Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
| * | | | add remaining includes | Konstantinos Margaritis | 2016-04-05 | |
| | | | | ||||
| * | | | complete int/double specialized traits for ZVector | Konstantinos Margaritis | 2016-04-05 | |
| | | | | ||||
| * | | | enable the other includes as well | Konstantinos Margaritis | 2016-04-05 | |
| | | | | ||||
| | | * | Merged eigen/eigen into default | Rasmus Larsen | 2016-04-04 | |
| | | |\ | |_|_|/ |/| | | | ||||
| | | * | Fix docstrings to list all supported decompositions. | Rasmus Munk Larsen | 2016-04-04 | |
| | | | | ||||
| | | * | Addresses comments on Eigen pull request PR-174. | Rasmus Munk Larsen | 2016-04-04 | |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Get rid of code-duplication for real vs. complex matrices. * Fix flipped arguments to select. * Make the condition estimation functions free functions. * Use Vector::Unit() to generate canonical unit vectors. * Misc. cleanup. | |||
* | | | | bug #1190 - Don't trust __ARM_FEATURE_FMA on Clang/ARM | Benoit Jacob | 2016-04-04 | |
| | | | | ||||
* | | | | bug #1191 - Prevent Clang/ARM from rewriting VMLA into VMUL+VADD | Benoit Jacob | 2016-04-04 | |
| | | | | ||||
| | * | | Refactored code into type-specific helper functions. | Till Hoffmann | 2016-04-04 | |
| | | | | ||||
* | | | | Updated the scalar_abs_op struct to make it compatible with cuda devices. | Benoit Steiner | 2016-04-04 | |
| | | | | ||||
* | | | | Fixed the signature of numext::abs to make it compatible with complex numbers | Benoit Steiner | 2016-04-04 | |
| | | | | ||||
| | | * | Merged eigen/eigen into default | Rasmus Larsen | 2016-04-01 | |
| | | |\ | |_|_|/ |/| | | | ||||
| | | * | Add rcond method to LDLT. | Rasmus Munk Larsen | 2016-04-01 | |
| | | | | ||||
| | | * | Add condition estimation to Cholesky (LLT) factorization. | Rasmus Munk Larsen | 2016-04-01 | |
| | | | | ||||
| | | * | Replace "inline static" with "static inline" for consistency. | Rasmus Munk Larsen | 2016-04-01 | |
| | | | | ||||
| | | * | Fix comments in ConditionEstimator and minor cleanup. | Rasmus Munk Larsen | 2016-04-01 | |
| | | | | ||||
| | | * | Add matrix condition estimator module that implements the Higham/Hager ↵ | Rasmus Munk Larsen | 2016-04-01 | |
| | | | | | | | | | | | | | | | | algorithm from http://www.maths.manchester.ac.uk/~higham/narep/narep135.pdf used in LPACK. Add rcond() methods to FullPivLU and PartialPivLU. | |||
| | * | | 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 | |
| | | ||||
| * | actually include ZVector files, passes most basic tests (float still fails) | Konstantinos Margaritis | 2016-03-28 | |
| | | ||||
| * | Merged eigen/eigen into default | Konstantinos Margaritis | 2016-03-28 | |
| |\ | |/ |/| | ||||
| * | some primitives ported, but missing intrinsics and crash with asm() are a ↵ | Konstantinos Margaritis | 2016-03-27 | |
| | | | | | | | | problem | |||
* | | 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 | |
| |