Date: Wed, 21 Jul 2021 20:10:31 GMT From: Piotr Kubaj <pkubaj@FreeBSD.org> To: ports-committers@FreeBSD.org, dev-commits-ports-all@FreeBSD.org, dev-commits-ports-main@FreeBSD.org Subject: git: 2b3e3f331065 - main - multimedia/handbrake: update to 1.4.0 Message-ID: <202107212010.16LKAVsu002496@gitrepo.freebsd.org>
next in thread | raw e-mail | index | archive | help
The branch main has been updated by pkubaj: URL: https://cgit.FreeBSD.org/ports/commit/?id=2b3e3f331065f84a1af8cf8363f2a30b28955f54 commit 2b3e3f331065f84a1af8cf8363f2a30b28955f54 Author: Piotr Kubaj <pkubaj@FreeBSD.org> AuthorDate: 2021-07-21 20:10:14 +0000 Commit: Piotr Kubaj <pkubaj@FreeBSD.org> CommitDate: 2021-07-21 20:10:14 +0000 multimedia/handbrake: update to 1.4.0 Differential revision: https://reviews.freebsd.org/D31252 Submitted by: naito.yuichiro@gmail.com (maintainer) --- multimedia/handbrake/Makefile | 21 +- multimedia/handbrake/distinfo | 32 +- .../files/P02-freebsd-ppc-libswscale.patch | 1323 -------------------- .../files/patch-contrib_ffmpeg_module.defs | 15 - .../files/patch-contrib_x265__10bit_module.defs | 10 +- .../files/patch-contrib_x265__12bit_module.defs | 10 +- multimedia/handbrake/files/patch-gtk_configure.ac | 12 - .../handbrake/files/patch-libhb_handbrake_ports.h | 36 - multimedia/handbrake/files/patch-libhb_ports.c | 41 - .../handbrake/files/patch-libhb_qsv__common.c | 20 - multimedia/handbrake/files/patch-make_configure.py | 29 - .../handbrake/files/patch-make_include_main.defs | 12 - multimedia/handbrake/files/patch-test_module.defs | 11 - multimedia/handbrake/files/version.txt | 10 +- multimedia/handbrake/pkg-plist | 4 + 15 files changed, 46 insertions(+), 1540 deletions(-) diff --git a/multimedia/handbrake/Makefile b/multimedia/handbrake/Makefile index e24f3f6e24bb..12fae398fed2 100644 --- a/multimedia/handbrake/Makefile +++ b/multimedia/handbrake/Makefile @@ -1,8 +1,7 @@ # Created by: Andrew Thompson <andy@fud.org.nz> PORTNAME= handbrake -DISTVERSION= 1.3.3 -PORTREVISION= 4 +DISTVERSION= 1.4.0 CATEGORIES= multimedia DIST_SUBDIR= ${PORTNAME} @@ -19,10 +18,12 @@ BUILD_DEPENDS= bash:shells/bash \ cmake:devel/cmake \ meson:devel/meson LIB_DEPENDS= libdbus-1.so:devel/dbus \ + libgudev-1.0.so:devel/libgudev \ libharfbuzz.so:print/harfbuzz \ libfontconfig.so:x11-fonts/fontconfig \ libfreetype.so:print/freetype2 \ libfribidi.so:converters/fribidi \ + libturbojpeg.so:graphics/libjpeg-turbo \ libxml2.so:textproc/libxml2 \ libass.so:multimedia/libass \ libspeex.so:audio/speex \ @@ -41,12 +42,13 @@ USES= autoreconf:build compiler:c11 gmake iconv libtool:build \ localbase:ldflags ninja:build pkgconfig python:3.6+,build CONTRIB_FILES= fdk-aac-2.0.1.tar.gz \ - ffmpeg-4.2.3.tar.bz2 \ - libbluray-1.1.2.tar.bz2 \ - libdvdnav-6.0.1.tar.bz2 \ - libdvdread-6.0.2.tar.bz2 \ - dav1d-0.5.1.tar.bz2 \ - x265_3.2.1.tar.gz + ffmpeg-4.4.tar.bz2 \ + libbluray-1.3.0.tar.bz2 \ + libdvdnav-6.1.1.tar.bz2 \ + libdvdread-6.1.1.tar.bz2 \ + dav1d-0.9.0.tar.bz2 \ + x265_3.5.tar.gz \ + zimg-3.0.1.tar.gz MASTER_SITES+= https://github.com/HandBrake/HandBrake-contribs/releases/download/contribs/:contrib @@ -126,9 +128,6 @@ pre-configure: # Following patches reduces warnings with clang. ${CP} ${FILESDIR}/P00-freebsd-libavutil-x86-asm-h.patch ${WRKSRC}/contrib/ffmpeg ${CP} ${FILESDIR}/P01-freebsd-ifo_types.h.patch ${WRKSRC}/contrib/libdvdread -# for powerpc64. -# picked from multimedia/ffmpeg/files/patch-libswscale_ppc_swscale__altivec.c - ${CP} ${FILESDIR}/P02-freebsd-ppc-libswscale.patch ${WRKSRC}/contrib/ffmpeg post-install-X11-on: ${LN} -sf ghb ${STAGEDIR}${PREFIX}/bin/HandBrake diff --git a/multimedia/handbrake/distinfo b/multimedia/handbrake/distinfo index d908b7e9f86e..e47319e4e17a 100644 --- a/multimedia/handbrake/distinfo +++ b/multimedia/handbrake/distinfo @@ -1,17 +1,19 @@ -TIMESTAMP = 1592180378 +TIMESTAMP = 1626703173 SHA256 (handbrake/fdk-aac-2.0.1.tar.gz) = a4142815d8d52d0e798212a5adea54ecf42bcd4eec8092b37a8cb615ace91dc6 SIZE (handbrake/fdk-aac-2.0.1.tar.gz) = 2488373 -SHA256 (handbrake/ffmpeg-4.2.3.tar.bz2) = 217eb211c33303b37c5521a5abe1f0140854d6810c6a6ee399456cc96356795e -SIZE (handbrake/ffmpeg-4.2.3.tar.bz2) = 10957405 -SHA256 (handbrake/libbluray-1.1.2.tar.bz2) = a3dd452239b100dc9da0d01b30e1692693e2a332a7d29917bf84bb10ea7c0b42 -SIZE (handbrake/libbluray-1.1.2.tar.bz2) = 745779 -SHA256 (handbrake/libdvdnav-6.0.1.tar.bz2) = e566a396f1950017088bfd760395b0565db44234195ada5413366c9d23926733 -SIZE (handbrake/libdvdnav-6.0.1.tar.bz2) = 378491 -SHA256 (handbrake/libdvdread-6.0.2.tar.bz2) = f91401af213b219cdde24b46c50a57f29301feb7f965678f1d7ed4632cc6feb0 -SIZE (handbrake/libdvdread-6.0.2.tar.bz2) = 405298 -SHA256 (handbrake/dav1d-0.5.1.tar.bz2) = 0214d201a338e8418f805b68f9ad277e33d79c18594dee6eaf6dcd74db2674a9 -SIZE (handbrake/dav1d-0.5.1.tar.bz2) = 548584 -SHA256 (handbrake/x265_3.2.1.tar.gz) = fb9badcf92364fd3567f8b5aa0e5e952aeea7a39a2b864387cec31e3b58cbbcc -SIZE (handbrake/x265_3.2.1.tar.gz) = 1426255 -SHA256 (handbrake/HandBrake-HandBrake-1.3.3_GH0.tar.gz) = 4a004666cdf4570385c7e4d8da093f36b4baa86e32bb0814b4d14e267905e3b3 -SIZE (handbrake/HandBrake-HandBrake-1.3.3_GH0.tar.gz) = 17925272 +SHA256 (handbrake/ffmpeg-4.4.tar.bz2) = 42093549751b582cf0f338a21a3664f52e0a9fbe0d238d3c992005e493607d0e +SIZE (handbrake/ffmpeg-4.4.tar.bz2) = 11489948 +SHA256 (handbrake/libbluray-1.3.0.tar.bz2) = e2dbaf99e84e0a9725f4985bcb85d41e52c2261cc651d8884b1b790b5ef016f9 +SIZE (handbrake/libbluray-1.3.0.tar.bz2) = 754069 +SHA256 (handbrake/libdvdnav-6.1.1.tar.bz2) = c191a7475947d323ff7680cf92c0fb1be8237701885f37656c64d04e98d18d48 +SIZE (handbrake/libdvdnav-6.1.1.tar.bz2) = 367606 +SHA256 (handbrake/libdvdread-6.1.1.tar.bz2) = 3e357309a17c5be3731385b9eabda6b7e3fa010f46022a06f104553bf8e21796 +SIZE (handbrake/libdvdread-6.1.1.tar.bz2) = 392134 +SHA256 (handbrake/dav1d-0.9.0.tar.bz2) = e0cb645f170e7a087bc76e501324177be51a8db21df22ad37b43d289d7d1f7b5 +SIZE (handbrake/dav1d-0.9.0.tar.bz2) = 771739 +SHA256 (handbrake/x265_3.5.tar.gz) = e70a3335cacacbba0b3a20ec6fecd6783932288ebc8163ad74bcc9606477cae8 +SIZE (handbrake/x265_3.5.tar.gz) = 1537044 +SHA256 (handbrake/zimg-3.0.1.tar.gz) = c50a0922f4adac4efad77427d13520ed89b8366eef0ef2fa379572951afcc73f +SIZE (handbrake/zimg-3.0.1.tar.gz) = 326304 +SHA256 (handbrake/HandBrake-HandBrake-1.4.0_GH0.tar.gz) = 32e9bb9d30d17c5d503ad29049d8e2b04a1ed900cf7877650139b7d504b0a2b3 +SIZE (handbrake/HandBrake-HandBrake-1.4.0_GH0.tar.gz) = 16787997 diff --git a/multimedia/handbrake/files/P02-freebsd-ppc-libswscale.patch b/multimedia/handbrake/files/P02-freebsd-ppc-libswscale.patch deleted file mode 100644 index 1c0eb8192f74..000000000000 --- a/multimedia/handbrake/files/P02-freebsd-ppc-libswscale.patch +++ /dev/null @@ -1,1323 +0,0 @@ ---- a/libswscale/ppc/swscale_altivec.c.orig 2019-08-11 20:06:32 UTC -+++ b/libswscale/ppc/swscale_altivec.c -@@ -153,13 +153,13 @@ static void yuv2plane1_float_altivec(const int32_t *sr - const int add = (1 << (shift - 1)); - const int clip = (1 << 16) - 1; - const float fmult = 1.0f / 65535.0f; -- const vector uint32_t vadd = (vector uint32_t) {add, add, add, add}; -- const vector uint32_t vshift = (vector uint32_t) vec_splat_u32(shift); -- const vector uint32_t vlargest = (vector uint32_t) {clip, clip, clip, clip}; -- const vector float vmul = (vector float) {fmult, fmult, fmult, fmult}; -- const vector float vzero = (vector float) {0, 0, 0, 0}; -- vector uint32_t v; -- vector float vd; -+ const vec_u32 vadd = (vec_u32) {add, add, add, add}; -+ const vec_u32 vshift = (vec_u32) vec_splat_u32(shift); -+ const vec_u32 vlargest = (vec_u32) {clip, clip, clip, clip}; -+ const vec_f vmul = (vec_f) {fmult, fmult, fmult, fmult}; -+ const vec_f vzero = (vec_f) {0, 0, 0, 0}; -+ vec_u32 v; -+ vec_f vd; - int i; - - yuv2plane1_float_u(src, dest, dst_u, 0); -@@ -186,14 +186,14 @@ static void yuv2plane1_float_bswap_altivec(const int32 - const int add = (1 << (shift - 1)); - const int clip = (1 << 16) - 1; - const float fmult = 1.0f / 65535.0f; -- const vector uint32_t vadd = (vector uint32_t) {add, add, add, add}; -- const vector uint32_t vshift = (vector uint32_t) vec_splat_u32(shift); -- const vector uint32_t vlargest = (vector uint32_t) {clip, clip, clip, clip}; -+ const vec_u32 vadd = (vec_u32) {add, add, add, add}; -+ const vec_u32 vshift = (vec_u32) vec_splat_u32(shift); -+ const vec_u32 vlargest = (vec_u32) {clip, clip, clip, clip}; - const vector float vmul = (vector float) {fmult, fmult, fmult, fmult}; - const vector float vzero = (vector float) {0, 0, 0, 0}; -- const vector uint32_t vswapbig = (vector uint32_t) {16, 16, 16, 16}; -- const vector uint16_t vswapsmall = vec_splat_u16(8); -- vector uint32_t v; -+ const vec_u32 vswapbig = (vec_u32) {16, 16, 16, 16}; -+ const vec_u16 vswapsmall = vec_splat_u16(8); -+ vec_u32 v; - vector float vd; - int i; - -@@ -208,8 +208,8 @@ static void yuv2plane1_float_bswap_altivec(const int32 - vd = vec_ctf(v, 0); - vd = vec_madd(vd, vmul, vzero); - -- vd = (vector float) vec_rl((vector uint32_t) vd, vswapbig); -- vd = (vector float) vec_rl((vector uint16_t) vd, vswapsmall); -+ vd = (vector float) vec_rl((vec_u32) vd, vswapbig); -+ vd = (vector float) vec_rl((vec_u16) vd, vswapsmall); - - vec_st(vd, 0, (float *) &dest[i]); - } ---- a/libswscale/ppc/swscale_vsx.c.orig 2019-08-11 20:06:32 UTC -+++ a/libswscale/ppc/swscale_vsx.c -@@ -103,9 +103,9 @@ static void yuv2plane1_8_vsx(const int16_t *src, uint8_t *dest, int dstW, - const int dst_u = -(uintptr_t)dest & 15; - int i, j; - LOCAL_ALIGNED(16, int16_t, val, [16]); -- const vector uint16_t shifts = (vector uint16_t) {7, 7, 7, 7, 7, 7, 7, 7}; -- vector int16_t vi, vileft, ditherleft, ditherright; -- vector uint8_t vd; -+ const vec_u16 shifts = (vec_u16) {7, 7, 7, 7, 7, 7, 7, 7}; -+ vec_s16 vi, vileft, ditherleft, ditherright; -+ vec_u8 vd; - - for (j = 0; j < 16; j++) { - val[j] = dither[(dst_u + offset + j) & 7]; -@@ -161,11 +161,11 @@ static void yuv2plane1_nbps_vsx(const int16_t *src, uint16_t *dest, int dstW, - const int shift = 15 - output_bits; - const int add = (1 << (shift - 1)); - const int clip = (1 << output_bits) - 1; -- const vector uint16_t vadd = (vector uint16_t) {add, add, add, add, add, add, add, add}; -- const vector uint16_t vswap = (vector uint16_t) vec_splat_u16(big_endian ? 8 : 0); -- const vector uint16_t vshift = (vector uint16_t) vec_splat_u16(shift); -- const vector uint16_t vlargest = (vector uint16_t) {clip, clip, clip, clip, clip, clip, clip, clip}; -- vector uint16_t v; -+ const vec_u16 vadd = (vec_u16) {add, add, add, add, add, add, add, add}; -+ const vec_u16 vswap = (vec_u16) vec_splat_u16(big_endian ? 8 : 0); -+ const vec_u16 vshift = (vec_u16) vec_splat_u16(shift); -+ const vec_u16 vlargest = (vec_u16) {clip, clip, clip, clip, clip, clip, clip, clip}; -+ vec_u16 v; - int i; - - yuv2plane1_nbps_u(src, dest, dst_u, big_endian, output_bits, 0); -@@ -209,20 +209,20 @@ static void yuv2planeX_nbps_vsx(const int16_t *filter, int filterSize, - const int add = (1 << (shift - 1)); - const int clip = (1 << output_bits) - 1; - const uint16_t swap = big_endian ? 8 : 0; -- const vector uint32_t vadd = (vector uint32_t) {add, add, add, add}; -- const vector uint32_t vshift = (vector uint32_t) {shift, shift, shift, shift}; -- const vector uint16_t vswap = (vector uint16_t) {swap, swap, swap, swap, swap, swap, swap, swap}; -- const vector uint16_t vlargest = (vector uint16_t) {clip, clip, clip, clip, clip, clip, clip, clip}; -- const vector int16_t vzero = vec_splat_s16(0); -- const vector uint8_t vperm = (vector uint8_t) {0, 1, 8, 9, 2, 3, 10, 11, 4, 5, 12, 13, 6, 7, 14, 15}; -- vector int16_t vfilter[MAX_FILTER_SIZE], vin; -- vector uint16_t v; -- vector uint32_t vleft, vright, vtmp; -+ const vec_u32 vadd = (vec_u32) {add, add, add, add}; -+ const vec_u32 vshift = (vec_u32) {shift, shift, shift, shift}; -+ const vec_u16 vswap = (vec_u16) {swap, swap, swap, swap, swap, swap, swap, swap}; -+ const vec_u16 vlargest = (vec_u16) {clip, clip, clip, clip, clip, clip, clip, clip}; -+ const vec_s16 vzero = vec_splat_s16(0); -+ const vec_u8 vperm = (vec_u8) {0, 1, 8, 9, 2, 3, 10, 11, 4, 5, 12, 13, 6, 7, 14, 15}; -+ vec_s16 vfilter[MAX_FILTER_SIZE], vin; -+ vec_u16 v; -+ vec_u32 vleft, vright, vtmp; - int i, j; - - for (i = 0; i < filterSize; i++) { -- vfilter[i] = (vector int16_t) {filter[i], filter[i], filter[i], filter[i], -- filter[i], filter[i], filter[i], filter[i]}; -+ vfilter[i] = (vec_s16) {filter[i], filter[i], filter[i], filter[i], -+ filter[i], filter[i], filter[i], filter[i]}; - } - - yuv2planeX_nbps_u(filter, filterSize, src, dest, dst_u, big_endian, output_bits, 0); -@@ -232,16 +232,16 @@ static void yuv2planeX_nbps_vsx(const int16_t *filter, int filterSize, - - for (j = 0; j < filterSize; j++) { - vin = vec_vsx_ld(0, &src[j][i]); -- vtmp = (vector uint32_t) vec_mule(vin, vfilter[j]); -+ vtmp = (vec_u32) vec_mule(vin, vfilter[j]); - vleft = vec_add(vleft, vtmp); -- vtmp = (vector uint32_t) vec_mulo(vin, vfilter[j]); -+ vtmp = (vec_u32) vec_mulo(vin, vfilter[j]); - vright = vec_add(vright, vtmp); - } - - vleft = vec_sra(vleft, vshift); - vright = vec_sra(vright, vshift); - v = vec_packsu(vleft, vright); -- v = (vector uint16_t) vec_max((vector int16_t) v, vzero); -+ v = (vec_u16) vec_max((vec_s16) v, vzero); - v = vec_min(v, vlargest); - v = vec_rl(v, vswap); - v = vec_perm(v, v, vperm); -@@ -279,11 +279,11 @@ static void yuv2plane1_16_vsx(const int32_t *src, uint16_t *dest, int dstW, - const int dst_u = -(uintptr_t)dest & 7; - const int shift = 3; - const int add = (1 << (shift - 1)); -- const vector uint32_t vadd = (vector uint32_t) {add, add, add, add}; -- const vector uint16_t vswap = (vector uint16_t) vec_splat_u16(big_endian ? 8 : 0); -- const vector uint32_t vshift = (vector uint32_t) vec_splat_u32(shift); -- vector uint32_t v, v2; -- vector uint16_t vd; -+ const vec_u32 vadd = (vec_u32) {add, add, add, add}; -+ const vec_u16 vswap = (vec_u16) vec_splat_u16(big_endian ? 8 : 0); -+ const vec_u32 vshift = (vec_u32) vec_splat_u32(shift); -+ vec_u32 v, v2; -+ vec_u16 vd; - int i; - - yuv2plane1_16_u(src, dest, dst_u, big_endian, output_bits, 0); -@@ -341,18 +341,18 @@ static void yuv2planeX_16_vsx(const int16_t *filter, int filterSize, - const int bias = 0x8000; - const int add = (1 << (shift - 1)) - 0x40000000; - const uint16_t swap = big_endian ? 8 : 0; -- const vector uint32_t vadd = (vector uint32_t) {add, add, add, add}; -- const vector uint32_t vshift = (vector uint32_t) {shift, shift, shift, shift}; -- const vector uint16_t vswap = (vector uint16_t) {swap, swap, swap, swap, swap, swap, swap, swap}; -- const vector uint16_t vbias = (vector uint16_t) {bias, bias, bias, bias, bias, bias, bias, bias}; -- vector int32_t vfilter[MAX_FILTER_SIZE]; -- vector uint16_t v; -- vector uint32_t vleft, vright, vtmp; -- vector int32_t vin32l, vin32r; -+ const vec_u32 vadd = (vec_u32) {add, add, add, add}; -+ const vec_u32 vshift = (vec_u32) {shift, shift, shift, shift}; -+ const vec_u16 vswap = (vec_u16) {swap, swap, swap, swap, swap, swap, swap, swap}; -+ const vec_u16 vbias = (vec_u16) {bias, bias, bias, bias, bias, bias, bias, bias}; -+ vec_s32 vfilter[MAX_FILTER_SIZE]; -+ vec_u16 v; -+ vec_u32 vleft, vright, vtmp; -+ vec_s32 vin32l, vin32r; - int i, j; - - for (i = 0; i < filterSize; i++) { -- vfilter[i] = (vector int32_t) {filter[i], filter[i], filter[i], filter[i]}; -+ vfilter[i] = (vec_s32) {filter[i], filter[i], filter[i], filter[i]}; - } - - yuv2planeX_16_u(filter, filterSize, src, dest, dst_u, big_endian, output_bits, 0); -@@ -364,15 +364,15 @@ static void yuv2planeX_16_vsx(const int16_t *filter, int filterSize, - vin32l = vec_vsx_ld(0, &src[j][i]); - vin32r = vec_vsx_ld(0, &src[j][i + 4]); - -- vtmp = (vector uint32_t) vec_mul(vin32l, vfilter[j]); -+ vtmp = (vec_u32) vec_mul(vin32l, vfilter[j]); - vleft = vec_add(vleft, vtmp); -- vtmp = (vector uint32_t) vec_mul(vin32r, vfilter[j]); -+ vtmp = (vec_u32) vec_mul(vin32r, vfilter[j]); - vright = vec_add(vright, vtmp); - } - - vleft = vec_sra(vleft, vshift); - vright = vec_sra(vright, vshift); -- v = (vector uint16_t) vec_packs((vector int32_t) vleft, (vector int32_t) vright); -+ v = (vec_u16) vec_packs((vec_s32) vleft, (vec_s32) vright); - v = vec_add(v, vbias); - v = vec_rl(v, vswap); - vec_st(v, 0, &dest[i]); -@@ -478,9 +478,9 @@ yuv2NBPSX(16, LE, 0, 16, int32_t) - out0 = vec_mergeh(bd, gd); \ - out1 = vec_mergeh(rd, ad); \ - \ -- tmp8 = (vector uint8_t) vec_mergeh((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergeh((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 0, dest); \ -- tmp8 = (vector uint8_t) vec_mergel((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergel((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 16, dest); \ - \ - dest += 32; \ -@@ -489,9 +489,9 @@ yuv2NBPSX(16, LE, 0, 16, int32_t) - out0 = vec_mergeh(rd, gd); \ - out1 = vec_mergeh(bd, ad); \ - \ -- tmp8 = (vector uint8_t) vec_mergeh((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergeh((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 0, dest); \ -- tmp8 = (vector uint8_t) vec_mergel((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergel((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 16, dest); \ - \ - dest += 32; \ -@@ -500,9 +500,9 @@ yuv2NBPSX(16, LE, 0, 16, int32_t) - out0 = vec_mergeh(ad, rd); \ - out1 = vec_mergeh(gd, bd); \ - \ -- tmp8 = (vector uint8_t) vec_mergeh((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergeh((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 0, dest); \ -- tmp8 = (vector uint8_t) vec_mergel((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergel((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 16, dest); \ - \ - dest += 32; \ -@@ -511,9 +511,9 @@ yuv2NBPSX(16, LE, 0, 16, int32_t) - out0 = vec_mergeh(ad, bd); \ - out1 = vec_mergeh(gd, rd); \ - \ -- tmp8 = (vector uint8_t) vec_mergeh((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergeh((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 0, dest); \ -- tmp8 = (vector uint8_t) vec_mergel((vector uint16_t) out0, (vector uint16_t) out1); \ -+ tmp8 = (vec_u8) vec_mergel((vec_u16) out0, (vec_u16) out1); \ - vec_vsx_st(tmp8, 16, dest); \ - \ - dest += 32; \ -@@ -528,48 +528,48 @@ yuv2rgb_full_X_vsx_template(SwsContext *c, const int16_t *lumFilter, - const int16_t **alpSrc, uint8_t *dest, - int dstW, int y, enum AVPixelFormat target, int hasAlpha) - { -- vector int16_t vv; -- vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -- vector int32_t R_l, R_r, G_l, G_r, B_l, B_r; -- vector int32_t tmp, tmp2, tmp3, tmp4; -- vector uint16_t rd16, gd16, bd16; -- vector uint8_t rd, bd, gd, ad, out0, out1, tmp8; -- vector int16_t vlumFilter[MAX_FILTER_SIZE], vchrFilter[MAX_FILTER_SIZE]; -- const vector int32_t ystart = vec_splats(1 << 9); -- const vector int32_t uvstart = vec_splats((1 << 9) - (128 << 19)); -- const vector uint16_t zero16 = vec_splat_u16(0); -- const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset); -- const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff); -- const vector int32_t y_add = vec_splats(1 << 21); -- const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -- const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -- const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -- const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -- const vector int32_t rgbclip = vec_splats(1 << 30); -- const vector int32_t zero32 = vec_splat_s32(0); -- const vector uint32_t shift22 = vec_splats(22U); -- const vector uint32_t shift10 = vec_splat_u32(10); -+ vec_s16 vv; -+ vec_s32 vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -+ vec_s32 R_l, R_r, G_l, G_r, B_l, B_r; -+ vec_s32 tmp, tmp2, tmp3, tmp4; -+ vec_u16 rd16, gd16, bd16; -+ vec_u8 rd, bd, gd, ad, out0, out1, tmp8; -+ vec_s16 vlumFilter[MAX_FILTER_SIZE], vchrFilter[MAX_FILTER_SIZE]; -+ const vec_s32 ystart = vec_splats(1 << 9); -+ const vec_s32 uvstart = vec_splats((1 << 9) - (128 << 19)); -+ const vec_u16 zero16 = vec_splat_u16(0); -+ const vec_s32 y_offset = vec_splats(c->yuv2rgb_y_offset); -+ const vec_s32 y_coeff = vec_splats(c->yuv2rgb_y_coeff); -+ const vec_s32 y_add = vec_splats(1 << 21); -+ const vec_s32 v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -+ const vec_s32 v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -+ const vec_s32 u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -+ const vec_s32 u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -+ const vec_s32 rgbclip = vec_splats(1 << 30); -+ const vec_s32 zero32 = vec_splat_s32(0); -+ const vec_u32 shift22 = vec_splats(22U); -+ const vec_u32 shift10 = vec_splat_u32(10); - int i, j; - - // Various permutations -- const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0, -- 0x1, 0x11, 0, -- 0x2, 0x12, 0, -- 0x3, 0x13, 0, -- 0x4, 0x14, 0, -- 0x5 }; -- const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0, -- 0x6, 0x16, 0, -- 0x7, 0x17, 0 }; -- const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10, -- 0x3, 0x4, 0x11, -- 0x6, 0x7, 0x12, -- 0x9, 0xa, 0x13, -- 0xc, 0xd, 0x14, -- 0xf }; -- const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15, -- 0x2, 0x3, 0x16, -- 0x5, 0x6, 0x17 }; -+ const vec_u8 perm3rg0 = (vec_u8) {0x0, 0x10, 0, -+ 0x1, 0x11, 0, -+ 0x2, 0x12, 0, -+ 0x3, 0x13, 0, -+ 0x4, 0x14, 0, -+ 0x5 }; -+ const vec_u8 perm3rg1 = (vec_u8) { 0x15, 0, -+ 0x6, 0x16, 0, -+ 0x7, 0x17, 0 }; -+ const vec_u8 perm3tb0 = (vec_u8) {0x0, 0x1, 0x10, -+ 0x3, 0x4, 0x11, -+ 0x6, 0x7, 0x12, -+ 0x9, 0xa, 0x13, -+ 0xc, 0xd, 0x14, -+ 0xf }; -+ const vec_u8 perm3tb1 = (vec_u8) { 0x0, 0x15, -+ 0x2, 0x3, 0x16, -+ 0x5, 0x6, 0x17 }; - - ad = vec_splats((uint8_t) 255); - -@@ -685,52 +685,52 @@ yuv2rgb_full_2_vsx_template(SwsContext *c, const int16_t *buf[2], - *abuf1 = hasAlpha ? abuf[1] : NULL; - const int16_t yalpha1 = 4096 - yalpha; - const int16_t uvalpha1 = 4096 - uvalpha; -- vector int16_t vy, vu, vv, A = vec_splat_s16(0); -- vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -- vector int32_t R_l, R_r, G_l, G_r, B_l, B_r; -- vector int32_t tmp, tmp2, tmp3, tmp4, tmp5, tmp6; -- vector uint16_t rd16, gd16, bd16; -- vector uint8_t rd, bd, gd, ad, out0, out1, tmp8; -- const vector int16_t vyalpha1 = vec_splats(yalpha1); -- const vector int16_t vuvalpha1 = vec_splats(uvalpha1); -- const vector int16_t vyalpha = vec_splats((int16_t) yalpha); -- const vector int16_t vuvalpha = vec_splats((int16_t) uvalpha); -- const vector uint16_t zero16 = vec_splat_u16(0); -- const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset); -- const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff); -- const vector int32_t y_add = vec_splats(1 << 21); -- const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -- const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -- const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -- const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -- const vector int32_t rgbclip = vec_splats(1 << 30); -- const vector int32_t zero32 = vec_splat_s32(0); -- const vector uint32_t shift19 = vec_splats(19U); -- const vector uint32_t shift22 = vec_splats(22U); -- const vector uint32_t shift10 = vec_splat_u32(10); -- const vector int32_t dec128 = vec_splats(128 << 19); -- const vector int32_t add18 = vec_splats(1 << 18); -+ vec_s16 vy, vu, vv, A = vec_splat_s16(0); -+ vec_s32 vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -+ vec_s32 R_l, R_r, G_l, G_r, B_l, B_r; -+ vec_s32 tmp, tmp2, tmp3, tmp4, tmp5, tmp6; -+ vec_u16 rd16, gd16, bd16; -+ vec_u8 rd, bd, gd, ad, out0, out1, tmp8; -+ const vec_s16 vyalpha1 = vec_splats(yalpha1); -+ const vec_s16 vuvalpha1 = vec_splats(uvalpha1); -+ const vec_s16 vyalpha = vec_splats((int16_t) yalpha); -+ const vec_s16 vuvalpha = vec_splats((int16_t) uvalpha); -+ const vec_u16 zero16 = vec_splat_u16(0); -+ const vec_s32 y_offset = vec_splats(c->yuv2rgb_y_offset); -+ const vec_s32 y_coeff = vec_splats(c->yuv2rgb_y_coeff); -+ const vec_s32 y_add = vec_splats(1 << 21); -+ const vec_s32 v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -+ const vec_s32 v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -+ const vec_s32 u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -+ const vec_s32 u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -+ const vec_s32 rgbclip = vec_splats(1 << 30); -+ const vec_s32 zero32 = vec_splat_s32(0); -+ const vec_u32 shift19 = vec_splats(19U); -+ const vec_u32 shift22 = vec_splats(22U); -+ const vec_u32 shift10 = vec_splat_u32(10); -+ const vec_s32 dec128 = vec_splats(128 << 19); -+ const vec_s32 add18 = vec_splats(1 << 18); - int i; - - // Various permutations -- const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0, -- 0x1, 0x11, 0, -- 0x2, 0x12, 0, -- 0x3, 0x13, 0, -- 0x4, 0x14, 0, -- 0x5 }; -- const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0, -- 0x6, 0x16, 0, -- 0x7, 0x17, 0 }; -- const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10, -- 0x3, 0x4, 0x11, -- 0x6, 0x7, 0x12, -- 0x9, 0xa, 0x13, -- 0xc, 0xd, 0x14, -- 0xf }; -- const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15, -- 0x2, 0x3, 0x16, -- 0x5, 0x6, 0x17 }; -+ const vec_u8 perm3rg0 = (vec_u8) {0x0, 0x10, 0, -+ 0x1, 0x11, 0, -+ 0x2, 0x12, 0, -+ 0x3, 0x13, 0, -+ 0x4, 0x14, 0, -+ 0x5 }; -+ const vec_u8 perm3rg1 = (vec_u8) { 0x15, 0, -+ 0x6, 0x16, 0, -+ 0x7, 0x17, 0 }; -+ const vec_u8 perm3tb0 = (vec_u8) {0x0, 0x1, 0x10, -+ 0x3, 0x4, 0x11, -+ 0x6, 0x7, 0x12, -+ 0x9, 0xa, 0x13, -+ 0xc, 0xd, 0x14, -+ 0xf }; -+ const vec_u8 perm3tb1 = (vec_u8) { 0x0, 0x15, -+ 0x2, 0x3, 0x16, -+ 0x5, 0x6, 0x17 }; - - av_assert2(yalpha <= 4096U); - av_assert2(uvalpha <= 4096U); -@@ -759,7 +759,7 @@ yuv2rgb_full_2_vsx_template(SwsContext *c, const int16_t *buf[2], - tmp3 = vec_sra(tmp3, shift19); - tmp4 = vec_sra(tmp4, shift19); - A = vec_packs(tmp3, tmp4); -- ad = vec_packsu(A, (vector int16_t) zero16); -+ ad = vec_packsu(A, (vec_s16) zero16); - } else { - ad = vec_splats((uint8_t) 255); - } -@@ -807,60 +807,60 @@ yuv2rgb_2_vsx_template(SwsContext *c, const int16_t *buf[2], - *abuf1 = hasAlpha ? abuf[1] : NULL; - const int16_t yalpha1 = 4096 - yalpha; - const int16_t uvalpha1 = 4096 - uvalpha; -- vector int16_t vy, vu, vv, A = vec_splat_s16(0); -- vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -- vector int32_t R_l, R_r, G_l, G_r, B_l, B_r, vud32_l, vud32_r, vvd32_l, vvd32_r; -- vector int32_t tmp, tmp2, tmp3, tmp4, tmp5, tmp6; -- vector uint16_t rd16, gd16, bd16; -- vector uint8_t rd, bd, gd, ad, out0, out1, tmp8; -- const vector int16_t vyalpha1 = vec_splats(yalpha1); -- const vector int16_t vuvalpha1 = vec_splats(uvalpha1); -- const vector int16_t vyalpha = vec_splats((int16_t) yalpha); -- const vector int16_t vuvalpha = vec_splats((int16_t) uvalpha); -- const vector uint16_t zero16 = vec_splat_u16(0); -- const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset); -- const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff); -- const vector int32_t y_add = vec_splats(1 << 21); -- const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -- const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -- const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -- const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -- const vector int32_t rgbclip = vec_splats(1 << 30); -- const vector int32_t zero32 = vec_splat_s32(0); -- const vector uint32_t shift19 = vec_splats(19U); -- const vector uint32_t shift22 = vec_splats(22U); -- const vector uint32_t shift10 = vec_splat_u32(10); -- const vector int32_t dec128 = vec_splats(128 << 19); -- const vector int32_t add18 = vec_splats(1 << 18); -+ vec_s16 vy, vu, vv, A = vec_splat_s16(0); -+ vec_s32 vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32; -+ vec_s32 R_l, R_r, G_l, G_r, B_l, B_r, vud32_l, vud32_r, vvd32_l, vvd32_r; -+ vec_s32 tmp, tmp2, tmp3, tmp4, tmp5, tmp6; -+ vec_u16 rd16, gd16, bd16; -+ vec_u8 rd, bd, gd, ad, out0, out1, tmp8; -+ const vec_s16 vyalpha1 = vec_splats(yalpha1); -+ const vec_s16 vuvalpha1 = vec_splats(uvalpha1); -+ const vec_s16 vyalpha = vec_splats((int16_t) yalpha); -+ const vec_s16 vuvalpha = vec_splats((int16_t) uvalpha); -+ const vec_u16 zero16 = vec_splat_u16(0); -+ const vec_s32 y_offset = vec_splats(c->yuv2rgb_y_offset); -+ const vec_s32 y_coeff = vec_splats(c->yuv2rgb_y_coeff); -+ const vec_s32 y_add = vec_splats(1 << 21); -+ const vec_s32 v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -+ const vec_s32 v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -+ const vec_s32 u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -+ const vec_s32 u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -+ const vec_s32 rgbclip = vec_splats(1 << 30); -+ const vec_s32 zero32 = vec_splat_s32(0); -+ const vec_u32 shift19 = vec_splats(19U); -+ const vec_u32 shift22 = vec_splats(22U); -+ const vec_u32 shift10 = vec_splat_u32(10); -+ const vec_s32 dec128 = vec_splats(128 << 19); -+ const vec_s32 add18 = vec_splats(1 << 18); - int i; - - // Various permutations -- const vector uint8_t doubleleft = (vector uint8_t) {0, 1, 2, 3, -- 0, 1, 2, 3, -- 4, 5, 6, 7, -- 4, 5, 6, 7 }; -- const vector uint8_t doubleright = (vector uint8_t) {8, 9, 10, 11, -- 8, 9, 10, 11, -- 12, 13, 14, 15, -- 12, 13, 14, 15 }; -- const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0, -- 0x1, 0x11, 0, -- 0x2, 0x12, 0, -- 0x3, 0x13, 0, -- 0x4, 0x14, 0, -- 0x5 }; -- const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0, -- 0x6, 0x16, 0, -- 0x7, 0x17, 0 }; -- const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10, -- 0x3, 0x4, 0x11, -- 0x6, 0x7, 0x12, -- 0x9, 0xa, 0x13, -- 0xc, 0xd, 0x14, -- 0xf }; -- const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15, -- 0x2, 0x3, 0x16, -- 0x5, 0x6, 0x17 }; -+ const vec_u8 doubleleft = (vec_u8) {0, 1, 2, 3, -+ 0, 1, 2, 3, -+ 4, 5, 6, 7, -+ 4, 5, 6, 7 }; -+ const vec_u8 doubleright = (vec_u8) {8, 9, 10, 11, -+ 8, 9, 10, 11, -+ 12, 13, 14, 15, -+ 12, 13, 14, 15 }; -+ const vec_u8 perm3rg0 = (vec_u8) {0x0, 0x10, 0, -+ 0x1, 0x11, 0, -+ 0x2, 0x12, 0, -+ 0x3, 0x13, 0, -+ 0x4, 0x14, 0, -+ 0x5 }; -+ const vec_u8 perm3rg1 = (vec_u8) { 0x15, 0, -+ 0x6, 0x16, 0, -+ 0x7, 0x17, 0 }; -+ const vec_u8 perm3tb0 = (vec_u8) {0x0, 0x1, 0x10, -+ 0x3, 0x4, 0x11, -+ 0x6, 0x7, 0x12, -+ 0x9, 0xa, 0x13, -+ 0xc, 0xd, 0x14, -+ 0xf }; -+ const vec_u8 perm3tb1 = (vec_u8) { 0x0, 0x15, -+ 0x2, 0x3, 0x16, -+ 0x5, 0x6, 0x17 }; - - av_assert2(yalpha <= 4096U); - av_assert2(uvalpha <= 4096U); -@@ -889,7 +889,7 @@ yuv2rgb_2_vsx_template(SwsContext *c, const int16_t *buf[2], - tmp3 = vec_sra(tmp3, shift19); - tmp4 = vec_sra(tmp4, shift19); - A = vec_packs(tmp3, tmp4); -- ad = vec_packsu(A, (vector int16_t) zero16); -+ ad = vec_packsu(A, (vec_s16) zero16); - } else { - ad = vec_splats((uint8_t) 255); - } -@@ -978,51 +978,51 @@ yuv2rgb_full_1_vsx_template(SwsContext *c, const int16_t *buf0, - { - const int16_t *ubuf0 = ubuf[0], *vbuf0 = vbuf[0]; - const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1]; -- vector int16_t vy, vu, vv, A = vec_splat_s16(0), tmp16; -- vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32, tmp32_2; -- vector int32_t R_l, R_r, G_l, G_r, B_l, B_r; -- vector uint16_t rd16, gd16, bd16; -- vector uint8_t rd, bd, gd, ad, out0, out1, tmp8; -- const vector uint16_t zero16 = vec_splat_u16(0); -- const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset); -- const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff); -- const vector int32_t y_add = vec_splats(1 << 21); -- const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -- const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -- const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -- const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -- const vector int32_t rgbclip = vec_splats(1 << 30); -- const vector int32_t zero32 = vec_splat_s32(0); -- const vector uint32_t shift2 = vec_splat_u32(2); -- const vector uint32_t shift22 = vec_splats(22U); -- const vector uint16_t sub7 = vec_splats((uint16_t) (128 << 7)); -- const vector uint16_t sub8 = vec_splats((uint16_t) (128 << 8)); -- const vector int16_t mul4 = vec_splat_s16(4); -- const vector int16_t mul8 = vec_splat_s16(8); -- const vector int16_t add64 = vec_splat_s16(64); -- const vector uint16_t shift7 = vec_splat_u16(7); -- const vector int16_t max255 = vec_splat_s16(255); -+ vec_s16 vy, vu, vv, A = vec_splat_s16(0), tmp16; -+ vec_s32 vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32, tmp32_2; -+ vec_s32 R_l, R_r, G_l, G_r, B_l, B_r; -+ vec_u16 rd16, gd16, bd16; -+ vec_u8 rd, bd, gd, ad, out0, out1, tmp8; -+ const vec_u16 zero16 = vec_splat_u16(0); -+ const vec_s32 y_offset = vec_splats(c->yuv2rgb_y_offset); -+ const vec_s32 y_coeff = vec_splats(c->yuv2rgb_y_coeff); -+ const vec_s32 y_add = vec_splats(1 << 21); -+ const vec_s32 v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -+ const vec_s32 v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -+ const vec_s32 u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -+ const vec_s32 u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -+ const vec_s32 rgbclip = vec_splats(1 << 30); -+ const vec_s32 zero32 = vec_splat_s32(0); -+ const vec_u32 shift2 = vec_splat_u32(2); -+ const vec_u32 shift22 = vec_splats(22U); -+ const vec_u16 sub7 = vec_splats((uint16_t) (128 << 7)); -+ const vec_u16 sub8 = vec_splats((uint16_t) (128 << 8)); -+ const vec_s16 mul4 = vec_splat_s16(4); -+ const vec_s16 mul8 = vec_splat_s16(8); -+ const vec_s16 add64 = vec_splat_s16(64); -+ const vec_u16 shift7 = vec_splat_u16(7); -+ const vec_s16 max255 = vec_splat_s16(255); - int i; - - // Various permutations -- const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0, -- 0x1, 0x11, 0, -- 0x2, 0x12, 0, -- 0x3, 0x13, 0, -- 0x4, 0x14, 0, -- 0x5 }; -- const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0, -- 0x6, 0x16, 0, -- 0x7, 0x17, 0 }; -- const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10, -- 0x3, 0x4, 0x11, -- 0x6, 0x7, 0x12, -- 0x9, 0xa, 0x13, -- 0xc, 0xd, 0x14, -- 0xf }; -- const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15, -- 0x2, 0x3, 0x16, -- 0x5, 0x6, 0x17 }; -+ const vec_u8 perm3rg0 = (vec_u8) {0x0, 0x10, 0, -+ 0x1, 0x11, 0, -+ 0x2, 0x12, 0, -+ 0x3, 0x13, 0, -+ 0x4, 0x14, 0, -+ 0x5 }; -+ const vec_u8 perm3rg1 = (vec_u8) { 0x15, 0, -+ 0x6, 0x16, 0, -+ 0x7, 0x17, 0 }; -+ const vec_u8 perm3tb0 = (vec_u8) {0x0, 0x1, 0x10, -+ 0x3, 0x4, 0x11, -+ 0x6, 0x7, 0x12, -+ 0x9, 0xa, 0x13, -+ 0xc, 0xd, 0x14, -+ 0xf }; -+ const vec_u8 perm3tb1 = (vec_u8) { 0x0, 0x15, -+ 0x2, 0x3, 0x16, -+ 0x5, 0x6, 0x17 }; - - for (i = 0; i < dstW; i += 8) { // The x86 asm also overwrites padding bytes. - vy = vec_ld(0, &buf0[i]); -@@ -1034,8 +1034,8 @@ yuv2rgb_full_1_vsx_template(SwsContext *c, const int16_t *buf0, - vu = vec_ld(0, &ubuf0[i]); - vv = vec_ld(0, &vbuf0[i]); - if (uvalpha < 2048) { -- vu = (vector int16_t) vec_sub((vector uint16_t) vu, sub7); -- vv = (vector int16_t) vec_sub((vector uint16_t) vv, sub7); -+ vu = (vec_s16) vec_sub((vec_u16) vu, sub7); -+ vv = (vec_s16) vec_sub((vec_u16) vv, sub7); - - tmp32 = vec_mule(vu, mul4); - tmp32_2 = vec_mulo(vu, mul4); -@@ -1048,10 +1048,10 @@ yuv2rgb_full_1_vsx_template(SwsContext *c, const int16_t *buf0, - } else { - tmp16 = vec_ld(0, &ubuf1[i]); - vu = vec_add(vu, tmp16); -- vu = (vector int16_t) vec_sub((vector uint16_t) vu, sub8); -+ vu = (vec_s16) vec_sub((vec_u16) vu, sub8); - tmp16 = vec_ld(0, &vbuf1[i]); - vv = vec_add(vv, tmp16); -- vv = (vector int16_t) vec_sub((vector uint16_t) vv, sub8); -+ vv = (vec_s16) vec_sub((vec_u16) vv, sub8); - - vu32_l = vec_mule(vu, mul8); - vu32_r = vec_mulo(vu, mul8); -@@ -1064,7 +1064,7 @@ yuv2rgb_full_1_vsx_template(SwsContext *c, const int16_t *buf0, - A = vec_add(A, add64); - A = vec_sr(A, shift7); - A = vec_max(A, max255); -- ad = vec_packsu(A, (vector int16_t) zero16); -+ ad = vec_packsu(A, (vec_s16) zero16); - } else { - ad = vec_splats((uint8_t) 255); - } -@@ -1107,60 +1107,60 @@ yuv2rgb_1_vsx_template(SwsContext *c, const int16_t *buf0, - { - const int16_t *ubuf0 = ubuf[0], *vbuf0 = vbuf[0]; - const int16_t *ubuf1 = ubuf[1], *vbuf1 = vbuf[1]; -- vector int16_t vy, vu, vv, A = vec_splat_s16(0), tmp16; -- vector int32_t vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32, tmp32_2; -- vector int32_t vud32_l, vud32_r, vvd32_l, vvd32_r; -- vector int32_t R_l, R_r, G_l, G_r, B_l, B_r; -- vector uint16_t rd16, gd16, bd16; -- vector uint8_t rd, bd, gd, ad, out0, out1, tmp8; -- const vector uint16_t zero16 = vec_splat_u16(0); -- const vector int32_t y_offset = vec_splats(c->yuv2rgb_y_offset); -- const vector int32_t y_coeff = vec_splats(c->yuv2rgb_y_coeff); -- const vector int32_t y_add = vec_splats(1 << 21); -- const vector int32_t v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -- const vector int32_t v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -- const vector int32_t u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -- const vector int32_t u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -- const vector int32_t rgbclip = vec_splats(1 << 30); -- const vector int32_t zero32 = vec_splat_s32(0); -- const vector uint32_t shift2 = vec_splat_u32(2); -- const vector uint32_t shift22 = vec_splats(22U); -- const vector uint16_t sub7 = vec_splats((uint16_t) (128 << 7)); -- const vector uint16_t sub8 = vec_splats((uint16_t) (128 << 8)); -- const vector int16_t mul4 = vec_splat_s16(4); -- const vector int16_t mul8 = vec_splat_s16(8); -- const vector int16_t add64 = vec_splat_s16(64); -- const vector uint16_t shift7 = vec_splat_u16(7); -- const vector int16_t max255 = vec_splat_s16(255); -+ vec_s16 vy, vu, vv, A = vec_splat_s16(0), tmp16; -+ vec_s32 vy32_l, vy32_r, vu32_l, vu32_r, vv32_l, vv32_r, tmp32, tmp32_2; -+ vec_s32 vud32_l, vud32_r, vvd32_l, vvd32_r; -+ vec_s32 R_l, R_r, G_l, G_r, B_l, B_r; -+ vec_u16 rd16, gd16, bd16; -+ vec_u8 rd, bd, gd, ad, out0, out1, tmp8; -+ const vec_u16 zero16 = vec_splat_u16(0); -+ const vec_s32 y_offset = vec_splats(c->yuv2rgb_y_offset); -+ const vec_s32 y_coeff = vec_splats(c->yuv2rgb_y_coeff); -+ const vec_s32 y_add = vec_splats(1 << 21); -+ const vec_s32 v2r_coeff = vec_splats(c->yuv2rgb_v2r_coeff); -+ const vec_s32 v2g_coeff = vec_splats(c->yuv2rgb_v2g_coeff); -+ const vec_s32 u2g_coeff = vec_splats(c->yuv2rgb_u2g_coeff); -+ const vec_s32 u2b_coeff = vec_splats(c->yuv2rgb_u2b_coeff); -+ const vec_s32 rgbclip = vec_splats(1 << 30); -+ const vec_s32 zero32 = vec_splat_s32(0); -+ const vec_u32 shift2 = vec_splat_u32(2); -+ const vec_u32 shift22 = vec_splats(22U); -+ const vec_u16 sub7 = vec_splats((uint16_t) (128 << 7)); -+ const vec_u16 sub8 = vec_splats((uint16_t) (128 << 8)); -+ const vec_s16 mul4 = vec_splat_s16(4); -+ const vec_s16 mul8 = vec_splat_s16(8); -+ const vec_s16 add64 = vec_splat_s16(64); -+ const vec_u16 shift7 = vec_splat_u16(7); -+ const vec_s16 max255 = vec_splat_s16(255); - int i; - - // Various permutations -- const vector uint8_t doubleleft = (vector uint8_t) {0, 1, 2, 3, -- 0, 1, 2, 3, -- 4, 5, 6, 7, -- 4, 5, 6, 7 }; -- const vector uint8_t doubleright = (vector uint8_t) {8, 9, 10, 11, -- 8, 9, 10, 11, -- 12, 13, 14, 15, -- 12, 13, 14, 15 }; -- const vector uint8_t perm3rg0 = (vector uint8_t) {0x0, 0x10, 0, -- 0x1, 0x11, 0, -- 0x2, 0x12, 0, -- 0x3, 0x13, 0, -- 0x4, 0x14, 0, -- 0x5 }; -- const vector uint8_t perm3rg1 = (vector uint8_t) { 0x15, 0, -- 0x6, 0x16, 0, -- 0x7, 0x17, 0 }; -- const vector uint8_t perm3tb0 = (vector uint8_t) {0x0, 0x1, 0x10, -- 0x3, 0x4, 0x11, -- 0x6, 0x7, 0x12, -- 0x9, 0xa, 0x13, -- 0xc, 0xd, 0x14, -- 0xf }; -- const vector uint8_t perm3tb1 = (vector uint8_t) { 0x0, 0x15, -- 0x2, 0x3, 0x16, -- 0x5, 0x6, 0x17 }; -+ const vec_u8 doubleleft = (vec_u8) {0, 1, 2, 3, -+ 0, 1, 2, 3, -+ 4, 5, 6, 7, -+ 4, 5, 6, 7 }; -+ const vec_u8 doubleright = (vec_u8) {8, 9, 10, 11, -+ 8, 9, 10, 11, -+ 12, 13, 14, 15, -+ 12, 13, 14, 15 }; -+ const vec_u8 perm3rg0 = (vec_u8) {0x0, 0x10, 0, -+ 0x1, 0x11, 0, -+ 0x2, 0x12, 0, -+ 0x3, 0x13, 0, -+ 0x4, 0x14, 0, -+ 0x5 }; -+ const vec_u8 perm3rg1 = (vec_u8) { 0x15, 0, -+ 0x6, 0x16, 0, -+ 0x7, 0x17, 0 }; -+ const vec_u8 perm3tb0 = (vec_u8) {0x0, 0x1, 0x10, -+ 0x3, 0x4, 0x11, -+ 0x6, 0x7, 0x12, -+ 0x9, 0xa, 0x13, -+ 0xc, 0xd, 0x14, -+ 0xf }; -+ const vec_u8 perm3tb1 = (vec_u8) { 0x0, 0x15, -+ 0x2, 0x3, 0x16, -+ 0x5, 0x6, 0x17 }; - - for (i = 0; i < (dstW + 1) >> 1; i += 8) { // The x86 asm also overwrites padding bytes. - vy = vec_ld(0, &buf0[i * 2]); -@@ -1172,8 +1172,8 @@ yuv2rgb_1_vsx_template(SwsContext *c, const int16_t *buf0, - vu = vec_ld(0, &ubuf0[i]); - vv = vec_ld(0, &vbuf0[i]); - if (uvalpha < 2048) { -- vu = (vector int16_t) vec_sub((vector uint16_t) vu, sub7); -- vv = (vector int16_t) vec_sub((vector uint16_t) vv, sub7); -+ vu = (vec_s16) vec_sub((vec_u16) vu, sub7); -+ vv = (vec_s16) vec_sub((vec_u16) vv, sub7); - - tmp32 = vec_mule(vu, mul4); - tmp32_2 = vec_mulo(vu, mul4); -@@ -1186,10 +1186,10 @@ yuv2rgb_1_vsx_template(SwsContext *c, const int16_t *buf0, - } else { - tmp16 = vec_ld(0, &ubuf1[i]); - vu = vec_add(vu, tmp16); -- vu = (vector int16_t) vec_sub((vector uint16_t) vu, sub8); -+ vu = (vec_s16) vec_sub((vec_u16) vu, sub8); - tmp16 = vec_ld(0, &vbuf1[i]); - vv = vec_add(vv, tmp16); -- vv = (vector int16_t) vec_sub((vector uint16_t) vv, sub8); -+ vv = (vec_s16) vec_sub((vec_u16) vv, sub8); - - vu32_l = vec_mule(vu, mul8); - vu32_r = vec_mulo(vu, mul8); -@@ -1202,7 +1202,7 @@ yuv2rgb_1_vsx_template(SwsContext *c, const int16_t *buf0, - A = vec_add(A, add64); - A = vec_sr(A, shift7); - A = vec_max(A, max255); -- ad = vec_packsu(A, (vector int16_t) zero16); -+ ad = vec_packsu(A, (vec_s16) zero16); - } else { - ad = vec_splats((uint8_t) 255); - } -@@ -1358,41 +1358,41 @@ YUV2RGBWRAPPERX(yuv2, rgb_full, rgb24_full, AV_PIX_FMT_RGB24, 0) - YUV2RGBWRAPPERX(yuv2, rgb_full, bgr24_full, AV_PIX_FMT_BGR24, 0) - - static av_always_inline void --write422(const vector int16_t vy1, const vector int16_t vy2, -- const vector int16_t vu, const vector int16_t vv, -+write422(const vec_s16 vy1, const vec_s16 vy2, -+ const vec_s16 vu, const vec_s16 vv, - uint8_t *dest, const enum AVPixelFormat target) - { -- vector uint8_t vd1, vd2, tmp; -- const vector uint8_t yuyv1 = (vector uint8_t) { -- 0x0, 0x10, 0x1, 0x18, -- 0x2, 0x11, 0x3, 0x19, -- 0x4, 0x12, 0x5, 0x1a, -- 0x6, 0x13, 0x7, 0x1b }; *** 785 LINES SKIPPED ***
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?202107212010.16LKAVsu002496>