aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported
Commit message (Collapse)AuthorAge
* Added the ability to query the minor version of a cuda deviceGravatar Benoit Steiner2016-02-19
|
* Started to work on contractions and reductions using half floatsGravatar Benoit Steiner2016-02-19
|
* Don't make the array constructors explicitGravatar Benoit Steiner2016-02-19
|
* Fixed a bug in the tensor type converterGravatar Benoit Steiner2016-02-19
|
* Added support for simple coefficient wise tensor expression using half ↵Gravatar Benoit Steiner2016-02-19
| | | | floats on CUDA devices
* FP16 on CUDA are only available starting with cuda 7.5. Disable them when ↵Gravatar Benoit Steiner2016-02-18
| | | | using an older version of CUDA
* Added regression test for float16Gravatar Benoit Steiner2016-02-19
|
* Reverted unintended changes introduced by a bad mergeGravatar Benoit Steiner2016-02-19
|
* Added preliminary support for half floats on CUDA GPU. For now we can simply ↵Gravatar Benoit Steiner2016-02-19
| | | | convert floats into half floats and vice versa
* Deleted outdated commentGravatar Benoit Steiner2016-02-11
|
* Added a method to conjugate the content of a tensor or the result of a ↵Gravatar Benoit Steiner2016-02-11
| | | | tensor expression.
* Worked around a few clang compilation warningsGravatar Benoit Steiner2016-02-10
|
* Fixed clang comilation warningsGravatar Benoit Steiner2016-02-10
|
* Fixed some clang compilation warningsGravatar Benoit Steiner2016-02-09
|
* Fixed compilation warningGravatar Benoit Steiner2016-02-09
|
* Updated the TensorIntDivisor code to work properly on LLP64 systemsGravatar Benoit Steiner2016-02-08
|
* Avoid unecessary type conversionsGravatar Benoit Steiner2016-02-05
|
* Only enable the cxx11_tensor_uint128 test on 64 bit machines since 32 bit ↵Gravatar Benoit Steiner2016-02-05
| | | | systems don't support the __uin128_t type
* Made the tensor fft test compile on tegra x1Gravatar Benoit Steiner2016-02-06
|
* Added support for vectorized type casting of int to char.Gravatar Benoit Steiner2016-02-03
|
* Fixed the initialization of the dummy member of the array class to make it ↵Gravatar Benoit Steiner2016-02-03
| | | | compatible with pairs of element.
* Made sure the dummy element of size 0 array is always intialized to silence ↵Gravatar Benoit Steiner2016-02-03
| | | | some compiler warnings
* Properly disable nvcc warning messages in user code.Gravatar Benoit Steiner2016-02-03
|
* Silenced the "calling a __host__ function from a __host__ __device__ ↵Gravatar Benoit Steiner2016-02-03
| | | | function is not allowed" messages
* Merged in ville-k/eigen/explicit_long_constructors (pull request PR-158)Gravatar Benoit Steiner2016-02-02
|\ | | | | | | Add constructor for long types.
| * Use EIGEN_STATIC_ASSERT for backward compatibility.Gravatar Ville Kallioniemi2016-02-02
| |
* | Don't try to use direct offsets when computing a tensor product, since the ↵Gravatar Benoit Steiner2016-02-02
| | | | | | | | required stride isn't available.
| * Replace separate low word constructors with a single templated constructor.Gravatar Ville Kallioniemi2016-02-01
| |
| * Rebase to latest.Gravatar Ville Kallioniemi2016-02-01
| |\ | |/ |/|
* | Cleaned up a tensor contraction testGravatar Benoit Steiner2016-02-01
| |
* | Sharded the cxx11_tensor_contract_cuda testGravatar Benoit Steiner2016-02-01
| |
* | Silenced a few compilation warningsGravatar Benoit Steiner2016-02-01
| |
* | Made it possible to limit the number of blocks that will be used to evaluate ↵Gravatar Benoit Steiner2016-02-01
| | | | | | | | a tensor expression on a CUDA device. This makesit possible to set aside streaming multiprocessors for other computations.
* | Shared the tensor reduction testGravatar Benoit Steiner2016-02-01
| |
* | Sharded the tensor device testGravatar Benoit Steiner2016-02-01
| |
* | Fixed a number of compilation warnings generated by the cuda testsGravatar Benoit Steiner2016-01-31
| |
* | Fixed a few compilation warningsGravatar Benoit Steiner2016-01-31
| |
* | Sharded the CUDA argmax tensor testGravatar Benoit Steiner2016-01-31
| |
* | Fixed a few memory leaks in the cuda testsGravatar Benoit Steiner2016-01-30
| |
* | Sharded the cxx11_tensor_cuda test and fixed a memory leakGravatar Benoit Steiner2016-01-30
| |
* | Added a test to cover threaded tensor shufflingGravatar Benoit Steiner2016-01-30
| |
* | Made the comparison between single and multithreaded contraction results ↵Gravatar Benoit Steiner2016-01-30
| | | | | | | | more resistant to numerical noise to prevent spurious test failures.
* | Made sure to use a tensor of rank 0 to store the result of a full reduction ↵Gravatar Benoit Steiner2016-01-30
| | | | | | | | in the tensor thread pool test
* | Sharded the tensor thread pool testGravatar Benoit Steiner2016-01-30
| |
* | Made the CUDA contract test more robust to numerical noise.Gravatar Benoit Steiner2016-01-30
| |
* | Marked several methods EIGEN_DEVICE_FUNCGravatar Benoit Steiner2016-01-28
| |
* | Fixed a couple of compilation warnings.Gravatar Benoit Steiner2016-01-28
| |
* | Made sure to call nvcc with the relaxed-constexpr flag.Gravatar Benoit Steiner2016-01-28
| |
* | mergeGravatar Gael Guennebaud2016-01-28
|\ \
* | | Fix unit test filename.Gravatar Gael Guennebaud2016-01-28
| | |
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-30 01:47:45 +0000