Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
* | | fpclassify isn't portable enough. In particular, the return values of the ↵ | 2016-04-27 | ||
| | | | | | | | | function are not available on all the platforms Eigen supportes: remove it from Eigen. | |||
* | | Made the index type a template parameter to evaluateProductBlockingSizes | 2016-04-27 | ||
|/ | | | | Use numext::mini and numext::maxi instead of std::min/std::max to compute blocking sizes. | |||
* | Improved support for min and max on 16 bit floats when running on recent ↵ | 2016-04-27 | ||
| | | | | cuda gpus | |||
* | Added support for fpclassify in Eigen::Numext | 2016-04-27 | ||
| | ||||
* | Merged in rmlarsen/eigen (pull request PR-179) | 2016-04-21 | ||
|\ | | | | | | | Prevent crash in CompleteOrthogonalDecomposition if object was default constructed. | |||
| * | Prevent crash in CompleteOrthogonalDecomposition if object was default ↵ | 2016-04-21 | ||
| | | | | | | | | constructed. | |||
* | | Don't attempt to leverage the _cvtss_sh and _cvtsh_ss instructions when ↵ | 2016-04-20 | ||
| | | | | | | | | compiling with clang since it's unclear which versions of clang actually support these instruction. | |||
* | | Made sure all the required header files are included when trying to use fp16 | 2016-04-19 | ||
|/ | ||||
* | Enable lazy-coeff-based-product for vector*(1x1) products | 2016-04-16 | ||
| | ||||
* | Deleted extraneous comma. | 2016-04-15 | ||
| | ||||
* | bug #1203: by-pass large stack-allocation in stableNorm if ↵ | 2016-04-15 | ||
| | | | | EIGEN_STACK_ALLOCATION_LIMIT is too small | |||
* | Improved the matrix multiplication blocking in the case where mr is not a ↵ | 2016-04-15 | ||
| | | | | power of 2 (e.g on Haswell CPUs). | |||
* | Fix trmv for mixing types. | 2016-04-15 | ||
| | ||||
* | Added ability to access the cache sizes from the tensor devices | 2016-04-14 | ||
| | ||||
* | Added support for exclusive or | 2016-04-14 | ||
| | ||||
* | Improve numerical robustness of JacoviSVD: | 2016-04-14 | ||
| | | | | | - avoid noise amplification in complex to real conversion - compare off-diagonal entries to the current biggest diagonal entry: no need to bother about a 2x2 block containing ridiculously small entries compared to the rest of the matrix. | |||
* | Force the inlining of the << operator on half floats | 2016-04-14 | ||
| | ||||
* | Inline the << operator on half floats | 2016-04-14 | ||
| | ||||
* | Added ability to printf fp16 | 2016-04-14 | ||
| | ||||
* | Cleaning pass on rcond estimator. | 2016-04-14 | ||
| | ||||
* | Better use .data() than &coeffRef(0) | 2016-04-14 | ||
| | ||||
* | Merged in rmlarsen/eigen (pull request PR-174) | 2016-04-14 | ||
|\ | | | | | | | Add matrix condition number estimation module. | |||
* | | Properly gate the definition of the error and gamma functions for fp16 | 2016-04-13 | ||
| | | ||||
* | | Improved support for trigonometric functions on GPU | 2016-04-13 | ||
| | | ||||
* | | Added basic implementation of the lgamma, digamma, igamma, igammac, ↵ | 2016-04-13 | ||
| | | | | | | | | polygamma, and zeta function for fp16 | |||
* | | merge | 2016-04-13 | ||
|\ \ | ||||
* | | | Fix JacobiSVD for complex when the complex-to-real update already gives a ↵ | 2016-04-13 | ||
| | | | | | | | | | | | | diagonal 2x2 block. | |||
| * | | Cleaned up the implementation of digamma | 2016-04-13 | ||
| | | | ||||
| * | | Pulled latest updates from trunk | 2016-04-13 | ||
|/| | | ||||
| * | | Added support for sin, cos, tan, and tanh on fp16 | 2016-04-13 | ||
| | | | ||||
* | | | Fix underflow in JacoviSVD's complex to real preconditioner | 2016-04-13 | ||
|/ / | ||||
* | | Added support for computing cos, sin, tan, and tanh on GPU. | 2016-04-13 | ||
| | | ||||
* | | Added constructors to convert unsigned integers into fp16 | 2016-04-13 | ||
| | | ||||
* | | Workaround a division by zero when outerstride==0 | 2016-04-13 | ||
| | | ||||
* | | Make use of is_same_dense helper instead of extract_data to detect ↵ | 2016-04-13 | ||
| | | | | | | | | input/outputs are the same. | |||
* | | Fix incomplete previous patch on matrix comparision. | 2016-04-13 | ||
| | | ||||
* | | Fix detection of same matrices when both matrices are not handled by ↵ | 2016-04-13 | ||
| | | | | | | | | extract_data. | |||
* | | Improve half-packet vectorization logic to distinguish linear versus inner ↵ | 2016-04-13 | ||
| | | | | | | | | traversal modes. | |||
* | | Enable half-packet in reduxions. | 2016-04-13 | ||
| | | ||||
* | | Don't put a command at the end of an enumerator list | 2016-04-12 | ||
| | | ||||
* | | Enable the use of half-packet in coeff-based product. | 2016-04-12 | ||
| | | | | | | | | For instance, Matrix4f*Vector4f is now vectorized again when using AVX. | |||
| * | Merged eigen/eigen into default | 2016-04-11 | ||
| |\ | ||||
* | | | More accurate cost estimates for exp, log, tanh, and sqrt. | 2016-04-11 | ||
| |/ |/| | ||||
* | | Added epsilon, dummy_precision, infinity and quiet_NaN NumTraits for fp16 | 2016-04-11 | ||
| | | ||||
* | | Pulled latest update from trunk | 2016-04-11 | ||
|\ \ | ||||
| * | | Move LAPACK declarations from blas.h to lapack.h and fix compatibility with ↵ | 2016-04-11 | ||
| | | | | | | | | | | | | EIGEN_USE_MKL | |||
| * | | Cleanup obsolete assign_scalar_eig2mkl helper. | 2016-04-11 | ||
| | | | ||||
| * | | Remove all references to MKL in BLAS wrappers. | 2016-04-11 | ||
| | | | ||||
| * | | Fix long to int conversion in BLAS API. | 2016-04-11 | ||
| | | | ||||
| * | | Silent unused warning. | 2016-04-11 | ||
| | | |