| Upstream-Status: Pending |
| |
| Make the assembly syntax compatible with x32 gcc. Othewise x32 gcc throws errors. |
| |
| Signed-Off-By: Nitin A Kamble <nitin.a.kamble@intel.com> |
| 2011/12/01 |
| |
| |
| Index: liboil-0.3.17/liboil/amd64/wavelet.c |
| =================================================================== |
| --- liboil-0.3.17.orig/liboil/amd64/wavelet.c |
| +++ liboil-0.3.17/liboil/amd64/wavelet.c |
| @@ -21,14 +21,14 @@ deinterleave2_asm (int16_t *d1, int16_t |
| asm volatile ("\n" |
| " sub $2, %%rcx\n" |
| "1:\n" |
| - " movw (%1,%%rcx,4), %%ax\n" |
| - " movw %%ax, (%0,%%rcx,2)\n" |
| - " movw 2(%1,%%rcx,4), %%ax\n" |
| - " movw %%ax, (%2,%%rcx,2)\n" |
| - " movw 4(%1,%%rcx,4), %%ax\n" |
| - " movw %%ax, 2(%0,%%rcx,2)\n" |
| - " movw 6(%1,%%rcx,4), %%ax\n" |
| - " movw %%ax, 2(%2,%%rcx,2)\n" |
| + " movw (%q1,%%rcx,4), %%ax\n" |
| + " movw %%ax, (%q0,%%rcx,2)\n" |
| + " movw 2(%q1,%%rcx,4), %%ax\n" |
| + " movw %%ax, (%q2,%%rcx,2)\n" |
| + " movw 4(%q1,%%rcx,4), %%ax\n" |
| + " movw %%ax, 2(%q0,%%rcx,2)\n" |
| + " movw 6(%q1,%%rcx,4), %%ax\n" |
| + " movw %%ax, 2(%q2,%%rcx,2)\n" |
| " sub $2, %%rcx\n" |
| " jge 1b\n" |
| : "+r" (d1), "+r" (s_2xn), "+r" (d2), "+c" (n) |
| @@ -53,20 +53,20 @@ deinterleave2_mmx (int16_t *d1, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%1,%%rcx,4), %%mm0\n" |
| - " movq 8(%1,%%rcx,4), %%mm1\n" |
| + " movq (%q1,%%rcx,4), %%mm0\n" |
| + " movq 8(%q1,%%rcx,4), %%mm1\n" |
| " pslld $16, %%mm0\n" |
| " pslld $16, %%mm1\n" |
| " psrad $16, %%mm0\n" |
| " psrad $16, %%mm1\n" |
| " packssdw %%mm1, %%mm0\n" |
| - " movq %%mm0, (%0,%%rcx,2)\n" |
| - " movq (%1,%%rcx,4), %%mm0\n" |
| - " movq 8(%1,%%rcx,4), %%mm1\n" |
| + " movq %%mm0, (%q0,%%rcx,2)\n" |
| + " movq (%q1,%%rcx,4), %%mm0\n" |
| + " movq 8(%q1,%%rcx,4), %%mm1\n" |
| " psrad $16, %%mm0\n" |
| " psrad $16, %%mm1\n" |
| " packssdw %%mm1, %%mm0\n" |
| - " movq %%mm0, (%2,%%rcx,2)\n" |
| + " movq %%mm0, (%q2,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %3, %%ecx\n" |
| " jl 1b\n" |
| @@ -93,10 +93,10 @@ deinterleave2_mmx_2 (int16_t *d1, int16_ |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " pshufw $0xd8, (%1,%%rcx,4), %%mm0\n" |
| - " movd %%mm0, (%0,%%rcx,2)\n" |
| - " pshufw $0x8d, (%1,%%rcx,4), %%mm0\n" |
| - " movd %%mm0, (%2,%%rcx,2)\n" |
| + " pshufw $0xd8, (%q1,%%rcx,4), %%mm0\n" |
| + " movd %%mm0, (%q0,%%rcx,2)\n" |
| + " pshufw $0x8d, (%q1,%%rcx,4), %%mm0\n" |
| + " movd %%mm0, (%q2,%%rcx,2)\n" |
| " add $2, %%rcx\n" |
| " cmp %3, %%ecx\n" |
| " jl 1b\n" |
| @@ -123,16 +123,16 @@ deinterleave2_mmx_3 (int16_t *d1, int16_ |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%1,%%rcx,4), %%mm1\n" |
| - " movq (%1,%%rcx,4), %%mm2\n" |
| - " movq 8(%1,%%rcx,4), %%mm0\n" |
| + " movq (%q1,%%rcx,4), %%mm1\n" |
| + " movq (%q1,%%rcx,4), %%mm2\n" |
| + " movq 8(%q1,%%rcx,4), %%mm0\n" |
| " punpcklwd %%mm0, %%mm1\n" |
| " punpckhwd %%mm0, %%mm2\n" |
| " movq %%mm1, %%mm0\n" |
| " punpcklwd %%mm2, %%mm0\n" |
| " punpckhwd %%mm2, %%mm1\n" |
| - " movq %%mm0, (%0,%%rcx,2)\n" |
| - " movq %%mm1, (%2,%%rcx,2)\n" |
| + " movq %%mm0, (%q0,%%rcx,2)\n" |
| + " movq %%mm1, (%q2,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %3, %%ecx\n" |
| " jl 1b\n" |
| @@ -159,26 +159,26 @@ deinterleave2_mmx_4 (int16_t *d1, int16_ |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%1,%%rcx,4), %%mm1\n" |
| + " movq (%q1,%%rcx,4), %%mm1\n" |
| " movq %%mm1, %%mm2\n" |
| - " movq 8(%1,%%rcx,4), %%mm0\n" |
| - " movq 16(%1,%%rcx,4), %%mm5\n" |
| + " movq 8(%q1,%%rcx,4), %%mm0\n" |
| + " movq 16(%q1,%%rcx,4), %%mm5\n" |
| " punpcklwd %%mm0, %%mm1\n" |
| " movq %%mm5, %%mm6\n" |
| " punpckhwd %%mm0, %%mm2\n" |
| - " movq 24(%1,%%rcx,4), %%mm4\n" |
| + " movq 24(%q1,%%rcx,4), %%mm4\n" |
| " movq %%mm1, %%mm0\n" |
| " punpcklwd %%mm4, %%mm5\n" |
| " punpcklwd %%mm2, %%mm0\n" |
| " punpckhwd %%mm4, %%mm6\n" |
| " punpckhwd %%mm2, %%mm1\n" |
| " movq %%mm5, %%mm4\n" |
| - " movq %%mm0, (%0,%%rcx,2)\n" |
| + " movq %%mm0, (%q0,%%rcx,2)\n" |
| " punpcklwd %%mm6, %%mm4\n" |
| - " movq %%mm1, (%2,%%rcx,2)\n" |
| + " movq %%mm1, (%q2,%%rcx,2)\n" |
| " punpckhwd %%mm6, %%mm5\n" |
| - " movq %%mm4, 8(%0,%%rcx,2)\n" |
| - " movq %%mm5, 8(%2,%%rcx,2)\n" |
| + " movq %%mm4, 8(%q0,%%rcx,2)\n" |
| + " movq %%mm5, 8(%q2,%%rcx,2)\n" |
| " add $8, %%rcx\n" |
| " cmp %3, %%ecx\n" |
| " jl 1b\n" |
| @@ -252,13 +252,13 @@ interleave2_mmx (int16_t *d_2xn, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%1,%%rcx,2), %%mm0\n" |
| - " movq (%2,%%rcx,2), %%mm1\n" |
| + " movq (%q1,%%rcx,2), %%mm0\n" |
| + " movq (%q2,%%rcx,2), %%mm1\n" |
| " movq %%mm0, %%mm2\n" |
| " punpckhwd %%mm1, %%mm0\n" |
| " punpcklwd %%mm1, %%mm2\n" |
| - " movq %%mm2, (%0,%%rcx,4)\n" |
| - " movq %%mm0, 8(%0,%%rcx,4)\n" |
| + " movq %%mm2, (%q0,%%rcx,4)\n" |
| + " movq %%mm0, 8(%q0,%%rcx,4)\n" |
| " add $4, %%rcx\n" |
| " cmp %3, %%ecx\n" |
| " jl 1b\n" |
| @@ -285,12 +285,12 @@ lift_add_shift1_mmx (int16_t *d, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%2,%%rcx,2), %%mm1\n" |
| - " movq (%3,%%rcx,2), %%mm2\n" |
| + " movq (%q2,%%rcx,2), %%mm1\n" |
| + " movq (%q3,%%rcx,2), %%mm2\n" |
| " paddw %%mm2, %%mm1\n" |
| " psraw $1, %%mm1\n" |
| - " paddw (%1,%%rcx,2), %%mm1\n" |
| - " movq %%mm1, (%0,%%rcx,2)\n" |
| + " paddw (%q1,%%rcx,2), %%mm1\n" |
| + " movq %%mm1, (%q0,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %4, %%ecx\n" |
| " jl 1b\n" |
| @@ -317,13 +317,13 @@ lift_sub_shift1_mmx (int16_t *d, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%2,%%rcx,2), %%mm1\n" |
| - " movq (%3,%%rcx,2), %%mm2\n" |
| - " movq (%1,%%rcx,2), %%mm0\n" |
| + " movq (%q2,%%rcx,2), %%mm1\n" |
| + " movq (%q3,%%rcx,2), %%mm2\n" |
| + " movq (%q1,%%rcx,2), %%mm0\n" |
| " paddw %%mm2, %%mm1\n" |
| " psraw $1, %%mm1\n" |
| " psubw %%mm1, %%mm0\n" |
| - " movq %%mm0, (%0,%%rcx,2)\n" |
| + " movq %%mm0, (%q0,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %4, %%ecx\n" |
| " jl 1b\n" |
| @@ -350,12 +350,12 @@ lift_add_shift2_mmx (int16_t *d, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%2,%%rcx,2), %%mm1\n" |
| - " movq (%3,%%rcx,2), %%mm2\n" |
| + " movq (%q2,%%rcx,2), %%mm1\n" |
| + " movq (%q3,%%rcx,2), %%mm2\n" |
| " paddw %%mm2, %%mm1\n" |
| " psraw $2, %%mm1\n" |
| - " paddw (%1,%%rcx,2), %%mm1\n" |
| - " movq %%mm1, (%0,%%rcx,2)\n" |
| + " paddw (%q1,%%rcx,2), %%mm1\n" |
| + " movq %%mm1, (%q0,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %4, %%ecx\n" |
| " jl 1b\n" |
| @@ -382,13 +382,13 @@ lift_sub_shift2_mmx (int16_t *d, int16_t |
| asm volatile ("\n" |
| " xor %%rcx, %%rcx\n" |
| "1:\n" |
| - " movq (%2,%%rcx,2), %%mm1\n" |
| - " movq (%3,%%rcx,2), %%mm2\n" |
| - " movq (%1,%%rcx,2), %%mm0\n" |
| + " movq (%q2,%%rcx,2), %%mm1\n" |
| + " movq (%q3,%%rcx,2), %%mm2\n" |
| + " movq (%q1,%%rcx,2), %%mm0\n" |
| " paddw %%mm2, %%mm1\n" |
| " psraw $2, %%mm1\n" |
| " psubw %%mm1, %%mm0\n" |
| - " movq %%mm0, (%0,%%rcx,2)\n" |
| + " movq %%mm0, (%q0,%%rcx,2)\n" |
| " add $4, %%rcx\n" |
| " cmp %4, %%ecx\n" |
| " jl 1b\n" |