aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Created a test to check that the sycl runtime can successfully report errors ↵Gravatar Benoit Steiner2016-11-17
| | | | | | (like ivision by 0). Small cleanup
* Avoid calling log(0) or 1/0Gravatar Benoit Steiner2016-11-17
|
* Fixed existing test.Gravatar Luke Iwanski2016-11-17
|
* Specialised basic math functions for SYCL device.Gravatar Luke Iwanski2016-11-17
|
* Merged eigen/eigen into defaultGravatar Benoit Steiner2016-11-14
|\
| * Reduce dispatch overhead in parallelFor by only calling ↵Gravatar Rasmus Munk Larsen2016-11-14
| | | | | | | | thread_pool.Schedule() for one of the two recursive calls in handleRange. This avoids going through the scedule path to push both recursive calls onto another thread-queue in the binary tree, but instead executes one of them on the main thread. At the leaf level this will still activate a full complement of threads, but will save up to 50% of the overhead in Schedule (random number generation, insertion in queue which includes signaling via atomics).
* | Adding extra test for non-fixed size to broadcast; Replacing stcl with sycl.Gravatar Mehdi Goli2016-11-14
| |
* | Adding TensorFixsize; adding sycl device memcpy; adding insial stage of slicing.Gravatar Mehdi Goli2016-11-14
| |
| * Optimize sparse<bool> && sparse<bool> to use the same path as for coeff-wise ↵Gravatar Gael Guennebaud2016-11-14
| | | | | | | | products.
| * bug #426: move operator && and || to MatrixBase and SparseMatrixBase.Gravatar Gael Guennebaud2016-11-14
| |
| * Merged in olesalscheider/eigen (pull request PR-248)Gravatar Gael Guennebaud2016-11-14
| |\ | | | | | | | | | Make sure not to call numext::maxi on expression templates
| * | Fix regression in SparseMatrix::ReverseInnerIteratorGravatar Gael Guennebaud2016-11-14
| | |
| | * Make sure not to call numext::maxi on expression templatesGravatar Niels Ole Salscheider2016-11-12
| |/
* | Adding comment to TensorDeviceSycl.h and cleaning the code.Gravatar Mehdi Goli2016-11-11
| |
| * Merged in benoitsteiner/opencl (pull request PR-247)Gravatar Benoit Steiner2016-11-11
| |\ | |/ |/|
* | Adding EIGEN_STRONG_INLINE back; using size() instead of ↵Gravatar Mehdi Goli2016-11-10
| | | | | | | | dimensions.TotalSize() on Tensor.
* | adding the missing in eigen_assert!Gravatar Mehdi Goli2016-11-10
| |
* | Adding Memset; optimising MecopyDeviceToHost by removing double copying;Gravatar Mehdi Goli2016-11-10
| |
| * bump to 3.3.0Gravatar Gael Guennebaud2016-11-10
| |
| * Fix printing of sparse expressionsGravatar Gael Guennebaud2016-11-10
| |
* | Added a test to validate memory transfers between host and sycl deviceGravatar Benoit Steiner2016-11-09
|/
* Merged in benoitsteiner/opencl (pull request PR-246)Gravatar Benoit Steiner2016-11-08
|\ | | | | | | Improved support for OpenCL
| * Fixed the formatting of the codeGravatar Benoit Steiner2016-11-08
| |
| * Fixed the indentation of the cmake fileGravatar Benoit Steiner2016-11-08
| |
| * #if EIGEN_EXCEPTION -> #ifdef EIGEN_EXCEPTIONS.Gravatar Luke Iwanski2016-11-08
| |
| * Fix for SYCL queue initialisation.Gravatar Luke Iwanski2016-11-08
| |
| * Use try/catch only when exceptions are enabled.Gravatar Luke Iwanski2016-11-08
| |
| * Converting all sycl buffers to uninitialised device only buffers; adding ↵Gravatar Mehdi Goli2016-11-08
| | | | | | | | memcpyHostToDevice and memcpyDeviceToHost on syclDevice; modifying all examples to obey the new rules; moving sycl queue creating to the device based on Benoit suggestion; removing the sycl specefic condition for returning m_result in TensorReduction.h according to Benoit suggestion.
* | Extend unit test to check sparse solvers with a SparseVector as the rhs and ↵Gravatar Gael Guennebaud2016-11-06
| | | | | | | | result.
* | Generalize Cholmod support to hanlde any sparse type as the rhs and result ↵Gravatar Gael Guennebaud2016-11-06
| | | | | | | | of the solve method
* | Generalize IterativeSolverBase::solve to hanlde any sparse type as the ↵Gravatar Gael Guennebaud2016-11-06
| | | | | | | | results (instead of SparseMatrix only)
* | Generalize solve_sparse_through_dense_panels to handle SparseVector.Gravatar Gael Guennebaud2016-11-06
| |
* | Add missing friend declarationGravatar Gael Guennebaud2016-11-06
| |
* | Add a default ctor to evaluator<SparseVector>.Gravatar Gael Guennebaud2016-11-06
| | | | | | | | Needed for evaluator<Solve>.
* | Enable swapping between SparseMatrix and SparseVectorGravatar Gael Guennebaud2016-11-06
| |
* | Removed unnecessary statementGravatar Benoit Steiner2016-11-05
| |
| * Added missing includesGravatar Benoit Steiner2016-11-05
| |
* | Extend mpreal unit test to check LLT with complexes.Gravatar Gael Guennebaud2016-11-05
| |
* | Fix compilation of LLT with complex<mpreal>.Gravatar Gael Guennebaud2016-11-05
| |
| * Merged eigen/eigen into defaultGravatar Benoit Steiner2016-11-04
| |\ | |/ |/|
| * Removed the sycl include from Eigen/Core and moved it to ↵Gravatar Mehdi Goli2016-11-04
| | | | | | | | Unsupported/Eigen/CXX11/Tensor; added TensorReduction for sycl (full reduction and partial reduction); added TensorReduction test case for sycl (full reduction and partial reduction); fixed the tile size on TensorSyclRun.h based on the device max work group size;
* | Added tag 3.3-rc2 for changeset ba05572dcb385c752fc2c0729f05ccb9ad04d7bdGravatar Gael Guennebaud2016-11-04
| |
* | bump to 3.3-rc2Gravatar Gael Guennebaud2016-11-04
| |
* | Improved AVX512 configurationGravatar Benoit Steiner2016-11-03
| |
* | Reenable the generation of dynamic blas libraries.Gravatar Benoit Steiner2016-11-03
| |
* | Improved AVX512 supportGravatar Benoit Steiner2016-11-03
| |
* | Merged eigen/eigen into defaultGravatar Benoit Steiner2016-11-03
|\ \
| * | bug #1337: improve doc of homogeneous() and hnormalized()Gravatar Gael Guennebaud2016-11-03
| | |
| * | bug #1330: Cholmod supports double precision only, so let's trigger a static ↵Gravatar Gael Guennebaud2016-11-03
| | | | | | | | | | | | assertion if the scalar type does not match this requirement.
| * | Merged in benoitsteiner/opencl (pull request PR-244)Gravatar Benoit Steiner2016-11-02
| |\| | | | | | | | | | Disable vectorization on device only when compiling for sycl