This reverts commit be12fefa4b7d224e9f39275a6bb4fab01b8bae3b
and commit 057c1c4034ba5b9bf360c5c1f600ebc6d0718c3a.
Also, the mismatch between the avx version and the
c version has been fixed.
BUG=https://bugs.chromium.org/p/webm/issues/detail?id=1168
For a rt encode using 1080p@60fps material, up to 11% performance
improvement overall was seen.
Change-Id: Icd1f216209ebc6fc0b8da885f32f356fa4355ed0
Function level timing test shows about 27% time saving on
a Xeon E5-2680 v2 desktop.
Rename vp9_dct_sse2.c to vp9_dct_intrin_sse2.c for vp9 and
rename dct_sse2.c to dct_intrin_sse2.c for vp10 to avoid
duplicate basenames.
Actually vp9_fwht4x4_mmx/sse2() and vp10_fwht4x4_mmx/sse2()
are identical. TODO: They should be unified later if there is
no intention to keep a duplicate.
Change-Id: I3e537b7bbd9ba417c606cd7c68c4dbbfa583f77d
the final sum may use up to 26 bits
+ add a unit test
+ disable the sse2 as the result will rollover; this will be fixed in a
future commit
Change-Id: I2a49811dfaa06abfd9fa1e1e65ed7cd68e4c97ce
This change alters the nature and use of exhaustive motion search.
Firstly any exhaustive search is preceded by a normal step search.
The exhaustive search is only carried out if the distortion resulting
from the step search is above a threshold value.
Secondly the simple +/- 64 exhaustive search is replaced by a
multi stage mesh based search where each stage has a range
and step/interval size. Subsequent stages use the best position from
the previous stage as the center of the search but use a reduced range
and interval size.
For example:
stage 1: Range +/- 64 interval 4
stage 2: Range +/- 32 interval 2
stage 3: Range +/- 15 interval 1
This process, especially when it follows on from a normal step
search, has shown itself to be almost as effective as a full range
exhaustive search with step 1 but greatly lowers the computational
complexity such that it can be used in some cases for speeds 0-2.
This patch also removes a double exhaustive search for sub 8x8 blocks
which also contained a bug (the two searches used different distortion
metrics).
For best quality in my test animation sequence this patch has almost
no impact on quality but improves encode speed by more than 5X.
Restricted use in good quality speeds 0-2 yields significant quality gains
on the animation test of 0.2 - 0.5 db with only a small impact on encode
speed. On most clips though the quality gain and speed impact are small.
Change-Id: Id22967a840e996e1db273f6ac4ff03f4f52d49aa
This function now has an AVX intrinsics version which is about 80%
faster compared to the C implementation. This provides a 2-4% total
speed-up for encode, depending on encoding parameters. The function
utilizes 3 properties of the cost function lookup table, constructed
in 'cal_nmvjointsadcost' and 'cal_nmvsadcosts'.
For the joint cost:
- mvjointsadcost[1] == mvjointsadcost[2] == mvjointsadcost[3]
For the component costs:
- For all i: mvsadcost[0][i] == mvsadcost[1][i]
(equal per component cost)
- For all i: mvsadcost[0][i] == mvsadcost[0][-i]
(Cost function is even)
These must hold, otherwise the AVX version of the function cannot be used.
Change-Id: I6c2791d43022822a9e6ab43cd124a773946d0bdc
This reverts commit f1342a7b070ef61b9fbdf03e899ac2107cfcb6bd.
This breaks 32-bit builds:
runtime error: load of misaligned address 0xf72fdd48 for type 'const
__m128i' (vector of 2 'long long' values), which requires 16 byte
alignment
+ _mm_set1_epi64x is incompatible with some versions of visual studio
Change-Id: I6f6fc3c11403344cef78d1c432cdc9147e5c1673
This function now has an AVX intrinsics version which is about 80%
faster compared to the C implementation. This provides a 2-4% total
speed-up for encode, depending on encoding parameters. The function
utilizes 3 properties of the cost function lookup table, constructed
in 'cal_nmvjointsadcost' and 'cal_nmvsadcosts'.
For the joint cost:
- mvjointsadcost[1] == mvjointsadcost[2] == mvjointsadcost[3]
For the component costs:
- For all i: mvsadcost[0][i] == mvsadcost[1][i]
(equal per component cost)
- For all i: mvsadcost[0][i] == mvsadcost[0][-i]
(Cost function is even)
These must hold, otherwise the AVX version of the function cannot be used.
Change-Id: I184055b864c5a2dc37b2d8c5c9012eb801e9daf6
A new version of vp9_highbd_error_8bit is now available which is
optimized with AVX assembly. AVX itself does not buy us too much, but
the non-destructive 3 operand format encoding of the 128bit SSEn integer
instructions helps to eliminate move instructions. The Sandy Bridge
micro-architecture cannot eliminate move instructions in the processor
front end, so AVX will help on these machines.
Further 2 optimizations are applied:
1. The common case of computing block error on 4x4 blocks is optimized
as a special case.
2. All arithmetic is speculatively done on 32 bits only. At the end of
the loop, the code detects if overflow might have happened and if so,
the whole computation is re-executed using higher precision arithmetic.
This case however is extremely rare in real use, so we can achieve a
large net gain here.
The optimizations rely on the fact that the coefficients are in the
range [-(2^15-1), 2^15-1], and that the quantized coefficients always
have the same sign as the input coefficients (in the worst case they are
0). These are the same assumptions that the old SSE2 assembly code for
the non high bitdepth configuration relied on. The unit tests have been
updated to take this constraint into consideration when generating test
input data.
Change-Id: I57d9888a74715e7145a5d9987d67891ef68f39b7
If high bit depth configuration is enabled, but encoding in profile 0,
the code now falls back on optimized SSE2 assembler to compute the
block errors, similar to when high bit depth is not enabled.
Change-Id: I471d1494e541de61a4008f852dbc0d548856484f
When configured with high bitdepth enabled, the 8bit transform
stopped using optimised code. This made 8bit content decode slowly.
Change-Id: I67d91f9b212921d5320f949fc0a0d3f32f90c0ea
This commit moves the module inverse transform functions from vp9
to vpx_dsp folder. The hybrid transform wrapper functions stay in
the vp9 folder, since it involves codec-specific data structures.
Change-Id: Ib066367c953d3d024c73ba65157bbd70a95c9ef8
It in essence refactors the code for both the interpolation
filtering and the convolution. This change includes the moving
of all the files as well as the changing of the code from vp9_
prefix to vpx_ prefix accordingly, for underneath architectures:
(1) x86;
(2) arm/neon; and
(3) mips/msa.
The work on mips/drsp2 will be done in a separate change list.
Change-Id: Ic3ce7fb7f81210db7628b373c73553db68793c46
This commit factors the 4x4, 8x8, and 16x16 2D-DCT forward
transform operations into vpx_dsp folder.
Change-Id: I084b117b79c0925edcbcabb93f62b9f4bf8dbe7d
The SSE2 version high bit-depth forward hybrid transforms are
essentially using the C functions via cross referencing to 1-D
functions in vp9_dct.c. This commit unifies the two versions and
removes the unnecessary dependency.
Change-Id: Ib4d0702a138f8daf7d0bd97c141ee7088f293765
The following quantization functions were moved:
vp9_quantize_b
vp9_quantize_b_32x32
vp9_highbd_quantize_b
vp9_highbd_quantize_b_32x32
vp9_quantize_dc
vp9_quantize_dc_32x32
vp9_highbd_quantize_dc
vp9_highbd_quantize_dc_32x32
The purpose of doing that was to allow these functions to be shared
by multiple codecs.
Change-Id: Id8ab939f283353cdd07bd930d47db3d932a5d87f
The various tap loop filter operations are common functions across
codec. This commit moves them along with SIMD optimizations to
vpx_dsp folder.
Change-Id: Ia5fa0b2e5289cdb98467502a549c380b9c60e92c
This reverts commit a42df86c035d1bc007dbc816b4b758605135d6d9.
this change causes MSA/VP9SubpelVarianceTest.Ref and
MSA/VP9SubpelVarianceTest.ExtremeRef failures under
mips32r5el-msa-linux-gnu and mips64r6el-msa-linux-gnu
Change-Id: I40b71a0b774eaeb31f66f795733f95cf360909f7
