aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/arm
Commit message (Expand)AuthorAgeFilesLines
* sbcenc: add armv6 and neon asm optimizationsAurelien Jacobs2018-03-074-0/+1067
* avcodec/arm/sbrdsp_neon: Use a free register instead of putting 2 things in oneMichael Niedermayer2018-01-121-2/+2
* arm/hevc_idct: fix compilation on AndroidJames Almer2017-12-091-59/+60
* Merge commit 'b487add7ecf78efda36d49815f8f8757bd24d4cb'James Almer2017-11-111-4/+2
|\
| * arm: Remove a redundant check in fmtconvert_init_arm.cMartin Storsjö2017-10-241-4/+2
* | Merge commit '9dde6ab06c48f9447cd16f39bee33569cddb7be4'James Almer2017-11-111-8/+12
|\|
| * arm: Fix SIGBUS on ARM when compiled with binutils 2.29Martin Storsjö2017-09-021-8/+12
* | Merge commit 'd7320ca3ed10f0d35b3740fa03341161e74275ea'James Almer2017-10-302-20/+5
|\|
| * arm: Avoid using .dn register aliasesMartin Storsjö2017-05-152-20/+5
* | Merge commit 'ce080f47b8b55ab3d41eb00487b138d9906d114d'James Almer2017-10-302-21/+294
|\|
| * hevc: Add NEON 32x32 IDCTAlexandra Hájková2017-05-042-21/+294
* | Merge commit '118dd4a321a2d67f67c21b076abd0b4d939ab642'James Almer2017-10-301-8/+8
|\|
| * hevc: 16x16 NEON idct: Use the right element size for loads/storesAlexandra Hájková2017-05-041-8/+8
* | Merge commit 'edbf0fffb15dde7a1de70b05855529d5fc769f14'James Almer2017-10-302-0/+102
|\|
| * hevc: Add NEON add_residual for bitdepth 10Alexandra Hájková2017-05-012-0/+102
* | Merge commit 'e1c2453a4fac1f7116244d0d05310935c20887e6'James Almer2017-10-301-16/+35
|\|
| * arm: hevc_idct: Tune the add_res_8x8 and add_res_32x32 functionsMartin Storsjö2017-04-281-16/+35
* | Merge commit '0d4d43513786f1df4d561e1fac924fb0722c6700'James Almer2017-10-302-75/+92
|\|
| * hevc: Add NEON add_residual for bitdepth 8Seppo Tomperi2017-04-272-0/+103
* | Merge commit '3d69dd65c6771c28d3bf4e8e53a905aa8cd01fd9'James Almer2017-10-302-12/+37
|\|
| * hevc: Add support for bitdepth 10 for IDCT DCAlexandra Hájková2017-04-252-12/+37
* | Merge commit '358adef0305618219522858e471edf7e0cb4043e'James Almer2017-10-302-84/+84
|\|
| * hevc: Add NEON IDCT DC functions for bitdepth 8Seppo Tomperi2017-04-252-0/+88
* | Merge commit '89d9869d2491d4209d707a8e7f29c58227ae5a4e'James Almer2017-10-272-0/+201
|\|
| * hevc: Add NEON 16x16 IDCTAlexandra Hájková2017-04-122-0/+201
| * arm: Always build the hevcdsp_init_arm.c fileMartin Storsjö2017-03-281-2/+2
* | Merge commit '0b9a237b2386ff84a6f99716bd58fa27a1b767e7'James Almer2017-10-244-238/+217
|\|
| * hevc: Add NEON 4x4 and 8x8 IDCTAlexandra Hájková2017-03-273-0/+277
| * arm/aarch64: vp9: Fix vertical alignmentMartin Storsjö2017-03-162-8/+8
| * arm/aarch64: vp9itxfm: Skip loading the min_eob pointer when it won't be usedMartin Storsjö2017-03-111-2/+2
| * arm: vp9itxfm: Template the quarter/half idct32 functionMartin Storsjö2017-03-111-37/+20
| * arm: vp9itxfm: Reorder iadst16 coeffsMartin Storsjö2017-02-241-6/+6
| * arm: vp9itxfm: Reorder the idct coefficients for better pairingMartin Storsjö2017-02-241-62/+62
| * arm: vp9itxfm: Avoid reloading the idct32 coefficientsMartin Storsjö2017-02-241-126/+120
| * arm: vp9lpf: Implement the mix2_44 function with one single filter passMartin Storsjö2017-02-242-3/+195
| * arm/aarch64: vp9lpf: Keep the comparison to E within 8 bitMartin Storsjö2017-02-241-6/+5
| * arm: vp9lpf: Interleave the start of flat8in into the calculation aboveMartin Storsjö2017-02-111-2/+6
| * arm: vp9lpf: Use orrs instead of orr+cmpMartin Storsjö2017-02-111-8/+4
| * arm/aarch64: vp9lpf: Calculate !hev directlyMartin Storsjö2017-02-111-3/+2
| * arm: vp9itxfm: Optimize 16x16 and 32x32 idct dc by unrollingMartin Storsjö2017-02-111-18/+36
| * arm: vp9mc: Calculate less unused data in the 4 pixel wide horizontal filterMartin Storsjö2017-02-111-11/+22
| * arm: vp9itxfm: Share instructions for loading idct coeffs in the 8x8 functionMartin Storsjö2017-02-091-2/+1
| * arm: vp9itxfm: Do a simpler half/quarter idct16/idct32 when possibleMartin Storsjö2017-02-091-54/+537
| * arm: vp9itxfm: Move the load_add_store macro out from the itxfm16 pass2 functionMartin Storsjö2017-02-091-36/+36
| * arm: vp9itxfm: Make the larger core transforms standalone functionsMartin Storsjö2017-02-091-17/+26
| * arm: vp9itxfm: Avoid .irp when it doesn't save any linesMartin Storsjö2017-02-051-12/+12
| * arm: vp9mc: Fix vertical alignment of operandsMartin Storsjö2017-01-031-3/+3
| * arm: vp9itxfm: Skip empty slices in the first pass of idct_idct 16x16 and 32x32Martin Storsjö2016-11-301-9/+66
| * arm: vp9itxfm: Only reload the idct coeffs for the iadst_idct combinationMartin Storsjö2016-11-301-1/+1
| * arm: vp9itxfm: Rename a macro parameter to fit betterMartin Storsjö2016-11-231-7/+7