- 86c6c49 Sk4f: add floor() by mtklein · 9 years ago
- e4c0bee sknx refactoring by mtklein · 9 years ago
- 81bb79b Remove SkNx AVX code. It is not really used. Getting in the way of refactoring. by mtklein · 9 years ago
- 507ef6d SkNx Load/store: take any pointer. by mtklein · 9 years ago
- c33065a add SkNx::abs(), for now only implemented for Sk4f by mtklein · 9 years ago
- fce612a Specialize Sk2d for SSE2 by mtklein · 9 years ago
- 6f37b4a Unify some SkNx code by mtklein · 9 years ago
- 9db43ac Add Sk4f::ToBytes(uint8_t[16], Sk4f, Sk4f, Sk4f, Sk4f) by mtklein · 9 years ago
- 6c221b4 Add SkNx_cast(). by mtklein · 9 years ago
- 084db25 float xfermodes (burn, dodge, softlight) in Sk8f, possibly using AVX. by mtklein · 9 years ago
- 6f79709 prune unused SkNx features by mtklein · 9 years ago
- a1c0ee4 SkNx_shuffle by mtklein · 9 years ago
- a508f3c Require Sk4f::toBytes() clamps by mtklein · 9 years ago
- aba1dc8 Move float<->byte conversions into Sk4f. by mtklein · 9 years ago
- 082e329 Revert of Refactor to put SkXfermode_opts inside SK_OPTS_NS. (patchset #1 id:1 of https://codereview.chromium.org/1286093004/ ) by mtklein · 9 years ago
- b07bee3 Refactor to put SkXfermode_opts inside SK_OPTS_NS. by mtklein · 9 years ago
- bfd9ee6 Fix typo in non-SIMD Sk4f::thenElse(). by mtklein · 9 years ago
- b5e8611 Implement four more xfermodes with Sk4px. by mtklein · 9 years ago
- 0cc1f0a Revert of Implement four more xfermodes with Sk4px. (patchset #16 id:290001 of https://codereview.chromium.org/1196713004/) by mtklein · 9 years ago
- b9d4163 Implement four more xfermodes with Sk4px. by mtklein · 9 years ago
- 3747875 Thorough tests for saturatedAdd and mulDiv255Round. by mtklein · 9 years ago
- f2fe0e0 Remove overly-promiscuous SkNx syntax sugar. by mtklein · 9 years ago
- aa999cb Everyone gets a namespace {}. by mtklein · 9 years ago
- 27e517a add Min to SkNi, specialized for u8 and u16 on SSE and NEON by mtklein · 9 years ago
- 6cbf18c Plus xfermode using Sk4px. by mtklein · 9 years ago
- d2ffd36 Sk4px by mtklein · 9 years ago
- d7c014f Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM by mtklein · 9 years ago
- 9a22f48 Revert of Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM (patchset #2 id:20001 of https://codereview.chromium.org/1109913002/) by mtklein · 9 years ago
- 9de1628 Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM by mtklein · 9 years ago
- 1113da7 Mike's radial gradient CL with better float -> int. by mtklein · 9 years ago
- 8d3e9df Revert of Mike's radial gradient CL with better float -> int. (patchset #7 id:120001 of https://codereview.chromium.org/1109643002/) by mtklein · 9 years ago
- abf6c5c Mike's radial gradient CL with better float -> int. by mtklein · 9 years ago
- 115acee Sk4h and Sk8h for SSE by mtklein · 9 years ago
- 8fe8fff Rename SkNi to SkNb. by mtklein · 9 years ago
- a156a8f Use switch operator[](int) to kth<int>() so we can use vget_lane. #floats by mtklein · 9 years ago
- c9adb05 Refactor Sk2x<T> + Sk4x<T> into SkNf<N,T> and SkNi<N,T> by mtklein · 9 years ago
- 3e490b7 Guard SIMD code with !defined(SKNX_NO_SIMD). by mtklein · 9 years ago