Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
| * | | Added support for isfinite on fp16 | 2016-04-06 | ||
| | | | ||||
| * | | Merged kmargar/eigen/tip into default | 2016-04-05 | ||
| |\ \ | ||||
| | * | | complete the port, remove float support | 2016-04-05 | ||
| | | | | ||||
| | | * | Merged eigen/eigen into default | 2016-04-05 | ||
| |_|/| |/| |/ | |/| | ||||
* | | | Added accuracy comments. | 2016-04-05 | ||
| | | | ||||
| * | | bug #1189: fix pow/atan2 compilation for AutoDiffScalar | 2016-04-05 | ||
| | | | ||||
| | * | add remaining includes | 2016-04-05 | ||
| | | | ||||
| | * | complete int/double specialized traits for ZVector | 2016-04-05 | ||
| | | | ||||
| | * | enable all tests again | 2016-04-05 | ||
| | | | ||||
| | * | enable the other includes as well | 2016-04-05 | ||
| | | | ||||
| * | | bug #1190 - Don't trust __ARM_FEATURE_FMA on Clang/ARM | 2016-04-04 | ||
| | | | ||||
| * | | bug #1191 - Prevent Clang/ARM from rewriting VMLA into VMUL+VADD | 2016-04-04 | ||
| | | | ||||
* | | | Merge upstream. | 2016-04-04 | ||
|\ \ \ | ||||
* | | | | Refactored code into type-specific helper functions. | 2016-04-04 | ||
| | | | | ||||
| | * | | Updated the scalar_abs_op struct to make it compatible with cuda devices. | 2016-04-04 | ||
| | | | | ||||
| | * | | Fixed the signature of numext::abs to make it compatible with complex numbers | 2016-04-04 | ||
| | | | | ||||
| * | | | Merged eigen/eigen into default | 2016-04-04 | ||
|/| | | | |/ / | ||||
| * | | Fix cross-compiling windows version detection | 2016-04-04 | ||
| | | | ||||
* | | | Merge upstream. | 2016-04-01 | ||
|\ \ \ | ||||
* | | | | Added CUDA tests. | 2016-04-01 | ||
| | | | | ||||
* | | | | Fixed CUDA signature. | 2016-04-01 | ||
| | | | | ||||
* | | | | Fixed suggestions by Eugene Brevdo. | 2016-04-01 | ||
| | | | | ||||
| * | | | Merged eigen/eigen into default | 2016-04-01 | ||
|/| | | | |/ / | ||||
* | | | Added polygamma function. | 2016-04-01 | ||
| | | | ||||
* | | | Added zeta function. | 2016-04-01 | ||
| | | | ||||
| * | | Relaxed the condition used to gate the fft code. | 2016-03-31 | ||
| | | | ||||
| * | | Hashing was only officially introduced in c++11. Therefore only define an ↵ | 2016-03-31 | ||
| | | | | | | | | | | | | implementation of the hash function for float16 if c++11 is enabled. | |||
| * | | Improved code formating | 2016-03-31 | ||
| | | | ||||
| * | | Added the ability to hash a fp16 | 2016-03-31 | ||
| | | | ||||
| * | | Properly gate the fft code | 2016-03-31 | ||
| | | | ||||
| * | | Made it possible to use the NumTraits for complex and Array in a cuda kernel. | 2016-03-31 | ||
| | | | ||||
| * | | Added __ldg primitive for fp16. | 2016-03-31 | ||
| | | | ||||
| * | | Added NumTraits for half floats | 2016-03-31 | ||
| | | | ||||
| * | | Fixed a typo | 2016-03-31 | ||
|/ / | ||||
* | | Fixed a off-by-one bug in a debug assertion | 2016-03-30 | ||
| | | ||||
* | | Added NumTraits for type2index. | 2016-03-30 | ||
| | | ||||
* | | Pull math functions from the global namespace only when compiling cuda code ↵ | 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. | 2016-03-30 | ||
| | | ||||
* | | Fixed compilation warning | 2016-03-30 | ||
| | | ||||
* | | Added missing assignment operator to the TensorUInt128 class, and made misc ↵ | 2016-03-30 | ||
| | | | | | | | | small improvements | |||
* | | bug #1186 - vreinterpretq_u64_f64 fails to build on Android/Aarch64/Clang ↵ | 2016-03-30 | ||
| | | | | | | | | toolchain | |||
* | | Fixed the formatting of the README. | 2016-03-29 | ||
| | | ||||
* | | Attempt to fix the formatting of the README | 2016-03-29 | ||
| | | ||||
* | | Pulled latest updates from trunk | 2016-03-29 | ||
|\ \ | ||||
| * | | Add regression test for nesting type handling in blas_traits | 2016-03-29 | ||
| | | | ||||
* | | | Added missing cuda template specializations for numext::ceil | 2016-03-29 | ||
|/ / | ||||
* | | Use false instead of 0 as the expected value of a boolean | 2016-03-29 | ||
| | | ||||
* | | Added support for standard mathematical functions and trancendentals(such ↵ | 2016-03-29 | ||
| | | | | | | | | as exp, log, abs, ...) on fp16 | |||
* | | Added support for fmod | 2016-03-28 | ||
| | | ||||
* | | Made it possible to customize the threadpool | 2016-03-28 | ||
| | |