summaryrefslogtreecommitdiff
path: root/vpx_dsp
AgeCommit message (Collapse)Author
2016-09-02Merge changes from topic 'Wundef'Johann Koenig
* changes: Enable -Wundef by default Define VP8_TEMPORAL_ALT_REF to !CONFIG_REALTIME_ONLY Remove CONFIG_DEBUG guards from assert() Remove unused function vpx_de_mblock Fix -Wundef warning for OUTPUT_FPF Fix -Wundef warning for __SANITIZE_ADDRESS__
2016-08-31Remove unused function vpx_de_mblockJohann
vpx_config.h was not included so CONFIG_POSTPROC was never defined. Change-Id: I777de499823afa286734549a8e7f4a93e7ad97f3
2016-08-31Update NEON transpose functions.Linfeng Zhang
Unify coding style. Change-Id: I5826f40c02c882df7353391e0c9dd6cef6bd4b97
2016-08-30Update vpx_lpf_vertical_16_dual_neon() intrinsicsLinfeng Zhang
Process 16 samples together. Change-Id: If6ee8e3377aa2786417f2fc411ba7d87ea8b6799
2016-08-27Update vpx_lpf_horizontal_edge_16_neon() intrinsicsLinfeng Zhang
Process 16 samples together. Change-Id: I9cfbe04c9d25d8b89f63f48f519e812746db754d
2016-08-26Merge "Remove halfpix specialization"Johann Koenig
2016-08-24add_noise,vpx_setup_noise: correct 'char_dist' typeJames Zern
fixes SSE2/AddNoiseTest.CheckCvsAssembly/0 with -funsigned-char. visibly broken since: 0dc69c7 postproc : fix function parameters for noise functions. where the types diverged (char vs. int8) but likely the return changed in: 2ca24b0 postproc - move filling of noise buffer to vpx_dsp. when multiple implementations were merged. Change-Id: I176ca1f170217f05ba7872b0c4de63e41949e999
2016-08-23Remove halfpix specializationJohann
This function only exists as a shortcut to subpixel variance with predefined offsets. xoffset = 4 for horizontal, yoffset = 4 for vertical and both for "hv" Removing this allows the existing optimizations for the variance functions to be called. Instead of having only sse2 optimizations, this gives sse2, ssse3, msa and neon. BUG=webm:1273 Change-Id: Ieb407b423b91b87d33c4263c6a1ad5e673b0efd6
2016-08-16NEON asm of vpx_lpf_{horizontal,vertical}_8_dual_neon()Linfeng Zhang
Also expose the NEON intrinsics version. BUG=webm:1261, webm:1266. Change-Id: I8c4ae658467dcf66ebf7a75982b2ef712dbb4535
2016-08-12Merge "variance_impl_avx2: restore table layout"James Zern
2016-08-12variance_impl_avx2: restore table layoutJames Zern
disable clang-format for bilinear_filters_avx2 restores the row layout prior to: 099bd7f vpx_dsp: apply clang-format but keeps the justification used by clang-format Change-Id: Icf1733a37edb807e74c26b23a93963c03bd08fd7
2016-08-12NEON intrinsics for 4 loopfilter functionsLinfeng Zhang
New NEON intrinsics functions: vpx_lpf_horizontal_edge_8_neon() vpx_lpf_horizontal_edge_16_neon() vpx_lpf_vertical_16_neon() vpx_lpf_vertical_16_dual_neon() BUG=webm:1262, webm:1263, webm:1264, webm:1265. Change-Id: I7a2aff2a358b22277429329adec606e08efbc8cb
2016-08-04Merge changes I6ef79702,Id332c641,I354b5d22,I84438013Johann Koenig
* changes: Use common transpose for vpx_idct32x32_1024_add_neon Use common transpose for vpx_idct8x8_[12|64]_add_neon Use common transpose for vp9_iht8x8_add_neon Use common transpose for vpx_idct16x16_[10|256]_add_neon
2016-08-04Merge "Remove armv6 target"Johann Koenig
2016-08-04Merge "correct break placement"James Zern
2016-08-04Use common transpose for vpx_idct32x32_1024_add_neonJohann
Change-Id: I6ef7970206d588761ebe80005aecd35365ec50ff
2016-08-04Use common transpose for vpx_idct8x8_[12|64]_add_neonJohann
Change-Id: Id332c641f05336ef9a45e17493ff149fd0a168f0
2016-08-04Use common transpose for vpx_idct16x16_[10|256]_add_neonJohann
Change-Id: I84438013f483e82084d33ba9a63c33273d35fcaa
2016-08-04Merge "Extract neon transpose for re-use"Johann Koenig
2016-08-04correct break placementJames Zern
these should be placed within {}s when present Change-Id: Ia775fac5373603e77360398f19b07958fb43f476
2016-08-04Remove armv6 targetJohann
Change-Id: I1fa81cc9cabf362a185fc3a53f1e58de533a41e5
2016-08-04Extract neon transpose for re-useJohann
Change-Id: I5e1c7f4c80d1c6f7fd582ac468c6eaaa3603a06c
2016-08-04Don't expand to Q register for 4x4 intrapredJohann
The code was expanding to Q registers so that vqrshn could be used, for vector quad round shift and narrow. If 4 values are added together, there is a shift by 2. If 8 values, a shift by 3. Since this accounts for any possibility of overflow, we can skip the narrowing shift. This allows keeping the values in D registers and casting the 16 bit value to 8 bits. Change-Id: I8d9cfa07176271f492c116ffa6a7b351af0b8751
2016-08-02Resolve -Wshorten-64-to-32 warnings in prob.h.Alex Converse
Change-Id: I1244ee908d81467f0fc8a8fce979fc8077a325b4
2016-08-02Merge "Resolve -Wshorten-64-to-32 in variance."Alex Converse
2016-07-28replace by VSTM/VLDM to reduce one of VST1/VLD1Min Chen
Change-Id: I596567570580babb1a52925541d1fd1045c352f5
2016-07-28Resolve -Wshorten-64-to-32 in variance.Alex Converse
The subtrahend is small enough to fit into uint32_t. Change-Id: Ic4d7128aaa665eaf6b25d562610ba8942c46137f
2016-07-27vpx_dsp/x86/quantize_sse2.c: apply clang-formatclang-format
post: e429080 .clang-format: disable DerivePointerAlignment Change-Id: I21a0546668edb2b09660e216d4875a1d2ad24d53
2016-07-25vpx_dsp: apply clang-formatclang-format
Change-Id: I3ea3e77364879928bd916f2b0a7838073ade5975
2016-07-25Fix compilation error under Clang 4.0.Ivan Krasin
The LLVM trunk has reached 4.0 and now __clang_major__ is not enough to distinguish between old XCode Clang and the new 'real' Clang. Using __apple_build_version__ allows to make this distinction. BUG=chromium:631144 Change-Id: I0b6e46fddfe4f409c7b7e558bda34872e60ee2d9
2016-07-22Add VPX_SWAP macroYury Gitman
Change-Id: I60e233eddef238ad918183392794084673f27d2d
2016-07-16vpx_plane_add_noise_c: normalize int typesJames Zern
quiets signed/unsigned mismatch warning Change-Id: Iaabd7dfff110ba26056258457541f5635d2e85e6
2016-07-15postproc : fix function parameters for noise functions.Jim Bankoski
Change-Id: I582b6307f28bfc987dcf8910379a52c6f679173c
2016-07-13Merge "postproc: noise style fixes."James Bankoski
2016-07-13Merge "Fix encoder crashes for odd size input"Yaowu Xu
2016-07-13postproc: noise style fixes.Jim Bankoski
Change-Id: Ifdcb36b8e77b65faeeb10644256e175acb32275d
2016-07-13Merge "postproc - move filling of noise buffer to vpx_dsp."James Bankoski
2016-07-13postproc - move filling of noise buffer to vpx_dsp.Jim Bankoski
Change-Id: I63ba35dc0ae9286c9812367a531e01d79a4c1635
2016-07-13deblock: missing const on extern const.Jim Bankoski
Change-Id: I0df08f7c431daf939e266f008bf5158b0c97358b
2016-07-12vp9_postproc.c missing extern.Jim Bankoski
BUG=webm:1256 Change-Id: I5271e71bc53cce033fb906040643dcdd5ccb2381
2016-07-12Fix encoder crashes for odd size inputYaowu Xu
Change-Id: Id5c30c419282369cc8c3280d9a70b34a859a71d8
2016-07-12deblock filter : moved from vp8 code branchJim Bankoski
The deblocking filters used in vp8 have been moved to vpx_dsp for use by both vp8 and vp9. Change-Id: I5209d76edafc894b550f751fc76d3aa6799b392d
2016-07-07Merge "Support measure distortion in the pixel domain"Jingning Han
2016-07-06Support measure distortion in the pixel domainJingning Han
Use pixel domain distortion metric in speed 0. This improves the compression performance by 0.3% for both low and high resolution test sets. Change-Id: I5b5b7115960de73f0b5e5d0c69db305e490e6f1d
2016-07-02Merge "improve vpx_filter_block1d* based on replace paddsw+psrlw to pmulhrsw"James Zern
2016-07-02Merge "Update vpx subpixel 1d filter ssse3 asm"James Zern
2016-06-29vpx_dsp: remove x86inc.asm distinctionJohann
BUG=b:29583530 Change-Id: I397d77536b0d3cee0a92cdfe8b76bc4e434d0720
2016-06-29Merge changes I9433d858,Iafd05637,If08ce6caJames Zern
* changes: tests: remove redundant round() definition remove visual studio < 2010 workarounds configure: remove old visual studio support (<2010)
2016-06-29Update vpx subpixel 1d filter ssse3 asmLinfeng Zhang
Speed test shows the new vertical filters have degradation on Celeron Chromebook. Added "X86_SUBPIX_VFILTER_PREFER_SLOW_CELERON" to control the vertical filters activated code. Now just simply active the code without degradation on Celeron. Later there should be 2 set of vertical filters ssse3 functions, and let jump table to choose based on CPU type. Change-Id: Iba2f1f2fe059a9d142c396d03a6b8d2d3b981e87
2016-06-29Prevent negative varianceYaowu Xu
Due to rounding, hbd variance may become negative. This commit put in check and clamp of negative values to 0. Change-Id: I610d9c8aa2d4eebe7bc5f2c5624a9e3cadad4c94
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-15 19:22:13 +0000