Commit graph

2943 commits

Author SHA1 Message Date
Pauli Oikkonen 2b95d9cdd6 Align all DCT test buffers to 32 bytes
Now that most AVX2 DCTs use MOVDQA instead of MOVDQU, also adapt the
tests to that..
2019-10-28 16:19:42 +02:00
Pauli Oikkonen ca9409de2b Implement 16x16 DCT as butterfly algorithm in AVX2 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 7c69a26717 Use aligned loads and stores for AVX2 DCT 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 8e9c65dca6 Align DCT matrices and temp transform buffers 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 148a150522 Align DCT source and dest blocks to cache line 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 8e60bbf6a6 Slightly tune 16x16 forward DCT
Use an array of __m256i's to store temporary value, essentially letting
the compiler enforce alignment and use aligned loads and stores.
2019-10-28 16:19:42 +02:00
Pauli Oikkonen c0cc0e8a75 Optimize 16x16 multiply by only slicing right mat once 2019-10-28 16:19:42 +02:00
Pauli Oikkonen e463d27f22 Implement streamlined generic 16x16 matrix multiply
It can't be this fast for real, can it?
2019-10-28 16:19:42 +02:00
Pauli Oikkonen beb85ce9d6 Reorder parameters for 8x8 matrix multiplies 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 292af62256 Implement tailored 16x16 forward DCT 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 30ce461d98 Redo 4x4 matrix multiplication 2019-10-28 16:19:42 +02:00
Pauli Oikkonen 07970ea82f Streamline by-the-book 8x8 matrix multiplication
Also chop up the forward transform into two tailored multiply functions
2019-10-28 16:19:42 +02:00
Pauli Oikkonen 7ec7ab3361 Implement a tailored AVX2 8x8 DCT 2019-10-28 16:19:42 +02:00
Marko Viitanen ad7c8d40bc
Merge pull request #247 from pkubaj/master
Fix build on powerpc64 with LLVM
2019-09-12 16:11:19 +03:00
pkubaj 1d7fcf4227
Fix build on powerpc64 with LLVM 2019-09-12 15:05:00 +02:00
Marko Viitanen 4007485420 Update the ffmpeg version used in the tests 2019-09-11 14:52:30 +03:00
Marko Viitanen da5dca057d Change libtool path in tests to fix travis builds 2019-09-11 09:33:43 +03:00
Pauli Oikkonen 99597b828a Work around the ancient Win32 calling convention hassle
See if this'll work now
2019-09-06 13:14:42 +03:00
Pauli Oikkonen c5ca18950c Revert "Revert to 6924d90052 due to broken visual studio build"
This reverts commit 1dd0619bd7.
2019-09-05 18:21:55 +03:00
Pauli Oikkonen 55529decd5 Implement _mm256_insert_epi32 and extract pseudo-ops
Visual Studio headers apparently lack these guys
2019-09-05 18:20:52 +03:00
Ari Lemmetti 4e94d60552 Merge branch 'smp-merge-analysis' 2019-09-03 16:47:07 +03:00
Ari Lemmetti 147378e1f9 Prevent 8x4 and 4x8 bipred in merge analysis 2019-09-03 16:32:50 +03:00
Ari Lemmetti ef1fdbf259 Separate prediction of single PU/PB from CU/CB 2019-09-03 16:32:50 +03:00
Ari Lemmetti 3bc510712f Enable merge analysis for smp and amp 2019-09-02 17:31:51 +03:00
Ari Lemmetti 557bcbc6aa Make luma or chroma only inter "recon" or predict possible 2019-09-02 17:15:28 +03:00
Ari Lemmetti f7aa544443 Temporarily disable offending strategies to make tests not fail for everyone 2019-08-26 22:56:39 +03:00
Ari Lemmetti aa8ab195d1 Compare rough cost of the best merge mode against AMVP to make mode decision 2019-08-26 22:49:09 +03:00
Ari Lemmetti 8f866ff83a Use correct index 2019-08-26 20:10:10 +03:00
Ari Lemmetti 2343958a14 Fix transform split for small luma blocks 2019-08-24 21:50:17 +03:00
Ari Lemmetti ab872c0432 Merge branch 'early-skip-fixes' 2019-08-24 21:49:59 +03:00
Ari Lemmetti 800fc8644d Reset CBFs because CBFs might have been set earlier for depth earlier. 2019-08-24 21:49:33 +03:00
Ari Lemmetti a80de22bc7 Add only different candidates to the list 2019-08-24 21:49:33 +03:00
Ari Lemmetti 45c7961412 Remove tr depth fill. It should not be needed. 2019-08-24 21:49:32 +03:00
Ari Lemmetti ff8711aaab Add missing logic to add valid indices to list 2019-08-24 21:49:29 +03:00
Ari Lemmetti 1dd0619bd7 Revert to 6924d90052 due to broken visual studio build 2019-08-08 15:15:34 +03:00
Pauli Oikkonen 2852baa673 Separate sign3_diff_epu8 from calc_eo_cat
Just to keep things simple, clear and obvious
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 17947b79ee Add sao_shared_generics.h in Makefile.am 2019-08-07 16:35:24 +03:00
Pauli Oikkonen a8dd6ce351 Add a note about having implemented a separate AVX2 version of SAO offset array calculation 2019-08-07 16:35:24 +03:00
Pauli Oikkonen a858e7dd4b Combine duplicate code into inline functions 2019-08-07 16:35:24 +03:00
Pauli Oikkonen de0e97f711 Take 8/16/24b loads and stores into separate functions 2019-08-07 16:35:24 +03:00
Pauli Oikkonen 10979f58fe Tidy up code 2019-08-07 16:35:24 +03:00
Pauli Oikkonen 9cc11976c0 Combine the delta accumulation from edge and band ddistortion into shared func
This won't reduce object size, but there'll be less duplicate code
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 55d877bd66 Vectorize sao_edge_ddistortion 2019-08-07 16:35:24 +03:00
Pauli Oikkonen aef0f301d3 Fix function signatures
Mark anything intended as read-only to be const, and fix alignment
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 997fd369b3 Redo calc_sao_edge_dir_avx2
Do it wider, 32 pixels at once!
2019-08-07 16:35:24 +03:00
Pauli Oikkonen db1e475e02 Use i32 instead of i8 for x/y offsets
Doesn't matter too much, because this number isn't used in SIMD
computation, only as a memory reference offset.
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 12de466ef5 Reimplement non-band SAO color reconstruction in AVX2
Streamline things to work on 32 pixels at once instead of 8
2019-08-07 16:35:24 +03:00
Pauli Oikkonen e8bff99329 Redo the SAO_TYPE_BAND subsection of AVX2 SAO color reconstruction
Vectorize it all, hope this helps with perf
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 7b5dffa855 Implement calc_sao_offset_array in AVX2
To be efficient, the AVX2 color reconstruction algorithm will need
offsets in byte, not dword, arrays. This is completely specific to 8-bit
pixels and the function signature is fundamentally distinct from the
generic algorithm, so it's better to not strategize SAO offset array
calculation.
2019-08-07 16:35:24 +03:00
Pauli Oikkonen 29563b7039 Make kvz_calc_sao_offset_array more obvious
Name temporary values from array lookups etc that are referred multiple
times to, to make the behavior of the mechanism more transparent. Define
all the constant values at the beginning of the function and declare as
const.
2019-08-07 16:35:24 +03:00