hashirama/uvg266
1
0
Fork 0
mirror of https://github.com/ultravideo/uvg266.git synced 2024-11-24 10:34:05 +00:00
Code Issues Actions Projects Releases Wiki Activity
3001 commits 3 branches 6 tags 9.2 MiB
Commit graph

2554 commits

Author SHA1 Message Date
Pauli Oikkonen 84cf771dea Unroll 32 and 16 wide SAD vector implementations by 4 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 5df5c5f8a4 Cast all pointers to const types in vector SAD funcs 
Also tidy up the pointer arithmetic
 2019-02-04 20:41:40 +02:00
Pauli Oikkonen a711ce3df5 Inline fixed width vectorized SAD functions 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 6504145cce Remove 16-pixel wide AVX2 SAD implementation 
At least on Skylake, it's noticeably slower than the very simple
version using SSE4.1
 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 4cb371184b Add SSE4.1 strategy for 24px wide SAD and an AVX2 strategy for 16 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 796568d9cc Add SSE4.1 strategies for SAD on widths 4 and 12 and AVX2 strategies for 32 and 64 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 4d45d828fa Use constant-width SSE4.1 SAD funcs for AVX2 2019-02-04 20:41:40 +02:00
Pauli Oikkonen 2eaa7bc9d2 Move SSE4.1 SAD functions to separate header 2019-02-04 20:41:40 +02:00
Pauli Oikkonen d2db0086e1 Create constant width SAD versions for 8 and 16 pixels 2019-02-04 20:41:40 +02:00
Pauli Oikkonen a13fc51003 Include a blank AVX2 strategy registration function even in non-AVX2 builds 2019-02-04 19:52:24 +02:00
Pauli Oikkonen d55414db66 Only build AVX2 coeff encoding when supported 
..whoops
 2019-02-04 19:34:30 +02:00
Pauli Oikkonen 3fe2f29456 Merge branch 'encode-coeffs-avx2' 2019-02-04 18:52:31 +02:00
Pauli Oikkonen 722b738888 Fix more naming issues 2019-02-04 16:05:43 +02:00
Pauli Oikkonen e26d98fb75 Rename a couple variables and add crucial comments 2019-02-04 15:57:07 +02:00
Pauli Oikkonen f186455619 Move encode_last_significant_xy out of strategy modules 
It's the exact same in both AVX2 and generic, and does not seem to
be worth even trying to vectorize
 2019-02-04 14:55:41 +02:00
Pauli Oikkonen 3f7340c932 Fine-tune pack_16x16b_to_16x2b 
Avoid mm_set1 operation when it's possible to create the constant with
one bit-shift operation from another instead. Thanks Intel for
3-operand instruction encoding!
 2019-02-04 14:44:47 +02:00
Pauli Oikkonen 314f5b0e1f Rename 16x2b cmpgt function, comment it better, optimize it slightly 
Eliminate an unnecessary bit masking to make it even more messy
 2019-02-04 14:44:32 +02:00
Pauli Oikkonen d8ff6a6459 Fix _andn_u32 to work on old Visual Studio 2019-02-01 15:34:42 +02:00
Pauli Oikkonen 26e1b2c783 Use (u)int32_t instead of (unsigned) int in reg_sad_sse41 2019-01-10 14:37:04 +02:00
Pauli Oikkonen 3a1f2eb752 Prefer SSE4.1 implementation of SAD over AVX2 
It seems that the 128-bit wide version consistently outperforms the
256-bit one
 2019-01-10 13:48:55 +02:00
Pauli Oikkonen 9b24d81c6a Use SSE instead of AVX for small widths 
Highly dubious if this will help performance at all
 2019-01-07 20:12:13 +02:00
Pauli Oikkonen b2176bf72a Optimize SSE4.1 version of SAD 
Make it use the same vblend trick as AVX2. Interestingly, on my test
setup this seems to be faster than the same code using 256-bit AVX
vectors.
 2019-01-07 19:40:57 +02:00
Pauli Oikkonen 887d7700a8 Modify AVX2 SAD to mask data by byte granularity in AVX registers 
Avoids using any SAD calculations narrower than 256 bits, and
simplifies the code. Also improves execution speed
 2019-01-07 18:53:15 +02:00
Pauli Oikkonen 7585f79a71 AVX2-ize SAD calculation 
Performance is no better than SSE though
 2019-01-07 16:26:24 +02:00
Pauli Oikkonen ab3dc58df6 Copy SAD SSE4.1 impl to AVX2 2019-01-03 18:31:57 +02:00
Pauli Oikkonen 45ac6e6d03 Tidy pack_16x16b_to_16x2b comments 2019-01-03 16:37:05 +02:00
Ari Lemmetti cd818db724 Add missing quantization and residual in cost calculation (inter rd=2). 2018-12-21 15:55:29 +02:00
Pauli Oikkonen 016eb014ad Move packing 16x16b -> 16x2b into separate function 2018-12-20 10:51:44 +02:00
Ari Lemmetti b234897e8a Fix smp and amp blocks in fme and revert previous change. 
Filter 8x8 (sub)blocks even with 8x4, 4x8, 16x4, 4x16 etc.
Calculate SATD on the 8x4, ... part
 2018-12-19 21:30:53 +02:00
Pauli Oikkonen 9aaa6f260d Fixes to enable portability 2018-12-18 20:42:09 +02:00
Pauli Oikkonen 2fdbbe9730 Move CG reordering code from quant-avx2 to shared header 2018-12-18 19:42:18 +02:00
Pauli Oikkonen d02207306d Create a header file for shared AVX2 code 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 361bf0c7db Precompute >=2 coeff encoding loop with 2-bit arithmetic 
Who needs 16x16b vectors when you can do practically the same with
16x2b pseudovectors in 32-bit general purpose registers!
 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 940b0e9e6a Require BMI2 for AVX2 build 
Any processor implementing AVX2 should also implement BMI2
 2018-12-18 19:41:09 +02:00
Pauli Oikkonen f66cb23d5b Optimize greater1 encoding loop 
Calculating the c1 variable need not be a serial operation!
 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 8c8b791c35 Vectorize kvz_context_get_sig_ctx_inc 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 033261eb74 Eliminate two branches using bit magic 2018-12-18 19:41:09 +02:00
Pauli Oikkonen c4434e8d04 Scan CG's in forward order to simplify finding last significant 2018-12-18 19:41:09 +02:00
Pauli Oikkonen efd097f5a5 Vectorize the coeff group loop to some extent 2018-12-18 19:41:09 +02:00
Pauli Oikkonen a01362e638 use the efficient method of reordering raster->scan 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 50a888e789 Use the efficient method to find first and last nz coeffs in block 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 7e9203f566 Scan coeff groups in scan order to help find last significant one 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 9a5a6fdbc7 Simplify two ifs in encode_coeff_nxn-avx2 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 37a2a8bac8 See if loop can be optimized by rearranging 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 584f2f74b6 Vectorize significant coeff group scanning loop 2018-12-18 19:41:09 +02:00
Pauli Oikkonen 1bfed73221 Add AVX2 strategy for encode_coding_tree 2018-12-18 19:41:09 +02:00
Pauli Oikkonen c3a6f3112a Add generic strategy group for encode_coding_tree 2018-12-18 19:41:09 +02:00
Marko Viitanen 1ef851ab4b Disable FME on amp/smp blocks with width or height not divisible by 8 2018-12-18 10:28:21 +02:00
Joose Sainio b71c5573f0 Merge branch 'rate_control_fix' 2018-12-17 12:39:27 +02:00
Sergei Trofimovich 68a70e45a1 x86 asm: mark stack as non-executable 
Gentoo's `scanelf` QA tool detects writable/executable stack
of assembly-writtent files as:

```
$ scanelf -qRa  .
 0644 LE !WX --- ---     ./src/strategies/x86_asm/.libs/picture-x86-asm-sad.o
 0644 LE !WX --- ---     ./src/strategies/x86_asm/.libs/picture-x86-asm-satd.o
 0644 LE !WX --- ---     ./src/strategies/x86_asm/picture-x86-asm-sad.o
 0644 LE !WX --- ---     ./src/strategies/x86_asm/picture-x86-asm-satd.o
```

Normally C compiler emits non-executable stack marking (or GNU assembler
via `-Wa,--noexecstack`).

The change adds non-executable stack marking for yasm-based assmbly files.

https://wiki.gentoo.org/wiki/Hardened/GNU_stack_quickstart has more details.

Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>
 2018-12-16 11:31:56 +00:00
Reima Hyvönen 1fcc5c6a8d Merge branch 'bipred_recon' 2018-12-11 09:59:35 +02:00
Reima Hyvönen e4a10880f3 Added case 12 to bipred_recon no mov 2018-12-11 09:52:17 +02:00
Marko Viitanen a4f3968e52 Fix Visual Studio errors by initializing some variables used in AVX2 signhiding 2018-12-11 09:33:26 +02:00
Ari Lemmetti ac943147e3 Calculate satd cost for whole non-square blocks as well. 2018-12-10 17:04:29 +02:00
Pauli Oikkonen c465578048 Add a descriptive comment to coefficient reordering 2018-12-03 15:36:32 +02:00
Pauli Oikkonen f78bf2ebcb Optimize q_coefs usage for indexed fetch 2018-12-03 15:36:32 +02:00
Pauli Oikkonen d9591f1b49 Eliminate midway buffering of reordered coefs 
TODO: For some mysterious reason seems slightly slower than the
buffered one
 2018-12-03 15:36:32 +02:00
Pauli Oikkonen 7fe454c51f Optimize get_cheapest_alternative() 2018-12-03 15:36:32 +02:00
Pauli Oikkonen 6bbd3e5a44 Optimize rearrange_512 function 2018-12-03 15:36:32 +02:00
Pauli Oikkonen cb8209d1b3 Vectorize transform coefficient reordering loop 2018-12-03 15:36:32 +02:00
Pauli Oikkonen 7cf4c7ae5f Rename "reduce" functions to hsum 
That's what the functions fundamendally do anyway
 2018-12-03 15:36:32 +02:00
Pauli Oikkonen 316cd8a846 Fix ALIGNED keyword and grow alignment to 64B 2018-12-03 15:36:32 +02:00
Pauli Oikkonen 1befc69a4c Implement sign bit hiding in AVX2 2018-12-03 15:36:32 +02:00
Pauli Oikkonen c5cd03497e Require BMI and ABM instruction sets for AVX2 build 
AVX2 support on a processor should always imply BMI and ABM support.
The lzcnt and tzcnt instructions have more suitable semantics in the
corner case that source word is 0, and allow us to even handle that
scenario without a branch. Apparently Visual Studio will already
include this support when building with AVX2 enabled, so only the
automake files need to be tweaked.
 2018-12-03 15:36:32 +02:00
Reima Hyvönen f8696b54a4 Updated bipred_recon_avx2 in avx2/picture-avx2.c. Now it detects blocks that can be not equal to 8 (ie. width = 12) 2018-11-20 17:09:19 +02:00
Marko Viitanen a5a10a33c3 Enable --scaling-list parameter and add to the documentation 2018-11-19 10:47:30 +02:00
Reima Hyvönen 710ba288db Chroma has some problems 2018-11-15 16:42:48 +02:00
Sami Ahovainio 8f98d4aac7 Added square search 2018-11-14 14:50:31 +02:00
Marko Viitanen 6871490dd5 Simplify get_mvd_coding_cost(), only include golomb coding 2018-11-14 14:33:31 +02:00
Ari Lemmetti a832206bb6 Replace 32-bit incompatible instrinsics 2018-11-12 18:54:33 +02:00
Ari Lemmetti 5c774c4105 Rewrite most of FME and interpolation filters 
Changes had to break a lot of stuff and were just squashed into this horrible code dump
 2018-11-08 20:21:16 +02:00
Joose Sainio 1c8a1f24e2 Don't assume anything about bits spent 2018-11-07 16:03:38 +02:00
Joose Sainio 3471e2470d Fix using uninitialized value for the first frame 2018-11-07 08:17:39 +02:00
Joose Sainio d95ac11a3b Fix rate_control for other LP-GOPS 2018-11-06 14:20:44 +02:00
Joose Sainio 67a6ba667e Fix rate control for flat lp-gop 2018-11-06 09:38:17 +02:00
Reima Hyvönen 7406c33a42 Some more cleaning 2018-10-26 12:25:18 +03:00
Reima Hyvönen 4c71546b2e Cleaned some coding 2018-10-26 12:19:44 +03:00
Reima Hyvönen 4fe3909e48 Switched luma to use 32bits size ints intstead of 16bit size 2018-10-24 18:24:46 +03:00
Eemeli Kallio 284e73839e Calculating zero cost moved to its own function 2018-10-16 11:02:01 +03:00
Reima Hyvönen 381e786e10 Trying to find the bug in luma 2018-10-11 18:08:41 +03:00
Marko Viitanen c589e5ed36 Fix closed-gop frame feed, the ordering was incorrect after the first GOP 2018-10-10 11:12:03 +03:00
Reima Hyvönen 2f5f81bac3 removed the non-optimated bipred function 2018-10-09 11:19:23 +03:00
Marko Viitanen 75dce4f3ce Fix low-delay-gop usage with --no-open-gop 2018-10-04 15:16:02 +03:00
Marko Viitanen de71b58f76 Change closed GOP structure to include an additional IDR between GOPs 2018-10-04 11:17:03 +03:00
Reima Hyvönen 212a8e68fa Modified to avoid memory overflow, still some bug inside luma 2018-10-02 20:23:32 +03:00
Marko Viitanen 954f07e3d7 Add --(no-)open-gop option 2018-10-02 10:05:32 +03:00
Marko Viitanen 8bef85e056 Merge branch 'set-qp-in-cu' 2018-09-03 08:33:33 +03:00
Ari Lemmetti 2fdcc2b79d Add option --set-qp-in-cu 2018-09-03 08:32:45 +03:00
Reima Hyvönen 896034b7cf Some renamed functions back 2018-08-28 15:31:10 +03:00
Reima Hyvönen e8b5e6db4c Did some merging 2018-08-28 15:26:27 +03:00
Reima Hyvönen 7de5c74434 Updated bipred_recon to work faster 2018-08-28 15:12:31 +03:00
Reima Hyvönen 47b357cca2 Comment one test 2018-08-27 18:52:14 +03:00
Reima Hyvönen 2ca99a44e8 Updated shuffle operation to be in right order 2018-08-27 18:16:38 +03:00
Marko Viitanen b85ae3688e Signal QP in slice header if tiles and slices=tiles are enabled 
Keeps the PPS constant for various purposes
 2018-08-16 08:44:39 +03:00
Reima Hyvönen 508b218a12 some modifications made to prevent reading too much 2018-08-14 10:50:39 +03:00
Reima Hyvönen 1d935ee888 some useless stuff removed 2018-08-13 16:47:11 +03:00
Reima Hyvönen ce3ac4c05e some modifications to no_mov 2018-08-13 16:41:02 +03:00
Reima Hyvönen 15a613ae94 test if no_mov breaks testing 2018-08-13 16:02:56 +03:00
Reima Hyvönen 97a2049e58 removed pointer declaration out from switch 2018-08-10 16:42:26 +03:00
Reima Hyvönen aa94bcedbc Stream is now pointer 2018-08-10 16:38:49 +03:00
Reima Hyvönen fa5b227ece 256 to 32 doesn't work, made them by hand 2018-08-10 16:01:20 +03:00
Reima Hyvönen 408dedbcc8 removed _mm256_extract_epi8 and replaced with _mm_stream 2018-08-10 15:53:26 +03:00
Reima Hyvönen 31c35091c6 _mm256_cvtsi256_si32 removed 2018-08-10 10:06:40 +03:00
Reima Hyvönen 99dc43074f _mm256_cvtsi256_si32 breaks system, too much bits. back to extract 2018-08-10 09:59:33 +03:00
Reima Hyvönen 4f1f80b2cb Transformed convert from 256 to cast 256 -> 128 and then convert from 128 2018-08-09 15:35:54 +03:00
Reima Hyvönen 4957555eb3 Removed leftover from 939 2018-08-09 15:25:03 +03:00
Reima Hyvönen 28b165c971 Clearified some sections, added _MM_SHUFFLE macro 2018-08-09 15:23:01 +03:00
Reima Hyvönen dd04df8667 testing if error in both avx2 functions 2018-08-03 11:49:00 +03:00
Reima Hyvönen ed50d71fde Switched some variables to different location, altered inter_recon_bipred_avx2 function 2018-08-02 16:08:59 +03:00
Reima Hyvönen f5739a0028 Renaming and removing useless prints 2018-08-02 14:47:17 +03:00
Reima Hyvönen bc09f59bb6 Edited some definitions 2018-08-02 11:54:53 +03:00
Arttu Ylä-Outinen 83555c3d6d Enable --fast-residual-cost with fastest presets 2018-07-16 12:31:20 +03:00
Arttu Ylä-Outinen c438bb4a19 Add an option to skip CABAC for residual costs 
Adds command line option --fast-residual-cost=<limit>. When QP is below
the limit, estimates the cost of coding the residual coefficients from
the sum of absolute coefficients. Skipping CABAC is not worth it with
high QPs because there are fewer coefficients so CABAC is not as slow.
 2018-07-16 12:31:20 +03:00
Reima Hyvönen a4bf77f208 Tested some extract functions 2018-07-12 09:29:32 +03:00
Reima Hyvönen c05033a893 Even more useless vectors removed 2018-07-11 15:09:14 +03:00
Reima Hyvönen 884cb77238 Removed some not used vectors 2018-07-11 15:06:11 +03:00
Reima Hyvönen 792689a5ff Removed for-loops, added extract instead 2018-07-11 14:56:41 +03:00
Reima Hyvönen f9c7f6ee66 Added some break-operations for avx2 optimation 2018-07-11 14:15:38 +03:00
Reima Hyvönen cc064da143 some more optimation for bipred 2018-07-11 11:27:54 +03:00
Reima Hyvönen 9a339eef89 Merge branch 'bipred_recon' of https://gitlab.tut.fi/TIE/ultravideo/kvazaar into HEAD 
# Conflicts:
#	build/kvazaar_lib/kvazaar_lib.vcxproj
 2018-07-10 16:21:04 +03:00
Reima Hyvönen a22cf03ddb Updated to have no movement function to avx2 strategies 2018-07-10 16:07:15 +03:00
Arttu Ylä-Outinen b7474eb532 Fix SAO buffer sizes 
Increases sizes of buffers used for SAO reconstruction to avoid stack
buffer overflow in AVX2 SAO reconstruction.
 2018-07-05 15:56:30 +03:00
Arttu Ylä-Outinen b37470e80f
Merge pull request #207 from jbeich/maltivec 
Unbreak build on PowerPC if AltiVec isn't supported
 2018-07-04 11:06:41 +03:00
Reima Hyvönen ea83ae45f0 Toimiva ratkaisu 2018-07-03 11:18:51 +03:00
Jan Beich 4f4bea7496 Check -maltivec is supported before using 
PowerPC target may lack or have non-standard FPU:

$ cc -dumpmachine
powerpcspe-undermydesk-freebsd
$ cc -c -maltivec -Isrc src/strategies/altivec/picture-altivec.c
src/strategies/altivec/picture-altivec.c:1: error: AltiVec and E500 instructions cannot coexist
 2018-07-02 23:25:23 +00:00
Jan Beich b892d820f8 Clean up macOS includes on powerpc* after 93e1c9f1c3 
strategyselector.c:426:25: machine/cpu.h: No such file or directory
 2018-07-02 21:52:45 +00:00
Reima Hyvönen 17babfffa4 25.6 working optimation, ~50% faster than original 2018-06-25 17:06:16 +03:00
Arttu Ylä-Outinen 2f995f4325
Merge pull request #205 from jbeich/powerpc 
Unbreak build on non-Linux powerpc*
 2018-06-19 13:28:00 +03:00
Arttu Ylä-Outinen c1398ef818 Permit --period=1 with any GOP structure 
All intra coding is a special case so it can be permitted even though
Kvazaar normally only supports intra periods that are divisible by the
GOP length.
 2018-06-18 12:26:11 +03:00
Arttu Ylä-Outinen abdebe0bf9 Fix --owf help message 
The number of parallel frames is --owf plus one, not --owf minus one.

Fixes #204.
 2018-06-18 09:33:36 +03:00
Jan Beich 93e1c9f1c3 Add AltiVec detection for BSDs 
strategyselector.c:377:26: linux/auxvec.h: No such file or directory
 2018-06-17 15:38:24 +00:00
Miika Metsoila 98972d26c2 Document that the high tier requires level 4 or higher 2018-06-14 12:41:03 +03:00
Miika Metsoila 62b44efaa4 Write the encoding tier (main/high) into the bitstream 2018-06-14 12:41:03 +03:00
Arttu Ylä-Outinen a343f6d587 Prepare for delta QPs at CU-level 
- Replaces lcu_dqp_enabled with max_qp_delta_depth in encoder_control_t.
- Fixes set_cu_qps so that it can handle quantization groups of
  arbitrary size.
- Fixes computation of QP predictors so that it works for quantization
  groups of arbitrary size.
 2018-06-13 15:36:19 +03:00
Arttu Ylä-Outinen dc6b2024ea Modify reference count asserts to fix data races 
Changes asserts on the reference count of objects to assert the value
after KVZ_ATOMIC_INC instead of directly checking the value. Fixes some
data races detected by TSan.
 2018-06-12 09:35:07 +03:00
Ari Lemmetti 4fb1c16c61 Add early termination for intra rdo when a zero coefficient block is found. 2018-06-08 21:03:07 +03:00
Ari Lemmetti 492529fb7a Add the same comment to help message as well... 2018-05-30 14:13:15 +03:00
Ari Lemmetti 0d5972bf03 Add missing sort to intra transform split search so mode at 0 is the best 2018-05-21 13:10:38 +03:00
Sebastien Alaiwan 954bca7d6e Fix memset parameter 2018-05-17 11:24:49 +02:00
Jaakko Laitinen f9466efcbb Close file on error 2018-05-15 11:50:16 +03:00
Reima Hyvönen 9fed29f950 optimation for inter_recon_bipred 2018-04-18 15:25:44 +03:00
Arttu Ylä-Outinen 5c585c4fbc Update help message 
Updates the default option values to match the medium preset.
 2018-04-03 10:40:37 +03:00
Arttu Ylä-Outinen 2b4e22111a Update presets 
The new presets are slower but have better coding efficiency.
 2018-04-03 10:37:30 +03:00
Arttu Ylä-Outinen 7185519a1b Update command line help 
- Adds missing default values.
- Adds help for --crypto and --key.
- Adds help for --rd=3.
- Adds help for --sao options.
- Some changes to help wording.
 2018-03-23 14:33:04 +02:00
Arttu Ylä-Outinen 3606860504 Add --no-cpuid option 
Equivalent to --cpuid=0.
 2018-03-23 12:32:27 +02:00
Arttu Ylä-Outinen fb462b25ef Fix transform skip for inter 
The transform skip flag in cu_info_t was stored under the intra
substruct even though transform skip can be used for inter as well. This
caused bitstream errors. Fixed by moving the flag out of the substruct.
 2018-03-20 11:01:33 +02:00
Arttu Ylä-Outinen b64e46707d Skip raster scan step in TZ search 
Raster scan is very slow and the BD-rate improvement is marginal.
 2018-03-01 14:04:03 +02:00
Arttu Ylä-Outinen 6877064230 Add zero neighborhood check to TZ search 
Adds an additional grid search step that starts from the zero motion
vector after the normal grid search. The search range for this step is
half of the normal range.
 2018-03-01 14:02:13 +02:00
Arttu Ylä-Outinen 74a413c46a Switch to star refinement in TZ search 2018-03-01 13:06:14 +02:00
Arttu Ylä-Outinen ebee428ee1 Add loop termination to TZ grid search 
Terminates the grid search if no better motion vector was found in the
last three iterations.
 2018-03-01 13:06:06 +02:00
Arttu Ylä-Outinen 4c175621dd Fix TZ grid search and star refinement 
- Changes TZ grid search and star refinement to keep the origin constant
  instead of moving to the best position after each iteration.
- Changes star refinement to loop until there is no more improvement,
  instead of running the step only once.
 2018-03-01 12:56:57 +02:00
Arttu Ylä-Outinen 9c2d0074a2 Add rounding of motion vectors in inter search 
When the starting point for integer motion estimation was selected among
the merge candidates, the candidate motion vectors were always rounded
down. This commit changes the rounding so that they are rounded to the
nearest integer MV instead.
 2018-03-01 09:39:21 +02:00
Ari Lemmetti 662430d441 Select CU type based on SSD, transform unit tree and mode cost of luma and chroma on --rd=2 2018-02-22 19:26:48 +02:00
Arttu Ylä-Outinen cb06cfeadb Drop temporary arrays in bipred search 
Changes bipred search to use the original source and reconstruction
arrays directly instead of copying them.
 2018-02-14 11:20:51 +02:00
Arttu Ylä-Outinen 0ea516ba30 Move bipred search to a separate function 2018-02-14 09:56:53 +02:00
Arttu Ylä-Outinen 6f506be12d Drop dynamic allocation from bipred search 
Moves the temporary LCU struct used in bipred search from the heap to
the stack. The single malloc call was a huge bottleneck in bipred.
 2018-02-14 09:55:02 +02:00
Arttu Ylä-Outinen 7155dd0db7 Add negative references to L1 list 
Changes reference index list creation so that the negative references
are added to L1 in addition to L0 when biprediction is enabled and no
reordering of pictures is done. Biprediction can now be used with the
low-delay GOP structure.
 2018-02-07 14:54:52 +02:00
Arttu Ylä-Outinen 4b24cd03a2 Update for crypto++ 6.0.0 compatibility 
Changes the crypto module to use unsigned char instead of byte. The byte
typedef is no longer included in the global namespace in crypto++ 6.0.0.
See https://github.com/weidai11/cryptopp/issues/442.

Fixes #184.
 2018-02-05 13:35:03 +02:00
Arttu Ylä-Outinen 8c53417006 Check zero coefficient cost for inter 
Checks the cost of flushing all coefficients of an inter block to zero.
This is much faster than doing full RDOQ but can still reduce bitrate
significantly. Encoding speed is increased since fewer coefficient bits
have to be coded with CABAC.
 2018-01-29 12:41:56 +02:00
Arttu Ylä-Outinen 018b5ffa64 Move inter CU reconstruction to a new function 
Moves code for reconstructing all PUs in an inter CU to a new function
kvz_inter_recon_cu in inter.c.
 2018-01-24 15:05:39 +02:00
Arttu Ylä-Outinen 405b8c1069 Refactor inter MVD cost functions 
Moves duplicate code for writing the MVD of a single motion vector from
kvz_get_mvd_coding_cost_cabac and encoder_inter_prediction_unit to a new
function.
 2018-01-19 08:29:17 +02:00
Arttu Ylä-Outinen c1cca1ad7f Refactor inter MV candidate selection 
Moves duplicate code for checking the best MV candidate from functions
calc_mvd_cost, search_pu_inter_ref and search_pu_inter to a new
function.
 2018-01-19 08:29:17 +02:00
Arttu Ylä-Outinen 9067aa4535 Remove an unnecessary copy in SMP/AMP search 
SMP/AMP search is performed using a lower work tree level than the
normal inter search so the prediction info must be copied up if an
SMP/AMP mode is chosen. Previously pixels and coefficient were copied as
well. Changed to only copy prediction info.
 2018-01-18 10:36:26 +02:00
Arttu Ylä-Outinen 89a930d6dd Add part mode bitcost when using SMP/AMP blocks 2018-01-18 10:36:26 +02:00
Arttu Ylä-Outinen fc43643ba5 Use a transform split for SMP and AMP blocks 2018-01-18 10:36:25 +02:00
Arttu Ylä-Outinen c74ede148b Fix CBF flags for 4x4 luma blocks 
CBF flags were not being propagated to the upper level from blocks of
size 4x4.
 2018-01-18 10:36:25 +02:00
Arttu Ylä-Outinen 0a69e6d18f Fix selection of transform function for 4x4 blocks 
DST function was returned for inter luma transform blocks of size 4x4
even though they must use DCT. Fixed by checking the prediction mode of
the block in addition to whether it is chroma or luma.
 2018-01-18 10:36:25 +02:00
Miika Metsoila bcedfd6669 Remove the usage of errno in me-steps argument parsing 2018-01-16 14:38:43 +02:00
Miika Metsoila 39ed36830e Merge branch 'me_steps' 2018-01-16 14:22:59 +02:00
Miika Metsoila 61213e3ad9 Improve step parameter parsing and usage 2018-01-10 15:16:52 +02:00
Arttu Ylä-Outinen 649113a821 Fix inter search being used for 4x4 blocks 
When 4x4 intra blocks are enabled and inter search is limited to 16x16
and larger blocks, it is possible that inter search is accidentally done
for 4x4 blocks. Fixed by checking that block size is at least 8x8 before
doing inter search.
 2018-01-10 14:21:48 +02:00
Miika Metsoila e8e0e7596a Add a step-cutoff parameter for motion estimation search 2017-12-22 14:04:25 +02:00
Miika Metsoila 4e13608b01 Merge branch 'diamond_search' 2017-12-18 14:11:53 +02:00
Miika Metsoila 2cde0d1a18 Document diamond search option 2017-12-12 14:45:01 +02:00
Miika Metsoila b923b63b42 Add diamond search 2017-12-12 14:40:14 +02:00
Ari Lemmetti 14892fda00 Replace simple coefficient cost estimation with CABAC. Substantial improvement. 
Approximation proved to be too inaccurate while not giving actually that much speedup.
 2017-12-10 01:23:48 +02:00
Miika Metsoila ea79069dc8 Fix a type warning in encmain.c 2017-12-08 16:22:40 +02:00
Miika Metsoila 6aa4cd7528 Fix type warnings 2017-12-08 16:16:36 +02:00
Miika Metsoila b3486b5114 Fix gcc/clang warnings and errors in cfg.c 2017-12-08 16:09:00 +02:00
Miika Metsoila bac07457ea Merge branch 'hevc_level' 2017-12-08 15:57:38 +02:00
Miika Metsoila c67a24e6ec Update readme and --help text 2017-12-07 12:32:46 +02:00
Ari Lemmetti 713e694d82 Define HAVE_STRUCT_TIMESPEC on Visual Studio 2015 and later 
Fixes redefinition of timespec that Pthreads-Win32 does even if it has been already defined.
 2017-12-05 18:26:12 +02:00
Miika Metsoila f64d42169f Improve bitrate checking to accommodate non-integer and less than 1 framerates 2017-12-01 17:20:12 +02:00
Miika Metsoila 57cf92d35f Implement level's bitrate limit checking during encoding 2017-11-28 16:19:44 +02:00
Miika Metsoila 021fb27787 Add high-tier flag 2017-11-20 16:05:28 +02:00
Miika Metsoila d249059d61 Minor refactoring of level checking 2017-11-20 13:25:26 +02:00
Arttu Ylä-Outinen cf85d52b9d Kvazaar version 1.2.0 2017-11-17 15:23:33 +02:00
Miika Metsoila 4c1512e8c5 Add a check for maximum picture width and height for the given level 2017-11-15 16:39:59 +02:00
Arttu Ylä-Outinen 4cb054295a Fix linkers 
Overrides the linkers used for kvazaar, libkvazaar.la and kvazaar_tests.
When crypto++ is enabled, the C++ linker is used and when it is
disabled, the C linker is used.

This removes the need to explicitly specify -lstdc++ in configure when
crypto++ is used and fixes the build with crypto++ when libstd++ is not
installed.
 2017-11-13 15:09:38 +02:00
Miika Metsoila f9a4aba867 Update documentation, fix input fps default value, remove 0 as default level 2017-11-09 16:53:31 +02:00
Miika Metsoila ebba0a4f01 Test if input conforms to it's level's limits (excluding bitrate) 2017-11-08 16:15:41 +02:00
Miika Metsoila fb4d0c3cf2 Move level argument parsing to the correct place and give it initial values 2017-11-03 15:47:35 +02:00
Miika Metsoila 61a31054e1 Add level command-line parameter 2017-11-03 13:04:05 +02:00
Arttu Ylä-Outinen 9974380cdd Fix bipred and temporal MVP 
- Fixes two errors in calculating the POC for the reference frame for
  temporal candidate MV scaling.
- Fixes using the MV for the wrong direction when the temporal MV
  predictor block uses bi-prediction.

Fixes #160.
 2017-10-25 12:26:41 +03:00
Arttu Ylä-Outinen 841597e123 Fix picture and slice types 
Changes handling of intra pictures for --gop=8 so that every picture
with POC divisible by the intra period is intra. The first picture is
IDR and the rest of the intra pictures are CRA. POC is not reset at CRA
pictures. The leading pictures that follow the CRA picture are changed
to RASL so they are allowed to refer to pictures before the CRA picture.

Changes inter slice types to P when the L1 reference list is empty and
to B otherwise.

In all-intra, all pictures are now IDR pictures with POC zero.
 2017-10-20 13:35:26 +03:00
Jaakko Laitinen 957b6850c3 Change ref list printout to match hm decoded printout 2017-09-25 13:48:56 +03:00
Arttu Ylä-Outinen 20aea8df63 Fix POCs when using --gop=8 
When using --gop=8 with an intra period greater than one, a single POC
would be skipped before every intra frame. This commit fixes the problem
by turning the intra frames into BLA frames with leading pictures when
using --gop=8.
 2017-09-19 09:31:58 +03:00
Miika Metsoila 6e00f63469 Remove unused variables from search_pu_inter_ref function 2017-09-18 15:36:37 +03:00
Miika Metsoila 7b0101ce3d Merge branch 'reflist_changes' 
# Conflicts:
#	src/encoderstate.c
#	src/search_inter.c
 2017-09-18 14:59:37 +03:00
Miika Metsoila 769b17768d Change max function to MAX macro for clang/gcc compatibility. 
Remove couple of unnecessary comments
 2017-09-15 14:21:51 +03:00
Miika Metsoila 5f7c5443a3 Remove inter.poc 2017-09-12 14:23:19 +03:00
Miika Metsoila 6bd78a3da7 Reverse L0 list sort direction 2017-09-12 14:23:18 +03:00
Miika Metsoila 83dc7e7f50 Made L0 to sort and fixed mv_ref_coded in search_pu_inter 2017-09-12 14:23:18 +03:00
Timothe FRIGNAC d3362a238e changed strtod to strtol 2017-08-31 15:14:31 +02:00
Timothe FRIGNAC 3a1ab54ff0 Fixed memory leaks 2017-08-31 11:51:41 +02:00
Timothe FRIGNAC 466297fd77 Fixed build error 2017-08-29 17:01:18 +02:00
Timothe FRIGNAC 2e130912cb Add --key opt 2017-08-28 17:15:13 +02:00
Miika Metsoila a5f4cf09b5 Switched from storing POCs in inter.poc to state->frame->refLXs array 2017-08-21 16:34:57 +03:00
Arttu Ylä-Outinen 409d2114f0 Fix motion vector constraints 
Fixes integer motion vectors being constrained more than what was
necessary when using --mv-constraint or --wpp.
 2017-08-11 14:41:36 +03:00
Arttu Ylä-Outinen 7144a00beb Rewrite thread queue 
Changes thread queue so that only the jobs that are ready to run are
stored in the queue. Other jobs are kept track of by pointers in the
reverse dependency lists of other jobs. When a job is ready to run it is
appended to the queue. The job queue is stored as a linked list.

The definitions of threadqueue_queue_t and threadqueue_job_t are moved
to the .c file, turning them into opaque structs.

Makes thread queue code simpler. Fixes some TSan errors.
 2017-08-11 14:18:12 +03:00
Arttu Ylä-Outinen bc47fe94af Drop thread queue debug code 2017-08-11 14:18:12 +03:00
Eemeli Kallio e5cbc7a205 --sao now enables full sao 2017-08-11 13:26:55 +03:00
Eemeli Kallio 4c3453d26f Fixed issue with no-sao argument 2017-08-11 13:12:22 +03:00
Eemeli Kallio 8674c0f5ee Added paremeter for band and edge sao. 2017-08-11 11:57:09 +03:00
Eemeli Kallio d9b93ea368 Added possibility to skip edge or band sao. 2017-08-11 11:51:49 +03:00
Arttu Ylä-Outinen 4b73bdd9aa Skip checked motion vectors in early termination 
Changes the second iteration of early termination to skip the motion
vectors that were already checked in the first iteration.
 2017-08-09 14:29:09 +03:00
Arttu Ylä-Outinen 606d441362 Skip computing MV cost twice in hexagon search 
Changes the first step of hexagon search to skip the zero offset since
the cost of the motion vector has already been computed.
 2017-08-09 14:29:09 +03:00
Arttu Ylä-Outinen fa4648061d Add mv, cost and bitcost to inter_search_info_t 2017-08-09 14:29:08 +03:00
Arttu Ylä-Outinen 328f051d7f Put inter search parameters in a single struct 
Adds struct inter_search_info_t for holding the parameters that are used
by most function related to inter search. Passing the parameters in
a single struct greatly reduces the number of parameters for many
functions.
 2017-08-09 14:27:53 +03:00
Miika Metsoila 0dd069f8af Fixed using wrong POC in add_temporal_candidate 2017-08-09 13:50:21 +03:00
Miika Metsoila 25e0a954c7 Fixed 2 bugs causing incorrect video output 2017-08-09 13:50:21 +03:00
Arttu Ylä-Outinen 24ecddd2a5 Fix wrong strides in SAO reconstruction 
Functions kvz_sao_reconstruct and encoder_sao_reconstruct used
frame->width as the stride instead of frame->rec->stride when accessing
frame->rec->data. This caused errors when using tiles and SAO.
 2017-08-01 15:40:49 +03:00
Arttu Ylä-Outinen f0bf959d17 Fix alignment errors in 32-bit build with MSVC 
Changes the work_tree parameter in search.c functions from an array to
a pointer. Fixes "formal parameter with requested alignment of 8 won't
be aligned" errors.
 2017-07-28 09:27:02 +03:00
Arttu Ylä-Outinen 9694bd2fae Fix build on 32-bit systems 
Function coeff_abs_sum_avx2 that was added in e950c9b was outside the
AVX2 #if directive.
 2017-07-28 09:19:29 +03:00
Arttu Ylä-Outinen ecb0275cdd Store CU arrays as pointers to the main array 
Changes field state->tile->frame->cu_array->data to point to the CU
array in the main encoder state. Removes the need to copy the CU array
to the main CU array after search.
 2017-07-28 08:36:45 +03:00
Arttu Ylä-Outinen e950c9b101 Add AVX2 implementation for coefficient sum 2017-07-28 07:39:36 +03:00
Arttu Ylä-Outinen d50ae6990c Add sum of absolute coefficients to strategies 2017-07-28 07:39:15 +03:00
Arttu Ylä-Outinen 59faca0646 Skip CABAC coefficient cost for --rd=0 2017-07-28 07:33:03 +03:00
Arttu Ylä-Outinen 19e051ea40 Reduce intra threshold 
Reduces intra threshold for --rd=0 from 20 to 8. Threshold of 20
increased BD-Rate too much.
 2017-07-25 13:26:38 +03:00
Arttu Ylä-Outinen e9cf15465e Fix inter cost in bipred 
The cost of coding MV ref indices and MV direction was added to bitcost
but not inter cost. Fixed by adding the extra bits to inter as well.
 2017-07-24 15:24:04 +03:00
Arttu Ylä-Outinen edbe00763e Drop extra parameter in kvz_image_calc_sad 
Drops the parameter max_lcu_below which was always set to -1.
 2017-07-24 15:21:19 +03:00
Arttu Ylä-Outinen ffac29061f Fix extrapolated inter SATD 2017-07-24 15:11:05 +03:00
Arttu Ylä-Outinen 631ef53d2a Fix inter cost calculations 
Inter costs are computed using SAD except when fractional motion
estimation or bi-prediction is enabled. This commit changes
search_pu_inter_ref to recalculate the cost with SATD. Fixes inter/intra
cost comparisons since intra costs are always SATD costs.
 2017-07-24 15:11:05 +03:00
Arttu Ylä-Outinen 6ce2fb1238 Add pixel offsets to encoder_state_config_tile_t 
Adds fields offset_x and offset_y to encoder_state_config_tile_t.
 2017-07-24 15:11:05 +03:00
Arttu Ylä-Outinen 2380ba0d41 Reduce copying in kvz_get_coeff_cost 
Changes function kvz_get_coeff_cost to only copy the CABAC contexts and
not the whole encoder state.

Other threads could be simultaneously using the other parts of the
encoder state. Only copying the CABAC fixes a TSan data race warning.
 2017-07-24 12:38:41 +03:00
Arttu Ylä-Outinen 24b462f801 Align coefficients to 8 bytes 
Adds alignment attribute to lcu_coeff_t. The coefficients are sometimes
handled as 64-bit integers containing four coefficients so the arrays
should be aligned to 8 bytes.

Fixes a UBSan error about misaligned reads.
 2017-07-24 12:37:37 +03:00
Arttu Ylä-Outinen 5ddb43c6fe Fix undefined left shifts in rdo 
Replaces left shifts by multiplications when the operand may be
a negative value. Left shift of a negative value is undefined behavior.
 2017-07-24 12:35:10 +03:00
Arttu Ylä-Outinen d1e64ad62b Fix undefined left shifts 
Replaces left shifts by multiplications when the operand may be
a negative value. Left shift of a negative value is undefined behavior.
 2017-07-20 11:15:30 +03:00
Arttu Ylä-Outinen 07b5fb9caf Fix out-of-bounds read in encoderstate 
When calling encoder_state_encode_leaf with POC 0, index -1 of the GOP
array would be accessed. Fixed by skipping the code for I-frames.
 2017-07-20 11:15:30 +03:00
Arttu Ylä-Outinen 8c4a3473a8 Change --owf=auto and --threads=auto selection 
Changes OWF selection so that it is chosen based on the maximum number
of parallel CTUs. Number of threads is limited to prevent overhead from
extra threads.
 2017-07-20 09:42:28 +03:00
Arttu Ylä-Outinen 4fc9b743c1 Drop an unnecessary pthread_cond_broadcast 
Drop pthread_cond_broadcast on threadqueue->cond in function
kvz_threadqueue_waitfor. The broadcast caused threads to be woken up
more often than necessary.
 2017-07-19 11:09:30 +03:00
Arttu Ylä-Outinen 14003c6a30 Disable printing PSNR with --no-psnr 2017-07-19 10:38:37 +03:00
Arttu Ylä-Outinen e90bde5c62 Clarify PSNR output 
Adds letters Y, U and V to the PSNR output to make it clearer that the
printed values are the luma and chroma PSNR.
 2017-07-19 10:33:43 +03:00
Arttu Ylä-Outinen fdb3480b54 Enable strategies for SAO reconstruction 
Re-enables strategies for SAO reconstruction. They were disabled in
commit ec9ff42.
 2017-07-11 10:35:18 +03:00
Arttu Ylä-Outinen 333dba3884 Add static to SAO strategies 2017-07-11 10:02:01 +03:00
Miika Metsoila e8cc2d8f6a Small fixes 2017-07-07 13:58:19 +03:00
Arttu Ylä-Outinen 67a60a35e3 Fix invalid calls to normalize_lcu_weights 
Changes encoder_state_init_new_frame to only call normalize_lcu_weights
when the weights have been written to the array and rate control is
enabled. When rate control is disabled, the weights are not used.
 2017-07-07 11:05:31 +03:00
Arttu Ylä-Outinen 563bc26e71 Fix out-of-bounds read in AVX2 SAO 
AVX2 version of SAO loaded offsets with a 256 bit read even though there
are only five 32 bit integers.
 2017-07-06 13:04:52 +03:00
Arttu Ylä-Outinen 0850b17f96 Drop get_wpp_limit in search_inter 
WPP limit for motion vectors is now computed inside fracmv_within_tile.
 2017-07-05 13:22:53 +03:00
Arttu Ylä-Outinen 2a85f0f5a4 Move hard-coded MV limits to encoder_control_t 
Adds field max_inter_ref_lcu to encoder_control_t. It is used to set up
inter-LCU dependencies in encoder_state_encode_leaf and restrict motion
vectors in fracmv_within_tile.
 2017-07-05 13:22:53 +03:00