aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Modify GEMM to handle m=0, n=0, and k=0 cases.Gravatar Eric Martin2015-07-11
|
* Added support for generation of random complex numbers on CUDA devicesGravatar Benoit Steiner2015-07-07
|
* Use NumTraits<T>::RequireInitialization instead of ↵Gravatar Benoit Steiner2015-07-07
| | | | internal::is_arithmetic<T>::value to check whether it's possible to bypass the type constructor in the tensor code.
* Updated internal::is_arithmetic::value to be true for complex numbersGravatar Benoit Steiner2015-07-07
|
* Pulled latest changes from trunkGravatar Benoit Steiner2015-07-07
|\
* | Improved and cleaned up the 2d patch extraction codeGravatar Benoit Steiner2015-07-07
| |
| * typoGravatar Gael Guennebaud2015-07-07
|/
* Rotation2D: fix slerp to take the shortest path, and add convenient method ↵Gravatar Gael Guennebaud2015-07-07
| | | | to get the angle in [-pi,pi] or [0,pi]
* Use numext::swap instead of std::swapGravatar Benoit Steiner2015-07-06
|
* use Eigen smart_copy instead of std::copyGravatar Benoit Steiner2015-07-06
|
* Fixed a compilation warning generated by clangGravatar Benoit Steiner2015-07-06
|
* Only attempt to use the texture path on GPUs when it's supported by CUDAGravatar Benoit Steiner2015-07-06
|
* Misc small fixes to the tensor slicing code.Gravatar Benoit Steiner2015-07-06
|
* Merged in Emie/eigen (pull request PR-121)Gravatar Gael Guennebaud2015-07-06
|\ | | | | | | typo correction in mathFunction
| * typo correction in mathFunctionGravatar Emilie Guy2015-07-06
| |
* | Merged eigen/eigen into defaultGravatar Nicolas Mellado2015-07-03
|\|
* | Fixed a typo in the patchGravatar Benoit Steiner2015-07-02
| |
| * Added a default value for the cuda stream in the GpuDevice constructorGravatar Benoit Steiner2015-07-01
| |
| * Misc improvements and optimizationsGravatar Benoit Steiner2015-07-01
| |
| * Improved a previous fixGravatar Benoit Steiner2015-07-01
| |
| * Fixed a couple of mistakes in the previous commit.Gravatar Benoit Steiner2015-07-01
| |
| * Enabled the vectorized evaluation of several tensor expressions that was ↵Gravatar Benoit Steiner2015-07-01
| | | | | | | | previously disabled by mistake
| * Marked the cast functions as EIGEN_DEVICE_FUNC to ensure that we can run ↵Gravatar Benoit Steiner2015-06-30
| | | | | | | | casting on GPUs
| * Silenced a compilation warningGravatar Benoit Steiner2015-06-30
| |
| * Added support for user defined custom tensor op.Gravatar Benoit Steiner2015-06-30
| |
| * Added support for 3D patch extractionGravatar Benoit Steiner2015-06-30
| |
| * Made ThreadPoolDevice inherit from a new pure abstract ThreadPoolInterface ↵Gravatar Benoit Steiner2015-06-30
| | | | | | | | class: this enables users to leverage their existing threadpool when using eigen tensors.
| * Turned Eigen::array::size into a function to make the code compatible with ↵Gravatar Benoit Steiner2015-06-30
| | | | | | | | std::array
| * Added a test for multithreaded full reductionsGravatar Benoit Steiner2015-06-30
| |
| * Fixed a few compilation warningsGravatar Benoit Steiner2015-06-30
| |
| * Silenced a number of compilation warningsGravatar Benoit Steiner2015-06-29
| |
| * Added a test for full reductions on GPUGravatar Benoit Steiner2015-06-29
| |
| * Improved performance of full reduction by 2 order of magnitude on CPU and 3 ↵Gravatar Benoit Steiner2015-06-29
| | | | | | | | orders of magnitude on GPU
| * Improved support for fixed size tensorsGravatar Benoit Steiner2015-06-29
| |
| * Express the full reduction operations (such as sum, max, min) using ↵Gravatar Benoit Steiner2015-06-29
| | | | | | | | TensorDimensionList
| * Added support for tanh function to the tensor codeGravatar Benoit Steiner2015-06-29
| |
| * Moved some utilities to TensorMeta.h to make it easier to reuse them accross ↵Gravatar Benoit Steiner2015-06-29
| | | | | | | | | | | | several tensor operations. Created the TensorDimensionList class to encode the list of all the dimensions of a tensor of rank n. This could be done using TensorIndexList, however TensorIndexList require cxx11 which isn't yet supported as widely as we'd like.
| * Use VERIFY_IS_EQUAL instead of VERIFY(a==b) to get more feedback in case of ↵Gravatar Gael Guennebaud2015-06-26
| | | | | | | | failure
| * split compiler intensive bdcsvd_1 unit testGravatar Gael Guennebaud2015-06-26
| |
| * Add special path for matrix<complex>/real.Gravatar Gael Guennebaud2015-06-26
| | | | | | | | This also fixes underflow issues when scaling complex matrices through complex/complex operator.
| * bug #1026: fix infinite loop for an empty inputGravatar Gael Guennebaud2015-06-26
| |
| * Doc: explain perf and multithreading issues in sparse iterative solversGravatar Gael Guennebaud2015-06-26
| |
| * Enable OpenMP parallelization of row-major-sparse * dense products.Gravatar Gael Guennebaud2015-06-26
| | | | | | | | I observed significant speed-up of the CG solver.
| * More msvc 2013/2015 workaroundsGravatar Gael Guennebaud2015-06-26
| |
| * Optimize CG to enable faster spare row-major * dense vector products when ↵Gravatar Gael Guennebaud2015-06-25
| | | | | | | | the input matrix is complete (Upper|Lower) but column major.
| * Fix assignement to selfadjoint-view when testing real-world problemsGravatar Gael Guennebaud2015-06-25
| |
| * Remove redundant accessors in ReverseGravatar Gael Guennebaud2015-06-25
| |
| * Avoid division by a zero complexGravatar Gael Guennebaud2015-06-25
| |
| * Clarify documentation of the tolerance and error returned in iterative solversGravatar Gael Guennebaud2015-06-25
| |
| * workaround msvc 2013/2015 wrong instanciation of isnan, isfinite, isinfGravatar Gael Guennebaud2015-06-25
| |
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-25 06:32:37 +0000