Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Combine ffts_tranpose_scalar and ffts_transpose, and use ↵ | Jukka Ojanen | 2016-04-05 | 1 | -111/+1 |
| | | | | ffts_transpose_scalar as native C fallback | ||||
* | Fix ffts_init_nd() for 3 or higher rank complex FFTs | Jukka Ojanen | 2016-04-05 | 1 | -25/+30 |
| | |||||
* | Fix neon_transpose8 for non-square matrices, move loops to assembly side, ↵ | Jukka Ojanen | 2016-03-29 | 1 | -7/+1 |
| | | | | about 5% faster | ||||
* | Rename neon_transpose to neon_transpose4, 4x4 tiled matrix transpose. | Jukka Ojanen | 2016-03-28 | 1 | -2/+2 |
| | | | | Rename neon_transpose_to_buf to neon_transpose8, 8x8 tiled matrix transpose. | ||||
* | "transpose_buf" is not used | Jukka Ojanen | 2016-03-28 | 1 | -14/+9 |
| | |||||
* | Improve performance of small complex 2D Neon transform by 15% | Jukka Ojanen | 2016-03-28 | 1 | -63/+6 |
| | |||||
* | Enable building shared library and start version numbering from 0.9.0. On ↵ | Jukka Ojanen | 2015-11-30 | 1 | -2/+4 |
| | | | | Windows when using FFTS as a DLL, define FFTS_SHARED. This is not mandatory, but it offers a little performance increase. Hide symbols when possible to improve compiler optimization and sizeof binary. Use CMake target alias "ffts" to choose between static and shared library, preferring static | ||||
* | ffts_nd.c is using SSE2 intrinsics, detect and include emmintrin.h instead ↵ | Jukka Ojanen | 2015-03-19 | 1 | -2/+2 |
| | | | | xmmintrin.h, and fix GCC error: inlining failed in call to always_inline '_mm_load_pd': target specific option mismatch by adding "-msse2" instead of "-msse" | ||||
* | Improve header logic | Jukka Ojanen | 2015-03-10 | 1 | -3/+1 |
| | |||||
* | Fix warning "comparison between signed and unsigned integer expressions" | Jukka Ojanen | 2014-12-09 | 1 | -3/+4 |
| | |||||
* | Fix redefinition of ffts_plan_t | Jukka Ojanen | 2014-11-17 | 1 | -1/+1 |
| | |||||
* | Add forgotten "ffts.h" header | Jukka Ojanen | 2014-11-16 | 1 | -0/+1 |
| | |||||
* | Cleaning and reorganizing | Jukka Ojanen | 2014-10-29 | 1 | -250/+331 |
| | |||||
* | Adding in Vim modelines to all .c and .h files. | Robert Massaioli | 2013-12-05 | 1 | -0/+1 |
| | |||||
* | Fixed transpose -- thanks to Sowon Kim <mogyak@gmail.com> | Anthony Blake | 2013-07-16 | 1 | -1/+1 |
| | |||||
* | Fixed up the smaller VFP transforms. Inverse VFP and real/nd VFP still not ↵ | Anthony Blake | 2013-04-22 | 1 | -2/+4 |
| | | | | working yet. | ||||
* | Changes to ND code | Anthony Blake | 2013-01-25 | 1 | -36/+69 |
| | |||||
* | misc | Anthony Blake | 2012-12-13 | 1 | -1/+37 |
| | |||||
* | Slight speed improvement for ARM ND | Anthony Blake | 2012-12-12 | 1 | -2/+2 |
| | |||||
* | Fixed ND segfault | Anthony Blake | 2012-12-12 | 1 | -4/+4 |
| | |||||
* | 2D real-valued transforms work | Anthony Blake | 2012-11-15 | 1 | -7/+7 |
| | |||||
* | Fixed some compiler warnings, generalized transform interface (in prep for ↵ | Anthony Blake | 2012-11-15 | 1 | -1/+1 |
| | | | | double etc) | ||||
* | Uses slightly faster call to internal transforms | Anthony Blake | 2012-11-14 | 1 | -2/+2 |
| | |||||
* | Multi-dimensional saves some planning | Anthony Blake | 2012-11-14 | 1 | -2/+17 |
| | |||||
* | Slightly better transpose for NEON | Anthony Blake | 2012-11-08 | 1 | -34/+87 |
| | |||||
* | Build warnings | Anthony Blake | 2012-11-07 | 1 | -4/+4 |
| | |||||
* | Fixed compile warnings | Anthony Blake | 2012-11-07 | 1 | -1/+1 |
| | |||||
* | 2D has SIMD transpose (still needs work though) | Anthony Blake | 2012-11-06 | 1 | -4/+32 |
| | |||||
* | Multi-dimensional works (slow transpose tho) | Anthony Blake | 2012-11-02 | 1 | -42/+15 |
| | |||||
* | 2D transforms work | Anthony Blake | 2012-10-31 | 1 | -19/+23 |
| | |||||
* | Square 2D works | Anthony Blake | 2012-10-31 | 1 | -4/+76 |
| | |||||
* | Initial multi-dimensional structure | Anthony Blake | 2012-10-31 | 1 | -0/+66 |