generic-library/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
5d0616ce0e
ffmpeg/libavfilter/x86/Makefile

33 lines
1.9 KiB
Makefile
Raw Normal View History

avfilter: Port mp=eq/eq2 to lavfi Code adapted from James Darnley's port Some fixes from Paul B Mahol <onemda@gmail.com> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2015-01-18 23:26:48 +01:00
OBJS-$(CONFIG_EQ_FILTER) += x86/vf_eq.o
x86/vf_fspp: port inline asm to yasm Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>
2014-12-26 19:37:54 +01:00
OBJS-$(CONFIG_FSPP_FILTER) += x86/vf_fspp_init.o
avfilter: x86: Port gradfun filter optimizations to yasm Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-10-22 02:37:46 +02:00
OBJS-$(CONFIG_GRADFUN_FILTER) += x86/vf_gradfun_init.o
vf_hqdn3d: x86: Add proper arch optimization initialization
2013-01-22 01:39:37 +01:00
OBJS-$(CONFIG_HQDN3D_FILTER) += x86/vf_hqdn3d_init.o
avfilter/vf_idet: MMX/MMXEXT/SSE2 implementation of idet's filter_line() integration by Neil Birkbeck, with help from Vitor Sessak. core SSE2 loop by Skal (pascal.massimino@gmail.com) Reviewed-by: Clément Bœsch <u@pkh.me> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-09-03 11:02:32 +02:00
OBJS-$(CONFIG_IDET_FILTER) += x86/vf_idet_init.o
vf_interlace: Add SIMD for lowpass filter Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2014-11-11 19:43:42 +01:00
OBJS-$(CONFIG_INTERLACE_FILTER) += x86/vf_interlace_init.o
x86/vf_noise: move asm code to a separate file Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-17 03:24:42 +02:00
OBJS-$(CONFIG_NOISE_FILTER) += x86/vf_noise.o
x86/vf_pp7: port dctB_mmx to yasm Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>
2015-01-09 20:51:13 +01:00
OBJS-$(CONFIG_PP7_FILTER) += x86/vf_pp7_init.o
vf_psnr: sse2 optimizations for sum-squared-error. The internal line accumulator for 16bit can overflow, so I changed that from int to uint64_t in the C code. The matching assembly looks a little weird but output looks correct. (avx2 should be trivial to add later.) Reviewed-by: Paul B Mahol <onemda@gmail.com> Reviewed-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2015-07-12 12:44:39 +02:00
OBJS-$(CONFIG_PSNR_FILTER) += x86/vf_psnr_init.o
avfilter: port pullup filter from libmpcodecs Signed-off-by: Paul B Mahol <onemda@gmail.com>
2013-07-08 14:42:53 +02:00
OBJS-$(CONFIG_PULLUP_FILTER) += x86/vf_pullup_init.o
avfilter/vf_removegrain: add x86 and x86_64 SSE2 functions Speed of all modes increased by a factor between 7.4 and 19.8 largely depending on whether bytes are unpacked into words. Modes 2, 3, and 4 have been sped-up by a factor of 43 (thanks quick sort!) All modes are available on x86_64 but only modes 1, 10, 11, 12, 13, 14, 19, 20, 21, and 22 are available on x86 due to the number of SIMD registers used. With a contribution from James Almer <jamrial@gmail.com>
2015-07-15 01:48:47 +02:00
OBJS-$(CONFIG_REMOVEGRAIN_FILTER) += x86/vf_removegrain_init.o
lavfi: add spp filter.
2013-05-11 12:03:38 +02:00
OBJS-$(CONFIG_SPP_FILTER) += x86/vf_spp.o
vf_ssim: x86 simd for ssim_4x4xN and ssim_endN. Both are 2-2.5x faster than their C counterpart. Reviewed-by: Paul B Mahol <onemda@gmail.com> Reviewed-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2015-07-13 01:33:06 +02:00
OBJS-$(CONFIG_SSIM_FILTER) += x86/vf_ssim_init.o
avfilter/tinterlace: add Support for ff_lowpass_line_avx() & ff_lowpass_line_sse2() Based-on: 2e1704059ae8625beda2ffde847ad22c5ba416dc by Kieran Kunhya Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-11-15 03:49:37 +01:00
OBJS-$(CONFIG_TINTERLACE_FILTER) += x86/vf_tinterlace_init.o
x86: af_volume: add SSE2-optimized s16 volume scaling
2012-09-23 20:49:26 +02:00
OBJS-$(CONFIG_VOLUME_FILTER) += x86/af_volume_init.o
Revert "Revert "vf_yadif: move x86 init code to x86/yadif.c"" This reverts commit 975110a85ef8e794fdc041455ff41b0ad30bc01e. Signed-off-by: Robert Krüger <krueger@lesspain.de> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-01-04 13:49:38 +01:00
OBJS-$(CONFIG_YADIF_FILTER) += x86/vf_yadif_init.o
avfilter: call x86 init functions under if (ARCH_X86), not if (HAVE_MMX)
2012-08-29 19:37:14 +02:00
x86/vf_fspp: port inline asm to yasm Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>
2014-12-26 19:37:54 +01:00
YASM-OBJS-$(CONFIG_FSPP_FILTER) += x86/vf_fspp.o
avfilter: x86: Port gradfun filter optimizations to yasm Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-10-22 02:37:46 +02:00
YASM-OBJS-$(CONFIG_GRADFUN_FILTER) += x86/vf_gradfun.o
avfilter: x86: consistent filenames for filter optimizations
2013-02-01 13:14:31 +01:00
YASM-OBJS-$(CONFIG_HQDN3D_FILTER) += x86/vf_hqdn3d.o
avfilter/vf_idet: MMX/MMXEXT/SSE2 implementation of idet's filter_line() integration by Neil Birkbeck, with help from Vitor Sessak. core SSE2 loop by Skal (pascal.massimino@gmail.com) Reviewed-by: Clément Bœsch <u@pkh.me> Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-09-03 11:02:32 +02:00
YASM-OBJS-$(CONFIG_IDET_FILTER) += x86/vf_idet.o
vf_interlace: Add SIMD for lowpass filter Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2014-11-11 19:43:42 +01:00
YASM-OBJS-$(CONFIG_INTERLACE_FILTER) += x86/vf_interlace.o
x86/vf_pp7: port dctB_mmx to yasm Reviewed-by: Michael Niedermayer <michaelni@gmx.at> Signed-off-by: James Almer <jamrial@gmail.com>
2015-01-09 20:51:13 +01:00
YASM-OBJS-$(CONFIG_PP7_FILTER) += x86/vf_pp7.o
vf_psnr: sse2 optimizations for sum-squared-error. The internal line accumulator for 16bit can overflow, so I changed that from int to uint64_t in the C code. The matching assembly looks a little weird but output looks correct. (avx2 should be trivial to add later.) Reviewed-by: Paul B Mahol <onemda@gmail.com> Reviewed-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2015-07-12 12:44:39 +02:00
YASM-OBJS-$(CONFIG_PSNR_FILTER) += x86/vf_psnr.o
avfilter: port pullup filter from libmpcodecs Signed-off-by: Paul B Mahol <onemda@gmail.com>
2013-07-08 14:42:53 +02:00
YASM-OBJS-$(CONFIG_PULLUP_FILTER) += x86/vf_pullup.o
avfilter/vf_removegrain: add x86 and x86_64 SSE2 functions Speed of all modes increased by a factor between 7.4 and 19.8 largely depending on whether bytes are unpacked into words. Modes 2, 3, and 4 have been sped-up by a factor of 43 (thanks quick sort!) All modes are available on x86_64 but only modes 1, 10, 11, 12, 13, 14, 19, 20, 21, and 22 are available on x86 due to the number of SIMD registers used. With a contribution from James Almer <jamrial@gmail.com>
2015-07-15 01:48:47 +02:00
ifdef CONFIG_GPL
YASM-OBJS-$(CONFIG_REMOVEGRAIN_FILTER) += x86/vf_removegrain.o
endif
vf_ssim: x86 simd for ssim_4x4xN and ssim_endN. Both are 2-2.5x faster than their C counterpart. Reviewed-by: Paul B Mahol <onemda@gmail.com> Reviewed-by: James Almer <jamrial@gmail.com> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2015-07-13 01:33:06 +02:00
YASM-OBJS-$(CONFIG_SSIM_FILTER) += x86/vf_ssim.o
avfilter/tinterlace: add Support for ff_lowpass_line_avx() & ff_lowpass_line_sse2() Based-on: 2e1704059ae8625beda2ffde847ad22c5ba416dc by Kieran Kunhya Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-11-15 03:49:37 +01:00
YASM-OBJS-$(CONFIG_TINTERLACE_FILTER) += x86/vf_interlace.o
x86: af_volume: add SSE2-optimized s16 volume scaling
2012-09-23 20:49:26 +02:00
YASM-OBJS-$(CONFIG_VOLUME_FILTER) += x86/af_volume.o
yadif: x86 assembly for 9 to 14-bit samples These smaller samples do not need to be unpacked to double words allowing the code to process more pixels every iteration (still 2 in MMX but 6 in SSE2). It also avoids emulating the missing double word instructions on older instruction sets. Like with the previous code for 16-bit samples this has been tested on an Athlon64 and a Core2Quad. Athlon64: 1809275 decicycles in C, 32718 runs, 50 skips 911675 decicycles in mmx, 32727 runs, 41 skips, 2.0x faster 495284 decicycles in sse2, 32747 runs, 21 skips, 3.7x faster Core2Quad: 921363 decicycles in C, 32756 runs, 12 skips 486537 decicycles in mmx, 32764 runs, 4 skips, 1.9x faster 293296 decicycles in sse2, 32759 runs, 9 skips, 3.1x faster 284910 decicycles in ssse3, 32759 runs, 9 skips, 3.2x faster Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-03-16 21:42:24 +01:00
YASM-OBJS-$(CONFIG_YADIF_FILTER) += x86/vf_yadif.o x86/yadif-16.o x86/yadif-10.o
Reference in New Issue Copy Permalink