aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Fixed the implementation of Eigen::numext::isfinite, Eigen::numext::isnan, ↵Gravatar Benoit Steiner2016-04-08
| | | | andEigen::numext::isinf on CUDA devices
* Fixed isfinite_impl: NumTraits<T>::highest() and NumTraits<T>::lowest() are ↵Gravatar Benoit Steiner2016-04-08
| | | | finite numbers.
* Disabled the use of half2 on cuda devices of compute capability < 5.3Gravatar Benoit Steiner2016-04-08
|
* Initial support for taking the power of fp16Gravatar Benoit Steiner2016-04-08
|
* Fixed the packet_traits for half floats.Gravatar Benoit Steiner2016-04-08
|
* Created the new EIGEN_TEST_CUDA_CLANG option to compile the CUDA tests using ↵Gravatar Benoit Steiner2016-04-08
| | | | clang instead of nvcc
* Don't test the division by 0 on float16 when compiling with msvc since msvc ↵Gravatar Benoit Steiner2016-04-08
| | | | detects and errors out on divisions by 0.
* Add references to filed LLVM bugsGravatar Benoit Jacob2016-04-08
|
* Properly handle complex numbers.Gravatar Benoit Steiner2016-04-07
|
* Turn on the coeffWise benchmarks on fp16Gravatar Benoit Steiner2016-04-07
|
* Fixed the type casting benchmarks for fp16Gravatar Benoit Steiner2016-04-07
|
* Merged in parthaEth/eigen (pull request PR-175)Gravatar Benoit Steiner2016-04-07
|\ | | | | | | Static casting scalar types so as to let chlesky module of eigen work with ceres
* | Renamed float16 into cxx11_float16 since the test relies on c++11 featuresGravatar Benoit Steiner2016-04-07
| |
* | Added missing EIGEN_DEVICE_FUNC to the tensor conversion code.Gravatar Benoit Steiner2016-04-07
| |
* | Fixed the benchmarking of fp16 coefficient wise operationsGravatar Benoit Steiner2016-04-07
| |
| * Static casting scalar types so as to let chlesky module of eigen work with ceresGravatar parthaEth2016-04-08
|/
* Worked around numerical noise in the test for the zeta function.Gravatar Benoit Steiner2016-04-07
|
* Fixed a typo in the polygamma test.Gravatar Benoit Steiner2016-04-07
|
* Updated the unary functors to use the numext implementation of typicall ↵Gravatar Benoit Steiner2016-04-07
| | | | functions instead of the one provided in the standard library. The standard library functions aren't supported officially by cuda, so we're better off using the numext implementations.
* Move the functions operating on fp16 out of the std namespace and into the ↵Gravatar Benoit Steiner2016-04-07
| | | | Eigen::numext namespace
* Added tests for float16Gravatar Benoit Steiner2016-04-07
|
* Fixed a typo in a testGravatar Benoit Steiner2016-04-07
|
* Updated the isnan, isinf and isfinite functions to make compatible with cuda ↵Gravatar Benoit Steiner2016-04-07
| | | | devices.
* Added support for isinf, isnan, and isfinite checks to the tensor apiGravatar Benoit Steiner2016-04-07
|
* Fixed a possible integer overflow.Gravatar Benoit Steiner2016-04-07
|
* Fixed compilation warning triggered by msvcGravatar Benoit Steiner2016-04-06
|
* Fixed packet_traits<half>Gravatar Benoit Steiner2016-04-06
|
* Added support for hardware conversion between fp16 and full floats wheneverGravatar Benoit Steiner2016-04-06
| | | | possible.
* Fixed the tests for the zeta and polygamma functionsGravatar Benoit Steiner2016-04-06
|
* Fixed typos in the implementation of the zeta and polygamma ops.Gravatar Benoit Steiner2016-04-06
|
* Made the fp16 code more portable.Gravatar Benoit Steiner2016-04-06
|
* Added some missing conversions to the Half class, and fixed the ↵Gravatar Benoit Steiner2016-04-06
| | | | implementation of the < operator on cuda devices.
* Merged in tillahoffmann/eigen (pull request PR-173)Gravatar Benoit Steiner2016-04-06
|\ | | | | | | Added zeta function of two arguments and polygamma function
* | Renamed the EIGEN_TEST_NVCC cmake option into EIGEN_TEST_CUDA per the ↵Gravatar Benoit Steiner2016-04-06
| | | | | | | | discussion in bug #1173.
* | Added support for isfinite on fp16Gravatar Benoit Steiner2016-04-06
| |
* | Merged kmargar/eigen/tip into defaultGravatar Konstantinos Margaritis2016-04-05
|\ \
| * | complete the port, remove float supportGravatar Konstantinos Margaritis2016-04-05
| | |
| | * Merged eigen/eigen into defaultGravatar tillahoffmann2016-04-05
| | |\ | |_|/ |/| |
| | * Added accuracy comments.Gravatar Till Hoffmann2016-04-05
| | |
* | | bug #1189: fix pow/atan2 compilation for AutoDiffScalarGravatar Gael Guennebaud2016-04-05
| | |
| * | add remaining includesGravatar Konstantinos Margaritis2016-04-05
| | |
| * | complete int/double specialized traits for ZVectorGravatar Konstantinos Margaritis2016-04-05
| | |
| * | enable all tests againGravatar Konstantinos Margaritis2016-04-05
| | |
| * | enable the other includes as wellGravatar Konstantinos Margaritis2016-04-05
| | |
* | | bug #1190 - Don't trust __ARM_FEATURE_FMA on Clang/ARMGravatar Benoit Jacob2016-04-04
| | |
* | | bug #1191 - Prevent Clang/ARM from rewriting VMLA into VMUL+VADDGravatar Benoit Jacob2016-04-04
| | |
| | * Merge upstream.Gravatar Till Hoffmann2016-04-04
| | |\
| | * | Refactored code into type-specific helper functions.Gravatar Till Hoffmann2016-04-04
| | | |
* | | | Updated the scalar_abs_op struct to make it compatible with cuda devices.Gravatar Benoit Steiner2016-04-04
| | | |
* | | | Fixed the signature of numext::abs to make it compatible with complex numbersGravatar Benoit Steiner2016-04-04
| | | |
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-03 00:16:55 +0000