mirror of
https://gitlab.com/libeigen/eigen.git
synced 2026-01-18 17:31:19 +01:00
Merge branch eigen:master into master
This commit is contained in:
Rasmus Munk Larsen
@@ -1,4 +1,4 @@
|
||||
<!--
|
||||
<!--
|
||||
Thanks for contributing a merge request!
|
||||
|
||||
We recommend that first-time contributors read our [contribution guidelines](https://eigen.tuxfamily.org/index.php?title=Contributing_to_Eigen).
|
||||
@@ -22,7 +22,7 @@ Note that we are a team of volunteers; we appreciate your patience during the re
|
||||
|
||||
### Reference issue
|
||||
<!--
|
||||
You can link to a specific issue using the gitlab syntax #<issue number>.
|
||||
You can link to a specific issue using the gitlab syntax #<issue number>.
|
||||
If the MR fixes an issue, write "Fixes #<issue number>" to have the issue automatically closed on merge.
|
||||
-->
|
||||
|
||||
160
CHANGELOG.md
160
CHANGELOG.md
@@ -355,16 +355,16 @@ Changes since 3.3.5:
|
||||
* #1617: Fix triangular solve crashing for empty matrix.
|
||||
* #785: Make dense Cholesky decomposition work for empty matrices.
|
||||
* #1634: Remove double copy in move-ctor of non movable Matrix/Array.
|
||||
* Changeset 588e1eb34eff: Workaround weird MSVC bug.
|
||||
* Changeset a2d6c106a450: Workaround weird MSVC bug.
|
||||
* #1637 Workaround performance regression in matrix products with gcc>=6 and clang>=6.0.
|
||||
* Changeset bf0f100339c1: Fix some implicit 0 to Scalar conversions.
|
||||
* Changeset 9ccbaaf3dd4c: Fix some implicit 0 to Scalar conversions.
|
||||
* #1605: Workaround ABI issue with vector types (aka `__m128`) versus scalar types (aka float).
|
||||
* Changeset d1421c479baa: Fix for gcc<4.6 regarding usage of #pragma GCC diagnostic push/pop.
|
||||
* Changeset c20b83b9d736: Fix conjugate-gradient for right-hand-sides with a very small magnitude.
|
||||
* Changeset 281a877a3bf7: Fix product of empty arrays (returned 0 instead of 1).
|
||||
* Changeset 148e579cc004: Fix for gcc<4.6 regarding usage of #pragma GCC diagnostic push/pop.
|
||||
* Changeset bc000deaae45: Fix conjugate-gradient for right-hand-sides with a very small magnitude.
|
||||
* Changeset 5be00b0e2964: Fix product of empty arrays (returned 0 instead of 1).
|
||||
* #1590: Fix collision with some system headers defining the macro FP32.
|
||||
* #1584: Fix possible undefined behavior in random generation.
|
||||
* Changeset d632d18db8ca: Fix fallback to BLAS for rankUpdate.
|
||||
* Changeset e4127b0f7d3b: Fix fallback to BLAS for rankUpdate.
|
||||
* Fixes for NVCC 9.
|
||||
* Fix matrix-market IO.
|
||||
* Various fixes in the doc.
|
||||
@@ -375,94 +375,94 @@ Changes since 3.3.5:
|
||||
Changes since 3.3.4:
|
||||
|
||||
* General bug fixes:
|
||||
* Fix GeneralizedEigenSolver when requesting for eigenvalues only (0d15855abb30)
|
||||
* #1560 fix product with a 1x1 diagonal matrix (90d7654f4a59)
|
||||
* Fix GeneralizedEigenSolver when requesting for eigenvalues only (ab3fa2e12308)
|
||||
* #1560 fix product with a 1x1 diagonal matrix (483beabab9bf)
|
||||
* #1543: fix linear indexing in generic block evaluation
|
||||
* Fix compilation of product with inverse transpositions (e.g., `mat * Transpositions().inverse()`) (14a13748d761)
|
||||
* #1509: fix `computeInverseWithCheck` for complexes (8be258ef0b6d)
|
||||
* #1521: avoid signalling `NaN` in hypot and make it std::complex<> friendly (a9c06b854991).
|
||||
* #1517: fix triangular product with unit diagonal and nested scaling factor: `(s*A).triangularView<UpperUnit>()*B` (a546d43bdd4f)
|
||||
* Fix compilation of stableNorm for some odd expressions as input (499e982b9281)
|
||||
* #1485: fix linking issue of non template functions (ae28c2aaeeda)
|
||||
* Fix overflow issues in BDCSVD (92060f82e1de)
|
||||
* #1468: add missing `std::` to `memcpy` (4565282592ae)
|
||||
* #1453: fix Map with non-default inner-stride but no outer-stride (af00212cf3a4)
|
||||
* Fix mixing types in sparse matrix products (7e5fcd0008bd)
|
||||
* #1544: Generate correct Q matrix in complex case (c0c410b508a1)
|
||||
* #1461: fix compilation of `Map<const Quaternion>::x()` (69652a06967d)
|
||||
* Fix compilation of product with inverse transpositions (e.g., `mat * Transpositions().inverse()`) (170914dbbcc3)
|
||||
* #1509: fix `computeInverseWithCheck` for complexes (a2a2c3c86507)
|
||||
* #1521: avoid signalling `NaN` in hypot and make it std::complex<> friendly (b18e2d422b09).
|
||||
* #1517: fix triangular product with unit diagonal and nested scaling factor: `(s*A).triangularView<UpperUnit>()*B` (c24844195d90)
|
||||
* Fix compilation of stableNorm for some odd expressions as input (33b972d8b384)
|
||||
* #1485: fix linking issue of non template functions (d18877f18d8e)
|
||||
* Fix overflow issues in BDCSVD (7a875acfb05f)
|
||||
* #1468: add missing `std::` to `memcpy` (32a6db0f8cd5)
|
||||
* #1453: fix Map with non-default inner-stride but no outer-stride (1ca9072b51d8)
|
||||
* Fix mixing types in sparse matrix products (4ead16cdd6c8)
|
||||
* #1544: Generate correct Q matrix in complex case (39125654ce9e)
|
||||
* #1461: fix compilation of `Map<const Quaternion>::x()` (9a266e5118cf)
|
||||
|
||||
* Backends:
|
||||
* Fix MKL backend for symmetric eigenvalues on row-major matrices (4726d6a24f69)
|
||||
* #1527: fix support for MKL's VML (972424860545)
|
||||
* Fix incorrect ldvt in LAPACKE call from JacobiSVD (88c4604601b9)
|
||||
* Fix support for MKL's BLAS when using `MKL_DIRECT_CALL` (205731b87e19, b88c70c6ced7, 46e2367262e1)
|
||||
* Use MKL's lapacke.h header when using MKL (19bc9df6b726)
|
||||
* Fix MKL backend for symmetric eigenvalues on row-major matrices (eab7afe25273)
|
||||
* #1527: fix support for MKL's VML (86a939451c75)
|
||||
* Fix incorrect ldvt in LAPACKE call from JacobiSVD (bfc66e8b9a3b)
|
||||
* Fix support for MKL's BLAS when using `MKL_DIRECT_CALL` (9df7f3d8e9cd, 3108fbf76708, 292dea7922e7)
|
||||
* Use MKL's lapacke.h header when using MKL (070b5958e0ae)
|
||||
|
||||
* Diagnostics:
|
||||
* #1516: add assertion for out-of-range diagonal index in `MatrixBase::diagonal(i)` (783d38b3c78c)
|
||||
* Add static assertion for fixed sizes `Ref<>` (e1203d5ceb8e)
|
||||
* Add static assertion on selfadjoint-view's UpLo parameter. (b84db94c677e, 0ffe8a819801)
|
||||
* #1479: fix failure detection in LDLT (67719139abc3)
|
||||
* #1516: add assertion for out-of-range diagonal index in `MatrixBase::diagonal(i)` (273738ba6f6e)
|
||||
* Add static assertion for fixed sizes `Ref<>` (1724dae8b834)
|
||||
* Add static assertion on selfadjoint-view's UpLo parameter. (74daf12e525e, 190b46dd1f05)
|
||||
* #1479: fix failure detection in LDLT (c20043c8fd64)
|
||||
|
||||
* Compiler support:
|
||||
* #1555: compilation fix with XLC
|
||||
* Workaround MSVC 2013 ambiguous calls (1c7b59b0b5f4)
|
||||
* Adds missing `EIGEN_STRONG_INLINE` to help MSVC properly inlining small vector calculations (1ba3f10b91f2)
|
||||
* Several minor warning fixes: 3c87fc0f1042, ad6bcf0e8efc, "used uninitialized" (20efc44c5500), Wint-in-bool-context (131da2cbc695, b4f969795d1b)
|
||||
* #1428: make NEON vectorization compilable by MSVC. (* 3d1b3dbe5927, 4e1b7350182a)
|
||||
* Fix compilation and SSE support with PGI compiler (faabf000855d 90d33b09040f)
|
||||
* #1555: compilation fix with XLC (23eb37691f14)
|
||||
* #1520: workaround some `-Wfloat-equal` warnings by calling `std::equal_to` (7d9a9456ed7c)
|
||||
* Make the TensorStorage class compile with clang 3.9 (eff7001e1f0a)
|
||||
* Misc: some old compiler fixes (493691b29be1)
|
||||
* Fix MSVC warning C4290: C++ exception specification ignored except to indicate a function is not `__declspec(nothrow)` (524918622506)
|
||||
* Workaround MSVC 2013 ambiguous calls (c92536d92647)
|
||||
* Adds missing `EIGEN_STRONG_INLINE` to help MSVC properly inlining small vector calculations (01fb6217335b)
|
||||
* Several minor warning fixes: f90d136c8445, 542fb03968c2, "used uninitialized" (7634a44bfe11), Wint-in-bool-context (3d1795da28c2, d1c2d6683c55)
|
||||
* #1428: make NEON vectorization compilable by MSVC. (* 1e2d2693b911, 927d023ceaab)
|
||||
* Fix compilation and SSE support with PGI compiler (bb87f618bfc3 450c5e5d2771)
|
||||
* #1555: compilation fix with XLC (20ca86888e70)
|
||||
* #1520: workaround some `-Wfloat-equal` warnings by calling `std::equal_to` (1c4fdad7bd6f)
|
||||
* Make the TensorStorage class compile with clang 3.9 (a7144f8d6a94)
|
||||
* Misc: some old compiler fixes (b60cbbef3791)
|
||||
* Fix MSVC warning C4290: C++ exception specification ignored except to indicate a function is not `__declspec(nothrow)` (3df78d5afc1e)
|
||||
|
||||
* Architecture support:
|
||||
* Several AVX512 fixes for `log`, `sqrt`, `rsqrt`, non `AVX512ER` CPUs, `apply_rotation_in_the_plane` b64275e912ba cab3d626a59e 7ce234652ab9, d89b9a754371.
|
||||
* AltiVec fixes: 9450038e380d
|
||||
* NEON fixes: const-cast (e8a69835ccda), compilation of Jacobi rotations (c06cfd545b15,#1436).
|
||||
* Changeset d0658cc9d4a2: Define `pcast<>` for SSE types even when AVX is enabled. (otherwise float are silently reinterpreted as int instead of being converted)
|
||||
* #1494: makes `pmin`/`pmax` behave on Altivec/VSX as on x86 regarding NaNs (d0af83f82b19)
|
||||
* Several AVX512 fixes for `log`, `sqrt`, `rsqrt`, non `AVX512ER` CPUs, `apply_rotation_in_the_plane` 5c59564bfb92 1939c971a3db c2f9e6cb37e5, 609e425166f6.
|
||||
* AltiVec fixes: 1641a6cdd5a4
|
||||
* NEON fixes: const-cast (877a2b64c9ba), compilation of Jacobi rotations (bc837b797559,#1436).
|
||||
* Changeset 971b32440c74: Define `pcast<>` for SSE types even when AVX is enabled. (otherwise float are silently reinterpreted as int instead of being converted)
|
||||
* #1494: makes `pmin`/`pmax` behave on Altivec/VSX as on x86 regarding NaNs (892c0a79ce93)
|
||||
|
||||
* Documentation:
|
||||
* Update manual pages regarding BDCSVD (#1538)
|
||||
* Add aliasing in common pitfaffs (2a5a8408fdc5)
|
||||
* Update `aligned_allocator` (21e03aef9f2b)
|
||||
* #1456: add perf recommendation for LLT and storage format (c8c154ebf130, 9aef1e23dbe0)
|
||||
* #1455: Cholesky module depends on Jacobi for rank-updates (2e6e26b851a8)
|
||||
* #1458: fix documentation of LLT and LDLT `info()` method (2a4cf4f473dd)
|
||||
* Warn about constness in `LLT::solveInPlace` (518f97b69bdf)
|
||||
* Fix lazyness of `operator*` with CUDA (c4dbb556bd36)
|
||||
* #336: improve doc for `PlainObjectBase::Map` (13dc446545fe)
|
||||
* Add aliasing in common pitfaffs (656712d48f6b)
|
||||
* Update `aligned_allocator` (6fc0f2be70a4)
|
||||
* #1456: add perf recommendation for LLT and storage format (55fbf4fedd04, 9fd138e2b333)
|
||||
* #1455: Cholesky module depends on Jacobi for rank-updates (b87875abf8dc)
|
||||
* #1458: fix documentation of LLT and LDLT `info()` method (ac2c97edff07)
|
||||
* Warn about constness in `LLT::solveInPlace` (51e1aa153957)
|
||||
* Fix lazyness of `operator*` with CUDA (fa77d713359d)
|
||||
* #336: improve doc for `PlainObjectBase::Map` (18868228adae)
|
||||
|
||||
* Other general improvements:
|
||||
* Enable linear indexing in generic block evaluation (31537598bf83, 5967bc3c2cdb, #1543).
|
||||
* Fix packet and alignment propagation logic of `Block<Xpr>` expressions. In particular, `(A+B).col(j)` now preserve vectorisation. (b323cc9c2c7f)
|
||||
* Several fixes regarding custom scalar type support: hypot (f8d6c791791d), boost-multiprec (acb8ef9b2478), literal casts (6bbd97f17534, 39f65d65894f),
|
||||
* LLT: avoid making a copy when decomposing in place (2f7e28920f4e), const the arg to `solveInPlace()` to allow passing `.transpose()`, `.block()`, etc. (c31c0090e998).
|
||||
* Add possibility to overwrite `EIGEN_STRONG_INLINE` (7094bbdf3f4d)
|
||||
* #1528: use `numeric_limits::min()` instead of `1/highest()` that might underflow (dd823c64ade7)
|
||||
* #1532: disable `stl::*_negate` in C++17 (they are deprecated) (88e9452099d5)
|
||||
* Add C++11 `max_digits10` for half (faf74dde8ed1)
|
||||
* Make sparse QR result sizes consistent with dense QR (4638bc4d0f96)
|
||||
* Enable linear indexing in generic block evaluation (15752027ec2f, 80af7d6a47c1, #1543).
|
||||
* Fix packet and alignment propagation logic of `Block<Xpr>` expressions. In particular, `(A+B).col(j)` now preserve vectorisation. (9c9e90f6db7e)
|
||||
* Several fixes regarding custom scalar type support: hypot (385d8b5e42c2), boost-multiprec (5f71579a2d3f), literal casts (e6577f3c3049, fbb0c510c52f),
|
||||
* LLT: avoid making a copy when decomposing in place (9d03711df8bc), const the arg to `solveInPlace()` to allow passing `.transpose()`, `.block()`, etc. (0137ed4f19b6).
|
||||
* Add possibility to overwrite `EIGEN_STRONG_INLINE` (6d6e5fcd4356)
|
||||
* #1528: use `numeric_limits::min()` instead of `1/highest()` that might underflow (9ff315024335)
|
||||
* #1532: disable `stl::*_negate` in C++17 (they are deprecated) (3fb42ff7b278)
|
||||
* Add C++11 `max_digits10` for half (70ac6c923001)
|
||||
* Make sparse QR result sizes consistent with dense QR (2136cfa17e28)
|
||||
|
||||
* Unsupported/unit-tests/cmake/unvisible internals/etc.
|
||||
* #1484: restore deleted line for 128 bits long doubles, and improve dispatching logic. (dffc0f957f19)
|
||||
* #1462: remove all occurences of the deprecated `__CUDACC_VER__` macro by introducing `EIGEN_CUDACC_VER` (a201b8438d36)
|
||||
* Changeset 2722aa8eb93f: Fix oversharding bug in parallelFor.
|
||||
* Changeset ea1db80eab46: commit 45e9c9996da790b55ed9c4b0dfeae49492ac5c46 (HEAD -> memory_fix)
|
||||
* Changeset 350957be012c: Fix int versus Index
|
||||
* Changeset 424038431015: fix linking issue
|
||||
* Changeset 3f938790b7e0: Fix short vs long
|
||||
* Changeset ba14974d054a: Fix cmake scripts with no fortran compiler
|
||||
* Changeset 2ac088501976: add cmake-option to enable/disable creation of tests
|
||||
* Changeset 56996c54158b: Use col method for column-major matrix
|
||||
* Changeset 762373ca9793: #1449: fix `redux_3` unit test
|
||||
* Changeset eda96fd2fa30: Fix uninitialized output argument.
|
||||
* Changeset 75a12dff8ca4: Handle min/max/inf/etc issue in `cuda_fp16.h` directly in `test/main.h`
|
||||
* Changeset 568614bf79b8: Add tests for sparseQR results (value and size) covering bugs 1522 and 1544
|
||||
* Changeset 12c9ece47d14: `SelfAdjointView<...,Mode>` causes a static assert since commit c73a77e47db8
|
||||
* Changeset 899fd2ef704f: weird compilation issue in `mapped_matrix.cpp`
|
||||
* #1484: restore deleted line for 128 bits long doubles, and improve dispatching logic. (c8e663fe87ec)
|
||||
* #1462: remove all occurences of the deprecated `__CUDACC_VER__` macro by introducing `EIGEN_CUDACC_VER` (e7c065ec717b)
|
||||
* Changeset fea50d40ea79: Fix oversharding bug in parallelFor.
|
||||
* Changeset 866d222d6065: commit 45e9c9996da790b55ed9c4b0dfeae49492ac5c46 (HEAD -> memory_fix)
|
||||
* Changeset 48048172e5aa: Fix int versus Index
|
||||
* Changeset 906a98fe39c3: fix linking issue
|
||||
* Changeset 352489edbe36: Fix short vs long
|
||||
* Changeset 81e94eea024c: Fix cmake scripts with no fortran compiler
|
||||
* Changeset 8bd392ca0e3f: add cmake-option to enable/disable creation of tests
|
||||
* Changeset 02c0cef97fb5: Use col method for column-major matrix
|
||||
* Changeset a8d2459f8e1f: #1449: fix `redux_3` unit test
|
||||
* Changeset e90a14609a56: Fix uninitialized output argument.
|
||||
* Changeset 5d40715db6a7: Handle min/max/inf/etc issue in `cuda_fp16.h` directly in `test/main.h`
|
||||
* Changeset 2f9de522457b: Add tests for sparseQR results (value and size) covering bugs 1522 and 1544
|
||||
* Changeset 4662c610c13c: `SelfAdjointView<...,Mode>` causes a static assert since commit d820ab9edc0b
|
||||
* Changeset 96134409fc91: weird compilation issue in `mapped_matrix.cpp`
|
||||
|
||||
## [3.3.4] - 2017-06-15
|
||||
|
||||
@@ -697,7 +697,7 @@ Main changes since 3.3-beta1:
|
||||
* #779: in `Map`, allows non aligned buffers for buffers smaller than the requested alignment.
|
||||
* Add a complete orthogonal decomposition class: [CompleteOrthogonalDecomposition](http://eigen.tuxfamily.org/dox-devel/classEigen_1_1CompleteOrthogonalDecomposition.html)
|
||||
* Improve robustness of JacoviSVD with complexes (underflow, noise amplification in complex to real conversion, compare off-diagonal entries to the current biggest diagonal entry instead of the global biggest, null inputs).
|
||||
* Change Eigen's ColPivHouseholderQR to use a numerically stable norm downdate formula (changeset 9da6c621d055)
|
||||
* Change Eigen's ColPivHouseholderQR to use a numerically stable norm downdate formula (changeset acce4dd0500f)
|
||||
* #1214: consider denormals as zero in D&C SVD. This also workaround infinite binary search when compiling with ICC's unsafe optimizations.
|
||||
* Add log1p for arrays.
|
||||
* #1193: now `lpNorm<Infinity>` supports empty inputs.
|
||||
@@ -720,7 +720,7 @@ Main changes since 3.3-beta1:
|
||||
* Performance improvements:
|
||||
* #256: enable vectorization with unaligned loads/stores. This concerns all architectures and all sizes. This new behavior can be disabled by defining `EIGEN_UNALIGNED_VECTORIZE=0`
|
||||
* Add support for s390x(zEC13) ZVECTOR instruction set.
|
||||
* Optimize mixing of real with complex matrices by avoiding a conversion from real to complex when the real types do not match exactly. (see bccae23d7018)
|
||||
* Optimize mixing of real with complex matrices by avoiding a conversion from real to complex when the real types do not match exactly. (see 76faf4a9657e)
|
||||
* Speedup square roots in performance critical methods such as norm, normalize(d).
|
||||
* #1154: use dynamic scheduling for spmv products.
|
||||
* #667, #1181: improve perf with MSVC and ICC through `FORCE_INLINE`
|
||||
@@ -910,7 +910,7 @@ Main changes since 3.3-alpha1:
|
||||
* Add temporary-free evaluation of `D.nolias() *= C + A*B`.
|
||||
* Add vectorization of round, ceil and floor for SSE4.1/AVX.
|
||||
* Optimize assignment into a `Block<SparseMatrix>` by using Ref and avoiding useless updates in non-compressed mode. This make row-by-row filling of a row-major sparse matrix very efficient.
|
||||
* Improve internal cost model leading to faster code in some cases (see changeset 1bcb41187a45).
|
||||
* Improve internal cost model leading to faster code in some cases (see changeset 77ff3386b7d2).
|
||||
* #1090: improve redux evaluation logic.
|
||||
* Enable unaligned vectorization of small fixed size matrix products.
|
||||
|
||||
|
||||
@@ -106,6 +106,11 @@
|
||||
#include <thread>
|
||||
#endif
|
||||
|
||||
// for __cpp_lib feature test macros
|
||||
#if defined(__has_include) && __has_include(<version>)
|
||||
#include <version>
|
||||
#endif
|
||||
|
||||
// for std::bit_cast()
|
||||
#if defined(__cpp_lib_bit_cast) && __cpp_lib_bit_cast >= 201806L
|
||||
#include <bit>
|
||||
|
||||
@@ -15,6 +15,7 @@
|
||||
#include "Householder"
|
||||
#include "LU"
|
||||
#include "Geometry"
|
||||
#include "Sparse" // Needed by ComplexQZ.
|
||||
|
||||
#include "src/Core/util/DisableStupidWarnings.h"
|
||||
|
||||
@@ -32,8 +33,6 @@
|
||||
* \endcode
|
||||
*/
|
||||
|
||||
#include "src/misc/RealSvd2x2.h"
|
||||
|
||||
// IWYU pragma: begin_exports
|
||||
#include "src/Eigenvalues/Tridiagonalization.h"
|
||||
#include "src/Eigenvalues/RealSchur.h"
|
||||
|
||||
@@ -33,7 +33,6 @@
|
||||
*/
|
||||
|
||||
// IWYU pragma: begin_exports
|
||||
#include "src/misc/RealSvd2x2.h"
|
||||
#include "src/SVD/UpperBidiagonalization.h"
|
||||
#include "src/SVD/SVDBase.h"
|
||||
#include "src/SVD/JacobiSVD.h"
|
||||
|
||||
@@ -2831,7 +2831,7 @@ inline __m128i segment_mask_4x8(Index begin, Index count) {
|
||||
mask <<= CHAR_BIT * count;
|
||||
mask--;
|
||||
mask <<= CHAR_BIT * begin;
|
||||
#if defined(_WIN32) && !defined(_WIN64)
|
||||
#if !EIGEN_ARCH_x86_64
|
||||
return _mm_loadl_epi64(reinterpret_cast<const __m128i*>(&mask));
|
||||
#else
|
||||
return _mm_cvtsi64_si128(mask);
|
||||
@@ -2847,7 +2847,7 @@ inline __m128i segment_mask_8x8(Index begin, Index count) {
|
||||
mask <<= (CHAR_BIT / 2) * count;
|
||||
mask--;
|
||||
mask <<= CHAR_BIT * begin;
|
||||
#if defined(_WIN32) && !defined(_WIN64)
|
||||
#if !EIGEN_ARCH_x86_64
|
||||
return _mm_loadl_epi64(reinterpret_cast<const __m128i*>(&mask));
|
||||
#else
|
||||
return _mm_cvtsi64_si128(mask);
|
||||
|
||||
@@ -11,14 +11,9 @@
|
||||
//
|
||||
// Derived from: Eigen/src/Eigenvalues/RealQZ.h
|
||||
|
||||
#include "Eigen/Core"
|
||||
#include "Eigen/Jacobi"
|
||||
|
||||
#ifndef EIGEN_COMPLEX_QZ_H_
|
||||
#define EIGEN_COMPLEX_QZ_H_
|
||||
|
||||
#include "../../SparseQR"
|
||||
|
||||
// IWYU pragma: private
|
||||
#include "./InternalHeaderCheck.h"
|
||||
|
||||
@@ -129,9 +124,7 @@ class ComplexQZ {
|
||||
computeQZ ? n : (MatrixType::ColsAtCompileTime == Eigen::Dynamic ? 0 : MatrixType::ColsAtCompileTime)),
|
||||
m_ws(2 * n),
|
||||
m_computeQZ(computeQZ),
|
||||
m_maxIters(maxIters){
|
||||
|
||||
};
|
||||
m_maxIters(maxIters) {}
|
||||
|
||||
/** \brief Constructor. computes the QZ decomposition of given matrices
|
||||
* upon creation
|
||||
@@ -181,14 +174,14 @@ class ComplexQZ {
|
||||
*
|
||||
* \returns \c Success if computation was successfull, \c NoConvergence otherwise.
|
||||
*/
|
||||
ComputationInfo info() const { return m_info; };
|
||||
ComputationInfo info() const { return m_info; }
|
||||
|
||||
/** \brief number of performed QZ steps
|
||||
*/
|
||||
unsigned int iterations() const {
|
||||
eigen_assert(m_isInitialized && "ComplexQZ is not initialized.");
|
||||
return m_global_iter;
|
||||
};
|
||||
}
|
||||
|
||||
private:
|
||||
Index m_n;
|
||||
@@ -269,8 +262,6 @@ void ComplexQZ<MatrixType_>::hessenbergTriangular(const MatrixType& A, const Mat
|
||||
|
||||
if (m_computeQZ) m_Z = MatrixType::Identity(m_n, m_n);
|
||||
|
||||
int steps = 0;
|
||||
|
||||
// reduce S to upper Hessenberg with Givens rotations
|
||||
for (Index j = 0; j <= m_n - 3; j++) {
|
||||
for (Index i = m_n - 1; i >= j + 2; i--) {
|
||||
@@ -300,7 +291,6 @@ void ComplexQZ<MatrixType_>::hessenbergTriangular(const MatrixType& A, const Mat
|
||||
// update Z
|
||||
if (m_computeQZ) m_Z.applyOnTheLeft(i - 1, i, G);
|
||||
}
|
||||
steps++;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -331,7 +321,6 @@ void ComplexQZ<MatrixType>::hessenbergTriangularSparse(const SparseMatrixType_&
|
||||
|
||||
if (m_computeQZ) m_Z = MatrixType::Identity(m_n, m_n);
|
||||
|
||||
unsigned int steps = 0;
|
||||
// reduce S to upper Hessenberg with Givens rotations
|
||||
for (Index j = 0; j <= m_n - 3; j++) {
|
||||
for (Index i = m_n - 1; i >= j + 2; i--) {
|
||||
@@ -363,7 +352,6 @@ void ComplexQZ<MatrixType>::hessenbergTriangularSparse(const SparseMatrixType_&
|
||||
// update Z
|
||||
if (m_computeQZ) m_Z.applyOnTheLeft(i - 1, i, G);
|
||||
}
|
||||
steps++;
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -615,7 +603,7 @@ void ComplexQZ<MatrixType_>::push_down_zero_ST(Index k, Index l) {
|
||||
m_T(l, l) = Scalar(0);
|
||||
m_S(l, l - 1) = Scalar(0);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/** \internal Computes vector L1 norms of S and T when in Hessenberg-Triangular form already */
|
||||
template <typename MatrixType_>
|
||||
@@ -627,7 +615,7 @@ void ComplexQZ<MatrixType_>::computeNorms() {
|
||||
m_normOfS += m_S.col(j).segment(0, (std::min)(size, j + 2)).cwiseAbs().sum();
|
||||
m_normOfT += m_T.row(j).segment(j, size - j).cwiseAbs().sum();
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/** \internal Look for single small sub-diagonal element S(res, res-1) and return res (or 0). Copied from Eigen3 RealQZ
|
||||
* implementation */
|
||||
|
||||
@@ -420,6 +420,34 @@ EIGEN_DEVICE_FUNC void inline apply_rotation_in_the_plane(DenseBase<VectorX>& xp
|
||||
x, incrx, y, incry, size, c, s);
|
||||
}
|
||||
|
||||
template <typename MatrixType, typename RealScalar, typename Index>
|
||||
void real_2x2_jacobi_svd(const MatrixType& matrix, Index p, Index q, JacobiRotation<RealScalar>* j_left,
|
||||
JacobiRotation<RealScalar>* j_right) {
|
||||
using std::abs;
|
||||
using std::sqrt;
|
||||
Matrix<RealScalar, 2, 2> m;
|
||||
m << numext::real(matrix.coeff(p, p)), numext::real(matrix.coeff(p, q)), numext::real(matrix.coeff(q, p)),
|
||||
numext::real(matrix.coeff(q, q));
|
||||
JacobiRotation<RealScalar> rot1;
|
||||
RealScalar t = m.coeff(0, 0) + m.coeff(1, 1);
|
||||
RealScalar d = m.coeff(1, 0) - m.coeff(0, 1);
|
||||
|
||||
if (abs(d) < (std::numeric_limits<RealScalar>::min)()) {
|
||||
rot1.s() = RealScalar(0);
|
||||
rot1.c() = RealScalar(1);
|
||||
} else {
|
||||
// If d!=0, then t/d cannot overflow because the magnitude of the
|
||||
// entries forming d are not too small compared to the ones forming t.
|
||||
RealScalar u = t / d;
|
||||
RealScalar tmp = sqrt(RealScalar(1) + numext::abs2(u));
|
||||
rot1.s() = RealScalar(1) / tmp;
|
||||
rot1.c() = u / tmp;
|
||||
}
|
||||
m.applyOnTheLeft(0, 1, rot1);
|
||||
j_right->makeJacobi(m, 0, 1);
|
||||
*j_left = rot1 * j_right->transpose();
|
||||
}
|
||||
|
||||
} // end namespace internal
|
||||
|
||||
} // end namespace Eigen
|
||||
|
||||
@@ -89,7 +89,7 @@ struct simpl_chol_helper {
|
||||
m_set[u] = v;
|
||||
u = next;
|
||||
}
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
// Computes the higher adjacency pattern by transposing the input lower adjacency matrix.
|
||||
|
||||
@@ -140,7 +140,7 @@ class SparseVector : public SparseCompressedBase<SparseVector<Scalar_, Options_,
|
||||
return insertBack(inner);
|
||||
}
|
||||
inline Scalar& insertBack(Index i) {
|
||||
m_data.append(0, i);
|
||||
m_data.append(Scalar(0), i);
|
||||
return m_data.value(m_data.size() - 1);
|
||||
}
|
||||
|
||||
@@ -150,7 +150,7 @@ class SparseVector : public SparseCompressedBase<SparseVector<Scalar_, Options_,
|
||||
return insertBackUnordered(inner);
|
||||
}
|
||||
inline Scalar& insertBackUnordered(Index i) {
|
||||
m_data.append(0, i);
|
||||
m_data.append(Scalar(0), i);
|
||||
return m_data.value(m_data.size() - 1);
|
||||
}
|
||||
|
||||
@@ -367,7 +367,7 @@ class SparseVector : public SparseCompressedBase<SparseVector<Scalar_, Options_,
|
||||
|
||||
/** \internal \deprecated use insertBack(Index) */
|
||||
EIGEN_DEPRECATED_WITH_REASON("Use .insertBack() instead.") Scalar& fill(Index i) {
|
||||
m_data.append(0, i);
|
||||
m_data.append(Scalar(0), i);
|
||||
return m_data.value(m_data.size() - 1);
|
||||
}
|
||||
|
||||
|
||||
@@ -1,53 +0,0 @@
|
||||
// This file is part of Eigen, a lightweight C++ template library
|
||||
// for linear algebra.
|
||||
//
|
||||
// Copyright (C) 2009-2010 Benoit Jacob <jacob.benoit.1@gmail.com>
|
||||
// Copyright (C) 2013-2016 Gael Guennebaud <gael.guennebaud@inria.fr>
|
||||
//
|
||||
// This Source Code Form is subject to the terms of the Mozilla
|
||||
// Public License v. 2.0. If a copy of the MPL was not distributed
|
||||
// with this file, You can obtain one at http://mozilla.org/MPL/2.0/.
|
||||
|
||||
#ifndef EIGEN_REALSVD2X2_H
|
||||
#define EIGEN_REALSVD2X2_H
|
||||
|
||||
// IWYU pragma: private
|
||||
#include "./InternalHeaderCheck.h"
|
||||
|
||||
namespace Eigen {
|
||||
|
||||
namespace internal {
|
||||
|
||||
template <typename MatrixType, typename RealScalar, typename Index>
|
||||
void real_2x2_jacobi_svd(const MatrixType &matrix, Index p, Index q, JacobiRotation<RealScalar> *j_left,
|
||||
JacobiRotation<RealScalar> *j_right) {
|
||||
using std::abs;
|
||||
using std::sqrt;
|
||||
Matrix<RealScalar, 2, 2> m;
|
||||
m << numext::real(matrix.coeff(p, p)), numext::real(matrix.coeff(p, q)), numext::real(matrix.coeff(q, p)),
|
||||
numext::real(matrix.coeff(q, q));
|
||||
JacobiRotation<RealScalar> rot1;
|
||||
RealScalar t = m.coeff(0, 0) + m.coeff(1, 1);
|
||||
RealScalar d = m.coeff(1, 0) - m.coeff(0, 1);
|
||||
|
||||
if (abs(d) < (std::numeric_limits<RealScalar>::min)()) {
|
||||
rot1.s() = RealScalar(0);
|
||||
rot1.c() = RealScalar(1);
|
||||
} else {
|
||||
// If d!=0, then t/d cannot overflow because the magnitude of the
|
||||
// entries forming d are not too small compared to the ones forming t.
|
||||
RealScalar u = t / d;
|
||||
RealScalar tmp = sqrt(RealScalar(1) + numext::abs2(u));
|
||||
rot1.s() = RealScalar(1) / tmp;
|
||||
rot1.c() = u / tmp;
|
||||
}
|
||||
m.applyOnTheLeft(0, 1, rot1);
|
||||
j_right->makeJacobi(m, 0, 1);
|
||||
*j_left = rot1 * j_right->transpose();
|
||||
}
|
||||
|
||||
} // end namespace internal
|
||||
|
||||
} // end namespace Eigen
|
||||
|
||||
#endif // EIGEN_REALSVD2X2_H
|
||||
@@ -164,7 +164,7 @@ build:linux:cuda-12.2:clang-12:
|
||||
EIGEN_CI_CXX_COMPILER: clang++-12
|
||||
EIGEN_CI_TEST_CUDA_CLANG: "on"
|
||||
|
||||
# ######## HIP ###################################################################
|
||||
######### HIP ##################################################################
|
||||
# Note: these are currently build-only, until we get an AMD-supported runner.
|
||||
|
||||
# ROCm HIP
|
||||
@@ -176,7 +176,7 @@ build:linux:rocm-latest:gcc-10:
|
||||
EIGEN_CI_CXX_COMPILER: g++-10
|
||||
EIGEN_CI_BUILD_TARGET: buildtests_gpu
|
||||
EIGEN_CI_ADDITIONAL_ARGS: -DEIGEN_TEST_HIP=on
|
||||
cache: {} # Disable cache for ROCm, since it fails whenever the image updates.
|
||||
cache: [] # Disable cache for ROCm, since it fails whenever the image updates.
|
||||
|
||||
|
||||
######## Arm ###################################################################
|
||||
@@ -290,7 +290,7 @@ build:linux:cross:x86-64:gcc-10:default:smoketest:
|
||||
rules:
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
|
||||
tags:
|
||||
- saas-linux-small-amd64
|
||||
- saas-linux-medium-amd64
|
||||
|
||||
build:linux:cross:x86-64:clang-12:default:smoketest:
|
||||
extends: build:linux:cross:x86-64:clang-12:default
|
||||
@@ -299,4 +299,4 @@ build:linux:cross:x86-64:clang-12:default:smoketest:
|
||||
rules:
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
|
||||
tags:
|
||||
- saas-linux-small-amd64
|
||||
- saas-linux-medium-amd64
|
||||
|
||||
@@ -13,19 +13,29 @@ elif [[ ${EIGEN_CI_CTEST_LABEL} ]]; then
|
||||
target="-L ${EIGEN_CI_CTEST_LABEL}"
|
||||
fi
|
||||
|
||||
# Repeat tests up to three times to ignore flakes. Do not re-run with -T test,
|
||||
# otherwise we lose test results for those that passed.
|
||||
# Note: starting with CMake 3.17, we can use --repeat until-pass:3, but we have
|
||||
# no way of easily installing this on ppc64le.
|
||||
ctest ${EIGEN_CI_CTEST_ARGS} --parallel ${NPROC} \
|
||||
--output-on-failure --no-compress-output \
|
||||
--build-no-clean -T test ${target} || \
|
||||
ctest ${EIGEN_CI_CTEST_ARGS} --parallel ${NPROC} \
|
||||
--output-on-failure --no-compress-output --rerun-failed || \
|
||||
ctest ${EIGEN_CI_CTEST_ARGS} --parallel ${NPROC} \
|
||||
--output-on-failure --no-compress-output --rerun-failed
|
||||
set +x
|
||||
|
||||
ctest_cmd="ctest ${EIGEN_CI_CTEST_ARGS} --parallel ${NPROC} --output-on-failure --no-compress-output --build-noclean ${target}"
|
||||
|
||||
echo "Running initial tests..."
|
||||
if ${ctest_cmd} -T test; then
|
||||
echo "Tests passed on the first attempt."
|
||||
exit_code=$?
|
||||
else
|
||||
echo "Initial tests failed with exit code $?. Retrying up to ${EIGEN_CI_CTEST_REPEAT} times..."
|
||||
if ${ctest_cmd} --rerun-failed --repeat until-pass:${EIGEN_CI_CTEST_REPEAT}; then
|
||||
echo "Tests passed on retry."
|
||||
exit_code=42
|
||||
else
|
||||
exit_code=$?
|
||||
fi
|
||||
fi
|
||||
|
||||
set -x
|
||||
|
||||
# Return to root directory.
|
||||
cd ${rootdir}
|
||||
|
||||
set +x
|
||||
|
||||
exit $exit_code
|
||||
|
||||
@@ -13,18 +13,32 @@ if (${EIGEN_CI_CTEST_REGEX}) {
|
||||
$target = "-L","${EIGEN_CI_CTEST_LABEL}"
|
||||
}
|
||||
|
||||
# Repeat tests up to three times to ignore flakes. Do not re-run with -T test,
|
||||
# otherwise we lose test results for those that passed.
|
||||
# Note: starting with CMake 3.17, we can use --repeat until-pass:3, but we have
|
||||
# no way of easily installing this on ppc64le.
|
||||
ctest $EIGEN_CI_CTEST_ARGS -j$NPROC --output-on-failure --no-compress-output --build-no-clean -T test $target || `
|
||||
ctest $EIGEN_CI_CTEST_ARGS -j$NPROC --output-on-failure --no-compress-output --rerun-failed || `
|
||||
ctest $EIGEN_CI_CTEST_ARGS -j$NPROC --output-on-failure --no-compress-output --rerun-failed
|
||||
$ctest_cmd = { ctest ${EIGEN_CI_CTEST_ARGS} --parallel ${NPROC} --output-on-failure --no-compress-output --build-noclean ${target} }
|
||||
|
||||
$success = $LASTEXITCODE
|
||||
Write-Host "Running initial tests..."
|
||||
|
||||
& $ctest_cmd "-T test"
|
||||
$exit_code = $LASTEXITCODE
|
||||
|
||||
if ($exit_code -eq 0) {
|
||||
Write-Host "Tests passed on the first attempt."
|
||||
}
|
||||
else {
|
||||
Write-Host "Initial tests failed with exit code $exit_code. Retrying up to $EIGEN_CI_CTEST_REPEAT times..."
|
||||
# TODO: figure out how to use --repeat until-pass
|
||||
for ($i = 1; $i -le $EIGEN_CI_CTEST_REPEAT; $i++) {
|
||||
& $ctest_cmd "--rerun-failed"
|
||||
$exit_code = $LASTEXITCODE
|
||||
|
||||
if ($exit_code -eq 0) {
|
||||
Write-Host "Tests passed on retry."
|
||||
$exit_code = 42
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
# Return to root directory.
|
||||
cd ${rootdir}
|
||||
|
||||
# Explicitly propagate exit code to indicate pass/failure of test command.
|
||||
if($success -ne 0) { Exit $success }
|
||||
Exit $exit_code
|
||||
|
||||
@@ -11,6 +11,8 @@
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event" && $CI_PROJECT_NAMESPACE == "libeigen" && $CI_MERGE_REQUEST_LABELS =~ "/all-tests/"
|
||||
tags:
|
||||
- saas-linux-2xlarge-amd64
|
||||
allow_failure:
|
||||
exit_codes: 42
|
||||
|
||||
##### x86-64 ###################################################################
|
||||
.test:linux:x86-64:
|
||||
@@ -384,7 +386,7 @@ test:linux:x86-64:gcc-10:default:smoketest:
|
||||
rules:
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
|
||||
tags:
|
||||
- saas-linux-small-amd64
|
||||
- saas-linux-medium-amd64
|
||||
|
||||
test:linux:x86-64:clang-12:default:smoketest:
|
||||
extends: .test:linux:x86-64:clang-12:default
|
||||
@@ -394,4 +396,4 @@ test:linux:x86-64:clang-12:default:smoketest:
|
||||
rules:
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event"
|
||||
tags:
|
||||
- saas-linux-small-amd64
|
||||
- saas-linux-medium-amd64
|
||||
|
||||
@@ -9,11 +9,12 @@
|
||||
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PROJECT_NAMESPACE == "libeigen"
|
||||
- if: $CI_PIPELINE_SOURCE == "web" && $CI_PROJECT_NAMESPACE == "libeigen"
|
||||
- if: $CI_PIPELINE_SOURCE == "merge_request_event" && $CI_PROJECT_NAMESPACE == "libeigen" && $CI_MERGE_REQUEST_LABELS =~ "/all-tests/"
|
||||
|
||||
tags:
|
||||
- eigen-runner
|
||||
- windows
|
||||
- x86-64
|
||||
allow_failure:
|
||||
exit_codes: 42
|
||||
|
||||
##### MSVC #####################################################################
|
||||
|
||||
|
||||
@@ -91,7 +91,7 @@ set(ei_smoke_test_list
|
||||
qr_1
|
||||
qr_colpivoting_7
|
||||
qr_fullpivoting_4
|
||||
rand
|
||||
rand_1
|
||||
real_qz_1
|
||||
redux_1
|
||||
ref_1
|
||||
|
||||
@@ -36,9 +36,9 @@ option in `find_package`:
|
||||
```
|
||||
find_package(Eigen3 3.4 REQUIRED NO_MODULE) # Restricts to 3.4.z
|
||||
```
|
||||
or to support a range of versions:
|
||||
Starting with Eigen 3.4.1, we also support a range spanning major versions:
|
||||
```
|
||||
find_package(Eigen3 3.4...5 REQUIRED NO_MODULE) # Any version >=3.4.0 but <6.0.0.
|
||||
find_package(Eigen3 3.4...5 REQUIRED NO_MODULE) # Any version >=3.4.1 but <6.0.0.
|
||||
```
|
||||
|
||||
Do not forget to set the <a href="https://cmake.org/cmake/help/v3.7/variable/CMAKE_PREFIX_PATH.html">\c CMAKE_PREFIX_PATH </a> variable if Eigen is not installed in a default location or if you want to pick a specific version. For instance:
|
||||
|
||||
12
test/main.h
12
test/main.h
@@ -186,7 +186,7 @@ inline void on_temporary_creation(long int size, int) {
|
||||
|
||||
namespace Eigen {
|
||||
static std::vector<std::string> g_test_stack;
|
||||
// level == 0 <=> abort if test fail
|
||||
// level == 0 <=> return 1 if test fail
|
||||
// level >= 1 <=> warning message to std::cerr if test fail
|
||||
static int g_test_level = 0;
|
||||
static int g_repeat = 1;
|
||||
@@ -356,7 +356,7 @@ inline void verify_impl(bool condition, const char* testname, const char* file,
|
||||
const int test_stack_size = static_cast<int>(Eigen::g_test_stack.size());
|
||||
for (int i = test_stack_size - 1; i >= 0; --i) std::cerr << " - " << Eigen::g_test_stack[i] << "\n";
|
||||
std::cerr << "\n";
|
||||
if (Eigen::g_test_level == 0) abort();
|
||||
if (Eigen::g_test_level == 0) exit(1);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -858,6 +858,12 @@ inline void set_seed_from_string(const char* str) {
|
||||
g_has_set_seed = true;
|
||||
}
|
||||
|
||||
inline void set_seed_from_time() {
|
||||
using namespace std::chrono;
|
||||
long long ns = duration_cast<nanoseconds>(high_resolution_clock::now().time_since_epoch()).count();
|
||||
g_seed = static_cast<decltype(g_seed)>(ns);
|
||||
}
|
||||
|
||||
int main(int argc, char* argv[]) {
|
||||
g_has_set_repeat = false;
|
||||
g_has_set_seed = false;
|
||||
@@ -896,7 +902,7 @@ int main(int argc, char* argv[]) {
|
||||
char* env_EIGEN_SEED = getenv("EIGEN_SEED");
|
||||
if (!g_has_set_seed && env_EIGEN_SEED) set_seed_from_string(env_EIGEN_SEED);
|
||||
|
||||
if (!g_has_set_seed) g_seed = (unsigned int)time(NULL);
|
||||
if (!g_has_set_seed) set_seed_from_time();
|
||||
if (!g_has_set_repeat) g_repeat = DEFAULT_REPEAT;
|
||||
|
||||
std::cout << "Initializing random number generator with seed " << g_seed << std::endl;
|
||||
|
||||
@@ -454,8 +454,16 @@ ArpackGeneralizedSelfAdjointEigenSolver<MatrixType, MatrixSolver, BisSPD>::compu
|
||||
}
|
||||
}
|
||||
|
||||
if (!(mode == 1 && isBempty) && !(mode == 2 && isBempty) && OP.info() != Success)
|
||||
std::cout << "Error factoring matrix" << std::endl;
|
||||
if (!(mode == 1 && isBempty) && !(mode == 2 && isBempty) && OP.info() != Success) {
|
||||
m_info = OP.info() delete[] v;
|
||||
delete[] iparam;
|
||||
delete[] ipntr;
|
||||
delete[] workd;
|
||||
delete[] workl;
|
||||
delete[] resid;
|
||||
m_isInitialized = false;
|
||||
return *this;
|
||||
}
|
||||
|
||||
do {
|
||||
internal::arpack_wrapper<Scalar, RealScalar>::saupd(&ido, bmat, &n, whch, &nev, &tol, resid, &ncv, v, &ldv, iparam,
|
||||
@@ -572,7 +580,7 @@ ArpackGeneralizedSelfAdjointEigenSolver<MatrixType, MatrixSolver, BisSPD>::compu
|
||||
delete[] workl;
|
||||
delete[] resid;
|
||||
|
||||
m_isInitialized = true;
|
||||
m_isInitialized = (m_info == Success);
|
||||
|
||||
return *this;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user