| Commit message (Expand) | Author | Age |
... | |
* | | Added missing EIGEN_DEVICE_FUNC qualifier | Benoit Steiner | 2016-05-23 |
* | | Use the Index type instead of integers to specify the strides in pgather/psca... | Benoit Steiner | 2016-05-23 |
* | | Added missing alignment in the fp16 packet traits | Benoit Steiner | 2016-05-23 |
* | | ptranspose is not a template. | Benoit Steiner | 2016-05-23 |
* | | Avoid unnecessary float to double conversion. | Benoit Steiner | 2016-05-23 |
* | | Started to vectorize the processing of 16bit floats on CPU. | Benoit Steiner | 2016-05-23 |
* | | Replace multiple constructors of half-type by a generic/templated constructor... | Christoph Hertzberg | 2016-05-23 |
* | | Make EIGEN_HAS_C99_MATH user configurable | Gael Guennebaud | 2016-05-20 |
* | | Fixed a couple of bugs related to the Pascalfamily of GPUs | Benoit Steiner | 2016-05-11 |
* | | Added the ability to load fp16 using the texture path. | Benoit Steiner | 2016-05-11 |
* | | Misc fixes for fp16 | Benoit Steiner | 2016-05-11 |
* | | Made predux_min and predux_max on fp16 less noisy | Benoit Steiner | 2016-05-11 |
* | | __ldg is only available with cuda architectures >= 3.5 | Benoit Steiner | 2016-05-11 |
* | | Fixed a typo | Benoit Steiner | 2016-05-11 |
* | | Added missing EIGEN_DEVICE_FUNC | Benoit Steiner | 2016-05-11 |
|\ \ |
|
| * | | Added missing EIGEN_DEVICE_FUNC qualifiers | Benoit Steiner | 2016-05-11 |
|/ / |
|
* | | Added packet primitives to compute exp, log, sqrt and rsqrt on fp16. This imp... | Benoit Steiner | 2016-05-10 |
* | | Added support for packet processing of fp16 on kepler and maxwell gpus | Benoit Steiner | 2016-05-06 |
* | | Relaxed the dummy precision for fp16 | Benoit Steiner | 2016-05-05 |
* | | Fixed compilation error with cuda >= 7.5 | Benoit Steiner | 2016-05-03 |
* | | Made a cast explicit | Benoit Steiner | 2016-05-02 |
* | | Fixed compilation errors generated by clang | Benoit Steiner | 2016-04-29 |
| * | define Packet2d constants with VSX only | Konstantinos Margaritis | 2016-04-28 |
| * | remove accidentally pasted code | Konstantinos Margaritis | 2016-04-28 |
| * | improve state of MathFunctions as well | Konstantinos Margaritis | 2016-04-28 |
| * | bring Altivec/VSX to a better state, implement some of the missing functions | Konstantinos Margaritis | 2016-04-28 |
| * | add name to copyrights | Konstantinos Margaritis | 2016-04-28 |
| * | minor fix, add to copyright | Konstantinos Margaritis | 2016-04-28 |
* | | fpclassify isn't portable enough. In particular, the return values of the fun... | Benoit Steiner | 2016-04-27 |
* | | Improved support for min and max on 16 bit floats when running on recent cuda... | Benoit Steiner | 2016-04-27 |
* | | Added support for fpclassify in Eigen::Numext | Benoit Steiner | 2016-04-27 |
| * | remove pgather/pscatter for std::complex<double> for s390x | Konstantinos Margaritis | 2016-04-15 |
|/ |
|
* | Force the inlining of the << operator on half floats | Benoit Steiner | 2016-04-14 |
* | Inline the << operator on half floats | Benoit Steiner | 2016-04-14 |
* | Added ability to printf fp16 | Benoit Steiner | 2016-04-14 |
* | Properly gate the definition of the error and gamma functions for fp16 | Benoit Steiner | 2016-04-13 |
* | Added basic implementation of the lgamma, digamma, igamma, igammac, polygamma... | Benoit Steiner | 2016-04-13 |
* | Added support for sin, cos, tan, and tanh on fp16 | Benoit Steiner | 2016-04-13 |
* | Added constructors to convert unsigned integers into fp16 | Benoit Steiner | 2016-04-13 |
* | Added epsilon, dummy_precision, infinity and quiet_NaN NumTraits for fp16 | Benoit Steiner | 2016-04-11 |
* | Disabled the use of half2 on cuda devices of compute capability < 5.3 | Benoit Steiner | 2016-04-08 |
* | Initial support for taking the power of fp16 | Benoit Steiner | 2016-04-08 |
* | Fixed the packet_traits for half floats. | Benoit Steiner | 2016-04-08 |
* | Add references to filed LLVM bugs | Benoit Jacob | 2016-04-08 |
* | Move the functions operating on fp16 out of the std namespace and into the Ei... | Benoit Steiner | 2016-04-07 |
* | Fixed compilation warning triggered by msvc | Benoit Steiner | 2016-04-06 |
* | Fixed packet_traits<half> | Benoit Steiner | 2016-04-06 |
* | Added support for hardware conversion between fp16 and full floats whenever | Benoit Steiner | 2016-04-06 |
* | Made the fp16 code more portable. | Benoit Steiner | 2016-04-06 |
* | Added some missing conversions to the Half class, and fixed the implementatio... | Benoit Steiner | 2016-04-06 |