aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* 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
|\
* | Fix startRow()/startCol() for dense Block with direct access:Gravatar Gael Guennebaud2016-02-23
| | | | | | | | the initial implementation failed for empty rows/columns for which are ambiguous.
| * Updated the padding code to work with half floatsGravatar Benoit Steiner2016-02-23
| |
| * Extended the tensor benchmark suite to support types other than floatsGravatar Benoit Steiner2016-02-23
| |
| * Updated the tensor benchmarking code to work with compilers that don't ↵Gravatar Benoit Steiner2016-02-23
| | | | | | | | support cxx11.
| * Deleted the coordinate based evaluation of tensor expressions, since it's ↵Gravatar Benoit Steiner2016-02-22
| | | | | | | | hardly ever used and started to cause some issues with some versions of xcode.
| * Declare the half float type as arithmetic.Gravatar Benoit Steiner2016-02-22
| |
| * include <iostream> in the tensor header since we now use it to better report ↵Gravatar Benoit Steiner2016-02-22
| | | | | | | | cuda initialization errors
| * Fixed compilation warning generated by clangGravatar Benoit Steiner2016-02-21
| |
| * Implemented the ptranspose function on half floatsGravatar Benoit Steiner2016-02-21
| |
| * Pulled latest updates from trunkGravatar Benoit Steiner2016-02-21
| |\
| * | Added the ability to compute the absolute value of a half floatGravatar Benoit Steiner2016-02-21
| | |
| | * Added some debugging information to the test to figure out why it fails ↵Gravatar Benoit Steiner2016-02-21
| | | | | | | | | | | | sometimes
| | * Optimized casting of tensors in the case where the casting happens to be a no-opGravatar Benoit Steiner2016-02-21
| |/
| * Prevent unecessary Index to int conversionsGravatar Benoit Steiner2016-02-21
|/
* Moved some of the fp16 operators outside the Eigen namespace to workaround ↵Gravatar Benoit Steiner2016-02-20
| | | | some nvcc limitations.
* Fixed the float16 tensor test.Gravatar Benoit Steiner2016-02-20
|
* Get rid of duplicate code.Gravatar Rasmus Munk Larsen2016-02-19
|
* Speed up tensor FFT by up ~25-50%.Gravatar Rasmus Munk Larsen2016-02-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Benchmark Base (ns) New (ns) Improvement ------------------------------------------------------------------ BM_tensor_fft_single_1D_cpu/8 132 134 -1.5% BM_tensor_fft_single_1D_cpu/9 1162 1229 -5.8% BM_tensor_fft_single_1D_cpu/16 199 195 +2.0% BM_tensor_fft_single_1D_cpu/17 2587 2267 +12.4% BM_tensor_fft_single_1D_cpu/32 373 341 +8.6% BM_tensor_fft_single_1D_cpu/33 5922 4879 +17.6% BM_tensor_fft_single_1D_cpu/64 797 675 +15.3% BM_tensor_fft_single_1D_cpu/65 13580 10481 +22.8% BM_tensor_fft_single_1D_cpu/128 1753 1375 +21.6% BM_tensor_fft_single_1D_cpu/129 31426 22789 +27.5% BM_tensor_fft_single_1D_cpu/256 4005 3008 +24.9% BM_tensor_fft_single_1D_cpu/257 70910 49549 +30.1% BM_tensor_fft_single_1D_cpu/512 8989 6524 +27.4% BM_tensor_fft_single_1D_cpu/513 165402 107751 +34.9% BM_tensor_fft_single_1D_cpu/999 198293 115909 +41.5% BM_tensor_fft_single_1D_cpu/1ki 21289 14143 +33.6% BM_tensor_fft_single_1D_cpu/1k 361980 233355 +35.5% BM_tensor_fft_double_1D_cpu/8 138 131 +5.1% BM_tensor_fft_double_1D_cpu/9 1253 1133 +9.6% BM_tensor_fft_double_1D_cpu/16 218 200 +8.3% BM_tensor_fft_double_1D_cpu/17 2770 2392 +13.6% BM_tensor_fft_double_1D_cpu/32 406 368 +9.4% BM_tensor_fft_double_1D_cpu/33 6418 5153 +19.7% BM_tensor_fft_double_1D_cpu/64 856 728 +15.0% BM_tensor_fft_double_1D_cpu/65 14666 11148 +24.0% BM_tensor_fft_double_1D_cpu/128 1913 1502 +21.5% BM_tensor_fft_double_1D_cpu/129 36414 24072 +33.9% BM_tensor_fft_double_1D_cpu/256 4226 3216 +23.9% BM_tensor_fft_double_1D_cpu/257 86638 52059 +39.9% BM_tensor_fft_double_1D_cpu/512 9397 6939 +26.2% BM_tensor_fft_double_1D_cpu/513 203208 114090 +43.9% BM_tensor_fft_double_1D_cpu/999 237841 125583 +47.2% BM_tensor_fft_double_1D_cpu/1ki 20921 15392 +26.4% BM_tensor_fft_double_1D_cpu/1k 455183 250763 +44.9% BM_tensor_fft_single_2D_cpu/8 1051 1005 +4.4% BM_tensor_fft_single_2D_cpu/9 16784 14837 +11.6% BM_tensor_fft_single_2D_cpu/16 4074 3772 +7.4% BM_tensor_fft_single_2D_cpu/17 75802 63884 +15.7% BM_tensor_fft_single_2D_cpu/32 20580 16931 +17.7% BM_tensor_fft_single_2D_cpu/33 345798 278579 +19.4% BM_tensor_fft_single_2D_cpu/64 97548 81237 +16.7% BM_tensor_fft_single_2D_cpu/65 1592701 1227048 +23.0% BM_tensor_fft_single_2D_cpu/128 472318 384303 +18.6% BM_tensor_fft_single_2D_cpu/129 7038351 5445308 +22.6% BM_tensor_fft_single_2D_cpu/256 2309474 1850969 +19.9% BM_tensor_fft_single_2D_cpu/257 31849182 23797538 +25.3% BM_tensor_fft_single_2D_cpu/512 10395194 8077499 +22.3% BM_tensor_fft_single_2D_cpu/513 144053843 104242541 +27.6% BM_tensor_fft_single_2D_cpu/999 279885833 208389718 +25.5% BM_tensor_fft_single_2D_cpu/1ki 45967677 36070985 +21.5% BM_tensor_fft_single_2D_cpu/1k 619727095 456489500 +26.3% BM_tensor_fft_double_2D_cpu/8 1110 1016 +8.5% BM_tensor_fft_double_2D_cpu/9 17957 15768 +12.2% BM_tensor_fft_double_2D_cpu/16 4558 4000 +12.2% BM_tensor_fft_double_2D_cpu/17 79237 66901 +15.6% BM_tensor_fft_double_2D_cpu/32 21494 17699 +17.7% BM_tensor_fft_double_2D_cpu/33 357962 290357 +18.9% BM_tensor_fft_double_2D_cpu/64 105179 87435 +16.9% BM_tensor_fft_double_2D_cpu/65 1617143 1288006 +20.4% BM_tensor_fft_double_2D_cpu/128 512848 419397 +18.2% BM_tensor_fft_double_2D_cpu/129 7271322 5636884 +22.5% BM_tensor_fft_double_2D_cpu/256 2415529 1922032 +20.4% BM_tensor_fft_double_2D_cpu/257 32517952 24462177 +24.8% BM_tensor_fft_double_2D_cpu/512 10724898 8287617 +22.7% BM_tensor_fft_double_2D_cpu/513 146007419 108603266 +25.6% BM_tensor_fft_double_2D_cpu/999 296351330 221885776 +25.1% BM_tensor_fft_double_2D_cpu/1ki 59334166 48357539 +18.5% BM_tensor_fft_double_2D_cpu/1k 666660132 483840349 +27.4%
* mergeGravatar Gael Guennebaud2016-02-19
|\
* | Add COD and BDCSVD in list of benched solvers.Gravatar Gael Guennebaud2016-02-19
| |
* | Extend unit test to stress smart_copy with empty input/output.Gravatar Gael Guennebaud2016-02-19
| |
* | bug #1170: skip calls to memcpy/memmove for empty imput.Gravatar Gael Guennebaud2016-02-19
| |
| * Print an error message to stderr when the initialization of the CUDA runtime ↵Gravatar Benoit Steiner2016-02-19
| | | | | | | | fails. This helps debugging setup issues.
* | Fix nesting type and complete reflection methods of Block expressions.Gravatar Gael Guennebaud2016-02-19
| |
* | Add typedefs for the return type of all block methods.Gravatar Gael Guennebaud2016-02-19
| |
| * Updated the contraction code to make it compatible with half floats.Gravatar Benoit Steiner2016-02-19
| |
| * Added support for tensor reductions on half floatsGravatar Benoit Steiner2016-02-19
| |
| * Implemented the scalar division of 2 half floatsGravatar Benoit Steiner2016-02-19
| |
| * 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
| |
| * Added support for operators +=, -=, *= and /= on CUDA half floatsGravatar Benoit Steiner2016-02-19
| |
| * Implemented protate() for CUDAGravatar 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
| |
| * Pulled latest updates from trunkGravatar 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
| * | Improved implementation of ptanh for SSE and AVXGravatar Benoit Steiner2016-02-18
| | |
| * | Merged eigen/eigen into defaultGravatar Eugene Brevdo2016-02-17
| |\ \ | |/ / |/| |
| * | Tiny bugfix in SpecialFunctions: some compilers don't like doublesGravatar Eugene Brevdo2016-02-17
| | | | | | | | | | | | implicitly downcast to floats in an array constructor.
* | | bug #1166: fix shortcomming in gemv when the destination is not a vector at ↵Gravatar Gael Guennebaud2016-02-15
| | | | | | | | | | | | compile-time.
* | | Import wiki's paragraph: "I disabled vectorization, but I'm still getting ↵Gravatar Gael Guennebaud2016-02-12
| | | | | | | | | | | | annoyed about alignment issues"
* | | bug #795: mention allocate_shared as a condidate for aligned_allocator.Gravatar Gael Guennebaud2016-02-12
| | |
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-30 07:25:44 +0000