5391 Commits (e5f640182c692cf7030669c3fe65fcdad5782a1b)

Author SHA1 Message Date
Stefan Nikolei e5f640182c use CI environment variable to also build on .net5.0 5 years ago
Stefan Nikolei 58491c9c12 remove .net50 target framework 5 years ago
Stefan Nikolei 862c939a3a Add net5.0 target 5 years ago
Nicolas Portmann 81c728e05b Vectorize Scale16X16To8X8 5 years ago
Sergio Pedri ed4cfaa0ae Workaround for incorrect codegen on .NET 5 5 years ago
Sergio Pedri e68a21de52 Add missing indexing update 5 years ago
Sergio Pedri e0b2defde2 Add unrolled FMA loop 5 years ago
Sergio Pedri 0e465cd8c3 Revert to FMA, codegen improvements 5 years ago
Sergio Pedri 1169e73915 Switch from FMA to AVX2 instructions 5 years ago
Sergio Pedri c825eccd10 Improved loading of factors using permutation 5 years ago
Sergio Pedri 1033297a37 Add initial FMA resize kernel convolve implementation 5 years ago
Nicolas Portmann 5033e3eb95 Improve algorithm 5 years ago
Nicolas Portmann 93099d1585 Add unit tests for both converters 5 years ago
Nicolas Portmann 429696bd5e Fix mistakes in final touches 5 years ago
Nicolas Portmann efd4d22665 Add initial vectorized implementation with benchmarks 5 years ago
Brian Popow a968b289a0 Use this.maxColors when getting size of the reduced palette, fixes #1505 5 years ago
Petar Tasev 62a01b7475 Split PixelConversionModifiers into a separate function. 5 years ago
Petar Tasev 0df047222b Add PremultiplyAlpha to ResizeOptions 5 years ago
James Jackson-South 3cbd8e393d Use explicit threadsafety declaration. 5 years ago
James Jackson-South bf9f25a142 Use properties for true Lazy. 5 years ago
James Jackson-South 016de29898 Fix alpha companding. 5 years ago
James Jackson-South 1ea6a00338 intitial implementation 5 years ago
James Jackson-South 89007db1a6 Minor style cleanup. 5 years ago
Sergio Pedri 14d2af4bdd Codegen improvements to Numerics.Clamp 5 years ago
Sergio Pedri aab2837d28 More codegen improvements to shared methods 5 years ago
Sergio Pedri a5bbe95e95 More codegen improvements to bokeh blur 5 years ago
Sergio Pedri ff86b651d2 More performance improvements to 2 pass convolution 5 years ago
Sergio Pedri f88fca750c Minor code tweaks 5 years ago
Sergio Pedri 4609fa0b40 Remove leftover ConvolutionRowOperation<TPixel> type 5 years ago
Sergio Pedri e8bf265468 Remove transposed 1D kernels, switch to float[] type 5 years ago
Sergio Pedri 9c2ce4105e Remove convolution state, more optimizations 5 years ago
Sergio Pedri 82d0ba44cf Switch to shared sampling map for convolution passes 5 years ago
Sergio Pedri 9959ba0d0b Remove unnecessary inner loop coordinate sampling 5 years ago
Sergio Pedri d41cf15023 Port vertical convolution processor, remove X loop 5 years ago
Sergio Pedri b62d3ec863 Port horizontal convolution processor, remove Y loop 5 years ago
Sergio Pedri 80617a060c Add more codegen improvements 5 years ago
Sergio Pedri e7cdb0aaab Add FMA support, more SSE optimizations 5 years ago
Sergio Pedri df18c4e4c8 Switch to explicit SSE Newton approximations 5 years ago
Sergio Pedri 4aa8bc6e57 Improve formatting for XML docs 5 years ago
Sergio Pedri 76e704d461 Minor codegen tweaks 5 years ago
Sergio Pedri 392afeadef Fix vectorized cube root on x86-64 with no SSE41 5 years ago
Sergio Pedri 3bba7deda1 Initial vectorized cube root implementation 5 years ago
Sergio Pedri 0903a58e58 Switch to vectorized clamping 5 years ago
Sergio Pedri 8292407ae2 Add optimized paths for default gamma exposure 5 years ago
Sergio Pedri 3356225bb1 Remove unnecessary offset indirections 5 years ago
Sergio Pedri 0a6f7baa71 Fix NullReferenceException in KernelSamplingMap.Dispose 5 years ago
Sergio Pedri 6187fb55e0 Fix blur processing when constrained to region 5 years ago
Sergio Pedri 16f4842f64 Fix gamma processing out of image bounds 5 years ago
Sergio Pedri f8f3eaa321 Remove unnecessary code 5 years ago
Sergio Pedri 68eeca9282 Restore temporary changes 5 years ago