aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Expand)AuthorAge
* Improved support for integer moduloGravatar Benoit Steiner2016-03-25
* Improved the cost estimate of the quotient opGravatar Benoit Steiner2016-03-25
* Started to model the cost of divisions more accurately.Gravatar Benoit Steiner2016-03-25
* Fixed compilation error on windowsGravatar Benoit Steiner2016-03-24
* Updated the benchmarking code to use Eigen::half instead of halfGravatar Benoit Steiner2016-03-24
* Made sure that the cxx11_tensor_cuda test can be compiled even without suppor...Gravatar Benoit Steiner2016-03-23
* Use numext::abs instead of abs to avoid incorrect conversion to integer of th...Gravatar Benoit Steiner2016-03-23
* Avoid unnecessary conversionsGravatar Benoit Steiner2016-03-23
* Fixed compilation warningGravatar Benoit Steiner2016-03-23
* Use portable includesGravatar Benoit Steiner2016-03-23
* Added commentGravatar Benoit Steiner2016-03-23
* Removed executable bit from header filesGravatar Benoit Steiner2016-03-23
* Removed executable bit from header filesGravatar Benoit Steiner2016-03-23
* Fixed contractions of fp16Gravatar Benoit Steiner2016-03-23
* Made the tensor benchmarks compile on MacOSGravatar Benoit Steiner2016-03-23
* Added a test to verify that notifications are working properlyGravatar Benoit Steiner2016-03-23
* Made type conversion explicitGravatar Benoit Steiner2016-03-23
* Added the ability to divide a half float by an indexGravatar Benoit Steiner2016-03-23
* Added more conversion operators for half floatsGravatar Benoit Steiner2016-03-23
* Replace all M_PI by EIGEN_PI and add a check to the testsuite.Gravatar Christoph Hertzberg2016-03-23
* Merged patch 672 from Justin Lebar: Don't use long doubles with cudaGravatar Benoit Steiner2016-03-22
* Fixed compilation errorGravatar Benoit Steiner2016-03-22
* Pulled latest updates from trunkGravatar Benoit Steiner2016-03-22
|\
* | Use a single Barrier instead of a collection of Notifications to reduce the t...Gravatar Benoit Steiner2016-03-22
| * Fixed a couple of typosGravatar Benoit Steiner2016-03-22
| * Filter some compilation flags that nvcc warns about.Gravatar Benoit Steiner2016-03-22
| * Avoid using std::vector whenever possibleGravatar Benoit Steiner2016-03-22
|/
* Use an enum instead of a static const int to prevent possible link errorGravatar Benoit Steiner2016-03-22
* Fixed contractions of 16 bit floatsGravatar Benoit Steiner2016-03-22
* Worked around a constness related issueGravatar Benoit Steiner2016-03-21
* Small cleanupGravatar Benoit Steiner2016-03-21
* Marked variables that's only used in debug mode as suchGravatar Benoit Steiner2016-03-21
* Explicitly cast the default value into the proper scalar type.Gravatar Benoit Steiner2016-03-21
* bug #1178: Simplified modification of the SSE control register for better por...Gravatar Christoph Hertzberg2016-03-20
* Renamed some class members to make the code more readable.Gravatar Benoit Steiner2016-03-18
* Fixed a bug in the padding of extracted image patches.Gravatar Benoit Steiner2016-03-18
* Completed the implementation of vectorized type casting of half floats.Gravatar Benoit Steiner2016-03-18
* Make all the conversions explicitGravatar Benoit Steiner2016-03-18
* Gate all the CUDA tests under the EIGEN_TEST_NVCC optionGravatar Benoit Steiner2016-03-18
* Fixed a typoGravatar Benoit Steiner2016-03-18
* Added a test to validate the fallback path for half floatsGravatar Benoit Steiner2016-03-18
* Worked around constness issueGravatar Benoit Steiner2016-03-18
* Fixed compilation warningGravatar Benoit Steiner2016-03-18
* Fixed compilation warnings in the cuda testsGravatar Benoit Steiner2016-03-18
* pulled latest updates from trunkGravatar Benoit Steiner2016-03-17
|\
* | Avoid mutable class members when possibleGravatar Benoit Steiner2016-03-17
* | Implemented some of the missing type casting for half floatsGravatar Benoit Steiner2016-03-17
| * Made sure to use the hard abi when compiling with NEON instructions to avoid ...Gravatar Benoit Steiner2016-03-17
|/
* Allocate the mersenne twister used by the random number generators on the hea...Gravatar Benoit Steiner2016-03-17
* Fix bug in tensor contraction. The code assumes that contraction axis indices...Gravatar Benoit Steiner2016-03-17
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-25 06:20:08 +0000