Hi, Again, thanks for your patience and review. New patch please find in the attachment. The fate test results on both LE and BE are as follows: Regards, Rong Yan ------------------ The world has enough for everyone's need, but not enough for everyone's greed.
------------------ ???????? ------------------ ??????: "Tony Lin";<linzhaolo...@gmail.com>; ????????: 2014??11??12??(??????) ????9:38 ??????: "rongyan"<rongyan...@foxmail.com>; ????: Fwd: [FFmpeg-devel] Resubmit patch02 - [patch 4/4] Fix bugforPOWERLE: libswscale/ppc/swscale_altivec.c Forwarded conversation Subject: [FFmpeg-devel] Resubmit patch02 - [patch 4/4] Fix bug forPOWERLE: libswscale/ppc/swscale_altivec.c ------------------------ From: rongyan <rongyan...@foxmail.com> Date: 2014-11-11 14:18 GMT+08:00 To: ffmpeg-devel <ffmpeg-devel@ffmpeg.org> Hi, Thanks for your patience and review. New patch please find in the attachment. This is the second of two. The fate test result is here: Regards, Rong Yan ________________________________________________________________________________________________ Subject: [FFmpeg-devel] Resubmit patch02 - Fwd: [patch 4/4] Fix bug for POWERLE: libswscale/ppc/swscale_altivec.c ------------------------ From: rongyan <rongyan...@foxmail.com> Date: 2014-11-10 17:03 GMT+08:00 To: ffmpeg-devel <ffmpeg-devel@ffmpeg.org> Cc: Tony Lin <linzhaolo...@gmail.com> Hi, New patch please find in the attachment. There are two patches to re-submit, this is the second. The fate test result is here: Rong Yan ------------------ ???????? ------------------ ??????: "Tony Lin";<linzhaolo...@gmail.com>; ????????: 2014??11??10??(??????) ????11:32 ??????: "rongyan"<rongyan...@foxmail.com>; ????: Fwd: [FFmpeg-devel] [patch 4/4] Fix bug for POWERLE: libswscale/ppc/swscale_altivec.c Forwarded conversation Subject: [FFmpeg-devel] [patch 4/4] Fix bug for POWERLE: libswscale/ppc/swscale_altivec.c ------------------------ From: rongyan <rongyan...@foxmail.com> Date: 2014-11-07 17:43 GMT+08:00 To: ffmpeg-devel <ffmpeg-devel@ffmpeg.org> Hi, There are 4 patches presented to fix bugs for POWER8 little endian. I will send 4 patches in 4 different email. This is the fourth. It fixed the function hScale_altivec_real(), yuv2planeX_16_altivec(), yuv2planeX_8(). The fate test result on POWER BE and POWER LE after merge these 4 patches are attached here to facilitate the review: The passed test cases change from 1679/2182 to 2010/2236. Rong Yan ------------------ The world has enough for everyone's need, but not enough for everyone's greed. _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel ---------- From: Michael Niedermayer <michae...@gmx.at> Date: 2014-11-08 1:54 GMT+08:00 To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org> > swscale_altivec.c | 142 > +++++++++++++++++++----------------------------------- > 1 file changed, 50 insertions(+), 92 deletions(-) > 0c364d48e08b7df42bee5e269fe46b2d7be0f4b9 > 0004-libswscale-ppc-swscale_altivec.c-fix-hScale_altivec_.patch > From 9ec626726d1cc30db54390ee81f52cfe53ebeedf Mon Sep 17 00:00:00 2001 > From: Rong Yan <rongyan...@gmail.com> > Date: Fri, 7 Nov 2014 09:09:09 +0000 > Subject: [PATCH 4/4] libswscale/ppc/swscale_altivec.c : fix > hScale_altivec_real() yuv2planeX_16_altivec() yuv2planeX_8() for POWER LE > > --- > libswscale/ppc/swscale_altivec.c | 142 > ++++++++++++++------------------------- > 1 file changed, 50 insertions(+), 92 deletions(-) > > diff --git a/libswscale/ppc/swscale_altivec.c > b/libswscale/ppc/swscale_altivec.c > index 86f40ab..1673b8b 100644 > --- a/libswscale/ppc/swscale_altivec.c > +++ b/libswscale/ppc/swscale_altivec.c > @@ -29,20 +29,30 @@ > #include "libavutil/attributes.h" > #include "libavutil/cpu.h" > #include "yuv2rgb_altivec.h" > +#include "libavutil/ppc/util_altivec.h" > > #if HAVE_ALTIVEC > #define vzero vec_splat_s32(0) > > -#define yuv2planeX_8(d1, d2, l1, src, x, perm, filter) do { \ > - vector signed short l2 = vec_ld(((x) << 1) + 16, src); \ > - vector signed short ls = vec_perm(l1, l2, perm); \ > - vector signed int i1 = vec_mule(filter, ls); \ > - vector signed int i2 = vec_mulo(filter, ls); \ > - vector signed int vf1 = vec_mergeh(i1, i2); \ > - vector signed int vf2 = vec_mergel(i1, i2); \ > - d1 = vec_add(d1, vf1); \ > - d2 = vec_add(d2, vf2); \ > - l1 = l2; \ > +#if HAVE_BIGENDIAN > +#define GET_VF(a, b) {\ > + a = vec_mergeh(i1, i2);\ > + b = vec_mergel(i1, i2);\ > + } > +#else > +#define GET_VF(a, b) {\ > + a = vec_mergel(i2, i1);\ > + b = vec_mergeh(i2, i1);\ > + } > +#endif > + > +#define yuv2planeX_8(d1, d2, l1, src, x, filter) do {\ > + vector signed int i1 = vec_mule(filter, l1);\ > + vector signed int i2 = vec_mulo(filter, l1);\ > + vector signed int vf1, vf2;\ > + GET_VF(vf1, vf2);\ > + d1 = vec_add(d1, vf1);\ > + d2 = vec_add(d2, vf2);\ > } while (0) > > static void yuv2planeX_16_altivec(const int16_t *filter, int filterSize, > @@ -66,16 +76,13 @@ static void yuv2planeX_16_altivec(const int16_t *filter, > int filterSize, > vo4 = vec_ld(48, val); > > for (j = 0; j < filterSize; j++) { > - vector signed short l1, vLumFilter = vec_ld(j << 1, filter); > - vector unsigned char perm, perm0 = vec_lvsl(j << 1, filter); > - vLumFilter = vec_perm(vLumFilter, vLumFilter, perm0); > + vector signed short l1, l2; > + vector signed short vLumFilter = (vector signed > short)unaligned_load(j << 1, filter); > vLumFilter = vec_splat(vLumFilter, 0); // lumFilter[j] is loaded 8 > times in vLumFilter > - > - perm = vec_lvsl(x << 1, src[j]); > - l1 = vec_ld(x << 1, src[j]); > - > - yuv2planeX_8(vo1, vo2, l1, src[j], x, perm, vLumFilter); > - yuv2planeX_8(vo3, vo4, l1, src[j], x + 8, perm, vLumFilter); > + l1 = (vector signed short)unaligned_load(x << 1, src[j]); > + l2 = (vector signed short)unaligned_load(((x) << 1) + 16, src[j]); > + yuv2planeX_8(vo1, vo2, l1, src[j], x, vLumFilter); > + yuv2planeX_8(vo3, vo4, l2, src[j], x + 8, vLumFilter); > } i belive this uses more vec_ld() on big endian than before. i counted 4 before and 6 after the change this would likely slow big endian down [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Into a blind darkness they enter who follow after the Ignorance, they as if into a greater darkness enter who devote themselves to the Knowledge alone. -- Isha Upanishad _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel ---------- From: Michael Niedermayer <michae...@gmx.at> Date: 2014-11-10 23:13 GMT+08:00 To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org> > swscale_altivec.c | 163 > +++++++++++++++++++++++++----------------------------- > 1 file changed, 77 insertions(+), 86 deletions(-) > faf64846206b6d93a709b40f9e229a2329285ede > 0002-libswscale-ppc-swscale_altivec.c-fix-hScale_altivec_.patch > From 68a7c25b17cce4e473ddb458e7dfc93a58d4a560 Mon Sep 17 00:00:00 2001 > From: Rong Yan <rongyan...@gmail.com> > Date: Mon, 10 Nov 2014 08:42:10 +0000 > Subject: [PATCH 2/2] libswscale/ppc/swscale_altivec.c : fix > hScale_altivec_real() yuv2planeX_16_altivec() yuv2planeX_8() add marcos > GET_LS() GET_VF() for POWER LE > > --- > libswscale/ppc/swscale_altivec.c | 163 > ++++++++++++++++++--------------------- > 1 file changed, 77 insertions(+), 86 deletions(-) > > diff --git a/libswscale/ppc/swscale_altivec.c > b/libswscale/ppc/swscale_altivec.c > index 86f40ab..390c4bb 100644 > --- a/libswscale/ppc/swscale_altivec.c > +++ b/libswscale/ppc/swscale_altivec.c > @@ -29,22 +29,62 @@ > #include "libavutil/attributes.h" > #include "libavutil/cpu.h" > #include "yuv2rgb_altivec.h" > +#include "libavutil/ppc/util_altivec.h" > > #if HAVE_ALTIVEC > #define vzero vec_splat_s32(0) > > +#if HAVE_BIGENDIAN > +#define GET_LS(a,b,c,s) {\ > + vector signed short l2 = vec_ld(((b) << 1) + 16, s); \ > + ls = vec_perm(a, l2, c);\ > + a = l2;\ > + } > +#define GET_VF(a, b) {\ > + a = vec_mergeh(i1, i2);\ > + b = vec_mergel(i1, i2);\ > + } > +#else > +#define GET_LS(a,b,c,s) {\ > + ls = a; \ > + a = vec_vsx_ld(((b) << 1) + 16, s);\ > + } > +#define GET_VF(a, b) {\ > + a = vec_mergel(i2, i1);\ > + b = vec_mergeh(i2, i1);\ > + } i1 and i2 should be passed into the macro as well for example GET_VF(a, b, i1, i2) [...] > @@ -177,19 +201,12 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > for (i = 0; i < dstW; i++) { > register int srcPos = filterPos[i]; > > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char src_v1, src_vF; > + vector unsigned char src_vF = unaligned_load(srcPos, src); > vector signed short src_v, filter_v; > vector signed int val_v, val_s; > - if ((((uintptr_t)src + srcPos) % 16) > 8) { > - src_v1 = vec_ld(srcPos + 16, src); > - } > - src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src)); > - > src_v = // vec_unpackh sign-extends... > - (vector signed short)(vec_mergeh((vector unsigned > char)vzero, src_vF)); > - filter_v = vec_ld(i << 4, filter); > - // the 4 above is 3 (filterSize == 8) + 1 (sizeof(short) == > 2) > + (vector signed short)(VEC_MERGEH((vector unsigned > char)vzero, src_vF)); > + filter_v = (vector signed short)unaligned_load(i << 4, > filter); > > val_v = vec_msums(src_v, filter_v, (vector signed int)vzero); > val_s = vec_sums(val_v, vzero); the removed code does up to 3 vec_ld() on big endian, the added code does 4 vec_ld() > @@ -202,25 +219,21 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > for (i = 0; i < dstW; i++) { > register int srcPos = filterPos[i]; > > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char src_v1 = vec_ld(srcPos + 16, src); > - vector unsigned char src_vF = vec_perm(src_v0, src_v1, > vec_lvsl(srcPos, src)); > - > + vector unsigned char src_vF = unaligned_load(srcPos, src); > vector signed short src_vA = // vec_unpackh sign-extends... > - (vector signed > short)(vec_mergeh((vector unsigned char)vzero, src_vF)); > + (vector signed > short)(VEC_MERGEH((vector unsigned char)vzero, src_vF)); > vector signed short src_vB = // vec_unpackh sign-extends... > - (vector signed > short)(vec_mergel((vector unsigned char)vzero, src_vF)); > + (vector signed > short)(VEC_MERGEL((vector unsigned char)vzero, src_vF)); > > - vector signed short filter_v0 = vec_ld(i << 5, filter); > - vector signed short filter_v1 = vec_ld((i << 5) + 16, > filter); > - // the 5 above are 4 (filterSize == 16) + 1 (sizeof(short) > == 2) > + vector signed short filter_v0 = (vector signed > short)unaligned_load(i << 5, filter); > + vector signed short filter_v1 = (vector signed > short)unaligned_load((i << 5) + 16, filter); > > vector signed int val_acc = vec_msums(src_vA, filter_v0, > (vector signed int)vzero); > vector signed int val_v = vec_msums(src_vB, filter_v1, > val_acc); > > vector signed int val_s = vec_sums(val_v, vzero); > > - vec_st(val_s, 0, tempo); > + VEC_ST(val_s, 0, tempo); > dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1); > } the removed code does 3 vec_ld() the added code does 6 vec_ld() on big endian [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Its not that you shouldnt use gotos but rather that you should write readable code and code with gotos often but not always is less readable _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel ---------- From: Michael Niedermayer <michae...@gmx.at> Date: 2014-11-12 2:31 GMT+08:00 To: FFmpeg development discussions and patches <ffmpeg-devel@ffmpeg.org> [...] > @@ -140,31 +180,15 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > for (i = 0; i < dstW; i++) { > register int srcPos = filterPos[i]; > > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char src_v1, src_vF; > + vector unsigned char src_vF = unaligned_load(srcPos, src); > vector signed short src_v, filter_v; > vector signed int val_vEven, val_s; > - if ((((uintptr_t)src + srcPos) % 16) > 12) { > - src_v1 = vec_ld(srcPos + 16, src); > - } > - src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src)); > - > src_v = // vec_unpackh sign-extends... > - (vector signed short)(vec_mergeh((vector unsigned > char)vzero, src_vF)); > + (vector signed short)(VEC_MERGEH((vector unsigned > char)vzero, src_vF)); > // now put our elements in the even slots > src_v = vec_mergeh(src_v, (vector signed short)vzero); > - > - filter_v = vec_ld(i << 3, filter); > - // The 3 above is 2 (filterSize == 4) + 1 (sizeof(short) == > 2). > - > - // The neat trick: We only care for half the elements, > - // high or low depending on (i<<3)%16 (it's 0 or 8 here), > - // and we're going to use vec_mule, so we choose > - // carefully how to "unpack" the elements into the even > slots. > - if ((i << 3) % 16) > - filter_v = vec_mergel(filter_v, (vector signed > short)vzero); > - else > - filter_v = vec_mergeh(filter_v, (vector signed > short)vzero); > + filter_v = (vector signed short)unaligned_load(i << 3, > filter); > + filter_v = vec_mergeh(filter_v, (vector signed short)vzero); > > val_vEven = vec_mule(src_v, filter_v); > val_s = vec_sums(val_vEven, vzero); i see 3 vec_ld() before and 2 unaligned_load() each 2 vec_ld() afterwards on big endian > @@ -172,25 +196,16 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1); > } > break; > - > case 8: > for (i = 0; i < dstW; i++) { > register int srcPos = filterPos[i]; > > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char src_v1, src_vF; > + vector unsigned char src_vF = unaligned_load(srcPos, src); > vector signed short src_v, filter_v; > vector signed int val_v, val_s; > - if ((((uintptr_t)src + srcPos) % 16) > 8) { > - src_v1 = vec_ld(srcPos + 16, src); > - } > - src_vF = vec_perm(src_v0, src_v1, vec_lvsl(srcPos, src)); > - > src_v = // vec_unpackh sign-extends... > - (vector signed short)(vec_mergeh((vector unsigned > char)vzero, src_vF)); > + (vector signed short)(VEC_MERGEH((vector unsigned > char)vzero, src_vF)); > filter_v = vec_ld(i << 4, filter); > - // the 4 above is 3 (filterSize == 8) + 1 (sizeof(short) == > 2) > - > val_v = vec_msums(src_v, filter_v, (vector signed int)vzero); > val_s = vec_sums(val_v, vzero); > vec_st(val_s, 0, tempo); > @@ -202,25 +217,20 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > for (i = 0; i < dstW; i++) { > register int srcPos = filterPos[i]; > > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char src_v1 = vec_ld(srcPos + 16, src); > - vector unsigned char src_vF = vec_perm(src_v0, src_v1, > vec_lvsl(srcPos, src)); > - > + vector unsigned char src_vF = unaligned_load(srcPos, src); > vector signed short src_vA = // vec_unpackh sign-extends... > - (vector signed > short)(vec_mergeh((vector unsigned char)vzero, src_vF)); > + (vector signed > short)(VEC_MERGEH((vector unsigned char)vzero, src_vF)); > vector signed short src_vB = // vec_unpackh sign-extends... > - (vector signed > short)(vec_mergel((vector unsigned char)vzero, src_vF)); > - > + (vector signed > short)(VEC_MERGEL((vector unsigned char)vzero, src_vF)); > vector signed short filter_v0 = vec_ld(i << 5, filter); > vector signed short filter_v1 = vec_ld((i << 5) + 16, > filter); > - // the 5 above are 4 (filterSize == 16) + 1 (sizeof(short) > == 2) > > vector signed int val_acc = vec_msums(src_vA, filter_v0, > (vector signed int)vzero); > vector signed int val_v = vec_msums(src_vB, filter_v1, > val_acc); > > vector signed int val_s = vec_sums(val_v, vzero); > > - vec_st(val_s, 0, tempo); > + VEC_ST(val_s, 0, tempo); > dst[i] = FFMIN(tempo[3] >> 7, (1 << 15) - 1); > } > break; > @@ -231,56 +241,34 @@ static void hScale_altivec_real(SwsContext *c, int16_t > *dst, int dstW, > register int srcPos = filterPos[i]; > > vector signed int val_s, val_v = (vector signed int)vzero; > - vector signed short filter_v0R = vec_ld(i * 2 * filterSize, > filter); > - vector unsigned char permF = vec_lvsl((i * 2 * > filterSize), filter); > - > - vector unsigned char src_v0 = vec_ld(srcPos, src); > - vector unsigned char permS = vec_lvsl(srcPos, src); > > for (j = 0; j < filterSize - 15; j += 16) { > - vector unsigned char src_v1 = vec_ld(srcPos + j + 16, > src); > - vector unsigned char src_vF = vec_perm(src_v0, src_v1, > permS); > - > + vector unsigned char src_vF = unaligned_load(srcPos + j, > src); > vector signed short src_vA = // vec_unpackh > sign-extends... > - (vector signed > short)(vec_mergeh((vector unsigned char)vzero, src_vF)); > + (vector signed > short)(VEC_MERGEH((vector unsigned char)vzero, src_vF)); > vector signed short src_vB = // vec_unpackh > sign-extends... > - (vector signed > short)(vec_mergel((vector unsigned char)vzero, src_vF)); > - > - vector signed short filter_v1R = vec_ld((i * 2 * > filterSize) + (j * 2) + 16, filter); > - vector signed short filter_v2R = vec_ld((i * 2 * > filterSize) + (j * 2) + 32, filter); > - vector signed short filter_v0 = vec_perm(filter_v0R, > filter_v1R, permF); > - vector signed short filter_v1 = vec_perm(filter_v1R, > filter_v2R, permF); > + (vector signed > short)(VEC_MERGEL((vector unsigned char)vzero, src_vF)); > + vector signed short filter_v0 = (vector signed > short)unaligned_load((i * 2 * filterSize) + (j * 2), filter); > + vector signed short filter_v1 = (vector signed > short)unaligned_load((i * 2 * filterSize) + (j * 2) + 16, filter); > > vector signed int val_acc = vec_msums(src_vA, filter_v0, > val_v); > val_v = vec_msums(src_vB, filter_v1, val_acc); > - > - filter_v0R = filter_v2R; > - src_v0 = src_v1; > } i count 3 vec_ld() before and 6 (2 for each unaligned_load()) after the change for big endian [...] -- Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Awnsering whenever a program halts or runs forever is On a turing machine, in general impossible (turings halting problem). On any real computer, always possible as a real computer has a finite number of states N, and will either halt in less than N cycles or never halt. _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
0001-libswscale-ppc-swscale_altivec.c-fix-hScale_altivec_.patch
Description: Binary data
_______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
