Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Remove clang warning | Gael Guennebaud | 2018-07-13 |
| | |||
* | Print more debug info in gpu_basic | Gael Guennebaud | 2018-07-13 |
| | |||
* | Introduce gpu_assert for assertion in device-code, and disable them with ↵ | Gael Guennebaud | 2018-07-13 |
| | | | | clang-cuda. | ||
* | Make EIGEN_TEST_CUDA_CLANG more friendly with OSX | Gael Guennebaud | 2018-07-13 |
| | |||
* | Forward declaring std::array does not work with all std libs, so let's just ↵ | Gael Guennebaud | 2018-07-13 |
| | | | | include <array> | ||
* | Add support for MIPS SIMD (MSA) | Alexey Frunze | 2018-07-06 |
| | |||
* | Add unit test for -Tensor<complex> on GPU | Gael Guennebaud | 2018-07-12 |
| | |||
* | Remove local Index typedef from unit-tests | Gael Guennebaud | 2018-07-12 |
| | |||
* | Disable eigenvalues test for clang-cuda | Gael Guennebaud | 2018-07-12 |
| | |||
* | fix unused warning | Gael Guennebaud | 2018-07-12 |
| | |||
* | Fix shadowing typedefs | Gael Guennebaud | 2018-07-12 |
| | |||
* | Fix compilation regarding std::array | Gael Guennebaud | 2018-07-12 |
| | |||
* | fix unused warning | Gael Guennebaud | 2018-07-12 |
| | |||
* | Cleanup the mess in Eigen/Core by moving CUDA/HIP stuff at more appropriate ↵ | Gael Guennebaud | 2018-07-12 |
| | | | | | | places (Macros.h), and alignment/vectorization logic is now in util/ConfigureVectorization.h | ||
* | Fix cxx11_tensor_fft not building on Windows. | Thales Sabino | 2018-07-12 |
| | | | | | | The type used in Eigen::DSizes needs to be at least 8 bytes long. Internally Tensor tries to convert this to an __int64 on Windows and this fails to build. On Linux, long and long long are both 8 byte integer types. * * * Changing from "long long" to "std::int64_t". | ||
* | Fix doc | Gael Guennebaud | 2018-07-12 |
| | |||
* | Add missing consts for rows and cols functions in SparseLU | Julian Kent | 2018-02-10 |
| | |||
* | FindEigen3: Set Eigen3_FOUND variable | Daniele E. Domenichelli | 2018-07-11 |
| | |||
* | remove double ;; | Gael Guennebaud | 2018-07-12 |
| | |||
* | bug #1570: fix warning | Gael Guennebaud | 2018-07-12 |
| | |||
* | Add deprecated header files for TensorFlow | Gael Guennebaud | 2018-07-12 |
| | |||
* | Merged in deven-amd/eigen (pull request PR-402) | Gael Guennebaud | 2018-07-12 |
|\ | | | | | | | Adding support for using Eigen in HIP kernels. | ||
* | | Remove useless specialization thanks to is_convertible being more robust. | Gael Guennebaud | 2018-07-12 |
| | | |||
* | | Add some basic unit-tests | Gael Guennebaud | 2018-07-12 |
| | | |||
* | | spellcheck | Gael Guennebaud | 2018-07-12 |
| | | |||
* | | Make is_convertible more robust and conformant to std::is_convertible | Gael Guennebaud | 2018-07-12 |
| | | |||
* | | Optimize the product of a householder-sequence with the identity, and ↵ | Gael Guennebaud | 2018-07-11 |
| | | | | | | | | optimize the evaluation of a HouseholderSequence to a dense matrix using faster blocked product. | ||
* | | Fix regression in 9357838f94d2907996adadc7e5200376f3561ed4 | Gael Guennebaud | 2018-07-11 |
| | | |||
* | | Fix double ;; | Gael Guennebaud | 2018-07-11 |
| | | |||
| * | Updates corresponding to the latest round of PR feedback | Deven Desai | 2018-07-11 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | The major changes are 1. Moving CUDA/PacketMath.h to GPU/PacketMath.h 2. Moving CUDA/MathFunctions.h to GPU/MathFunction.h 3. Moving CUDA/CudaSpecialFunctions.h to GPU/GpuSpecialFunctions.h The above three changes effectively enable the Eigen "Packet" layer for the HIP platform 4. Merging the "hip_basic" and "cuda_basic" unit tests into one ("gpu_basic") 5. Updating the "EIGEN_DEVICE_FUNC" marking in some places The change has been tested on the HIP and CUDA platforms. | ||
| * | deleting hip specific files that are no longer required | Deven Desai | 2018-07-11 |
| | | |||
| * | renaming CUDA* to GPU* for some header files | Deven Desai | 2018-07-11 |
| | | |||
| * | renaming CUDA* to GPU* for some header files | Deven Desai | 2018-07-11 |
| | | |||
| * | merging updates from upstream | Deven Desai | 2018-07-11 |
| |\ | |/ |/| | |||
* | | Optimize extraction of Q in SparseQR by exploiting the structure of the ↵ | Gael Guennebaud | 2018-07-11 |
| | | | | | | | | identity matrix. | ||
* | | Add internall::is_identity compile-time helper | Gael Guennebaud | 2018-07-11 |
| | | |||
* | | Fix conversion warning | Gael Guennebaud | 2018-07-10 |
| | | |||
* | | bug #1543: improve linear indexing for general block expressions | Gael Guennebaud | 2018-07-10 |
| | | |||
* | | Introduce the macro ei_declare_local_nested_eval to help allocating on the ↵ | Gael Guennebaud | 2018-07-09 |
| | | | | | | | | | | | | stack local temporaries via alloca, and let outer-products makes a good use of it. If successful, we should use it everywhere nested_eval is used to declare local dense temporaries. | ||
* | | bug #1567: add optimized path for tensor broadcasting and 'Channel First' shape | Gael Guennebaud | 2018-07-09 |
| | | |||
* | | Skip null numerators in triangular-vector-solve (as in BLAS TRSV). | Gael Guennebaud | 2018-07-09 |
| | | |||
* | | Fix legitimate "declaration shadows a typedef" warning | Gael Guennebaud | 2018-07-09 |
| | | |||
| * | merging from master | Deven Desai | 2018-06-20 |
| |\ | |||
| * | | merging the CUDA and HIP implementation for the Tensor directory and the ↵ | Deven Desai | 2018-06-20 |
| | | | | | | | | | | | | unit tests | ||
| * | | removing the *Hip files from the unsupported/Eigen/CXX11/src/Tensor and ↵ | Deven Desai | 2018-06-20 |
| | | | | | | | | | | | | unsupported/test directories | ||
| * | | renaming *Cuda files to *Gpu in the unsupported/Eigen/CXX11/src/Tensor and ↵ | Deven Desai | 2018-06-20 |
| | | | | | | | | | | | | unsupported/test directories | ||
| | * | Merged eigen/eigen into default | Deven Desai | 2018-06-20 |
| |/| | |||
* | | | Fix the Packet16h version of ptranspose | Mark D Ryan | 2018-06-16 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The AVX512 version of ptranpose for PacketBlock<Packet16h,16> was reordering the PacketBlock argument incorrectly. This lead to errors in the multiplication of matrices composed of 16 bit floats on AVX512 machines, if at least of the matrices was using RowMajor order. This error is responsible for one tensorflow unit test failure on AVX512 machines: //tensorflow/python/kernel_tests:batch_matmul_op_test | ||
* | | | Fix a few issues with Packet16h | Gael Guennebaud | 2018-07-07 |
| | | | |||
* | | | complete implementation of Packet16h (AVX512) | Gael Guennebaud | 2018-07-06 |
| | | |