| Commit message (Expand) | Author | Age | Files | Lines |
* | diracdsp_mmx: Fix some more indentations | Timothy Gu | 2016-02-01 | 1 | -6/+6 |
* | diracdsp_mmx: Fix indentation | Timothy Gu | 2016-02-01 | 1 | -8/+8 |
* | x86: vc1dsp: Convert vc1_inv_trans_*_dc to NASM format | Timothy Gu | 2016-02-01 | 3 | -207/+111 |
* | all: Make header guard names consistent | Timothy Gu | 2016-01-31 | 1 | -2/+2 |
* | avcodec/dca: add new decoder based on libdcadec | foo86 | 2016-01-31 | 1 | -2/+2 |
* | avcodec/dca: remove old decoder | foo86 | 2016-01-31 | 3 | -169/+2 |
* | x86/imdct36: use extractps inside the STORE macro | James Almer | 2016-01-28 | 1 | -0/+7 |
* | Merge commit '4f22b138886e29f7fffa8c715673951e51be9f32' | Derek Buitenhuis | 2016-01-27 | 1 | -1/+0 |
|\ |
|
| * | x86: ac3dsp: Drop forward declaration for nonexisting function | Diego Biurrun | 2016-01-18 | 1 | -1/+0 |
* | | avcodec/synth_filter: split off remaining code from dcadec files | James Almer | 2016-01-25 | 5 | -275/+324 |
* | | x86inc: Add debug symbols indicating sizes of compiled functions | Geza Lore | 2016-01-21 | 2 | -2/+2 |
* | | videodsp: fix 1-byte overread in top/bottom READ_NUM_BYTES iterations. | Ronald S. Bultje | 2016-01-18 | 1 | -15/+6 |
* | | avcodec/v210: guard new avx2 functions from old assemblers | James Darnley | 2016-01-17 | 1 | -0/+6 |
* | | avcodec/v210: add avx2 version of the 10-bit line encoder | James Darnley | 2016-01-17 | 4 | -7/+22 |
* | | avcodec/v210: add avx2 version of the 8-bit line encoder | James Darnley | 2016-01-17 | 4 | -19/+41 |
* | | avcodec/x86/fmtconvert: Add emms to int32_to_float_fmul_array8_sse() | Michael Niedermayer | 2016-01-15 | 1 | -1/+8 |
* | | Merge commit '8563f9887194b07c972c3475d6b51592d77f73f7' | Hendrik Leppkes | 2016-01-02 | 1 | -1/+8 |
|\| |
|
| * | x86: use emms after ff_int32_to_float_fmul_scalar_sse | Janne Grunau | 2015-12-30 | 1 | -1/+8 |
* | | Merge commit 'f4f27e4cf1013c55b2c7df359ce8d58ee922662c' | Hendrik Leppkes | 2016-01-02 | 1 | -4/+1 |
|\| |
|
| * | x86: zero extend the 32-bit length in int32_to_float_fmul_scalar implicitly | Janne Grunau | 2015-12-29 | 1 | -4/+1 |
* | | Merge commit '2008f76054906e9ff6bf744800af0e5a5bfe61be' | Hendrik Leppkes | 2016-01-02 | 2 | -106/+0 |
|\| |
|
| * | dca: remove unused decode_hf function and quant_d tables | Alexandra Hájková | 2015-12-24 | 2 | -106/+0 |
* | | Merge commit '5dfe4edad63971d669ae456b0bc40ef9364cca80' | Hendrik Leppkes | 2016-01-02 | 1 | -0/+3 |
|\| |
|
| * | x86_64: int32_to_float_fmul_scalar sign extend integer length | Janne Grunau | 2015-12-14 | 1 | -0/+3 |
| * | hevcdsp: use a macro for .rodata section | Dave Yeo | 2015-12-11 | 1 | -1/+1 |
| * | hevcdsp: add x86 SIMD for MC | Anton Khirnov | 2015-12-05 | 3 | -5/+1090 |
* | | x86/hevc_sao: add ff_hevc_sao_edge_filter_{8,16}_{10,12} | James Almer | 2015-12-20 | 2 | -7/+10 |
* | | x86/hevc_sao: simplify sao_edge_filter 10/12bit | James Almer | 2015-12-20 | 1 | -96/+54 |
* | | x86/hevc_sao: simplify sao_band_filter 10/12bit | James Almer | 2015-12-20 | 1 | -85/+57 |
* | | diracdec: Template DSP functions adding 10-bit versions | Kieran Kunhya | 2015-12-10 | 3 | -23/+50 |
* | | pixblockdsp: x86: Condense diff_pixels_* to a shared macro | Timothy Gu | 2015-11-07 | 1 | -34/+30 |
* | | all: fix -Wextra-semi reported on clang | Ganesh Ajjanagadde | 2015-10-24 | 5 | -350/+345 |
* | | videodsp: don't overread edges in vfix3 emu_edge. | Ronald S. Bultje | 2015-10-24 | 1 | -4/+11 |
* | | avcodec/x86/vc1dsp: Remove unused macro | Michael Niedermayer | 2015-10-22 | 1 | -7/+0 |
* | | lavc/x86/vc1dsp_init: Fix compilation with --disable-yasm. | Carl Eugen Hoyos | 2015-10-22 | 1 | -2/+2 |
* | | x86/Makefile: move decoder/encoder objects out of the subsystems section | James Almer | 2015-10-22 | 1 | -9/+8 |
* | | vc1dsp: Port ff_vc1_put_ver_16b_shift2_mmx to yasm | Timothy Gu | 2015-10-21 | 2 | -53/+95 |
* | | huffyuvencdsp: Cherry pick changes left out in the last commit | Timothy Gu | 2015-10-21 | 1 | -3/+3 |
* | | huffyuvencdsp: Add ff_diff_bytes_{sse2,avx2} | Timothy Gu | 2015-10-21 | 2 | -19/+105 |
* | | huffyuvencdsp: Convert ff_diff_bytes_mmx to yasm | Timothy Gu | 2015-10-20 | 3 | -30/+81 |
* | | huffyuvencdsp: Use intptr_t for width | Timothy Gu | 2015-10-19 | 1 | -2/+3 |
* | | x86: vc1dsp_mmx: Move yasm initiation steps to vc1dsp_init | Timothy Gu | 2015-10-19 | 2 | -38/+25 |
* | | x86: fpel: Remove erroneous ff_put_pixels8_mmxext prototype | Timothy Gu | 2015-10-19 | 1 | -2/+0 |
* | | x86: fpel: Move prototypes for 4-px block functions | Timothy Gu | 2015-10-19 | 2 | -4/+6 |
* | | x86/vp9itxfm: fix register clobbering in ff_vp9_idct_idct_4x4_add_12_sse2 | James Almer | 2015-10-13 | 1 | -1/+1 |
* | | x86: simple_idct10_template: use const | Christophe Gisquet | 2015-10-13 | 5 | -57/+39 |
* | | vp9: use registers for constant loading where possible. | Ronald S. Bultje | 2015-10-13 | 1 | -122/+146 |
* | | vp9: refactor itx coefficients and share between 8 and 10/12bpp. | Ronald S. Bultje | 2015-10-13 | 2 | -88/+91 |
* | | vp9: add itxfm_add eob shortcuts to 10/12bpp functions. | Ronald S. Bultje | 2015-10-13 | 1 | -33/+200 |
* | | vp9: add 10/12bpp idct_idct_32x32 sse2 SIMD version. | Ronald S. Bultje | 2015-10-13 | 2 | -44/+488 |