| Commit message (Expand) | Author | Age | Files | Lines |
* | ARM: NEON optimised int32_to_float_fmul_scalar | Måns Rullgård | 2009-09-23 | 2 | -0/+31 |
* | ARM: NEON optimised scalarproduct_float | Måns Rullgård | 2009-09-22 | 2 | -0/+15 |
* | ARM: NEON optimisations for some dsputil functions | Måns Rullgård | 2009-09-22 | 2 | -0/+171 |
* | ARM: merge two loops in ff_mdct_calc_neon | Måns Rullgård | 2009-09-21 | 1 | -68/+58 |
* | ARM: interleave cos/sin tables for improved NEON MDCT | Måns Rullgård | 2009-09-21 | 2 | -37/+18 |
* | ARM: remove broken IPP support | Måns Rullgård | 2009-09-21 | 1 | -36/+1 |
* | Merge FFTContext and MDCTContext | Måns Rullgård | 2009-09-20 | 2 | -21/+19 |
* | ARM: do not use movw/movt for relocatable values with PIC | Måns Rullgård | 2009-09-16 | 1 | -1/+1 |
* | Move per-arch fft init bits into the corresponding subdirs | Måns Rullgård | 2009-09-15 | 1 | -0/+39 |
* | ARM: 10l: fix large FFTs | Måns Rullgård | 2009-09-14 | 2 | -8/+16 |
* | ARM: NEON optimised MDCT | Måns Rullgård | 2009-09-11 | 1 | -0/+160 |
* | ARM: faster NEON IMDCT | Måns Rullgård | 2009-09-11 | 1 | -29/+17 |
* | ARM: NEON optimised FFT and MDCT | Måns Rullgård | 2009-09-10 | 2 | -0/+547 |
* | Add necessary #include for config.h. | Diego Biurrun | 2009-08-24 | 1 | -0/+1 |
* | 10L: remove instruction left over from debugging | Måns Rullgård | 2009-08-14 | 1 | -1/+0 |
* | ARM: NEON optimised vorbis_inverse_coupling | Måns Rullgård | 2009-08-14 | 2 | -0/+69 |
* | ARM: cleaner selection of ELF-spefic assembler directives | Måns Rullgård | 2009-07-27 | 1 | -8/+8 |
* | Conditionally compile ELF-specific ARM assembly bits that fail on Windows CE. | Martin Storsjö | 2009-07-27 | 1 | -0/+6 |
* | cosmetics: reindent/prettyprint after last commit | Diego Biurrun | 2009-07-22 | 1 | -70/+70 |
* | Only compile in NEON optimizations for H.264 when the H.264 decoder is enabled. | Diego Biurrun | 2009-07-22 | 1 | -0/+2 |
* | Do not redundantly check for both CONFIG_THEORA_DECODER and CONFIG_VP3_DECODER. | Diego Biurrun | 2009-07-22 | 2 | -2/+2 |
* | ARM: handle VFP register arguments in ff_vector_fmul_window_neon() | Måns Rullgård | 2009-07-20 | 1 | -2/+4 |
* | ARM: check for VFP register arguments | Måns Rullgård | 2009-07-20 | 1 | -0/+9 |
* | ARM: NEON VP3 IDCT | David Conrad | 2009-07-04 | 2 | -0/+292 |
* | ARM: slightly faster NEON H264 horizontal loop filter | Måns Rullgård | 2009-06-17 | 1 | -24/+25 |
* | ARM: add some PLD in NEON IDCT | Måns Rullgård | 2009-05-28 | 1 | -2/+15 |
* | ARM: actually add VP3 loop filter | David Conrad | 2009-05-23 | 1 | -0/+94 |
* | ARM: NEON VP3 Loop Filter | David Conrad | 2009-05-23 | 1 | -0/+8 |
* | ARM: Use fewer register in NEON put_pixels _y2 and _xy2 | David Conrad | 2009-04-29 | 1 | -38/+26 |
* | ARM: NEON put_pixels_clamped | David Conrad | 2009-04-29 | 2 | -0/+26 |
* | Add guaranteed alignment for loading dest pixels in avg_pixels16_neon | David Conrad | 2009-04-16 | 1 | -4/+4 |
* | ARM: NEON optimized put_signed_pixels_clamped | David Conrad | 2009-04-04 | 2 | -0/+39 |
* | ARM: NEON optimised add_pixels_clamped | Måns Rullgård | 2009-04-04 | 2 | -0/+49 |
* | ARM: disable inline asm for armcc | Måns Rullgård | 2009-03-05 | 1 | -0/+4 |
* | ARM: fix missing MUL16() return type | Måns Rullgård | 2009-03-01 | 1 | -1/+1 |
* | ARM: fix corner-case overflow in H.264 weighted prediction | Måns Rullgård | 2009-02-28 | 1 | -38/+43 |
* | ARM: NEON optimised vector_fmul_window | Måns Rullgård | 2009-01-30 | 2 | -0/+54 |
* | ARM: NEON optimised vector_fmul | Måns Rullgård | 2009-01-30 | 2 | -0/+44 |
* | ARM: remove some unused macro arguments | Måns Rullgård | 2009-01-27 | 1 | -9/+9 |
* | ARM: reorder some instructions in put_pixels*_arm for speed gains | Måns Rullgård | 2009-01-27 | 1 | -6/+6 |
* | ARM: replace jump tables with conditional branches | Måns Rullgård | 2009-01-27 | 1 | -81/+19 |
* | ARM: replace explicit literal loads with ldr Rd, =lit | Måns Rullgård | 2009-01-27 | 1 | -34/+28 |
* | ARM: change alignment of loops in put_pixels*_arm to 32 | Måns Rullgård | 2009-01-27 | 1 | -38/+33 |
* | ARM: optimised mid_pred() | Måns Rullgård | 2009-01-27 | 1 | -0/+18 |
* | ARM: allow register operands for shifts in MULL() | Måns Rullgård | 2009-01-27 | 1 | -1/+1 |
* | ARM: NEON optimised H.264 weighted prediction | Måns Rullgård | 2009-01-25 | 2 | -0/+158 |
* | ARM: NEON optimised H.264 biweighted prediction | Måns Rullgård | 2009-01-25 | 2 | -0/+202 |
* | cosmetics: Remove pointless period after copyright statement non-sentences. | Diego Biurrun | 2009-01-19 | 2 | -2/+2 |
* | ARM: simplify ff_put/avg_h264_chroma_mc4/8_neon definitions, no code change | Måns Rullgård | 2009-01-18 | 1 | -25/+18 |
* | replace all occurrence of ENABLE_ by the corresponding CONFIG_, HAVE_ or ARCH_ | Aurelien Jacobs | 2009-01-14 | 1 | -1/+1 |