], %[dst], %[stride] \n\t"
"bnez %[h], 1b \n\t"
: [ftmp0]"=&f"(ftmp[0]), [ftmp1]"=&f"(ftmp[1]),
[ftmp2]"=&f"(ftmp[2]), [ftmp3]"=&f"(ftmp[3]),
[ftmp4]"=&f"(ftmp[4]),
[ftmp4]"=&f"(ftmp[4]), [ftmp5]"=&f"(ftmp[5]),
[ftmp6]"=&f"(ftmp[6]), [ftmp7]"=&f"(ftmp[7]),
[tmp0]"=&r"(tmp[0]),
RESTRICT_ASM_ALL64
[dst]"+&r"(dst), [src]"+&r"(src),
[h]"+&r"(h)
: [stride]"r"((mips_reg)stride),[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A)
: [stride]"r"((mips_reg)stride),
[ff_pw_32]"f"(ff_pw_32),
[A]"f"(A), [E]"f"(E)
: "memory"
);
}
}
}
}
void ff_put_h264_chroma_mc4_mmi(uint8_t *dst, uint8_t *src, ptrdiff_t stride,