| Message ID | 20211216162710.2181015-1-alankelly@google.com |
|---|---|
| State | Accepted |
| Commit | 9092e58c4469f5488f305fdb85e34e61bba7b04a |
| Headers | show |
| Series | [FFmpeg-devel] x86/scale_avx2: Change asm indent from 2 to 4 spaces. | expand |
| Context | Check | Description |
|---|---|---|
| andriy/make_x86 | success | Make finished |
| andriy/make_fate_x86 | success | Make fate finished |
| andriy/make_ppc | success | Make finished |
| andriy/make_fate_ppc | success | Make fate finished |
On 12/16/2021 1:27 PM, Alan Kelly wrote: > --- > libswscale/x86/scale_avx2.asm | 96 +++++++++++++++++------------------ > 1 file changed, 48 insertions(+), 48 deletions(-) > > diff --git a/libswscale/x86/scale_avx2.asm b/libswscale/x86/scale_avx2.asm > index 2cd7e968d3..eb472db12f 100644 > --- a/libswscale/x86/scale_avx2.asm > +++ b/libswscale/x86/scale_avx2.asm > @@ -45,63 +45,63 @@ SECTION .text > > %macro SCALE_FUNC 1 > cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, count, inner > - pxor m0, m0 > - mova m15, [swizzle] > - mov countq, $0 > - movsxd wq, wd > + pxor m0, m0 > + mova m15, [swizzle] > + mov countq, $0 > + movsxd wq, wd > %ifidn %1, X4 > - mova m14, [four] > - shr fltsized, 2 > + mova m14, [four] > + shr fltsized, 2 > %endif > .loop: > - movu m1, [fltposq] > - movu m2, [fltposq+32] > + movu m1, [fltposq] > + movu m2, [fltposq+32] > %ifidn %1, X4 > - pxor m9, m9 > - pxor m10, m10 > - pxor m11, m11 > - pxor m12, m12 > - mov innerq, $0 > + pxor m9, m9 > + pxor m10, m10 > + pxor m11, m11 > + pxor m12, m12 > + mov innerq, $0 > .innerloop: > %endif > - vpcmpeqd m13, m13 > - vpgatherdd m3,[srcmemq + m1], m13 > - vpcmpeqd m13, m13 > - vpgatherdd m4,[srcmemq + m2], m13 > - vpunpcklbw m5, m3, m0 > - vpunpckhbw m6, m3, m0 > - vpunpcklbw m7, m4, m0 > - vpunpckhbw m8, m4, m0 > - vpmaddwd m5, m5, [filterq] > - vpmaddwd m6, m6, [filterq + 32] > - vpmaddwd m7, m7, [filterq + 64] > - vpmaddwd m8, m8, [filterq + 96] > - add filterq, $80 > + vpcmpeqd m13, m13 > + vpgatherdd m3,[srcmemq + m1], m13 > + vpcmpeqd m13, m13 > + vpgatherdd m4,[srcmemq + m2], m13 > + vpunpcklbw m5, m3, m0 > + vpunpckhbw m6, m3, m0 > + vpunpcklbw m7, m4, m0 > + vpunpckhbw m8, m4, m0 > + vpmaddwd m5, m5, [filterq] > + vpmaddwd m6, m6, [filterq + 32] > + vpmaddwd m7, m7, [filterq + 64] > + vpmaddwd m8, m8, [filterq + 96] > + add filterq, $80 > %ifidn %1, X4 > - paddd m9, m5 > - paddd m10, m6 > - paddd m11, m7 > - paddd m12, m8 > - paddd m1, m14 > - paddd m2, m14 > - add innerq, $1 > - cmp innerq, fltsizeq > - jl .innerloop > - vphaddd m5, m9, m10 > - vphaddd m6, m11, m12 > + paddd m9, m5 > + paddd m10, m6 > + paddd m11, m7 > + paddd m12, m8 > + paddd m1, m14 > + paddd m2, m14 > + add innerq, $1 > + cmp innerq, fltsizeq > + jl .innerloop > + vphaddd m5, m9, m10 > + vphaddd m6, m11, m12 > %else > - vphaddd m5, m5, m6 > - vphaddd m6, m7, m8 > + vphaddd m5, m5, m6 > + vphaddd m6, m7, m8 > %endif > - vpsrad m5, 7 > - vpsrad m6, 7 > - vpackssdw m5, m5, m6 > - vpermd m5, m15, m5 > - vmovdqu [dstq + countq * 2], m5 > - add fltposq, $40 > - add countq, $10 > - cmp countq, wq > - jl .loop > + vpsrad m5, 7 > + vpsrad m6, 7 > + vpackssdw m5, m5, m6 > + vpermd m5, m15, m5 > + vmovdqu [dstq + countq * 2], m5 > + add fltposq, $40 > + add countq, $10 > + cmp countq, wq > + jl .loop > REP_RET > %endmacro Applied, thanks.
diff --git a/libswscale/x86/scale_avx2.asm b/libswscale/x86/scale_avx2.asm index 2cd7e968d3..eb472db12f 100644 --- a/libswscale/x86/scale_avx2.asm +++ b/libswscale/x86/scale_avx2.asm @@ -45,63 +45,63 @@ SECTION .text %macro SCALE_FUNC 1 cglobal hscale8to15_%1, 7, 9, 16, pos0, dst, w, srcmem, filter, fltpos, fltsize, count, inner - pxor m0, m0 - mova m15, [swizzle] - mov countq, $0 - movsxd wq, wd + pxor m0, m0 + mova m15, [swizzle] + mov countq, $0 + movsxd wq, wd %ifidn %1, X4 - mova m14, [four] - shr fltsized, 2 + mova m14, [four] + shr fltsized, 2 %endif .loop: - movu m1, [fltposq] - movu m2, [fltposq+32] + movu m1, [fltposq] + movu m2, [fltposq+32] %ifidn %1, X4 - pxor m9, m9 - pxor m10, m10 - pxor m11, m11 - pxor m12, m12 - mov innerq, $0 + pxor m9, m9 + pxor m10, m10 + pxor m11, m11 + pxor m12, m12 + mov innerq, $0 .innerloop: %endif - vpcmpeqd m13, m13 - vpgatherdd m3,[srcmemq + m1], m13 - vpcmpeqd m13, m13 - vpgatherdd m4,[srcmemq + m2], m13 - vpunpcklbw m5, m3, m0 - vpunpckhbw m6, m3, m0 - vpunpcklbw m7, m4, m0 - vpunpckhbw m8, m4, m0 - vpmaddwd m5, m5, [filterq] - vpmaddwd m6, m6, [filterq + 32] - vpmaddwd m7, m7, [filterq + 64] - vpmaddwd m8, m8, [filterq + 96] - add filterq, $80 + vpcmpeqd m13, m13 + vpgatherdd m3,[srcmemq + m1], m13 + vpcmpeqd m13, m13 + vpgatherdd m4,[srcmemq + m2], m13 + vpunpcklbw m5, m3, m0 + vpunpckhbw m6, m3, m0 + vpunpcklbw m7, m4, m0 + vpunpckhbw m8, m4, m0 + vpmaddwd m5, m5, [filterq] + vpmaddwd m6, m6, [filterq + 32] + vpmaddwd m7, m7, [filterq + 64] + vpmaddwd m8, m8, [filterq + 96] + add filterq, $80 %ifidn %1, X4 - paddd m9, m5 - paddd m10, m6 - paddd m11, m7 - paddd m12, m8 - paddd m1, m14 - paddd m2, m14 - add innerq, $1 - cmp innerq, fltsizeq - jl .innerloop - vphaddd m5, m9, m10 - vphaddd m6, m11, m12 + paddd m9, m5 + paddd m10, m6 + paddd m11, m7 + paddd m12, m8 + paddd m1, m14 + paddd m2, m14 + add innerq, $1 + cmp innerq, fltsizeq + jl .innerloop + vphaddd m5, m9, m10 + vphaddd m6, m11, m12 %else - vphaddd m5, m5, m6 - vphaddd m6, m7, m8 + vphaddd m5, m5, m6 + vphaddd m6, m7, m8 %endif - vpsrad m5, 7 - vpsrad m6, 7 - vpackssdw m5, m5, m6 - vpermd m5, m15, m5 - vmovdqu [dstq + countq * 2], m5 - add fltposq, $40 - add countq, $10 - cmp countq, wq - jl .loop + vpsrad m5, 7 + vpsrad m6, 7 + vpackssdw m5, m5, m6 + vpermd m5, m15, m5 + vmovdqu [dstq + countq * 2], m5 + add fltposq, $40 + add countq, $10 + cmp countq, wq + jl .loop REP_RET %endmacro