mirror/eigen
2
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-03-07 18:27:40 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,411 Commits 11 Branches 89 Tags 183 MiB
2693fd54bf
Commit Graph

4860 Commits

Author SHA1 Message Date
Konstantinos Margaritis
6ed7a7281c remove accidentally pasted code 2016-04-28 14:35:55 -03:00
Konstantinos Margaritis
62f9093b31 improve state of MathFunctions as well 2016-04-28 14:33:09 -03:00
Konstantinos Margaritis
8ed26120c8 bring Altivec/VSX to a better state, implement some of the missing functions 2016-04-28 14:32:42 -03:00
Konstantinos Margaritis
950158f6d1 add name to copyrights 2016-04-28 14:32:11 -03:00
Konstantinos Margaritis
ee0459300b minor fix, add to copyright 2016-04-28 14:31:21 -03:00
Benoit Steiner
2b917291d9 Merged in rmlarsen/eigen2 (pull request PR-183) 
Detect cxx_constexpr support when compiling with clang.
 2016-04-27 15:19:54 -07:00
Rasmus Munk Larsen
09b9e951e3 Depend on the more extensive support for constexpr in clang: 
http://clang.llvm.org/docs/LanguageExtensions.html#c-1y-relaxed-constexpr
 2016-04-27 14:59:11 -07:00
Rasmus Munk Larsen
1a325ef71c Detect cxx_constexpr support when compiling with clang. 2016-04-27 14:33:51 -07:00
Benoit Steiner
c61170e87d fpclassify isn't portable enough. In particular, the return values of the function are not available on all the platforms Eigen supportes: remove it from Eigen. 2016-04-27 14:22:20 -07:00
Benoit Steiner
f629fe95c8 Made the index type a template parameter to evaluateProductBlockingSizes 
Use numext::mini and numext::maxi instead of std::min/std::max to compute blocking sizes.
 2016-04-27 13:11:19 -07:00
Benoit Steiner
25141b69d4 Improved support for min and max on 16 bit floats when running on recent cuda gpus 2016-04-27 12:57:21 -07:00
Benoit Steiner
6744d776ba Added support for fpclassify in Eigen::Numext 2016-04-27 12:10:25 -07:00
Konstantinos Margaritis
3f80696ae1 Merged eigen/eigen into default 2016-04-22 15:05:21 +03:00
Benoit Steiner
5c372d19e3 Merged in rmlarsen/eigen (pull request PR-179) 
Prevent crash in CompleteOrthogonalDecomposition if object was default constructed.
 2016-04-21 18:06:36 -07:00
Rasmus Munk Larsen
a3256d78d8 Prevent crash in CompleteOrthogonalDecomposition if object was default constructed. 2016-04-21 16:49:28 -07:00
Konstantinos Margaritis
e5b2ef47d5 Merged eigen/eigen into default 2016-04-21 18:03:08 +03:00
Benoit Steiner
80200a1828 Don't attempt to leverage the _cvtss_sh and _cvtsh_ss instructions when compiling with clang since it's unclear which versions of clang actually support these instruction. 2016-04-20 12:10:27 -07:00
Benoit Steiner
1d0238375d Made sure all the required header files are included when trying to use fp16 2016-04-19 17:44:12 -07:00
Gael Guennebaud
e4fe611e2c Enable lazy-coeff-based-product for vector*(1x1) products 2016-04-16 15:17:39 +02:00
Benoit Steiner
1a16fb1532 Deleted extraneous comma. 2016-04-15 15:50:13 -07:00
Gael Guennebaud
2a7115daca bug #1203: by-pass large stack-allocation in stableNorm if EIGEN_STACK_ALLOCATION_LIMIT is too small 2016-04-15 22:34:11 +02:00
Benoit Steiner
1d23430628 Improved the matrix multiplication blocking in the case where mr is not a power of 2 (e.g on Haswell CPUs). 2016-04-15 10:53:31 -07:00
Gael Guennebaud
1e80bddde3 Fix trmv for mixing types. 2016-04-15 17:58:36 +02:00
Konstantinos Margaritis
0e8fc31087 remove pgather/pscatter for std::complex<double> for s390x 2016-04-15 07:08:57 -04:00
Benoit Steiner
a62e924656 Added ability to access the cache sizes from the tensor devices 2016-04-14 21:25:06 -07:00
Benoit Steiner
18e6f67426 Added support for exclusive or 2016-04-14 20:37:46 -07:00
Gael Guennebaud
20f387fafa Improve numerical robustness of JacoviSVD: 
- avoid noise amplification in complex to real conversion
 - compare off-diagonal entries to the current biggest diagonal entry: no need to bother about a 2x2 block containing ridiculously small entries compared to the rest of the matrix.
 2016-04-14 22:46:55 +02:00
Benoit Steiner
7718749fee Force the inlining of the << operator on half floats 2016-04-14 11:51:54 -07:00
Benoit Steiner
5379d2b594 Inline the << operator on half floats 2016-04-14 11:40:48 -07:00
Benoit Steiner
5c13765ee3 Added ability to printf fp16 2016-04-14 10:24:52 -07:00
Gael Guennebaud
3551dea887 Cleaning pass on rcond estimator. 2016-04-14 16:45:41 +02:00
Gael Guennebaud
d402adc3d7 Better use .data() than &coeffRef(0) 2016-04-14 15:18:08 +02:00
Gael Guennebaud
ea7087ef31 Merged in rmlarsen/eigen (pull request PR-174) 
Add matrix condition number estimation module.
 2016-04-14 15:11:33 +02:00
Benoit Steiner
36f5a10198 Properly gate the definition of the error and gamma functions for fp16 2016-04-13 18:44:48 -07:00
Benoit Steiner
10b69810d1 Improved support for trigonometric functions on GPU 2016-04-13 16:00:51 -07:00
Benoit Steiner
d6105b53b8 Added basic implementation of the lgamma, digamma, igamma, igammac, polygamma, and zeta function for fp16 2016-04-13 15:26:02 -07:00
Gael Guennebaud
703251f10f merge 2016-04-13 23:45:10 +02:00
Gael Guennebaud
39211ba46b Fix JacobiSVD for complex when the complex-to-real update already gives a diagonal 2x2 block. 2016-04-13 23:43:26 +02:00
Benoit Steiner
2986253259 Cleaned up the implementation of digamma 2016-04-13 14:24:06 -07:00
Benoit Steiner
d5de1a8220 Pulled latest updates from trunk 2016-04-13 14:17:11 -07:00
Benoit Steiner
87ca15c4e8 Added support for sin, cos, tan, and tanh on fp16 2016-04-13 14:12:38 -07:00
Gael Guennebaud
feef39e2d1 Fix underflow in JacoviSVD's complex to real preconditioner 2016-04-13 22:49:51 +02:00
Benoit Steiner
bf3f6688f0 Added support for computing cos, sin, tan, and tanh on GPU. 2016-04-13 11:55:08 -07:00
Benoit Steiner
473c8380ea Added constructors to convert unsigned integers into fp16 2016-04-13 11:03:37 -07:00
Gael Guennebaud
42a3352a3b Workaround a division by zero when outerstride==0 2016-04-13 19:02:02 +02:00
Gael Guennebaud
6f960b83ff Make use of is_same_dense helper instead of extract_data to detect input/outputs are the same. 2016-04-13 18:47:12 +02:00
Gael Guennebaud
b7716c0328 Fix incomplete previous patch on matrix comparision. 2016-04-13 18:32:56 +02:00
Gael Guennebaud
2630d97c62 Fix detection of same matrices when both matrices are not handled by extract_data. 2016-04-13 18:26:08 +02:00
Gael Guennebaud
06447e0a39 Improve half-packet vectorization logic to distinguish linear versus inner traversal modes. 2016-04-13 18:15:49 +02:00
Gael Guennebaud
bbb8854bf7 Enable half-packet in reduxions. 2016-04-13 13:02:34 +02:00
Benoit Steiner
aa1ba8bbd2 Don't put a command at the end of an enumerator list 2016-04-12 16:28:11 -07:00
Gael Guennebaud
b67c983291 Enable the use of half-packet in coeff-based product. 
For instance, Matrix4f*Vector4f is now vectorized again when using AVX.
 2016-04-12 23:03:03 +02:00
Rasmus Larsen
6498dadc2f Merged eigen/eigen into default 2016-04-11 17:42:05 -07:00
Benoit Steiner
748c4c4599 More accurate cost estimates for exp, log, tanh, and sqrt. 2016-04-11 13:11:04 -07:00
Benoit Steiner
833efb39bf Added epsilon, dummy_precision, infinity and quiet_NaN NumTraits for fp16 2016-04-11 11:03:56 -07:00
Benoit Steiner
e939b087fe Pulled latest update from trunk 2016-04-11 11:03:02 -07:00
Gael Guennebaud
0483430283 Move LAPACK declarations from blas.h to lapack.h and fix compatibility with EIGEN_USE_MKL 2016-04-11 17:12:31 +02:00
Gael Guennebaud
097d1e8823 Cleanup obsolete assign_scalar_eig2mkl helper. 2016-04-11 16:09:29 +02:00
Gael Guennebaud
fec4c334ba Remove all references to MKL in BLAS wrappers. 2016-04-11 16:04:09 +02:00
Gael Guennebaud
ddabc992fa Fix long to int conversion in BLAS API. 2016-04-11 15:52:01 +02:00
Gael Guennebaud
8191f373be Silent unused warning. 2016-04-11 15:37:16 +02:00
Gael Guennebaud
6a9ca88e7e Relax dependency on MKL for EIGEN_USE_BLAS 2016-04-11 15:17:14 +02:00
Gael Guennebaud
4e8e5888d7 Improve constness of blas level-3 interface. 2016-04-11 15:12:44 +02:00
Gael Guennebaud
675e0a2224 Fix static/inline keywords order. 2016-04-11 15:06:20 +02:00
Till Hoffmann
643b697649 Proper handling of domain errors. 2016-04-10 00:37:53 +01:00
Rasmus Munk Larsen
1f70bd4134 Merge. 2016-04-09 15:31:53 -07:00
Rasmus Munk Larsen
096e355f8e Add short-circuit to avoid calling matrix norm for empty matrix. 2016-04-09 15:29:56 -07:00
Rasmus Larsen
be80fb49fc Merged default (4a92b590a0 
) into default
 2016-04-09 13:13:01 -07:00
Rasmus Larsen
7a8176587b Merged eigen/eigen into default 2016-04-09 12:47:41 -07:00
Rasmus Munk Larsen
4a92b590a0 Merge. 2016-04-09 12:47:24 -07:00
Rasmus Munk Larsen
ee6c69733a A few tiny adjustments to short-circuit logic. 2016-04-09 12:45:49 -07:00
Till Hoffmann
7f4826890c Merge upstream 2016-04-09 20:08:07 +01:00
Till Hoffmann
de057ebe54 Added nans to zeta function. 2016-04-09 20:07:36 +01:00
Benoit Steiner
5da90fc8dd Use numext::abs instead of std::abs in scalar_fuzzy_default_impl to make it usable inside GPU kernels. 2016-04-08 19:40:48 -07:00
Benoit Steiner
01bd577288 Fixed the implementation of Eigen::numext::isfinite, Eigen::numext::isnan, andEigen::numext::isinf on CUDA devices 2016-04-08 16:40:10 -07:00
Benoit Steiner
89a3dc35a3 Fixed isfinite_impl: NumTraits<T>::highest() and NumTraits<T>::lowest() are finite numbers. 2016-04-08 15:56:16 -07:00
Benoit Steiner
995f202cea Disabled the use of half2 on cuda devices of compute capability < 5.3 2016-04-08 14:43:36 -07:00
Benoit Steiner
8d22967bd9 Initial support for taking the power of fp16 2016-04-08 14:22:39 -07:00
Benoit Steiner
3394379319 Fixed the packet_traits for half floats. 2016-04-08 13:33:59 -07:00
Rasmus Larsen
0b81a18d12 Merged eigen/eigen into default 2016-04-08 12:58:57 -07:00
Benoit Jacob
cd2b667ac8 Add references to filed LLVM bugs 2016-04-08 08:12:47 -04:00
Benoit Steiner
3bd16457e1 Properly handle complex numbers. 2016-04-07 23:28:04 -07:00
Rasmus Larsen
c34e55c62b Merged eigen/eigen into default 2016-04-07 20:23:03 -07:00
Rasmus Munk Larsen
283c51cd5e Widen short-circuiting ReciprocalConditionNumberEstimate so we don't call InverseMatrixL1NormEstimate for dec.rows() <= 1. 2016-04-07 16:45:40 -07:00
Rasmus Munk Larsen
d51803a728 Use Index instead of int for indexing and sizes. 2016-04-07 16:39:48 -07:00
Rasmus Munk Larsen
fd872aefb3 Remove transpose() method from LLT and LDLT classes as it would imply conjugation. 
Explicitly cast constants to RealScalar in ConditionEstimator.h.
 2016-04-07 16:28:44 -07:00
Rasmus Munk Larsen
0b5546d182 Use lpNorm<1>() to compute l1 norms in LLT and LDLT. 2016-04-07 15:49:30 -07:00
parthaEth
2d5bb375b7 Static casting scalar types so as to let chlesky module of eigen work with ceres 2016-04-08 00:14:44 +02:00
Benoit Steiner
74f64838c5 Updated the unary functors to use the numext implementation of typicall functions instead of the one provided in the standard library. The standard library functions aren't supported officially by cuda, so we're better off using the numext implementations. 2016-04-07 11:42:14 -07:00
Benoit Steiner
737644366f Move the functions operating on fp16 out of the std namespace and into the Eigen::numext namespace 2016-04-07 11:40:15 -07:00
Benoit Steiner
b89d3f78b2 Updated the isnan, isinf and isfinite functions to make compatible with cuda devices. 2016-04-07 10:08:49 -07:00
Benoit Steiner
df838736e2 Fixed compilation warning triggered by msvc 2016-04-06 20:48:55 -07:00
Benoit Steiner
14ea7c7ec7 Fixed packet_traits<half> 2016-04-06 19:30:21 -07:00
Benoit Steiner
532fdf24cb Added support for hardware conversion between fp16 and full floats whenever 
possible.
 2016-04-06 17:11:31 -07:00
Benoit Steiner
58c1dbff19 Made the fp16 code more portable. 2016-04-06 13:44:08 -07:00
Benoit Steiner
cf7e73addd Added some missing conversions to the Half class, and fixed the implementation of the < operator on cuda devices. 2016-04-06 09:59:51 -07:00
Benoit Steiner
10bdd8e378 Merged in tillahoffmann/eigen (pull request PR-173) 
Added zeta function of two arguments and polygamma function
 2016-04-06 09:40:17 -07:00
Benoit Steiner
72abfa11dd Added support for isfinite on fp16 2016-04-06 09:07:30 -07:00
Rasmus Munk Larsen
4d07064a3d Fix bug in alternate lower bound calculation due to missing parentheses. 
Make a few expressions more concise.
 2016-04-05 16:40:48 -07:00
Konstantinos Margaritis
2bba4ee2cf Merged kmargar/eigen/tip into default 2016-04-05 22:22:08 +03:00
Konstantinos Margaritis
317384b397 complete the port, remove float support 2016-04-05 14:56:45 -04:00
tillahoffmann
726bd5f077 Merged eigen/eigen into default 2016-04-05 18:21:05 +01:00
Till Hoffmann
a350c25a39 Added accuracy comments. 2016-04-05 18:20:40 +01:00
Konstantinos Margaritis
bc0ad363c6 add remaining includes 2016-04-05 06:01:17 -04:00
Konstantinos Margaritis
2d41dc9622 complete int/double specialized traits for ZVector 2016-04-05 06:00:51 -04:00
Konstantinos Margaritis
988344daf1 enable the other includes as well 2016-04-05 05:59:30 -04:00
Rasmus Larsen
d7eeee0c1d Merged eigen/eigen into default 2016-04-04 15:58:27 -07:00
Rasmus Munk Larsen
513c372960 Fix docstrings to list all supported decompositions. 2016-04-04 14:34:59 -07:00
Rasmus Munk Larsen
86e0ed81f8 Addresses comments on Eigen pull request PR-174. 
* Get rid of code-duplication for real vs. complex matrices.
* Fix flipped arguments to select.
* Make the condition estimation functions free functions.
* Use Vector::Unit() to generate canonical unit vectors.
* Misc. cleanup.
 2016-04-04 14:20:01 -07:00
Benoit Jacob
158fea0f5e bug #1190 - Don't trust __ARM_FEATURE_FMA on Clang/ARM 2016-04-04 16:42:40 -04:00
Benoit Jacob
03f2997a11 bug #1191 - Prevent Clang/ARM from rewriting VMLA into VMUL+VADD 2016-04-04 16:41:47 -04:00
Till Hoffmann
b97911dd18 Refactored code into type-specific helper functions. 2016-04-04 19:16:03 +01:00
Benoit Steiner
c4179dd470 Updated the scalar_abs_op struct to make it compatible with cuda devices. 2016-04-04 11:11:51 -07:00
Benoit Steiner
1108b4f218 Fixed the signature of numext::abs to make it compatible with complex numbers 2016-04-04 11:09:25 -07:00
Rasmus Larsen
30242b7565 Merged eigen/eigen into default 2016-04-01 17:19:36 -07:00
Rasmus Munk Larsen
9d51f7c457 Add rcond method to LDLT. 2016-04-01 16:48:38 -07:00
Rasmus Munk Larsen
f54137606e Add condition estimation to Cholesky (LLT) factorization. 2016-04-01 16:19:45 -07:00
Rasmus Munk Larsen
fb8dccc23e Replace "inline static" with "static inline" for consistency. 2016-04-01 12:48:18 -07:00
Rasmus Munk Larsen
91414e0042 Fix comments in ConditionEstimator and minor cleanup. 2016-04-01 11:58:17 -07:00
Rasmus Munk Larsen
1aa89fb855 Add matrix condition estimator module that implements the Higham/Hager algorithm from http://www.maths.manchester.ac.uk/~higham/narep/narep135.pdf used in LPACK. Add rcond() methods to FullPivLU and PartialPivLU. 2016-04-01 10:27:59 -07:00
Till Hoffmann
80eba21ad0 Merge upstream. 2016-04-01 18:18:49 +01:00
Till Hoffmann
3cb0a237c1 Fixed suggestions by Eugene Brevdo. 2016-04-01 17:51:39 +01:00
tillahoffmann
49960adbdd Merged eigen/eigen into default 2016-04-01 14:36:15 +01:00
Till Hoffmann
57239f4a81 Added polygamma function. 2016-04-01 14:35:21 +01:00
Till Hoffmann
dd5d390daf Added zeta function. 2016-04-01 13:32:29 +01:00
Benoit Steiner
0ea7ab4f62 Hashing was only officially introduced in c++11. Therefore only define an implementation of the hash function for float16 if c++11 is enabled. 2016-03-31 14:44:55 -07:00
Benoit Steiner
92b7f7b650 Improved code formating 2016-03-31 13:09:58 -07:00
Benoit Steiner
f197813f37 Added the ability to hash a fp16 2016-03-31 13:09:23 -07:00
Benoit Steiner
4c859181da Made it possible to use the NumTraits for complex and Array in a cuda kernel. 2016-03-31 12:48:38 -07:00
Benoit Steiner
c36ab19902 Added __ldg primitive for fp16. 2016-03-31 10:55:03 -07:00
Benoit Steiner
b575fb1d02 Added NumTraits for half floats 2016-03-31 10:43:59 -07:00
Benoit Steiner
8c8a79cec1 Fixed a typo 2016-03-31 10:33:32 -07:00
Benoit Steiner
4f1a7e51c1 Pull math functions from the global namespace only when compiling cuda code with nvcc. When compiling with clang, we want to use the std namespace. 2016-03-30 17:59:49 -07:00
Benoit Steiner
bc68fc2fe7 Enable constant expressions when compiling cuda code with clang. 2016-03-30 17:58:32 -07:00
Benoit Jacob
01b5333e44 bug #1186 - vreinterpretq_u64_f64 fails to build on Android/Aarch64/Clang toolchain 2016-03-30 11:02:33 -04:00
Benoit Steiner
1841d6d4c3 Added missing cuda template specializations for numext::ceil 2016-03-29 13:29:34 -07:00
Benoit Steiner
e02b784ec3 Added support for standard mathematical functions and trancendentals(such as exp, log, abs, ...) on fp16 2016-03-29 09:20:36 -07:00
Benoit Steiner
c38295f0a0 Added support for fmod 2016-03-28 15:53:02 -07:00
Konstantinos Margaritis
01e7298fe6 actually include ZVector files, passes most basic tests (float still fails) 2016-03-28 10:58:02 -04:00
Konstantinos Margaritis
f48011119e Merged eigen/eigen into default 2016-03-28 01:48:45 +03:00
Konstantinos Margaritis
ed6b9d08f1 some primitives ported, but missing intrinsics and crash with asm() are a problem 2016-03-27 18:47:49 -04:00
Benoit Steiner
65716e99a5 Improved the cost estimate of the quotient op 2016-03-25 11:13:53 -07:00
Benoit Steiner
d94f6ba965 Started to model the cost of divisions more accurately. 2016-03-25 11:02:56 -07:00
Benoit Steiner
2e4e4cb74d Use numext::abs instead of abs to avoid incorrect conversion to integer of the argument 2016-03-23 16:57:12 -07:00
Benoit Steiner
81d340984a Removed executable bit from header files 2016-03-23 16:15:02 -07:00
Benoit Steiner
bff8cbad06 Removed executable bit from header files 2016-03-23 16:14:23 -07:00
Benoit Steiner
7a570e50ef Fixed contractions of fp16 2016-03-23 16:00:06 -07:00
Benoit Steiner
fc3660285f Made type conversion explicit 2016-03-23 09:56:50 -07:00
Benoit Steiner
0e68882604 Added the ability to divide a half float by an index 2016-03-23 09:46:42 -07:00
Benoit Steiner
6971146ca9 Added more conversion operators for half floats 2016-03-23 09:44:52 -07:00
Benoit Steiner
f9ad25e4d8 Fixed contractions of 16 bit floats 2016-03-22 09:30:23 -07:00
Benoit Steiner
134d750eab Completed the implementation of vectorized type casting of half floats. 2016-03-18 13:36:28 -07:00
Benoit Steiner
7bd551b3a9 Make all the conversions explicit 2016-03-18 12:20:08 -07:00
Benoit Steiner
7b98de1f15 Implemented some of the missing type casting for half floats 2016-03-17 21:45:45 -07:00
Christoph Hertzberg
46aa9772fc Merged in ebrevdo/eigen (pull request PR-169) 
Bugfixes to cuda tests, igamma & igammac implemented, & tests for digamma, igamma, igammac on CPU & GPU.
 2016-03-16 21:59:08 +01:00
Eugene Brevdo
1f69a1b65f Change the header guard around certain numext functions to be CUDA specific. 2016-03-16 12:44:35 -07:00
Benoit Steiner
5a51366ea5 Fixed a typo. 2016-03-14 09:25:16 -07:00
Benoit Steiner
fcf59e1c37 Properly gate the use of cuda intrinsics in the code 2016-03-14 09:13:44 -07:00
Benoit Steiner
97a1f1c273 Make sure we only use the half float intrinsic when compiling with a version of CUDA that is recent enough to provide them 2016-03-14 08:37:58 -07:00
Benoit Steiner
e29c9676b1 Don't mark the cast operator as explicit, since this is a c++11 feature that's not supported by older compilers. 2016-03-12 00:15:58 -08:00
Benoit Steiner
eecd914864 Also replaced uint32_t with unsigned int to make the code more portable 2016-03-11 19:34:21 -08:00
Benoit Steiner
1ca8c1ec97 Replaced a couple more uint16_t with unsigned short 2016-03-11 19:28:28 -08:00
Benoit Steiner
0423b66187 Use unsigned short instead of uint16_t since they're more portable 2016-03-11 17:53:41 -08:00
Benoit Steiner
048c4d6efd Made half floats usable on hardware that doesn't support them natively. 2016-03-11 17:21:42 -08:00
Benoit Steiner
456e038a4e Fixed the +=, -=, *= and /= operators to return a reference 2016-03-10 15:17:44 -08:00
Eugene Brevdo
836e92a051 Update MathFunctions/SpecialFunctions with intelligent header guards. 2016-03-09 09:04:45 -08:00
Eugene Brevdo
5e7de771e3 Properly fix merge issues. 2016-03-08 17:35:05 -08:00
Eugene Brevdo
73220d2bb0 Resolve bad merge. 2016-03-08 17:28:21 -08:00
Eugene Brevdo
14f0fde51f Add certain functions to numext (log, exp, tan) because CUDA doesn't support std:: 
Use these in SpecialFunctions.
 2016-03-08 17:17:44 -08:00
Eugene Brevdo
0bb5de05a1 Finishing touches on igamma/igammac for GPU. Tests now pass. 2016-03-07 15:35:09 -08:00
Eugene Brevdo
5707004d6b Fix Eigen's building of sharded tests that use CUDA & more igamma/igammac bugfixes. 
0. Prior to this PR, not a single sharded CUDA test was actually being *run*.
Fixed that.

GPU tests are still failing for igamma/igammac.

1. Add calls for igamma/igammac to TensorBase
2. Fix up CUDA-specific calls of igamma/igammac
3. Add unit tests for digamma, igamma, igammac in CUDA.
 2016-03-07 14:08:56 -08:00
Benoit Steiner
05bbca079a Turn on some of the cxx11 features when compiling with visual studio 2015 2016-03-05 10:52:08 -08:00
Eugene Brevdo
0b9e0abc96 Make igamma and igammac work correctly. 
This required replacing ::abs with std::abs.
Modified some unit tests.
 2016-03-04 21:12:10 -08:00
Eugene Brevdo
7ea35bfa1c Initial implementation of igamma and igammac. 2016-03-03 19:39:41 -08:00
Benoit Steiner
1032441c6f Enable partial support for half floats on Kepler GPUs. 2016-03-03 10:34:20 -08:00
Benoit Steiner
1da10a7358 Enable the conversion between floats and half floats on older GPUs that support it. 2016-03-03 10:33:20 -08:00
Benoit Steiner
2de8cc9122 Merged in ebrevdo/eigen (pull request PR-167) 
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.
 2016-03-03 09:42:12 -08:00
Eugene Brevdo
ab3dc0b0fe Small bugfix to numeric_limits for CUDA. 2016-03-02 21:48:46 -08:00
Eugene Brevdo
6afea46838 Add infinity() support to numext::numeric_limits, use it in lgamma. 
This makes the infinity access a __device__ function, removing
nvcc warnings.
 2016-03-02 21:35:48 -08:00
Gael Guennebaud
3fccef6f50 bug #537: fix compilation with Apples's compiler 2016-03-02 13:22:46 +01:00
Gael Guennebaud
dfa80b2060 Compilation fix 2016-03-01 12:48:56 +01:00
Gael Guennebaud
bee9efc203 Compilation fix 2016-03-01 12:47:27 +01:00
Gael Guennebaud
e9bea614ec Fix shortcoming in fixed-value deduction of startRow/startCol 2016-02-29 10:31:27 +01:00
Gael Guennebaud
8e6faab51e bug #1172: make valuePtr and innderIndexPtr properly return null for empty matrices. 2016-02-27 14:55:40 +01:00
Gael Guennebaud
91e1375ba9 merge 2016-02-23 11:09:05 +01:00
Gael Guennebaud
055000a424 Fix startRow()/startCol() for dense Block with direct access: 
the initial implementation failed for empty rows/columns for which are ambiguous.
 2016-02-23 11:07:59 +01:00
Benoit Steiner
6270d851e3 Declare the half float type as arithmetic. 2016-02-22 13:59:33 -08:00
Benoit Steiner
584832cb3c Implemented the ptranspose function on half floats 2016-02-21 12:44:53 -08:00
Benoit Steiner
95fceb6452 Added the ability to compute the absolute value of a half float 2016-02-21 20:24:11 +00:00
Benoit Steiner
9ff269a1d3 Moved some of the fp16 operators outside the Eigen namespace to workaround some nvcc limitations. 2016-02-20 07:47:23 +00:00
Gael Guennebaud
d90a2dac5e merge 2016-02-19 23:01:27 +01:00
Gael Guennebaud
6fa35bbd28 bug #1170: skip calls to memcpy/memmove for empty imput. 2016-02-19 22:58:52 +01:00
Gael Guennebaud
6f0992c05b Fix nesting type and complete reflection methods of Block expressions. 2016-02-19 22:21:02 +01:00
Gael Guennebaud
f3643eec57 Add typedefs for the return type of all block methods. 2016-02-19 22:15:01 +01:00
Benoit Steiner
180156ba1a Added support for tensor reductions on half floats 2016-02-19 10:05:59 -08:00
Benoit Steiner
5c4901b83a Implemented the scalar division of 2 half floats 2016-02-19 10:03:19 -08:00
Benoit Steiner
f7cb755299 Added support for operators +=, -=, *= and /= on CUDA half floats 2016-02-19 15:57:26 +00:00
Benoit Steiner
dc26459b99 Implemented protate() for CUDA 2016-02-19 15:16:54 +00:00
Benoit Steiner
ac5d706a94 Added support for simple coefficient wise tensor expression using half floats on CUDA devices 2016-02-19 08:19:12 +00:00
Benoit Steiner
0606a0a39b FP16 on CUDA are only available starting with cuda 7.5. Disable them when using an older version of CUDA 2016-02-18 23:15:23 -08:00
Benoit Steiner
7151bd8768 Reverted unintended changes introduced by a bad merge 2016-02-19 06:20:50 +00:00
Benoit Steiner
17b9fbed34 Added preliminary support for half floats on CUDA GPU. For now we can simply convert floats into half floats and vice versa 2016-02-19 06:16:07 +00:00
Benoit Steiner
8ce46f9d89 Improved implementation of ptanh for SSE and AVX 2016-02-18 13:24:34 -08:00
Eugene Brevdo
832380c455 Merged eigen/eigen into default 2016-02-17 14:44:06 -08:00
Eugene Brevdo
06a2bc7c9c Tiny bugfix in SpecialFunctions: some compilers don't like doubles 
implicitly downcast to floats in an array constructor.
 2016-02-17 14:41:59 -08:00
Gael Guennebaud
f6f057bb7d bug #1166: fix shortcomming in gemv when the destination is not a vector at compile-time. 2016-02-15 21:43:07 +01:00
Gael Guennebaud
4252af6897 Remove dead code. 2016-02-12 16:13:35 +01:00
Gael Guennebaud
2f5f56a820 Fix usage of evaluator in sparse * permutation products. 2016-02-12 16:13:16 +01:00
Gael Guennebaud
0a537cb2d8 bug #901: fix triangular-view with unit diagonal of sparse rectangular matrices. 2016-02-12 15:58:31 +01:00
Benoit Steiner
17e93ba148 Pulled latest updates from trunk 2016-02-11 15:05:38 -08:00
Benoit Steiner
3628f7655d Made it possible to run the scalar_binary_pow_op functor on GPU 2016-02-11 15:05:03 -08:00
Hauke Heibel
eeac46f980 bug #774: re-added comment referencing equations in the original paper 2016-02-11 19:38:37 +01:00
Benoit Steiner
c569cfe12a Inline the +=, -=, *= and /= operators consistently between DenseBase.h and SelfCwiseBinaryOp.h 2016-02-11 09:33:32 -08:00
Gael Guennebaud
8cc9232b9a bug #774: fix a numerical issue producing unwanted reflections. 2016-02-11 15:32:56 +01:00
Gael Guennebaud
2d35c0cb5f Merged in rmlarsen/eigen (pull request PR-163) 
Implement complete orthogonal decomposition in Eigen.
 2016-02-11 15:12:34 +01:00
Benoit Steiner
33e2373f01 Merged in nnyby/eigen/nnyby/doc-grammar-fix-linearly-space-linearly-1443742971203 (pull request PR-138) 
[doc] grammar fix: "linearly space" -> "linearly spaced"
 2016-02-10 23:29:59 -08:00
Benoit Steiner
6d8b1dce06 Avoid implicit cast from double to float. 2016-02-10 18:07:11 -08:00
Rasmus Munk Larsen
b6fdf7468c Rename inverse -> pseudoInverse. 2016-02-10 13:03:07 -08:00
Benoit Jacob
9d6f1ad398 I'm told to use __EMSCRIPTEN__ by an Emscripten dev. 2016-02-10 12:48:34 -05:00
Benoit Steiner
bfb3fcd94f Optimized implementation of the tanh function for SSE 2016-02-10 08:52:30 -08:00
Benoit Steiner
2d523332b3 Optimized implementation of the hyperbolic tangent function for AVX 2016-02-10 08:48:05 -08:00
Benoit Jacob
e6ee18d6b4 Make the GCC workaround for sqrt GCC-only; detect Emscripten as non-GCC 2016-02-10 11:11:49 -05:00
Benoit Jacob
964a95bf5e Work around Emscripten bug - https://github.com/kripken/emscripten/issues/4088 2016-02-10 10:37:22 -05:00
Benoit Steiner
970751ece3 Disabling the nvcc warnings in addition to the clang warnings when clang is used as a frontend for nvcc 2016-02-09 20:55:50 -08:00
Rasmus Munk Larsen
bb8811c655 Enable inverse() method for computing pseudo-inverse. 2016-02-09 20:35:20 -08:00
Benoit Steiner
5cc0dd5f44 Fixed the code that disables the use of variadic templates when compiling with nvcc on ARM devices. 2016-02-09 10:32:01 -08:00
Benoit Steiner
24d291cf16 Worked around nvcc crash when compiling Eigen on Tegra X1 2016-02-09 02:34:02 +00:00
Rasmus Munk Larsen
53f60e0afc Make applyZAdjointOnTheLeftInPlace protected. 2016-02-08 09:01:43 -08:00
Rasmus Munk Larsen
414efa47d3 Add missing calls to tests of COD. 
Fix a few mistakes in 3.2 -> 3.3 port.
 2016-02-08 08:50:34 -08:00
Gael Guennebaud
c2bf2f56ef Remove custom unaligned loads for SSE. They were only useful for core2 CPU. 2016-02-08 14:29:12 +01:00
Gael Guennebaud
a4c76f8d34 Improve inlining 2016-02-08 11:33:02 +01:00
Rasmus Munk Larsen
16ec450ca1 Nevermind. 2016-02-06 17:54:01 -08:00
Rasmus Munk Larsen
019fff9a00 Add my name to copyright notice in ColPivHouseholder.h, mostly for previous work on stable norm downdate formula. 2016-02-06 17:48:42 -08:00
Rasmus Munk Larsen
86d6201d7b Merge. 2016-02-06 16:36:56 -08:00
Rasmus Munk Larsen
d904c8ac8f Implement complete orthogonal decomposition in Eigen. 2016-02-06 16:32:00 -08:00
Gael Guennebaud
c6a12d1dc6 Fix warning with gcc < 4.8 2016-02-06 18:06:51 +01:00
Gael Guennebaud
5b2d287878 bug #779: allow non aligned buffers for buffers smaller than the requested alignment. 2016-02-05 21:46:39 +01:00
Gael Guennebaud
e8e1d504d6 Add an explicit assersion on the alignment of the pointer returned by std::malloc 2016-02-05 21:38:16 +01:00
Gael Guennebaud
62a1c911cd Remove posix_memalign, _mm_malloc, and _aligned_malloc special paths. 2016-02-05 21:24:35 +01:00
Benoit Steiner
bcdcdace48 Pulled latest updates from trunk 2016-02-04 08:56:49 -08:00
Gael Guennebaud
659fc9c159 Remove dead code 2016-02-04 09:55:09 +01:00
Gael Guennebaud
d5d7798b9d Improve heuritics for switching between coeff-based and general matrix product implementation. 2016-02-04 09:53:47 +01:00
Benoit Steiner
f535378995 Added support for vectorized type casting of int to char. 2016-02-03 18:58:29 -08:00
Benoit Steiner
727ff26960 Disable 2 more nvcc warning messages 2016-02-03 16:01:37 -08:00
Benoit Steiner
bcbde37a11 Made sure the code compiles when EIGEN_HAS_C99_MATH isn't defined 2016-02-03 14:53:08 -08:00
Benoit Steiner
f933f69021 Added a few comments 2016-02-03 14:12:18 -08:00
Benoit Steiner
5d82e47ef6 Properly disable nvcc warning messages in user code. 2016-02-03 14:10:06 -08:00
Benoit Steiner
d7742d22e4 Revert the nvcc messages to their default severity instead of the forcing them to be warnings 2016-02-03 13:47:28 -08:00
Benoit Steiner
ac26e1aaf3 Pulled latest updates from trunk 2016-02-03 12:52:20 -08:00
Benoit Steiner
492fe7ce02 Silenced some unhelpful warnings generated by nvcc. 2016-02-03 12:51:19 -08:00
Gael Guennebaud
b70db60e4d Merged in rmlarsen/eigen (pull request PR-161) 
Change Eigen's ColPivHouseholderQR to use  numerically stable norm downdate formula
 2016-02-03 21:37:06 +01:00
Rasmus Munk Larsen
5fb04ab2da Fix bad line break. Don't repeat Kahan matrix test since it is deterministic. 2016-02-03 10:12:10 -08:00
Rasmus Munk Larsen
d9a6f86cc0 Make the array of directly compute column norms a member to avoid allocation in computeInPlace. 2016-02-03 09:55:30 -08:00
Gael Guennebaud
70dc14e4e1 bug #1161: fix division by zero for huge scalar types 2016-02-03 18:25:41 +01:00
Damien R
c301f99208 bug #1164: fix list and deque specializations such that our aligned allocator is automatically activatived only when the user did not specified an allocator (or specified the default std::allocator). 2016-02-03 18:07:25 +01:00
Gael Guennebaud
eb6d9aea0e Clarify error message when writing to a read-only sparse-sub-matrix. 2016-02-03 16:58:23 +01:00
Rasmus Munk Larsen
00f9ef6c76 merging. 2016-02-01 11:10:30 -08:00
Gael Guennebaud
ff1157bcbf bug #694: document that SparseQR::matrixR is not sorted. 2016-02-01 16:09:34 +01:00
Gael Guennebaud
ec469700dc bug #557: make InnerIterator of sparse storage types more versatile by adding default-ctor, copy-ctor/assignment 2016-02-01 15:04:33 +01:00
Gael Guennebaud
6e0a86194c Fix integer path for num_steps==1 2016-02-01 15:00:04 +01:00
Gael Guennebaud
e1d219e5c9 bug #698: fix linspaced for integer types. 2016-02-01 14:25:34 +01:00
Gael Guennebaud
2c3224924b Fix warning and replace min/max macros by calls to mini/maxi 2016-02-01 10:23:45 +01:00
Benoit Steiner
3f1ee45833 Fixed compilation errors triggered by duplicate inline declaration 2016-01-31 10:48:49 -08:00
Gael Guennebaud
d142165942 bug #667: declare several critical functions as FORECE_INLINE to make ICC happier. 
<g.gael@free.fr> HG: branch 'default' HG: changed Eigen/src/Core/ArrayBase.h HG: changed Eigen/src/Core/AssignEvaluator.h HG: changed
Eigen/src/Core/CoreEvaluators.h HG: changed Eigen/src/Core/CwiseUnaryOp.h HG: changed Eigen/src/Core/DenseBase.h HG: changed Eigen/src/Core/MatrixBase.h
 2016-01-31 16:34:10 +01:00
Gael Guennebaud
1bc207c528 backout changeset d4a9e61569 
: the extended SparseView is not needed anymore
 2016-01-30 14:43:21 +01:00
Gael Guennebaud
8ed1553d20 bug #632: implement general coefficient-wise "dense op sparse" operations through specialized evaluators instead of using SparseView. 
This permits to deal with arbitrary storage order, and to by-pass the more complex iterator of the sparse-sparse case.
 2016-01-30 14:39:50 +01:00
Gael Guennebaud
699634890a bug #946: generalize Cholmod::solve to handle any rhs expression 2016-01-29 23:02:22 +01:00
Gael Guennebaud
15084cf1ac bug #632: add support for "dense +/- sparse" operations. The current implementation is based on SparseView to make the dense subexpression compatible with the sparse one. 2016-01-29 22:09:45 +01:00
Gael Guennebaud
d4a9e61569 Extend SparseView to allow keeping explicit zeros. This is equivalent to sparseView(1,-1) but faster because the test is removed at compile-time. 2016-01-29 22:07:56 +01:00
Gael Guennebaud
d8d37349c3 bug #696: enable zero-sized block at compile-time by relaxing the respective assertion 2016-01-29 12:44:49 +01:00
Gael Guennebaud
e8ccc06fe5 merge 2016-01-29 09:40:38 +01:00
Benoit Steiner
d3f533b395 Fixed compilation warning 2016-01-28 20:09:45 -08:00
Abhijit Kundu
3fde202215 Making ceil() functor generic w.r.t packet type 2016-01-28 21:27:00 -05:00
Rasmus Munk Larsen
acce4dd050 Change Eigen's ColPivHouseholderQR to use the numerically stable norm downdate formula from http://www.netlib.org/lapack/lawnspdf/lawn176.pdf, which has been used in LAPACK's xGEQPF and xGEQP3 since 2006. With the old formula, the code chooses the wrong pivots and fails to correctly determine rank on graded matrices. 
This change also adds additional checks for non-increasing diagonal in R11 to existing unit tests, and adds a new unit test with the Kahan matrix, which consistently fails for the original code.

Benchmark timings on Intel(R) Xeon(R) CPU E5-1650 v3 @ 3.50GHz. Code compiled with AVX & FMA. I just ran on square matrices of 3 difference sizes.

Benchmark               Time(ns)     CPU(ns) Iterations
-------------------------------------------------------
Before:
BM_EigencolPivQR/64        53677       53627      12890
BM_EigencolPivQR/512    15265408    15250784         46
BM_EigencolPivQR/4k  15403556228 15388788368          2

After (non-vectorized version):
Benchmark               Time(ns)     CPU(ns) Iterations  Degradation
--------------------------------------------------------------------
BM_EigencolPivQR/64        63736       63669      10844         18.5%
BM_EigencolPivQR/512    16052546    16037381         43          5.1%
BM_EigencolPivQR/4k  15149263620 15132025316          2         -2.0%

Performance-wise there seems to be a ~18.5% degradation for small (64x64) matrices, probably due to the cost of more O(min(m,n)^2) sqrt operations that are not needed for the unstable formula.
 2016-01-28 15:07:26 -08:00
Gael Guennebaud
b908e071a8 bug #178: get rid of some const_cast in SparseCore 2016-01-28 22:11:18 +01:00
Gael Guennebaud
c1d900af61 bug #178: remove additional const on nested expression, and remove several const_cast. 2016-01-28 21:43:20 +01:00
Gael Guennebaud
f50bb1e6f3 Fix compilation with gcc 2016-01-28 13:25:26 +01:00
Gael Guennebaud
ddf64babde merge 2016-01-28 13:21:48 +01:00
Gael Guennebaud
df15fbc452 bug #1158: PartialReduxExpr is a vector expression, and it thus must expose the LinearAccessBit flag 2016-01-28 13:16:30 +01:00
Gael Guennebaud
9bcadb7fd1 Disable stupid MSVC warning 2016-01-28 12:14:16 +01:00
Gael Guennebaud
b4d87fff4a Fix MSVC warning. 2016-01-28 12:12:30 +01:00
Gael Guennebaud
2bad3e78d9 bug #96, bug #1006: fix by value argument in result_of. 2016-01-28 12:12:06 +01:00
Benoit Steiner
291069e885 Fixed some compilation problems with nvcc + clang 2016-01-27 15:37:03 -08:00
Gael Guennebaud
4865e1e732 Update link to suitesparse. 2016-01-27 22:48:40 +01:00
Eugene Brevdo
c8d94ae944 digamma special function: merge shared code. 
Moved type-specific code into a helper class digamma_impl_maybe_poly<Scalar>.
 2016-01-27 09:52:29 -08:00
Gael Guennebaud
9c8f7dfe94 bug #1156: fix several function declarations whose arguments were passed by value instead of being passed by reference 2016-01-27 18:34:42 +01:00
Gael Guennebaud
9aa6fae123 bug #1154: move to dynamic scheduling for spmv products. 2016-01-27 18:03:51 +01:00
Gael Guennebaud
9801c959e6 Fix tri = complex * real product, and add respective unit test. 2016-01-27 17:12:25 +01:00
Gael Guennebaud
21b5345782 Add meta_least_common_multiple helper. 2016-01-27 17:11:39 +01:00
Gael Guennebaud
fecea26d93 Extend doc on shifting strategy 2016-01-27 15:55:15 +01:00
Gael Guennebaud
cfa21f8123 Remove dead code. 2016-01-26 23:33:15 +01:00
Gael Guennebaud
6850eab33b Re-enable blocking on rows in non-l3 blocking mode. 2016-01-26 23:32:48 +01:00
Gael Guennebaud
aa8c6a251e Make sure that micro-panel-size is smaller than blocking sizes (otherwise we might get a buffer overflow) 2016-01-26 23:31:48 +01:00
Gael Guennebaud
5b0a9ee003 Make sure that block sizes are smaller than input matrix sizes. 2016-01-26 23:30:24 +01:00
Christoph Hertzberg
44d4674955 bug #1153: Don't rely on __GXX_EXPERIMENTAL_CXX0X__ to detect C++11 support 2016-01-26 16:45:33 +01:00
Gael Guennebaud
8328caa618 bug #51: add block preallocation mechanism to selfadjoit*matrix product. 2016-01-25 22:06:42 +01:00
Gael Guennebaud
e58827d2ed bug #51: make general_matrix_matrix_triangular_product use L3-blocking helper so that general symmetric rank-updates and general-matrix-to-triangular products do not trigger dynamic memory allocation for fixed size matrices. 2016-01-25 17:16:33 +01:00
Gael Guennebaud
b114e6fd3b Improve documentation. 2016-01-25 11:56:25 +01:00
Gael Guennebaud
869b4443ac Add SparseVector::conservativeResize() method. 2016-01-25 11:55:39 +01:00
Gael Guennebaud
acf6f7af6b Merged in larsmans/eigen (pull request PR-156) 
Documentation fixes
 2016-01-24 22:28:49 +01:00