Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Merge upstream. | Till Hoffmann | 2016-04-01 |
|\ | |||
* | | Fixed suggestions by Eugene Brevdo. | Till Hoffmann | 2016-04-01 |
| | | |||
| * | Merged eigen/eigen into default | tillahoffmann | 2016-04-01 |
|/| | |||
* | | Added polygamma function. | Till Hoffmann | 2016-04-01 |
| | | |||
* | | Added zeta function. | Till Hoffmann | 2016-04-01 |
| | | |||
| * | Hashing was only officially introduced in c++11. Therefore only define an ↵ | Benoit Steiner | 2016-03-31 |
| | | | | | | | | implementation of the hash function for float16 if c++11 is enabled. | ||
| * | Improved code formating | Benoit Steiner | 2016-03-31 |
| | | |||
| * | Added the ability to hash a fp16 | Benoit Steiner | 2016-03-31 |
| | | |||
| * | Made it possible to use the NumTraits for complex and Array in a cuda kernel. | Benoit Steiner | 2016-03-31 |
| | | |||
| * | Added __ldg primitive for fp16. | Benoit Steiner | 2016-03-31 |
| | | |||
| * | Added NumTraits for half floats | Benoit Steiner | 2016-03-31 |
| | | |||
| * | Fixed a typo | Benoit Steiner | 2016-03-31 |
|/ | |||
* | Pull math functions from the global namespace only when compiling cuda code ↵ | Benoit Steiner | 2016-03-30 |
| | | | | with nvcc. When compiling with clang, we want to use the std namespace. | ||
* | Enable constant expressions when compiling cuda code with clang. | Benoit Steiner | 2016-03-30 |
| | |||
* | bug #1186 - vreinterpretq_u64_f64 fails to build on Android/Aarch64/Clang ↵ | Benoit Jacob | 2016-03-30 |
| | | | | toolchain | ||
* | Added missing cuda template specializations for numext::ceil | Benoit Steiner | 2016-03-29 |
| | |||
* | Added support for standard mathematical functions and trancendentals(such ↵ | Benoit Steiner | 2016-03-29 |
| | | | | as exp, log, abs, ...) on fp16 | ||
* | Added support for fmod | Benoit Steiner | 2016-03-28 |
| | |||
* | Improved the cost estimate of the quotient op | Benoit Steiner | 2016-03-25 |
| | |||
* | Started to model the cost of divisions more accurately. | Benoit Steiner | 2016-03-25 |
| | |||
* | Use numext::abs instead of abs to avoid incorrect conversion to integer of ↵ | Benoit Steiner | 2016-03-23 |
| | | | | the argument | ||
* | Removed executable bit from header files | Benoit Steiner | 2016-03-23 |
| | |||
* | Removed executable bit from header files | Benoit Steiner | 2016-03-23 |
| | |||
* | Fixed contractions of fp16 | Benoit Steiner | 2016-03-23 |
| | |||
* | Made type conversion explicit | Benoit Steiner | 2016-03-23 |
| | |||
* | Added the ability to divide a half float by an index | Benoit Steiner | 2016-03-23 |
| | |||
* | Added more conversion operators for half floats | Benoit Steiner | 2016-03-23 |
| | |||
* | Fixed contractions of 16 bit floats | Benoit Steiner | 2016-03-22 |
| | |||
* | Completed the implementation of vectorized type casting of half floats. | Benoit Steiner | 2016-03-18 |
| | |||
* | Make all the conversions explicit | Benoit Steiner | 2016-03-18 |
| | |||
* | Implemented some of the missing type casting for half floats | Benoit Steiner | 2016-03-17 |
| | |||
* | Merged in ebrevdo/eigen (pull request PR-169) | Christoph Hertzberg | 2016-03-16 |
|\ | | | | | | | Bugfixes to cuda tests, igamma & igammac implemented, & tests for digamma, igamma, igammac on CPU & GPU. | ||
| * | Change the header guard around certain numext functions to be CUDA specific. | Eugene Brevdo | 2016-03-16 |
| | | |||
* | | Fixed a typo. | Benoit Steiner | 2016-03-14 |
| | | |||
* | | Properly gate the use of cuda intrinsics in the code | Benoit Steiner | 2016-03-14 |
| | | |||
* | | Make sure we only use the half float intrinsic when compiling with a version ↵ | Benoit Steiner | 2016-03-14 |
| | | | | | | | | of CUDA that is recent enough to provide them | ||
* | | Don't mark the cast operator as explicit, since this is a c++11 feature ↵ | Benoit Steiner | 2016-03-12 |
| | | | | | | | | that's not supported by older compilers. | ||
* | | Also replaced uint32_t with unsigned int to make the code more portable | Benoit Steiner | 2016-03-11 |
| | | |||
* | | Replaced a couple more uint16_t with unsigned short | Benoit Steiner | 2016-03-11 |
| | | |||
* | | Use unsigned short instead of uint16_t since they're more portable | Benoit Steiner | 2016-03-11 |
| | | |||
* | | Made half floats usable on hardware that doesn't support them natively. | Benoit Steiner | 2016-03-11 |
| | | |||
* | | Fixed the +=, -=, *= and /= operators to return a reference | Benoit Steiner | 2016-03-10 |
| | | |||
| * | Update MathFunctions/SpecialFunctions with intelligent header guards. | Eugene Brevdo | 2016-03-09 |
| | | |||
| * | Properly fix merge issues. | Eugene Brevdo | 2016-03-08 |
| |\ | |||
| * | | Resolve bad merge. | Eugene Brevdo | 2016-03-08 |
| | | | |||
| * | | Add certain functions to numext (log, exp, tan) because CUDA doesn't support ↵ | Eugene Brevdo | 2016-03-08 |
|/ / | | | | | | | | | | | std:: Use these in SpecialFunctions. | ||
| * | Finishing touches on igamma/igammac for GPU. Tests now pass. | Eugene Brevdo | 2016-03-07 |
| | | |||
| * | Fix Eigen's building of sharded tests that use CUDA & more igamma/igammac ↵ | Eugene Brevdo | 2016-03-07 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | bugfixes. 0. Prior to this PR, not a single sharded CUDA test was actually being *run*. Fixed that. GPU tests are still failing for igamma/igammac. 1. Add calls for igamma/igammac to TensorBase 2. Fix up CUDA-specific calls of igamma/igammac 3. Add unit tests for digamma, igamma, igammac in CUDA. | ||
* | | Turn on some of the cxx11 features when compiling with visual studio 2015 | Benoit Steiner | 2016-03-05 |
| | | |||
| * | Make igamma and igammac work correctly. | Eugene Brevdo | 2016-03-04 |
| | | | | | | | | | | This required replacing ::abs with std::abs. Modified some unit tests. |