Age | Commit message (Collapse) | Author |
|
The high bit depth build failed while building for 32bit target.
The bugs were in vp9_highbd_subpel_variance.asm and
vp9_highbd_sad4d_sse2.asm functions. This patch fixed the bugs,
and made 32bit build work.
Change-Id: Idc8e5e1b7965bb70d4afba140c6583c5d9666b75
|
|
This patch was to fix issue 924:
https://code.google.com/p/webm/issues/detail?id=924
The SECTION_RODATA macro was modified to support macho32 format.
The sub-pixel functions were modified to pass in 2 more parameters
to handle the global offsets for PIC build.
Change-Id: I3bfcd336bcae945edf300bca4ab40376a2628cd4
|
|
This reverts commit 9946ee23e0a4c158e26a505b162a072f81b8a3be.
Fix the ssse3 asm function.
Change-Id: I07f77a63aa98087626e45c4e87aa5dcafc0b0b07
|
|
This reverts commit e9b586e21bb899e247346e82bccf5afb42604910.
Change-Id: I5b36e6727da6c05278d97e2c37b80c109f79bed4
|
|
zbin extra / zbin_oq_value was widely passed around,
hence removal touches a lot of code.
Change-Id: Idc94359735b60c38a160e4385ae09d5ca8b6b8e5
|
|
|
|
Change-Id: Id8c8c3be882bcd92afea3ccec6ebdf3f208d28ef
|
|
For key frame at speed 6: enable the non-rd mode selection in speed setting
and use the (non-rd) variance_based partition.
Adjust some logic/thresholds in variance partition selection for key frame only (no change to delta frames),
mainly to bias to selecting smaller prediction blocks, and also set max tx size of 16x16.
Loss in key frame quality (~0.6-0.7dB) compared to rd coding,
but speeds up key frame encoding by at least 6x.
Average PNSR/SSIM metrics over RTC clips go down by ~1-2% for speed 6.
Change-Id: Ie4845e0127e876337b9c105aa37e93b286193405
|
|
Also removes some spurious changes in common/vp9_blockd.h which
was introduced by a rebase issue between nextgen and master branches.
Change-Id: If359f0e9a71bca9c2ba685a87a355873536bb282
(cherry picked from commit 005d80cd05269a299cd2f7ddbc3d4d8b791aebba)
(cherry picked from commit 08d2f548007fd8d6fd41da8ef7fdb488b6485af3)
(cherry picked from commit 4230c2306c194c058f56433a5275aa02a2e71d56)
|
|
fixes non-Apple nasm part of issue #755
Change-Id: I11955d270c4ee55e3c00e99f568de01b95e7ea9a
|
|
|
|
Also includes block error.
(This patch is mostly cherry picked from
commit db7192e0b014a331a1dcb102c8a1148e9f0e1081)
Change-Id: Idef18f90b111a0d0c9546543d3347e551908fd78
|
|
It improves the speed performance of vp9_fdct8x8_quant_sse2 by
about 5%.
Change-Id: I74b093ba4d81df64caf71ac7693f3d917f673097
|
|
This commit reworks the forward transform and quantization process
for 8x8 block coding. It combines the two operations in a single
function to save a store/load stage of the original transform
coefficients. Overall the speed -6 is slightly faster (around 1%
range). The compression performance of speed -6 is improved by
3.4%.
Change-Id: Id6628daef123f3e4649248735ec2ad7423629387
|
|
vp9_quantize_fp is the quantization process used by rtc coding
mode. This commit adds a sse2 implementation of it. The
implementation is modified based on vp9_quantize_b_sse2. No speed
difference from ssse3 version.
Change-Id: I24949c5b27df160b4f35117d28858d269454e64a
|
|
Change-Id: I446bdf3a405e4e9d2aa633d6281d66ea0cdfd79f
(cherry picked from commit d7422b2b1eb9f0011a8c379c2be680d6892b16bc)
(cherry picked from commit 6d741e4d76a7d9ece69ca117d1d9e2f9ee48ef8c)
|
|
Change-Id: I1a74a1b032b198793ef9cc526327987f7799125f
(cherry picked from commit b1a6f6b9cb47eafe0ce86eaf0318612806091fe5)
|
|
For configured with --enable-vp9-highbitdepth
Change-Id: I2b181519d7192f8d7a241ad5760c3578255f24e6
|
|
Combined vp9_denoiser_8xM_sse2 and vp9_denoiser_4xM_sse2 into one
function vp9_denoiser_NxM_sse2_small and passed the bitexact testing.
Changed the name of the function vp9_denoiser_64_32_16xM_sse2 to
vp9_denoiser_NxM_sse2_big.
Change-Id: Ib22478df585994dd347ebae04202c0b701e7f451
|
|
|
|
denoiser_sse2.c: fix typos in comment.
Change-Id: Ic0fb102331b0e533c058da3cab1fbc30de9a0070
|
|
|
|
All sad function that process above 32 consecutive elements are optimized
for AVX2:
vp9_sad64x64
vp9_sad64x32
vp9_sad32x64
vp9_sad32x32
vp9_sad32x16
vp9_sad64x64_avg
vp9_sad64x32_avg
vp9_sad32x64_avg
vp9_sad32x32_avg
vp9_sad32x16_avg
The functions that appeared as a hotspot is vp9_sad32x32 and vp9_sad64x64
vp9_sad32x32 was optimized by 68% and vp9_sad64x64 was optimized by 90%
both of them gave and overall ~2.3% user level gain
Change-Id: Iccf86b375a2b54c5fbbe685902ead0c9a561b9fd
|
|
Change-Id: Ib5df91c8580d5dbeb0b3554edc9c2ca906ba4c4d
|
|
|
|
Change-Id: I5f63f48e11e31ea9951223c5b18f42a2471e4560
|
|
This is based on the 64-bit ssse3 quantizer.
1.1x speedup for screen content at speed 7.
Change-Id: I57d15415ef97c49165954bbe3daaaf9318e37448
|
|
immintrin.h -> emmintrin.h
fixes build where newer intrinsics are unavailable
Change-Id: I79311b39bfa782fc2abeb45884ecb417050cb9f8
|
|
The concept:
There's too much noise in source pixels for variance and at low bitrate
the reconstructed looks nothing like the source so we have problems
getting good partitionings with either. This skirts the issue by using
a box blur scaled down version for variance calculations. To compare
against source_var_ moved keyframe to be rd based like source_var.
Change-Id: Ie3babdbfadae324b7b5a76bea192893af27f0624
|
|
This SSE2 is based on VP8 denoiser's SSE2 code. In VP8, there are
only 16x16 blocks in denoiser, while in VP9, there are 13 different
block sizes.
By adding this SSE2 code, the improvement of encoder speed is around
20%(using C code vs using SSE2 code), vary for different clips.
The unit test for VP9 denoiser is to confirm that the SSE2 code is
bit-exact with the C code. The unit test covers all block size.
Change-Id: Ic8d8ac26db4ea40a5f146b5678a065af07eaaa3d
|
|
Change-Id: Ib4f5dd733eb2939b108070a01e83da5d9990bac0
|
|
Change-Id: I6786d25ce4f32b8d8912f2d239a45ca15b310c4b
|
|
|
|
|
|
Change-Id: I7b5c776d5e6f5ca428b87fa9411ae4012a9538ba
|
|
Removed functions:
* vp9_sad_16x16_mmx
* vp9_sad_8x16_mmx
* vp9_sad_16x8_mmx
* vp9_sad_8x8_mmx
* vp9_sad_4x4_mmx
Change-Id: Ic5174b93b64d65d846f0c11e72cab149e9472bc3
|
|
New code is 20% faster for 64-bit and 15% faster for 32-bit. Compiled
using clang.
Change-Id: Icfea461238411001fd093561293dbfedfbf8d0bb
|
|
Change-Id: I75eb47dd21f87015efd673dbd2aa71f4386afdf5
|
|
New code is 10% faster for 64-bit and 25% faster for 32-bit. Compiled
using clang.
Change-Id: I8ba1544c30dd6f3ca479db806384317549650dfc
|
|
Removed functions:
* vp9_mse16x16_mmx
* vp9_get_mb_ss_mmx
* vp9_get4x4var_mmx
* vp9_get8x8var_mmx
* vp9_variance4x4_mmx
* vp9_variance8x8_mmx
* vp9_variance16x16_mmx
* vp9_variance16x8_mmx
* vp9_variance8x16_mmx
They all have SSE2 equivalent.
Change-Id: I3796f2477c4f59b35b4828f46a300c16e62a2615
|
|
New SSE2 function is three times faster than MMX one.
Change-Id: I4f387ce9f75b88379176ec7bdc62d86eb5f70fbe
|
|
Properly pair the def/undef order.
Change-Id: I9736a6f8d2efc075b1d72dafc75b9350d055cf65
|
|
In the sub_pixel_avg_variance the parameter sec was also aligned load and
changed to unaligned.
Change-Id: I4d4966e0291059ea4d705baed1503dc58444fcb7
|
|
in the sub_pixel_*variance* function the dst is aligned to 16 bytes and not
to 32 bytes - now load unaligned data
Change-Id: I2e0b9745543697efc56fefa32857ea10117af135
|
|
in the function sad32x32x4d and sad64x64x4d the source is aligned to 16 bytes
and not to 32 bytes - the load is now unaligned.
Change-Id: I922fdba56d0936b5cf72e4503519f185645a168c
|
|
Remove all the redundant dct functions (dct4x4, dct8x8)
in avx2 except dct32x32 those functions were copied originally from dct_sse2
Change-Id: I742576fbf5175f3ac09f2076976a9247b259323e
|
|
This commit enables a new quantization process for 32x32 2D-DCT
transform coefficient blocks. It improves the compression
performance of speed 5 by 1.4%. The overall compression gains of
speed 5 due to the new quantization scheme is 4.7%. It also includes
the SSSE3 implementation of the 32x32 quantization process.
Change-Id: I0855b124fd6462418683f783f5bcb44255c9993b
|
|
This commit further simplifies the SSSE3 implementation of the fast
path quantization process.
Change-Id: I5be3286ec0f1bd81d1cf5be3168fece6384fb9ca
|
|
This commit re-designs the quantization process for transform
coefficient blocks of size 4x4 to 16x16. It improves compression
performance for speed 7 by 3.85%. The SSSE3 version for the
new quantization process is included.
The average runtime of the 8x8 block quantization is reduced
from 285 cycles -> 255 cycles, i.e., over 10% faster.
Change-Id: I61278aa02efc70599b962d3314671db5b0446a50
|
|
|