summaryrefslogtreecommitdiff
path: root/libavcodec/arm
Commit message (Collapse)AuthorAge
* motion_est: convert stride to ptrdiff_tVittorio Giovara2014-11-24
| | | | | CC: libav-stable@libav.org Bug-Id: CID 700556 / CID 700557 / CID 700558
* idctdsp: Add global function pointers for {add|put}_pixels_clamped functionsDiego Biurrun2014-09-02
| | | | | | These function pointers already existed in the ARM code. Adding them globally allows calls to the function pointers to access arch-optimized versions of the functions transparently.
* build: Add explanatory comments to (optimization) blocks in the MakefilesDiego Biurrun2014-08-15
|
* mpegvideo: cosmetics: Lowercase ugly uppercase MPV_ function name prefixesDiego Biurrun2014-08-15
|
* vc-1: Add platform-specific start code search routine to VC1DSPContext.Ben Avison2014-08-04
| | | | | | | Initialise VC1DSPContext for parser as well as for decoder. Note, the VC-1 code doesn't actually use the function pointer yet. Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
* h264: Move start code search functions into separate source files.Ben Avison2014-08-04
| | | | | | This permits re-use with parsers for codecs which use similar start codes. Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
* qpeldsp: Mark source pointer in qpel_mc_func function pointer constDiego Biurrun2014-07-25
|
* arm: Macroize the test for 'setend' CPU instruction supportBen Avison2014-07-21
| | | | Signed-off-by: Diego Biurrun <diego@biurrun.de>
* dct-test: Move arch-specific bits into arch-specific subdirectoriesDiego Biurrun2014-07-21
|
* idct: Move arm-specific declarations to a header in the arm directoryDiego Biurrun2014-07-20
|
* idctdsp: prettyprinting cosmeticsDiego Biurrun2014-07-18
|
* idct: Convert IDCT permutation #defines to an enumDiego Biurrun2014-07-18
| | | | Also rename the enum values to be consistent with other DCT permutations.
* arm: cosmetics: Consistently use lowercase for shift operatorsMartin Storsjö2014-07-18
| | | | Signed-off-by: Martin Storsjö <martin@martin.st>
* arm: cosmetics: Fix a misaligned asm operandMartin Storsjö2014-07-18
| | | | Signed-off-by: Martin Storsjö <martin@martin.st>
* armv6: Accelerate ff_fft_calc for general case (nbits != 4)Ben Avison2014-07-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | The previous implementation targeted DTS Coherent Acoustics, which only requires nbits == 4 (fft16()). This case was (and still is) linked directly rather than being indirected through ff_fft_calc_vfp(), but now the full range from radix-4 up to radix-65536 is available. This benefits other codecs such as AAC and AC3. The implementaion is based upon the C version, with each routine larger than radix-16 calling a hierarchy of smaller FFT functions, then performing a post-processing pass. This pass benefits a lot from loop unrolling to counter the long pipelines in the VFP. A relaxed calling standard also reduces the overhead of the call hierarchy, and avoiding the excessive inlining performed by GCC probably helps with I-cache utilisation too. I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder (starting from aac_decode_frame()) or specifically in the FFT routines (fft4() to fft512() and pass()) for the same sample AAC stream: Before After Mean StdDev Mean StdDev Confidence Change Audio decode 2245.5 53.1 1599.6 43.8 100.0% +40.4% FFT routines 940.6 22.0 348.1 20.8 100.0% +170.2% Signed-off-by: Martin Storsjö <martin@martin.st>
* armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6)Ben Avison2014-07-18
| | | | | | | | | | | | | | | | | | | | | | | | | | | The previous implementation targeted DTS Coherent Acoustics, which only requires mdct_bits == 6. This relatively small size lent itself to unrolling the loops a small number of times, and encoding offsets calculated at assembly time within the load/store instructions of each iteration. In the more general case (codecs such as AAC and AC3) much larger arrays are used - mdct_bits == [8, 9, 11]. The old method does not scale for these cases, so more integer registers are used with non-unrolled versions of the loops (and with some stack spillage). The postrotation filter loop is still unrolled by a factor of 2 to permit the double-buffering of some VFP registers to facilitate overlap of neighbouring iterations. I benchmarked the result by measuring the number of gperftools samples that hit anywhere in the AAC decoder (starting from aac_decode_frame()) or specifically in ff_imdct_half_c / ff_imdct_half_vfp, for the same example AAC stream: Before After Mean StdDev Mean StdDev Confidence Change aac_decode_frame 2368.1 35.8 2117.2 35.3 100.0% +11.8% ff_imdct_half_* 457.5 22.4 251.2 16.2 100.0% +82.1% Signed-off-by: Martin Storsjö <martin@martin.st>
* dsputil: Split motion estimation compare bits off into their own contextDiego Biurrun2014-07-17
|
* arm: dsputil: Coalesce all init filesDiego Biurrun2014-07-16
|
* dsputil: Drop unused bit_depth parameter from all init functionsDiego Biurrun2014-07-11
|
* dsputil: Split off pixel block routines into their own contextDiego Biurrun2014-07-09
|
* arm: Avoid using the 'setend' instruction on ARMv7 and newerMartin Storsjö2014-07-08
| | | | | | | | | | This instruction is deprecated on ARMv8, and it is serializing on some ARMv7 cores as well [1]. [1] http://article.gmane.org/gmane.linux.ports.arm.kernel/339293 CC: libav-stable@libav.org Signed-off-by: Martin Storsjö <martin@martin.st>
* dsputil: Move pix_sum, pix_norm1, shrink function pointers to mpegvideoencDiego Biurrun2014-07-06
|
* dsputil: Split off IDCT bits into their own contextDiego Biurrun2014-06-30
|
* h264: avoid using uninitialized memory in NEON chroma mcJanne Grunau2014-06-23
| | | | | Adapt commit 982b596ea6640bfe218a31f6c3fc542d9fe61c31 for the arm and aarch64 NEON asm. 5-10% faster on Cortex-A9.
* dsputil: Split audio operations off into a separate contextDiego Biurrun2014-06-22
|
* dsputil: Split clear_block*/fill_block* off into a separate contextDiego Biurrun2014-06-18
|
* arm: check if AS supports .dnJanne Grunau2014-06-03
| | | | | | | | | | | | Move the GNU as check before the arch specific asm checks since the .dn check requires gas compatible assembler. Disable the VC-1 motion compensation NEON asm which is the only part using that directive. The integrated assembler in the upcoming clang 3.5 does not support .dn/.qn without plans to change that. Too much effort to implement it while it is rarely used. http://llvm.org/bugs/show_bug.cgi?id=18199.
* dsputil: Move APE-specific bits into apedspDiego Biurrun2014-05-29
|
* mpegvideo: move the MpegEncContext fields used from arm asm to the beginningAnton Khirnov2014-04-29
| | | | | This should reduce the frequency with which the offsets need to be updated.
* lavu: add CHK_OFFS as AV_CHECK_OFFSET to check struct member offsetsJanne Grunau2014-04-24
|
* Remove a number of unnecessary dsputil.h #includesDiego Biurrun2014-04-04
|
* arm: asm decode_block_coeffs_internal is vp8 specificJanne Grunau2014-04-04
| | | | | Unbreaks compilation on arm due to conflicting types for 'ff_decode_block_coeffs_armv6'.
* On2 VP7 decoderPeter Ross2014-04-04
| | | | | | | | | Further performance improvements and security fixes by Vittorio Giovara, Luca Barbato and Diego Biurrun. Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com> Signed-off-by: Luca Barbato <lu_zero@gentoo.org> Signed-off-by: Diego Biurrun <diego@biurrun.de>
* arm: build: Maintain decoder objects separate from infrastructure objectsDiego Biurrun2014-03-27
|
* truehd: add hand-scheduled ARM asm version of ff_mlp_pack_output.Ben Avison2014-03-26
| | | | | | | | | | | | | | | | | | | | | | Profiling results for overall decode and the output_data function in particular are as follows: Before After Mean StdDev Mean StdDev Confidence Change 6:2 total 339.6 15.1 329.3 16.0 95.8% +3.1% (insignificant) 6:2 function 24.6 6.0 9.9 3.1 100.0% +148.5% 8:2 total 324.5 15.5 323.6 14.3 15.2% +0.3% (insignificant) 8:2 function 20.4 3.9 9.9 3.4 100.0% +104.7% 6:6 total 572.8 20.6 539.9 24.2 100.0% +6.1% 6:6 function 54.5 5.6 16.0 3.8 100.0% +240.9% 8:8 total 741.5 21.2 702.5 18.5 100.0% +5.6% 8:8 function 63.9 7.6 18.4 4.8 100.0% +247.3% The assembly version has also been tested with a fuzz tester to ensure that any combinations of inputs not exercised by my available test streams still generate mathematically identical results to the C version. Signed-off-by: Martin Storsjö <martin@martin.st>
* truehd: add hand-scheduled ARM asm version of ff_mlp_rematrix_channel.Ben Avison2014-03-26
| | | | | | | | | | | | | | | | | | | | | | Profiling results for overall audio decode and the rematrix_channels function in particular are as follows: Before After Mean StdDev Mean StdDev Confidence Change 6:2 total 370.8 17.0 348.8 20.1 99.9% +6.3% 6:2 function 46.4 8.4 45.8 6.6 18.0% +1.2% (insignificant) 8:2 total 343.2 19.0 339.1 15.4 54.7% +1.2% (insignificant) 8:2 function 38.9 3.9 40.2 6.9 52.4% -3.2% (insignificant) 6:6 total 658.4 15.7 604.6 20.8 100.0% +8.9% 6:6 function 109.0 8.7 59.5 5.4 100.0% +83.3% 8:8 total 896.2 24.5 766.4 17.6 100.0% +16.9% 8:8 function 223.4 12.8 93.8 5.0 100.0% +138.3% The assembly version has also been tested with a fuzz tester to ensure that any combinations of inputs not exercised by my available test streams still generate mathematically identical results to the C version. Signed-off-by: Martin Storsjö <martin@martin.st>
* truehd: add hand-scheduled ARM asm version of mlp_filter_channel.Ben Avison2014-03-26
| | | | | | | | | | | | | | | | | | | | | | | | | Profiling results for overall audio decode and the mlp_filter_channel(_arm) function in particular are as follows: Before After Mean StdDev Mean StdDev Confidence Change 6:2 total 380.4 22.0 370.8 17.0 87.4% +2.6% (insignificant) 6:2 function 60.7 7.2 36.6 8.1 100.0% +65.8% 8:2 total 357.0 17.5 343.2 19.0 97.8% +4.0% (insignificant) 8:2 function 60.3 8.8 37.3 3.8 100.0% +61.8% 6:6 total 717.2 23.2 658.4 15.7 100.0% +8.9% 6:6 function 140.4 12.9 81.5 9.2 100.0% +72.4% 8:8 total 981.9 16.2 896.2 24.5 100.0% +9.6% 8:8 function 193.4 15.0 103.3 11.5 100.0% +87.2% Experiments with adding preload instructions to this function yielded no useful benefit, so these have not been included. The assembly version has also been tested with a fuzz tester to ensure that any combinations of inputs not exercised by my available test streams still generate mathematically identical results to the C version. Signed-off-by: Martin Storsjö <martin@martin.st>
* dsputil: Refactor duplicated CALL_2X_PIXELS / PIXELS16 macrosDiego Biurrun2014-03-22
|
* dsputil: Use correct type in me_cmp_func function pointerDiego Biurrun2014-03-20
|
* build: Group general components separate from de/encoders in arch MakefilesDiego Biurrun2014-03-20
| | | | This is in line with how the top-level libavcodec Makefile is structured.
* dsputil: Propagate bit depth information to all (sub)init functionsDiego Biurrun2014-03-20
| | | | This avoids recalculating the value over and over again.
* arm: dsputil: K&R formatting cosmeticsDiego Biurrun2014-03-20
|
* arm: dsputil: Drop restrict keyword from add_pixels_clamped_armv6 prototypeDiego Biurrun2014-03-14
| | | | | | | | The function is assigned to a function pointer that does not have the restrict keyword for that parameter. This fixes compilation for MSVC builds that don't recognize "restrict", broken since ed9625eb62.
* Update dsputil- and SIMD-related comments to match reality more closelyDiego Biurrun2014-03-13
|
* arm: dsputil: Add a bunch of missing #includesDiego Biurrun2014-03-13
|
* dsputil: Remove prototypes for nonexisting optimization functionsDiego Biurrun2014-03-13
|
* armv6: vp8: use explicit labels in motion compensation asmJanne Grunau2014-03-12
| | | | | The integrated arm assembler in clang-503.0.38 (Xcode-5.1) fails to assemble a branch to 'label + offset' in thumb mode.
* arm: get_cabac inline asmJanne Grunau2014-03-09
| | | | | | | | | | Based on the aarch64 asm. CPU cycle counts on cortex-a9 compared to gcc 4.8.2: before: 475 decicycles in get_cabac_noinline, 67106035 runs, 2829 skips after: 393 decicycles in get_cabac_noinline, 67106474 runs, 2390 skips Overall speedup is above 2%. Code generated by clang 3.4 is slower on the same hardware and the relative change is a little larger.
* arm: vp3: remove incorrect const in ff_vp3_idct_dc_add_neon declarationJanne Grunau2014-03-09
| | | | | Was missed in aeaf268e52fc11c1f64914a319e0edddf1346d6a when integrating clear_blocks into the idct.
* arm: hpeldsp: fix put_pixels8_y2_{,no_rnd_}armv6Janne Grunau2014-03-08
| | | | | | | | The overread avoidance fix in cbddee1cca0ebd01e8c5aa694d31228eb4de4b41 broke the computation for the last row since it prevented the safe reading from the height+1-th row. CC: libav-stable@libav.org
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-26 04:17:29 +0000