Commit message (Collapse) | Author | Age | |
---|---|---|---|
* | Increased the robustness of the reduction tests on fp16 | 2016-10-05 | |
| | |||
* | Increase the tolerance to numerical noise. | 2016-10-05 | |
| | |||
* | Improved support for compiling CUDA code with clang as the host compiler | 2016-10-03 | |
| | |||
* | Updated the tensor sum and mean reducer to enable them to process complex ↵ | 2016-09-28 | |
| | | | | numbers on cuda gpus. | ||
* | Don't use c++11 features and fix include. | 2016-09-20 | |
| | |||
* | Add CUDA-specific std::complex<T> specializations for scalar_sum_op, ↵ | 2016-09-20 | |
| | | | | scalar_difference_op, scalar_product_op, and scalar_quotient_op. | ||
* | Made AutoDiffJacobian more intuitive to use and updated for C++11 | 2016-09-16 | |
| | | | | | | | | | | | | Changes: * Removed unnecessary types from the Functor by inferring from its types * Removed inputs() function reference, replaced with .rows() * Updated the forward constructor to use variadic templates * Added optional parameters to the Fuctor for passing parameters, control signals, etc * Has been tested with fixed size and dynamic matricies Ammendment by chtz: overload operator() for compatibility with not fully conforming compilers | ||
* | Register the cxx11_tensor_device only for recent cuda architectures (i.e. >= ↵ | 2016-09-12 | |
| | | | | 3.0) since the test instantiate contractions that require a modern gpu. | ||
* | CUDA contractions require arch >= 3.0: don't compile the cuda contraction ↵ | 2016-09-12 | |
| | | | | tests on older architectures. | ||
* | Fixed a bug impacting some outer reductions on GPU | 2016-09-12 | |
| | |||
* | Added the ability to compute the absolute value of a complex number on GPU, ↵ | 2016-09-12 | |
| | | | | as well as a test to catch the problem. | ||
* | Merged latest updates from trunk | 2016-09-12 | |
|\ | |||
* | | Properly size the list of waiters | 2016-09-12 | |
| | | |||
| * | Fix compilation when cuda_fp16.h does not exist. | 2016-09-05 | |
| | | |||
* | | Fixed a regression test | 2016-09-02 | |
|/ | |||
* | Fix the cxx11_tensor_cuda.cu test on 32bit platforms. | 2016-09-02 | |
| | |||
* | Added a test for nullary expressions on CUDA | 2016-09-01 | |
| | | | | Also check that we can mix 64 and 32 bit indices in the same compilation unit | ||
* | Updated the contraction code to support constant inputs. | 2016-09-01 | |
| | |||
* | Fix compilation with CUDA 8 | 2016-09-01 | |
| | |||
* | merge EulerAngles module | 2016-08-30 | |
|\ | |||
* | | Include missing forward declaration of SparseMatrix | 2016-08-29 | |
| | | |||
* | | Fix compilation with cuda 8 | 2016-08-29 | |
| | | |||
* | | enable vectorization path when testing half on cuda, and add test for log1p | 2016-08-26 | |
| | | |||
* | | Merge upstream changes | 2016-08-05 | |
|\ \ | |||
| * | | Fixed cut and paste bug in debud message | 2016-08-04 | |
| | | | |||
| * | | Extended a regression test to validate that we basic fp16 support works with ↵ | 2016-08-03 | |
| | | | | | | | | | | | | cuda 7.0 | ||
| * | | Deleted redundant regression test. | 2016-08-03 | |
| | | | |||
| * | | Cleaned up the new float16 test a bit | 2016-08-03 | |
| | | | |||
| * | | Added a test for fp16 | 2016-08-03 | |
| | | | |||
| * | | bug #1264: fix compilation | 2016-07-27 | |
| | | | |||
| * | | Big 1261: add missing max(ADS,ADS) overload (same for min) | 2016-07-27 | |
| | | | |||
| * | | bug #1260: add regression test | 2016-07-27 | |
| | | | |||
| * | | bug #1260: remove doubtful specializations of ScalarBinaryOpTraits | 2016-07-27 | |
| | | | |||
| * | | Implement digits10 for mpreal | 2016-07-25 | |
| | | | |||
| * | | Improved partial reductions in more cases | 2016-07-22 | |
| | | | |||
| * | | merge | 2016-07-22 | |
| |\ \ | |||
| | * | | Fix testing of log nearby 1 | 2016-07-22 | |
| | | | | |||
| | * | | Truely split unit test. | 2016-07-22 | |
| | | | | |||
| * | | | Move half unit test from unsupported to main tests | 2016-07-22 | |
| |/ / | |||
| * | | Extend unit testing of half with ADL and arrays. | 2016-07-21 | |
| | | | |||
| * | | Manually add -stdd=c++11 to nvcc for old cmake versions | 2016-07-12 | |
| | | | |||
| * | | reverted unintended change. | 2016-07-11 | |
| | | | |||
| * | | Made the packetmath test compile again. A better fix would be to move the ↵ | 2016-07-11 | |
| | | | | | | | | | | | | special function tests to the unsupported directory where the code now resides. | ||
| * | | merge | 2016-07-11 | |
| |\ \ | |||
| | * | | Fix configuration of CUDA: | 2016-07-11 | |
| | | | | | | | | | | | | | | | | | | | | | | | | - preserve user defined CUDA_NVCC_FLAGS - remove the -ansi flag that conflicts with -std=c++11 - do not add -std=c++11 if already there | ||
| | * | | Split test_slice_in_expr which seems to be huge for visual | 2016-07-11 | |
| | | | | |||
| | * | | Fix warnings | 2016-07-08 | |
| | | | | |||
| | * | | Fix warnings | 2016-07-08 | |
| | | | | |||
| * | | | bug #1232: refactor special functions as a new SpecialFunctions module, ↵ | 2016-07-08 | |
| |/ / | | | | | | | | | | currently in unsupported/. | ||
| * | | fix compilation with c++11 | 2016-07-07 | |
| | | |