aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* Use NumTraits::highest() and NumTraits::lowest() instead of the ↵Gravatar Benoit Steiner2016-03-07
| | | | std::numeric_limits to make the tensor min and max functors more CUDA friendly.
* Added the ability to pad a tensor using a non-zero valueGravatar Benoit Steiner2016-03-07
|
* Fix a couple of typos in the code.Gravatar Benoit Steiner2016-03-07
|
* Added a test to validate the behavior of some of the tensor syntactic sugar.Gravatar Benoit Steiner2016-03-07
|
* Added missing includeGravatar Benoit Steiner2016-03-06
|
* Don't try to compile the uint128 test with compilers that don't support uint127Gravatar Benoit Steiner2016-03-06
|
* Don't warn that msvc 2015 isn't c++11 compliant just because it doesn't ↵Gravatar Benoit Steiner2016-03-06
| | | | claim to be.
* Turn on some of the cxx11 features when compiling with visual studio 2015Gravatar Benoit Steiner2016-03-05
|
* Don't test our 128bit emulation code when compiling with msvcGravatar Benoit Steiner2016-03-05
|
* Avoid using initializer lists in test since not all version of msvc support themGravatar Benoit Steiner2016-03-05
|
* Use EIGEN_PI instead of redefining our own constant PIGravatar Benoit Steiner2016-03-05
|
* Use the CMAKE_CXX_STANDARD variable to turn on cxx11Gravatar Benoit Steiner2016-03-04
|
* Don't rely on the M_PI constant since not all compilers provide it.Gravatar Benoit Steiner2016-03-04
|
* Fixed the computation of leading zeros when compiling with msvc.Gravatar Benoit Steiner2016-03-04
|
* MSVC uses __uint128 while other compilers use __uint128_t to encode 128bit ↵Gravatar Benoit Steiner2016-03-04
| | | | unsigned integers. Make the cxx11_tensor_uint128.cpp test work in both cases.
* Fixed syntax errorGravatar Benoit Steiner2016-03-04
|
* Added missing includeGravatar Benoit Steiner2016-03-04
|
* Don't use implicit type conversions in initializer lists since not all ↵Gravatar Benoit Steiner2016-03-04
| | | | compilers support them.
* Made the contraction test more portableGravatar Benoit Steiner2016-03-04
|
* Fixed a typoGravatar Benoit Steiner2016-03-04
|
* Added tests to cover the new rounding, flooring and ceiling tensor operations.Gravatar Benoit Steiner2016-03-03
|
* Added support for rounding, flooring, and ceiling to the tensor apiGravatar Benoit Steiner2016-03-03
|
* Added a test to validate the conversion of half floats into floats on Kepler ↵Gravatar Benoit Steiner2016-03-03
| | | | | | GPUs. Restricted the testing of the random number generation code to GPU architecture greater than or equal to 3.5.
* Enable partial support for half floats on Kepler GPUs.Gravatar Benoit Steiner2016-03-03
|
* Enable the conversion between floats and half floats on older GPUs that ↵Gravatar Benoit Steiner2016-03-03
| | | | support it.
* Merged in ebrevdo/eigen (pull request PR-167)Gravatar Benoit Steiner2016-03-03
|\ | | | | | | | | | | Add infinity() support to numext::numeric_limits, use it in lgamma. I tested the code on my gtx-titan-black gpu, and it appears to work as expected.
| * Small bugfix to numeric_limits for CUDA.Gravatar Eugene Brevdo2016-03-02
| |
| * Add infinity() support to numext::numeric_limits, use it in lgamma.Gravatar Eugene Brevdo2016-03-02
| | | | | | | | | | This makes the infinity access a __device__ function, removing nvcc warnings.
* | bug #537: fix compilation with Apples's compilerGravatar Gael Guennebaud2016-03-02
| |
* | Pulled latest updates from trunkGravatar Benoit Steiner2016-03-01
|\ \
| * | Compilation fixGravatar Gael Guennebaud2016-03-01
| | |
| * | Compilation fixGravatar Gael Guennebaud2016-03-01
| | |
* | | Improved the performance of large outer reductions on cudaGravatar Benoit Steiner2016-02-29
|/ /
* | Added benchmarks for full reductionGravatar Benoit Steiner2016-02-29
| |
* | Made the signature of the inner and outer reducers consistentGravatar Benoit Steiner2016-02-29
| |
* | Optimized the performance of narrow reductions on CUDA devicesGravatar Benoit Steiner2016-02-29
| |
* | Fix shortcoming in fixed-value deduction of startRow/startColGravatar Gael Guennebaud2016-02-29
| |
* | Print some information to stderr when a CUDA kernel failsGravatar Benoit Steiner2016-02-27
| |
* | Improved the READMEGravatar Benoit Steiner2016-02-27
| |
* | bug #1172: make valuePtr and innderIndexPtr properly return null for empty ↵Gravatar Gael Guennebaud2016-02-27
| | | | | | | | matrices.
* | Properly vectorized the random number generatorsGravatar Benoit Steiner2016-02-26
| |
* | Made the TensorIndexList usable on GPU without having to use the ↵Gravatar Benoit Steiner2016-02-26
| | | | | | | | -relaxed-constexpr compilation flag
* | Added benchmarks for type casting of float16Gravatar Benoit Steiner2016-02-26
| |
* | Added benchmarks for fp16Gravatar Benoit Steiner2016-02-26
| |
* | Reverted previous commit since it caused more problems than it solvedGravatar Benoit Steiner2016-02-26
| |
* | Fixed handling of long doubles on aarch64Gravatar Benoit Steiner2016-02-26
| |
* | Made the CUDA architecture level a build setting.Gravatar Benoit Steiner2016-02-25
| |
* | Fixed a typo in the reduction code that could prevent large full reductionsx ↵Gravatar Benoit Steiner2016-02-24
| | | | | | | | from running properly on old cuda devices.
* | Marked the And and Or reducers as stateless.Gravatar Benoit Steiner2016-02-24
| |
* | mergeGravatar Gael Guennebaud2016-02-23
|\ \
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-29 23:09:58 +0000