aboutsummaryrefslogtreecommitdiffhomepage
path: root/unsupported/Eigen/src/SpecialFunctions
Commit message (Collapse)AuthorAge
* Return nan at poles of polygamma, digamma, and zeta if limit is not definedGravatar frgossen2021-02-19
|
* Fix bad NEON fp16 checkGravatar Antonio Sanchez2020-12-04
|
* Special function implementations for half/bfloat16 packets.Gravatar Antonio Sanchez2020-12-04
| | | | | | | | | | | | | Current implementations fail to consider half-float packets, only half-float scalars. Added specializations for packets on AVX, AVX512 and NEON. Added tests to `special_packetmath`. The current `special_functions` tests would fail for half and bfloat16 due to lack of precision. The NEON tests also fail with precision issues and due to different handling of `sqrt(inf)`, so special functions bessel, ndtri have been disabled. Tested with AVX, AVX512.
* Add EIGEN prefix for HAS_LGAMMA_RGravatar David Tellenbach2020-10-08
|
* Use lgamma_r if it is available (update check for glibc 2.19+)Gravatar Eugene Zhulenev2020-10-08
|
* Support BFloat16 in EigenGravatar Teng Lu2020-06-20
|
* fix hip-clang compilation due to new HIP scalar accessorGravatar Jeff Daily2020-01-20
|
* Fix for HIP breakage - 200115. Adding a missing EIGEN_DEVICE_FUNC attrGravatar Deven Desai2020-01-16
|
* Ensure Igamma does not NaN or Inf for large values.Gravatar Srinivas Vasudevan2020-01-14
|
* fix compilation due to new HIP scalar accessorGravatar Jeff Daily2019-12-17
|
* bug #1747: one more fix for MSVC regarding the Bessel implementation.Gravatar Gael Guennebaud2019-11-15
|
* bug #1747: fix compilation with MSVCGravatar Gael Guennebaud2019-10-14
|
* Use "pdiv" rather than operator/ to support packet types.Gravatar Rasmus Munk Larsen2019-10-04
|
* Move implementation of vectorized error function erf() to ↵Gravatar Rasmus Munk Larsen2019-09-27
| | | | SpecialFunctionsImpl.h.
* Fix for the HIP build+test errors.Gravatar Deven Desai2019-09-25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The errors were introduced by this commit : https://bitbucket.org/eigen/eigen/commits/d38e6fbc27abe0c354ffe90928f6741c378e76e1 After the above mentioned commit, some of the tests started failing with the following error ``` Building HIPCC object unsupported/test/CMakeFiles/cxx11_tensor_reduction_gpu_5.dir/cxx11_tensor_reduction_gpu_5_generated_cxx11_tensor_reduction_gpu.cu.o In file included from /home/rocm-user/eigen/unsupported/test/cxx11_tensor_reduction_gpu.cu:16: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/Tensor:29: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/../SpecialFunctions:70: /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/SpecialFunctionsHalf.h:28:22: error: call to 'erf' is ambiguous return Eigen::half(Eigen::numext::erf(static_cast<float>(a))); ^~~~~~~~~~~~~~~~~~ /home/rocm-user/eigen/unsupported/test/../../Eigen/src/Core/MathFunctions.h:1600:7: note: candidate function [with T = float] float erf(const float &x) { return ::erff(x); } ^ /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/SpecialFunctionsImpl.h:1897:5: note: candidate function [with Scalar = float] erf(const Scalar& x) { ^ In file included from /home/rocm-user/eigen/unsupported/test/cxx11_tensor_reduction_gpu.cu:16: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/Tensor:29: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/../SpecialFunctions:75: /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/arch/GPU/GpuSpecialFunctions.h:87:23: error: call to 'erf' is ambiguous return make_double2(erf(a.x), erf(a.y)); ^~~ /home/rocm-user/eigen/unsupported/test/../../Eigen/src/Core/MathFunctions.h:1603:8: note: candidate function [with T = double] double erf(const double &x) { return ::erf(x); } ^ /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/SpecialFunctionsImpl.h:1897:5: note: candidate function [with Scalar = double] erf(const Scalar& x) { ^ In file included from /home/rocm-user/eigen/unsupported/test/cxx11_tensor_reduction_gpu.cu:16: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/Tensor:29: In file included from /home/rocm-user/eigen/unsupported/Eigen/CXX11/../SpecialFunctions:75: /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/arch/GPU/GpuSpecialFunctions.h:87:33: error: call to 'erf' is ambiguous return make_double2(erf(a.x), erf(a.y)); ^~~ /home/rocm-user/eigen/unsupported/test/../../Eigen/src/Core/MathFunctions.h:1603:8: note: candidate function [with T = double] double erf(const double &x) { return ::erf(x); } ^ /home/rocm-user/eigen/unsupported/Eigen/CXX11/../src/SpecialFunctions/SpecialFunctionsImpl.h:1897:5: note: candidate function [with Scalar = double] erf(const Scalar& x) { ^ 3 errors generated. ``` This PR fixes the compile error by removing the "old" implementation for "erf" (assuming that the "new" implementation is what we want going forward. from a GPU point-of-view both implementations are the same). This PR also fixes what seems like a cut-n-paste error in the aforementioned commit
* Merged in rmlarsen/eigen (pull request PR-704)Gravatar Rasmus Larsen2019-09-24
|\ | | | | | | Add generic PacketMath implementation of the Error Function (erf).
| * Add TODO to cleanup FMA cost modelling.Gravatar Rasmus Munk Larsen2019-09-24
| |
* | Fix implicit conversion warnings and use pnegate to negate packetsGravatar Christoph Hertzberg2019-09-23
| |
| * Add generic PacketMath implementation of the Error Function (erf).Gravatar Rasmus Munk Larsen2019-09-19
|/
* Merging eigen/eigen.Gravatar Srinivas Vasudevan2019-09-16
|\
* | Add Bessel functions to SpecialFunctions.Gravatar Srinivas Vasudevan2019-09-14
|/ | | | | | | | | - Split SpecialFunctions files in to a separate BesselFunctions file. In particular add: - Modified bessel functions of the second kind k0, k1, k0e, k1e - Bessel functions of the first kind j0, j1 - Bessel functions of the second kind y0, y1
* Add packetized versions of i0e and i1e special functions.Gravatar Srinivas Vasudevan2019-09-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - In particular refactor the i0e and i1e code so scalar and vectorized path share code. - Move chebevl to GenericPacketMathFunctions. A brief benchmark with building Eigen with FMA, AVX and AVX2 flags Before: CPU: Intel Haswell with HyperThreading (6 cores) Benchmark Time(ns) CPU(ns) Iterations ----------------------------------------------------------------- BM_eigen_i0e_double/1 57.3 57.3 10000000 BM_eigen_i0e_double/8 398 398 1748554 BM_eigen_i0e_double/64 3184 3184 218961 BM_eigen_i0e_double/512 25579 25579 27330 BM_eigen_i0e_double/4k 205043 205042 3418 BM_eigen_i0e_double/32k 1646038 1646176 422 BM_eigen_i0e_double/256k 13180959 13182613 53 BM_eigen_i0e_double/1M 52684617 52706132 10 BM_eigen_i0e_float/1 28.4 28.4 24636711 BM_eigen_i0e_float/8 75.7 75.7 9207634 BM_eigen_i0e_float/64 512 512 1000000 BM_eigen_i0e_float/512 4194 4194 166359 BM_eigen_i0e_float/4k 32756 32761 21373 BM_eigen_i0e_float/32k 261133 261153 2678 BM_eigen_i0e_float/256k 2087938 2088231 333 BM_eigen_i0e_float/1M 8380409 8381234 84 BM_eigen_i1e_double/1 56.3 56.3 10000000 BM_eigen_i1e_double/8 397 397 1772376 BM_eigen_i1e_double/64 3114 3115 223881 BM_eigen_i1e_double/512 25358 25361 27761 BM_eigen_i1e_double/4k 203543 203593 3462 BM_eigen_i1e_double/32k 1613649 1613803 428 BM_eigen_i1e_double/256k 12910625 12910374 54 BM_eigen_i1e_double/1M 51723824 51723991 10 BM_eigen_i1e_float/1 28.3 28.3 24683049 BM_eigen_i1e_float/8 74.8 74.9 9366216 BM_eigen_i1e_float/64 505 505 1000000 BM_eigen_i1e_float/512 4068 4068 171690 BM_eigen_i1e_float/4k 31803 31806 21948 BM_eigen_i1e_float/32k 253637 253692 2763 BM_eigen_i1e_float/256k 2019711 2019918 346 BM_eigen_i1e_float/1M 8238681 8238713 86 After: CPU: Intel Haswell with HyperThreading (6 cores) Benchmark Time(ns) CPU(ns) Iterations ----------------------------------------------------------------- BM_eigen_i0e_double/1 15.8 15.8 44097476 BM_eigen_i0e_double/8 99.3 99.3 7014884 BM_eigen_i0e_double/64 777 777 886612 BM_eigen_i0e_double/512 6180 6181 100000 BM_eigen_i0e_double/4k 48136 48140 14678 BM_eigen_i0e_double/32k 385936 385943 1801 BM_eigen_i0e_double/256k 3293324 3293551 228 BM_eigen_i0e_double/1M 12423600 12424458 57 BM_eigen_i0e_float/1 16.3 16.3 43038042 BM_eigen_i0e_float/8 30.1 30.1 23456931 BM_eigen_i0e_float/64 169 169 4132875 BM_eigen_i0e_float/512 1338 1339 516860 BM_eigen_i0e_float/4k 10191 10191 68513 BM_eigen_i0e_float/32k 81338 81337 8531 BM_eigen_i0e_float/256k 651807 651984 1000 BM_eigen_i0e_float/1M 2633821 2634187 268 BM_eigen_i1e_double/1 16.2 16.2 42352499 BM_eigen_i1e_double/8 110 110 6316524 BM_eigen_i1e_double/64 822 822 851065 BM_eigen_i1e_double/512 6480 6481 100000 BM_eigen_i1e_double/4k 51843 51843 10000 BM_eigen_i1e_double/32k 414854 414852 1680 BM_eigen_i1e_double/256k 3320001 3320568 212 BM_eigen_i1e_double/1M 13442795 13442391 53 BM_eigen_i1e_float/1 17.6 17.6 41025735 BM_eigen_i1e_float/8 35.5 35.5 19597891 BM_eigen_i1e_float/64 240 240 2924237 BM_eigen_i1e_float/512 1424 1424 485953 BM_eigen_i1e_float/4k 10722 10723 65162 BM_eigen_i1e_float/32k 86286 86297 8048 BM_eigen_i1e_float/256k 691821 691868 1000 BM_eigen_i1e_float/1M 2777336 2777747 256 This shows anywhere from a 50% to 75% improvement on these operations. I've also benchmarked without any of these flags turned on, and got similar performance to before (if not better). Also tested packetmath.cpp + special_functions to ensure no regressions.
* Fix for the HIP build+test errors introduced by the ndtri support.Gravatar Deven Desai2019-09-06
| | | | | | | The fixes needed are * adding EIGEN_DEVICE_FUNC attribute to a couple of funcs (else HIPCC will error out when non-device funcs are called from global/device funcs) * switching to using ::<math_func> instead std::<math_func> (only for HIPCC) in cases where the std::<math_func> is not recognized as a device func by HIPCC * removing an errant "j" from a testcase (don't know how that made it in to begin with!)
* PR 681: Add ndtri function, the inverse of the normal distribution function.Gravatar Srinivas Vasudevan2019-08-12
|
* [SYCL] :Gravatar Mehdi Goli2019-07-01
| | | | | | | * Modifying TensorDeviceSYCL to use `EIGEN_THROW_X`. * Modifying TensorMacro to use `EIGEN_TRY/CATCH(X)` macro. * Modifying TensorReverse.h to use `EIGEN_DEVICE_REF` instead of `&`. * Fixing the SYCL device macro in SpecialFunctionsImpl.h.
* Fix doxygen warnings to enable statis code analysisGravatar Eugene Zhulenev2019-04-24
|
* Creating separate SYCL required PR for uncontroversial files.Gravatar Mehdi Goli2018-08-03
|
* Converting ad-hoc inline keyword to EIGEN_STRONG_INLINE MACRO.Gravatar Mehdi Goli2018-08-01
|
* Remove clang warningGravatar Gael Guennebaud2018-07-13
|
* Updates corresponding to the latest round of PR feedbackGravatar Deven Desai2018-07-11
| | | | | | | | | | | | | | The major changes are 1. Moving CUDA/PacketMath.h to GPU/PacketMath.h 2. Moving CUDA/MathFunctions.h to GPU/MathFunction.h 3. Moving CUDA/CudaSpecialFunctions.h to GPU/GpuSpecialFunctions.h The above three changes effectively enable the Eigen "Packet" layer for the HIP platform 4. Merging the "hip_basic" and "cuda_basic" unit tests into one ("gpu_basic") 5. Updating the "EIGEN_DEVICE_FUNC" marking in some places The change has been tested on the HIP and CUDA platforms.
* renaming CUDA* to GPU* for some header filesGravatar Deven Desai2018-07-11
|
* updates based on PR feedbackGravatar Deven Desai2018-06-14
| | | | | | | | | | | | | | | | | There are two major changes (and a few minor ones which are not listed here...see PR discussion for details) 1. Eigen::half implementations for HIP and CUDA have been merged. This means that - `CUDA/Half.h` and `HIP/hcc/Half.h` got merged to a new file `GPU/Half.h` - `CUDA/PacketMathHalf.h` and `HIP/hcc/PacketMathHalf.h` got merged to a new file `GPU/PacketMathHalf.h` - `CUDA/TypeCasting.h` and `HIP/hcc/TypeCasting.h` got merged to a new file `GPU/TypeCasting.h` After this change the `HIP/hcc` directory only contains one file `math_constants.h`. That will go away too once that file becomes a part of the HIP install. 2. new macros EIGEN_GPUCC, EIGEN_GPU_COMPILE_PHASE and EIGEN_HAS_GPU_FP16 have been added and the code has been updated to use them where appropriate. - `EIGEN_GPUCC` is the same as `(EIGEN_CUDACC || EIGEN_HIPCC)` - `EIGEN_GPU_DEVICE_COMPILE` is the same as `(EIGEN_CUDA_ARCH || EIGEN_HIP_DEVICE_COMPILE)` - `EIGEN_HAS_GPU_FP16` is the same as `(EIGEN_HAS_CUDA_FP16 or EIGEN_HAS_HIP_FP16)`
* syncing this fork with upstreamGravatar Deven Desai2018-06-13
|\
| * Merge from eigen/eigenGravatar Michael Figurnov2018-06-07
| |\
| | * Fix compilation of special functions without C99 math.Gravatar Michael Figurnov2018-06-07
| | | | | | | | | | | | | | | | | | The commit with Bessel functions i0e and i1e placed the ifdef/endif incorrectly, causing i0e/i1e to be undefined when EIGEN_HAS_C99_MATH=0. These functions do not actually require C99 math, so now they are always available.
| * | Updated the stopping criteria in igammac_cf_impl.Gravatar Michael Figurnov2018-06-07
| | | | | | | | | | | | Previously, when computing the derivative, it used a relative error threshold. Now it uses an absolute error threshold. The behavior for computing the value is unchanged. This makes more sense since we do not expect the derivative to often be close to zero. This change makes the derivatives about 30% faster across the board. The error for the igamma_der_a is almost unchanged, while for gamma_sample_der_alpha it is a bit worse for float32 and unchanged for float64.
| * | Derivative of the incomplete Gamma function and the sample of a Gamma random ↵Gravatar Michael Figurnov2018-06-06
| |/ | | | | | | | | | | | | | | | | | | variable. In addition to igamma(a, x), this code implements: * igamma_der_a(a, x) = d igamma(a, x) / da -- derivative of igamma with respect to the parameter * gamma_sample_der_alpha(alpha, sample) -- reparameterization derivative of a Gamma(alpha, 1) random variable sample with respect to the alpha parameter The derivatives are computed by forward mode differentiation of the igamma(a, x) code. Although gamma_sample_der_alpha can be implemented via igamma_der_a, a separate function is more accurate and efficient due to analytical cancellation of some terms. All three functions are implemented by a method parameterized with "mode" that always computes the derivatives, but does not return them unless required by the mode. The compiler is expected to (and, based on benchmarks, does) skip the unnecessary computations depending on the mode.
* / Adding support for using Eigen in HIP kernels.Gravatar Deven Desai2018-06-06
|/ | | | | | | | | This commit enables the use of Eigen on HIP kernels / AMD GPUs. Support has been added along the same lines as what already exists for using Eigen in CUDA kernels / NVidia GPUs. Application code needs to explicitly define EIGEN_USE_HIP when using Eigen in HIP kernels. This is because some of the CUDA headers get picked up by default during Eigen compile (irrespective of whether or not the underlying compiler is CUDACC/NVCC, for e.g. Eigen/src/Core/arch/CUDA/Half.h). In order to maintain this behavior, the EIGEN_USE_HIP macro is used to switch to using the HIP version of those header files (see Eigen/Core and unsupported/Eigen/CXX11/Tensor) Use the "-DEIGEN_TEST_HIP" cmake option to enable the HIP specific unit tests.
* Exponentially scaled modified Bessel functions of order zero and one.Gravatar Michael Figurnov2018-05-31
| | | | | | The functions are conventionally called i0e and i1e. The exponentially scaled version is more numerically stable. The standard Bessel functions can be obtained as i0(x) = exp(|x|) i0e(x) The code is ported from Cephes and tested against SciPy.
* protect calls to isnanGravatar Gael Guennebaud2018-04-03
|
* Improve robustness of igamma and igammac to bad inputs.Gravatar Rasmus Munk Larsen2018-03-19
| | | | | | Check for nan inputs and propagate them immediately. Limit the number of internal iterations to 2000 (same number as used by scipy.special.gammainc). This prevents an infinite loop when the function is called with nan or very large arguments. Original change by mfirgunov@google.com
* Add a EIGEN_NO_CUDA option, and introduce EIGEN_CUDACC and EIGEN_CUDA_ARCH ↵Gravatar Gael Guennebaud2017-07-17
| | | | aliases
* Fixed compilation warningsGravatar Benoit Steiner2016-11-26
|
* Don't call lgamma_r when compiling for an Apple device, since the function ↵Gravatar Benoit Steiner2016-11-02
| | | | isn't available on MacOS
* Don't attempts to use lgamma_r for CUDA devices.Gravatar Rasmus Munk Larsen2016-11-01
| | | | Fix type in lgamma_impl<double>.
* Use threadsafe versions of lgamma and lgammaf if possible.Gravatar Rasmus Munk Larsen2016-10-27
|
* bug #1167: simplify installation of header files using cmake's ↵Gravatar Gael Guennebaud2016-08-29
| | | | install(DIRECTORY ...) command.
* std::erfcf doesn't exist: use numext::erfc insteadGravatar Benoit Steiner2016-08-11
|
* Move CUDA's special functions to SpecialFunctions module.Gravatar Gael Guennebaud2016-07-11
|
* bug #1232: refactor special functions as a new SpecialFunctions module, ↵Gravatar Gael Guennebaud2016-07-08
currently in unsupported/.
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-02 03:52:18 +0000