Merge commit 'e2b9993558b6adee42dcc6eb385a14943aaca974'

* commit 'e2b9993558b6adee42dcc6eb385a14943aaca974':
  simple_idct: x86: Drop disabled IDCT implementation

Merged-by: Clément Bœsch <u@pkh.me>
This commit is contained in:
Clément Bœsch 2017-03-19 16:11:11 +01:00
commit 8695ce73ca

View File

@ -89,259 +89,6 @@ static inline void idct(int16_t *block)
int16_t * const temp= (int16_t*)align_tmp;
__asm__ volatile(
#if 0 //Alternative, simpler variant
#define ROW_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
"movq " #src0 ", %%mm0 \n\t" /* R4 R0 r4 r0 */\
"movq " #src4 ", %%mm1 \n\t" /* R6 R2 r6 r2 */\
"movq " #src1 ", %%mm2 \n\t" /* R3 R1 r3 r1 */\
"movq " #src5 ", %%mm3 \n\t" /* R7 R5 r7 r5 */\
"movq 16(%2), %%mm4 \n\t" /* C4 C4 C4 C4 */\
"pmaddwd %%mm0, %%mm4 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"movq 24(%2), %%mm5 \n\t" /* -C4 C4 -C4 C4 */\
"pmaddwd %%mm5, %%mm0 \n\t" /* -C4R4+C4R0 -C4r4+C4r0 */\
"movq 32(%2), %%mm5 \n\t" /* C6 C2 C6 C2 */\
"pmaddwd %%mm1, %%mm5 \n\t" /* C6R6+C2R2 C6r6+C2r2 */\
"movq 40(%2), %%mm6 \n\t" /* -C2 C6 -C2 C6 */\
"pmaddwd %%mm6, %%mm1 \n\t" /* -C2R6+C6R2 -C2r6+C6r2 */\
"movq 48(%2), %%mm7 \n\t" /* C3 C1 C3 C1 */\
"pmaddwd %%mm2, %%mm7 \n\t" /* C3R3+C1R1 C3r3+C1r1 */\
#rounder ", %%mm4 \n\t"\
"movq %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"paddd %%mm5, %%mm4 \n\t" /* A0 a0 */\
"psubd %%mm5, %%mm6 \n\t" /* A3 a3 */\
"movq 56(%2), %%mm5 \n\t" /* C7 C5 C7 C5 */\
"pmaddwd %%mm3, %%mm5 \n\t" /* C7R7+C5R5 C7r7+C5r5 */\
#rounder ", %%mm0 \n\t"\
"paddd %%mm0, %%mm1 \n\t" /* A1 a1 */\
"paddd %%mm0, %%mm0 \n\t" \
"psubd %%mm1, %%mm0 \n\t" /* A2 a2 */\
"pmaddwd 64(%2), %%mm2 \n\t" /* -C7R3+C3R1 -C7r3+C3r1 */\
"paddd %%mm5, %%mm7 \n\t" /* B0 b0 */\
"movq 72(%2), %%mm5 \n\t" /* -C5 -C1 -C5 -C1 */\
"pmaddwd %%mm3, %%mm5 \n\t" /* -C5R7-C1R5 -C5r7-C1r5 */\
"paddd %%mm4, %%mm7 \n\t" /* A0+B0 a0+b0 */\
"paddd %%mm4, %%mm4 \n\t" /* 2A0 2a0 */\
"psubd %%mm7, %%mm4 \n\t" /* A0-B0 a0-b0 */\
"paddd %%mm2, %%mm5 \n\t" /* B1 b1 */\
"psrad $" #shift ", %%mm7 \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"movq %%mm1, %%mm2 \n\t" /* A1 a1 */\
"paddd %%mm5, %%mm1 \n\t" /* A1+B1 a1+b1 */\
"psubd %%mm5, %%mm2 \n\t" /* A1-B1 a1-b1 */\
"psrad $" #shift ", %%mm1 \n\t"\
"psrad $" #shift ", %%mm2 \n\t"\
"packssdw %%mm1, %%mm7 \n\t" /* A1+B1 a1+b1 A0+B0 a0+b0 */\
"packssdw %%mm4, %%mm2 \n\t" /* A0-B0 a0-b0 A1-B1 a1-b1 */\
"movq %%mm7, " #dst " \n\t"\
"movq " #src1 ", %%mm1 \n\t" /* R3 R1 r3 r1 */\
"movq 80(%2), %%mm4 \n\t" /* -C1 C5 -C1 C5 */\
"movq %%mm2, 24+" #dst " \n\t"\
"pmaddwd %%mm1, %%mm4 \n\t" /* -C1R3+C5R1 -C1r3+C5r1 */\
"movq 88(%2), %%mm7 \n\t" /* C3 C7 C3 C7 */\
"pmaddwd 96(%2), %%mm1 \n\t" /* -C5R3+C7R1 -C5r3+C7r1 */\
"pmaddwd %%mm3, %%mm7 \n\t" /* C3R7+C7R5 C3r7+C7r5 */\
"movq %%mm0, %%mm2 \n\t" /* A2 a2 */\
"pmaddwd 104(%2), %%mm3 \n\t" /* -C1R7+C3R5 -C1r7+C3r5 */\
"paddd %%mm7, %%mm4 \n\t" /* B2 b2 */\
"paddd %%mm4, %%mm2 \n\t" /* A2+B2 a2+b2 */\
"psubd %%mm4, %%mm0 \n\t" /* a2-B2 a2-b2 */\
"psrad $" #shift ", %%mm2 \n\t"\
"psrad $" #shift ", %%mm0 \n\t"\
"movq %%mm6, %%mm4 \n\t" /* A3 a3 */\
"paddd %%mm1, %%mm3 \n\t" /* B3 b3 */\
"paddd %%mm3, %%mm6 \n\t" /* A3+B3 a3+b3 */\
"psubd %%mm3, %%mm4 \n\t" /* a3-B3 a3-b3 */\
"psrad $" #shift ", %%mm6 \n\t"\
"packssdw %%mm6, %%mm2 \n\t" /* A3+B3 a3+b3 A2+B2 a2+b2 */\
"movq %%mm2, 8+" #dst " \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"packssdw %%mm0, %%mm4 \n\t" /* A2-B2 a2-b2 A3-B3 a3-b3 */\
"movq %%mm4, 16+" #dst " \n\t"\
#define COL_IDCT(src0, src4, src1, src5, dst, shift) \
"movq " #src0 ", %%mm0 \n\t" /* R4 R0 r4 r0 */\
"movq " #src4 ", %%mm1 \n\t" /* R6 R2 r6 r2 */\
"movq " #src1 ", %%mm2 \n\t" /* R3 R1 r3 r1 */\
"movq " #src5 ", %%mm3 \n\t" /* R7 R5 r7 r5 */\
"movq 16(%2), %%mm4 \n\t" /* C4 C4 C4 C4 */\
"pmaddwd %%mm0, %%mm4 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"movq 24(%2), %%mm5 \n\t" /* -C4 C4 -C4 C4 */\
"pmaddwd %%mm5, %%mm0 \n\t" /* -C4R4+C4R0 -C4r4+C4r0 */\
"movq 32(%2), %%mm5 \n\t" /* C6 C2 C6 C2 */\
"pmaddwd %%mm1, %%mm5 \n\t" /* C6R6+C2R2 C6r6+C2r2 */\
"movq 40(%2), %%mm6 \n\t" /* -C2 C6 -C2 C6 */\
"pmaddwd %%mm6, %%mm1 \n\t" /* -C2R6+C6R2 -C2r6+C6r2 */\
"movq %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"movq 48(%2), %%mm7 \n\t" /* C3 C1 C3 C1 */\
"pmaddwd %%mm2, %%mm7 \n\t" /* C3R3+C1R1 C3r3+C1r1 */\
"paddd %%mm5, %%mm4 \n\t" /* A0 a0 */\
"psubd %%mm5, %%mm6 \n\t" /* A3 a3 */\
"movq %%mm0, %%mm5 \n\t" /* -C4R4+C4R0 -C4r4+C4r0 */\
"paddd %%mm1, %%mm0 \n\t" /* A1 a1 */\
"psubd %%mm1, %%mm5 \n\t" /* A2 a2 */\
"movq 56(%2), %%mm1 \n\t" /* C7 C5 C7 C5 */\
"pmaddwd %%mm3, %%mm1 \n\t" /* C7R7+C5R5 C7r7+C5r5 */\
"pmaddwd 64(%2), %%mm2 \n\t" /* -C7R3+C3R1 -C7r3+C3r1 */\
"paddd %%mm1, %%mm7 \n\t" /* B0 b0 */\
"movq 72(%2), %%mm1 \n\t" /* -C5 -C1 -C5 -C1 */\
"pmaddwd %%mm3, %%mm1 \n\t" /* -C5R7-C1R5 -C5r7-C1r5 */\
"paddd %%mm4, %%mm7 \n\t" /* A0+B0 a0+b0 */\
"paddd %%mm4, %%mm4 \n\t" /* 2A0 2a0 */\
"psubd %%mm7, %%mm4 \n\t" /* A0-B0 a0-b0 */\
"paddd %%mm2, %%mm1 \n\t" /* B1 b1 */\
"psrad $" #shift ", %%mm7 \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"movq %%mm0, %%mm2 \n\t" /* A1 a1 */\
"paddd %%mm1, %%mm0 \n\t" /* A1+B1 a1+b1 */\
"psubd %%mm1, %%mm2 \n\t" /* A1-B1 a1-b1 */\
"psrad $" #shift ", %%mm0 \n\t"\
"psrad $" #shift ", %%mm2 \n\t"\
"packssdw %%mm7, %%mm7 \n\t" /* A0+B0 a0+b0 */\
"movd %%mm7, " #dst " \n\t"\
"packssdw %%mm0, %%mm0 \n\t" /* A1+B1 a1+b1 */\
"movd %%mm0, 16+" #dst " \n\t"\
"packssdw %%mm2, %%mm2 \n\t" /* A1-B1 a1-b1 */\
"movd %%mm2, 96+" #dst " \n\t"\
"packssdw %%mm4, %%mm4 \n\t" /* A0-B0 a0-b0 */\
"movd %%mm4, 112+" #dst " \n\t"\
"movq " #src1 ", %%mm0 \n\t" /* R3 R1 r3 r1 */\
"movq 80(%2), %%mm4 \n\t" /* -C1 C5 -C1 C5 */\
"pmaddwd %%mm0, %%mm4 \n\t" /* -C1R3+C5R1 -C1r3+C5r1 */\
"movq 88(%2), %%mm7 \n\t" /* C3 C7 C3 C7 */\
"pmaddwd 96(%2), %%mm0 \n\t" /* -C5R3+C7R1 -C5r3+C7r1 */\
"pmaddwd %%mm3, %%mm7 \n\t" /* C3R7+C7R5 C3r7+C7r5 */\
"movq %%mm5, %%mm2 \n\t" /* A2 a2 */\
"pmaddwd 104(%2), %%mm3 \n\t" /* -C1R7+C3R5 -C1r7+C3r5 */\
"paddd %%mm7, %%mm4 \n\t" /* B2 b2 */\
"paddd %%mm4, %%mm2 \n\t" /* A2+B2 a2+b2 */\
"psubd %%mm4, %%mm5 \n\t" /* a2-B2 a2-b2 */\
"psrad $" #shift ", %%mm2 \n\t"\
"psrad $" #shift ", %%mm5 \n\t"\
"movq %%mm6, %%mm4 \n\t" /* A3 a3 */\
"paddd %%mm0, %%mm3 \n\t" /* B3 b3 */\
"paddd %%mm3, %%mm6 \n\t" /* A3+B3 a3+b3 */\
"psubd %%mm3, %%mm4 \n\t" /* a3-B3 a3-b3 */\
"psrad $" #shift ", %%mm6 \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"packssdw %%mm2, %%mm2 \n\t" /* A2+B2 a2+b2 */\
"packssdw %%mm6, %%mm6 \n\t" /* A3+B3 a3+b3 */\
"movd %%mm2, 32+" #dst " \n\t"\
"packssdw %%mm4, %%mm4 \n\t" /* A3-B3 a3-b3 */\
"packssdw %%mm5, %%mm5 \n\t" /* A2-B2 a2-b2 */\
"movd %%mm6, 48+" #dst " \n\t"\
"movd %%mm4, 64+" #dst " \n\t"\
"movd %%mm5, 80+" #dst " \n\t"\
#define DC_COND_ROW_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
"movq " #src0 ", %%mm0 \n\t" /* R4 R0 r4 r0 */\
"movq " #src4 ", %%mm1 \n\t" /* R6 R2 r6 r2 */\
"movq " #src1 ", %%mm2 \n\t" /* R3 R1 r3 r1 */\
"movq " #src5 ", %%mm3 \n\t" /* R7 R5 r7 r5 */\
"movq "MANGLE(wm1010)", %%mm4 \n\t"\
"pand %%mm0, %%mm4 \n\t"\
"por %%mm1, %%mm4 \n\t"\
"por %%mm2, %%mm4 \n\t"\
"por %%mm3, %%mm4 \n\t"\
"packssdw %%mm4,%%mm4 \n\t"\
"movd %%mm4, %%eax \n\t"\
"orl %%eax, %%eax \n\t"\
"jz 1f \n\t"\
"movq 16(%2), %%mm4 \n\t" /* C4 C4 C4 C4 */\
"pmaddwd %%mm0, %%mm4 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"movq 24(%2), %%mm5 \n\t" /* -C4 C4 -C4 C4 */\
"pmaddwd %%mm5, %%mm0 \n\t" /* -C4R4+C4R0 -C4r4+C4r0 */\
"movq 32(%2), %%mm5 \n\t" /* C6 C2 C6 C2 */\
"pmaddwd %%mm1, %%mm5 \n\t" /* C6R6+C2R2 C6r6+C2r2 */\
"movq 40(%2), %%mm6 \n\t" /* -C2 C6 -C2 C6 */\
"pmaddwd %%mm6, %%mm1 \n\t" /* -C2R6+C6R2 -C2r6+C6r2 */\
"movq 48(%2), %%mm7 \n\t" /* C3 C1 C3 C1 */\
"pmaddwd %%mm2, %%mm7 \n\t" /* C3R3+C1R1 C3r3+C1r1 */\
#rounder ", %%mm4 \n\t"\
"movq %%mm4, %%mm6 \n\t" /* C4R4+C4R0 C4r4+C4r0 */\
"paddd %%mm5, %%mm4 \n\t" /* A0 a0 */\
"psubd %%mm5, %%mm6 \n\t" /* A3 a3 */\
"movq 56(%2), %%mm5 \n\t" /* C7 C5 C7 C5 */\
"pmaddwd %%mm3, %%mm5 \n\t" /* C7R7+C5R5 C7r7+C5r5 */\
#rounder ", %%mm0 \n\t"\
"paddd %%mm0, %%mm1 \n\t" /* A1 a1 */\
"paddd %%mm0, %%mm0 \n\t" \
"psubd %%mm1, %%mm0 \n\t" /* A2 a2 */\
"pmaddwd 64(%2), %%mm2 \n\t" /* -C7R3+C3R1 -C7r3+C3r1 */\
"paddd %%mm5, %%mm7 \n\t" /* B0 b0 */\
"movq 72(%2), %%mm5 \n\t" /* -C5 -C1 -C5 -C1 */\
"pmaddwd %%mm3, %%mm5 \n\t" /* -C5R7-C1R5 -C5r7-C1r5 */\
"paddd %%mm4, %%mm7 \n\t" /* A0+B0 a0+b0 */\
"paddd %%mm4, %%mm4 \n\t" /* 2A0 2a0 */\
"psubd %%mm7, %%mm4 \n\t" /* A0-B0 a0-b0 */\
"paddd %%mm2, %%mm5 \n\t" /* B1 b1 */\
"psrad $" #shift ", %%mm7 \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"movq %%mm1, %%mm2 \n\t" /* A1 a1 */\
"paddd %%mm5, %%mm1 \n\t" /* A1+B1 a1+b1 */\
"psubd %%mm5, %%mm2 \n\t" /* A1-B1 a1-b1 */\
"psrad $" #shift ", %%mm1 \n\t"\
"psrad $" #shift ", %%mm2 \n\t"\
"packssdw %%mm1, %%mm7 \n\t" /* A1+B1 a1+b1 A0+B0 a0+b0 */\
"packssdw %%mm4, %%mm2 \n\t" /* A0-B0 a0-b0 A1-B1 a1-b1 */\
"movq %%mm7, " #dst " \n\t"\
"movq " #src1 ", %%mm1 \n\t" /* R3 R1 r3 r1 */\
"movq 80(%2), %%mm4 \n\t" /* -C1 C5 -C1 C5 */\
"movq %%mm2, 24+" #dst " \n\t"\
"pmaddwd %%mm1, %%mm4 \n\t" /* -C1R3+C5R1 -C1r3+C5r1 */\
"movq 88(%2), %%mm7 \n\t" /* C3 C7 C3 C7 */\
"pmaddwd 96(%2), %%mm1 \n\t" /* -C5R3+C7R1 -C5r3+C7r1 */\
"pmaddwd %%mm3, %%mm7 \n\t" /* C3R7+C7R5 C3r7+C7r5 */\
"movq %%mm0, %%mm2 \n\t" /* A2 a2 */\
"pmaddwd 104(%2), %%mm3 \n\t" /* -C1R7+C3R5 -C1r7+C3r5 */\
"paddd %%mm7, %%mm4 \n\t" /* B2 b2 */\
"paddd %%mm4, %%mm2 \n\t" /* A2+B2 a2+b2 */\
"psubd %%mm4, %%mm0 \n\t" /* a2-B2 a2-b2 */\
"psrad $" #shift ", %%mm2 \n\t"\
"psrad $" #shift ", %%mm0 \n\t"\
"movq %%mm6, %%mm4 \n\t" /* A3 a3 */\
"paddd %%mm1, %%mm3 \n\t" /* B3 b3 */\
"paddd %%mm3, %%mm6 \n\t" /* A3+B3 a3+b3 */\
"psubd %%mm3, %%mm4 \n\t" /* a3-B3 a3-b3 */\
"psrad $" #shift ", %%mm6 \n\t"\
"packssdw %%mm6, %%mm2 \n\t" /* A3+B3 a3+b3 A2+B2 a2+b2 */\
"movq %%mm2, 8+" #dst " \n\t"\
"psrad $" #shift ", %%mm4 \n\t"\
"packssdw %%mm0, %%mm4 \n\t" /* A2-B2 a2-b2 A3-B3 a3-b3 */\
"movq %%mm4, 16+" #dst " \n\t"\
"jmp 2f \n\t"\
"1: \n\t"\
"pslld $16, %%mm0 \n\t"\
"#paddd "MANGLE(d40000)", %%mm0 \n\t"\
"psrad $13, %%mm0 \n\t"\
"packssdw %%mm0, %%mm0 \n\t"\
"movq %%mm0, " #dst " \n\t"\
"movq %%mm0, 8+" #dst " \n\t"\
"movq %%mm0, 16+" #dst " \n\t"\
"movq %%mm0, 24+" #dst " \n\t"\
"2: \n\t"
//IDCT( src0, src4, src1, src5, dst, rounder, shift)
ROW_IDCT( (%0), 8(%0), 16(%0), 24(%0), 0(%1),paddd 8(%2), 11)
/*ROW_IDCT( 32(%0), 40(%0), 48(%0), 56(%0), 32(%1), paddd (%2), 11)
ROW_IDCT( 64(%0), 72(%0), 80(%0), 88(%0), 64(%1), paddd (%2), 11)
ROW_IDCT( 96(%0),104(%0),112(%0),120(%0), 96(%1), paddd (%2), 11)*/
DC_COND_ROW_IDCT( 32(%0), 40(%0), 48(%0), 56(%0), 32(%1),paddd (%2), 11)
DC_COND_ROW_IDCT( 64(%0), 72(%0), 80(%0), 88(%0), 64(%1),paddd (%2), 11)
DC_COND_ROW_IDCT( 96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11)
//IDCT( src0, src4, src1, src5, dst, shift)
COL_IDCT( (%1), 64(%1), 32(%1), 96(%1), 0(%0), 20)
COL_IDCT( 8(%1), 72(%1), 40(%1), 104(%1), 4(%0), 20)
COL_IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)
COL_IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
#else
#define DC_COND_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
"movq " #src0 ", %%mm0 \n\t" /* R4 R0 r4 r0 */\
"movq " #src4 ", %%mm1 \n\t" /* R6 R2 r6 r2 */\
@ -1121,8 +868,6 @@ IDCT( 16(%1), 80(%1), 48(%1), 112(%1), 8(%0), 20)
//IDCT( 24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
#endif
/*
Input
00 40 04 44 20 60 24 64