CFD/eigen
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,400 Commits 2 Branches 88 Tags 112 MiB
7dd81aad74
Commit Graph

681 Commits

Author SHA1 Message Date
Benoit Jacob
13f31b8daf * make PartialLU avoid to generate inf/nan when given a singular matrix 
(result undefined, but at least it won't take forever on intel 387)
* add lots of comments, especially to LU.h
* fix stuff I had broken in Inverse.h
* split inverse test
 2009-10-20 00:36:07 -04:00
Benoit Jacob
6c1b91678b kill ei_add_test_multi. Now the macro ei_add_test does all that automatically, by parsing the source file. No risk anymore to specify the wrong number of tests! Also, introduce CALL_SUBTESTX for X=1..10 that allows to port existing code much quicker. And port already the product* and eigensolver* files. 2009-10-19 14:40:35 -04:00
Benoit Jacob
580672ea43 Add new default option EIGEN_SPLIT_LARGE_TESTS and cmake macro ei_add_test_multi. 
When enabled, large tests are split into smaller executables.
This needs minimal changes in the unit tests.
Updated the LU test to use it.
 2009-10-19 13:29:00 -04:00
Benoit Jacob
9a700c2974 * LU unit test: finally test fixed sizes 
* ReturnByValue: after all don't eval to temporary for generic MatrixBase impl
 2009-10-19 10:56:37 -04:00
Benoit Jacob
47eeb40380 remove the m_originalMatrix member. Instead, image() now takes the original matrix as parameter. It was the only method to use it anyway. Introduce m_isInitialized. 2009-10-18 15:21:19 -04:00
Benoit Jacob
0255f28279 oops, didn't want to commit that 2009-10-18 01:35:07 -04:00
Benoit Jacob
8332c232db big huge changes in LU! 
* continue the decomposition until a pivot is exactly zero;
  don't try to compute the rank in the decomposition itself.
* Instead, methods such as rank() use a new internal parameter
  called 'threshold' to determine which pivots are to be
  considered nonzero.
* The threshold is by default determined by defaultThreshold()
  but the user can override that by calling useThreshold(value).
* In solve/kernel/image, don't assume that the diagonal of U
  is sorted in decreasing order, because that's only approximately
  true. Additional work was needed to extract the right pivots.
 2009-10-18 00:47:40 -04:00
Benoit Jacob
3c4a025a54 merge 2009-10-15 16:09:43 -04:00
Hauke Heibel
0927ba1fd3 More warning fixes. 2009-10-14 19:55:23 +02:00
Gael Guennebaud
1443094072 compilation fix: make the generic template ctor explicit 2009-10-13 09:23:09 +02:00
Gael Guennebaud
2049f742e4 trivial compilation fix 2009-10-13 08:53:01 +02:00
Benoit Jacob
c4ab6a2032 also test that the matrix Q is unitary 2009-10-12 22:33:51 -04:00
Hauke Heibel
e5bf72679c Fixed nmake parameter. 
Disabled debug_* targets for MSVC_IDE (they already exist).
Removed the make usage message for MSVC_IDE.
 2009-10-09 14:09:25 +02:00
Gael Guennebaud
af31345df3 really fix stable norm compilation for older gcc 2009-10-07 14:25:12 +02:00
Gael Guennebaud
4cf7366027 fix compilation in stable norm, move a platform check to the unit tests 2009-10-06 10:24:41 +02:00
Gael Guennebaud
904f35d194 discard vectorization in matrix-vector product when data is not even 
aligned on the scalar type size (e.g., for double on 32 bits system without -malign-double)
 2009-10-05 17:22:16 +02:00
Benoit Jacob
bb1cc0d092 after all we're not aligning to 8byte boundary 
keep most of the changes though as they make the code more extensible
 2009-10-05 10:55:42 -04:00
Benoit Jacob
d41577819b we were already aligning to 16 byte boundary fixed-size objects that are multiple of 16 bytes; 
now we also align to 8byte boundary fixed-size objects that are multiple of 8 bytes.
That's only useful for now for double, not e.g. for Vector2f, but that didn't seem to hurt. Am I missing something? Do you prefer that we don't align Vector2f at all?
Also, improvements in test_unalignedassert.
 2009-10-05 10:11:11 -04:00
Benoit Jacob
a9a9ba8453 remove unneeded stuff 2009-10-05 07:58:53 -04:00
Benoit Jacob
fa9fc1397b next attempt ... introduce EIGEN_CMAKE_RUN_FROM_CTEST, in that case don't EXCLUDE_FROM_ALL 2009-10-05 07:42:31 -04:00
Benoit Jacob
b78b2ede5f finally, the right fix: set CTEST_BUILD_TARGET. 
So this is the come-back of btest target, and the default target is empty again.
 2009-10-04 20:27:44 -04:00
Benoit Jacob
a1d9b76dd5 add debug targets like debug_qr to build a specific test with debug info 
remove the btest target, instead just do "make" since anyway we have to let "make" build the tests
 2009-10-03 16:50:50 -04:00
Hauke Heibel
7d2ca0e05e Added cmake project definitions. 2009-10-02 18:45:24 +02:00
Gael Guennebaud
9a3cae4655 better fix for (v * v') * v, we still have to find a way to reorder it 2009-10-01 13:27:03 +02:00
Benoit Jacob
4b04a9bcfa *add test to prevent future regression 2009-09-29 21:00:13 -04:00
Benoit Jacob
eeabd18afc Fix compilation of HouseholderQR and ColPivotingHouseholderQR for non-square fixed-size matrices. 
For Colpiv that was just changing MatrixQType to MatrixType in the instantiation of HouseholderSequence.
For HouseholderQR I also re-ported the solve method from Colpiv as there were multiple issues.
 2009-09-28 10:49:55 -04:00
Benoit Jacob
67bf7c90c5 * update test to expose bug #57 
* update createRandomMatrixOfRank to support fixed size
 2009-09-28 09:40:18 -04:00
Benoit Jacob
92480ffd26 * Introduce make targets btest (build tests), blas (build blas lib), demos (build demos). 
* remove EIGEN_BUILD_TESTS and siblings
* add summary at the end of cmake run, hopefully not too verbose
* fix build of quaternion demo
* kill remnants of old binary library option
 2009-09-27 17:48:53 -04:00
Benoit Jacob
e82ab8a5dd move also inverse() to ReturnByValue, by doing a solve on NestByValue<Identity>. 
also: adding resize() to MatrixBase was really needed ;)
 2009-09-26 11:40:29 -04:00
Benoit Jacob
176c26feb5 allow to do xpr = solve(b) etc... just by adding a dummy MatrixBase::resize() 2009-09-22 01:41:09 -04:00
Benoit Jacob
4f9e270343 * make LU::kernel() and LU::image() also use ReturnByValue 
* make them return zero vector in the degenerate case, instead of asserting
  (let's stick to the principle that we only assert on memory errors)
 2009-09-22 00:16:51 -04:00
Benoit Jacob
ab5cc8284a convert LU::solve() to the new API 2009-09-22 20:58:29 -04:00
Benoit Jacob
c1c780a94f * ReturnByValue: 
-- simpplify by removing the 2nd template parameter
  -- rename Functor to Derived, as now it's a usual CRTP
* Homogeneous:
  -- in products, honor the Max sizes etc.
 2009-09-22 12:20:45 -04:00
Benoit Jacob
1df54e3ac2 fix bug #42, add missing Transform::Identity() 2009-09-19 19:59:49 -04:00
Gael Guennebaud
3b5a9acba8 fix stable_norm unit test 2009-09-18 11:41:38 +02:00
Benoit Jacob
760636a237 fix bug #52: Transform::inverse() should return a Transform 2009-09-18 18:45:45 -04:00
Gael Guennebaud
fcae32cc3f compilation fixes 2009-09-17 15:11:13 +02:00
Gael Guennebaud
24950bdfcb make ColPivotingQR use HouseholderSequence 2009-09-16 15:56:20 +02:00
Gael Guennebaud
49dd5d7847 * add a HouseholderSequence class (not good enough yet for Triadiagonalization and HessenbergDecomposition) 
* rework a bit AnyMatrixBase, and mobe it to a separate file
 2009-09-16 14:35:42 +02:00
Benoit Jacob
a4fd0aa25b * fix bug in col-pivoting qr, forgot to swap the colNorms when swapping cols 
* add Gael a copyright line
 2009-09-16 14:19:59 -04:00
Benoit Jacob
46be9c9ac1 * fix super nasty bug: vector.maxCoeff(&index) didn't work when 'vector' 
was a row-vector. Fixed by splitting the vector version from the matrix version.
* add unit test, the visitors weren't covered by any test!!
 2009-09-16 14:18:30 -04:00
Gael Guennebaud
4a6e5694d6 disable warning 279: controlling expression is constant for ICC 2009-09-15 13:03:24 +02:00
Hauke Heibel
e6cac85333 Added missing casts. 2009-09-08 08:27:18 +02:00
Hauke Heibel
437a79e1ab Fixed unit test and improved code reusage for resizing. 2009-09-07 17:48:42 +02:00
Hauke Heibel
e49236bac6 Ups - that was not intended to be part of the commit. 2009-09-07 17:23:29 +02:00
Hauke Heibel
64095b6610 Changed the AnyMatrixBase / ei_special_scalar_op inheritance order as proposed by Gael. 
Added conservativeResizeLike as discussed on the mailing list.
 2009-09-07 17:22:01 +02:00
Gael Guennebaud
ae1d1c8f6c improve coverage of matrix-vector product 2009-09-07 14:04:56 +02:00
Gael Guennebaud
fb5f546161 improve coverage of unitOrthogonal 2009-09-07 12:53:25 +02:00
Gael Guennebaud
b56bb441dd add a stable_norm unit test 2009-09-07 12:46:16 +02:00
Gael Guennebaud
a921292381 uncomment stuff commented for debugging (sorry for the noise) 2009-09-07 11:26:20 +02:00
Gael Guennebaud
b0aa2520f1 * add real scalar * complex matrix, real matrix * complex scalar, 
and complex scalar * real matrix overloads
* allows the inner and outer product specialisations to mix real and complex
 2009-09-04 11:22:32 +02:00
Gael Guennebaud
6902ef0824 extend mixingtype test to check diagonal products and fix the later for real*complex products 2009-09-04 10:17:28 +02:00
Gael Guennebaud
68b28f7bfb rename the EigenSolver module to Eigenvalues 2009-09-04 09:23:38 +02:00
Hauke Heibel
7f5256f628 Added conservativeResize + unit test. 2009-09-03 17:27:51 +02:00
Gael Guennebaud
3eb37fe1fb update mixingtype unit test to reflect current status, but it is still clear 
we should allow matrix products between complex and real ?
 2009-09-03 13:03:26 +02:00
Gael Guennebaud
a54b99fa72 move eigen values related stuff of the QR module to a new EigenSolver module. 
- perhaps we can find a better name ?
- note that the QR module still includes the EigenSolver module for compatibility
 2009-09-03 11:39:44 +02:00
Hauke Heibel
e6c9d6c528 Remove last lazyness warnings. 2009-09-02 20:59:57 +02:00
Hauke Heibel
2abd5eeffd Added support to overwrite the generator type. 
Eigen'fied the new variables.
 2009-09-02 20:57:41 +02:00
Benoit Jacob
7aa6fd3625 big reorganization in JacobiSVD: 
- R-SVD preconditioning now done with meta selectors to avoid compiling useless code
- SVD options now honored, with options to hint "at least as many rows as cols" etc...
- fix compilation in bad cases (rectangular and fixed-size)
- the check for termination is now done on the fly, no more goto (should have done that earlier!)
 2009-09-03 02:53:51 -04:00
Benoit Jacob
ec20d58317 * add serious unit test for swap 
* fix my stupidity in Matrix::swap()
 2009-09-02 16:56:48 -04:00
Benoit Jacob
cc375e2f79 merge 2009-09-02 06:37:41 -04:00
Benoit Jacob
e6b77bcc6b JacobiSVD: implement general R-SVD using full-pivoting QR, so we now support any rectangular matrix size by reducing to the smaller of the two dimensions (which is also an optimization) 2009-09-02 06:36:55 -04:00
Hauke Heibel
59f5bce41c fix issue #49 2009-09-01 23:15:30 +02:00
Gael Guennebaud
5b8ffa4d46 clean a bit the previous commit which came from a patch queue, 
and since it was my first try of the patch queue feature I did not
managed to apply it with a good commit message, so here you go:
* Add a ComplexSchur decomposition class built on top of HessenbergDecomposition
* Add a ComplexEigenSolver built on top of ComplexSchur
There are still a couple of FIXME but at least they work for any reasonable matrices,
still have to extend the unit tests to stress them with nasty matrices...
 2009-09-01 16:35:23 +02:00
Gael Guennebaud
4d91229bdc [mq]: eigensolver 2009-09-01 16:20:56 +02:00
Gael Guennebaud
67ccc6b851 I've been too fast (again) 2009-09-01 13:44:21 +02:00
Gael Guennebaud
1e7a9ea70a fix issue #47: now m.noalias() = XXX properly resize m if needed 2009-09-01 13:35:44 +02:00
Benoit Jacob
6e4e94ff32 * JacobiSVD: 
- support complex numbers
 - big rewrite of the 2x2 kernel, much more robust
* Jacobi:
 - fix weirdness in initial design, e.g. applyJacobiOnTheRight actually did the inverse transformation
 - fully support complex numbers
 - fix logic to decide whether to vectorize
 - remove several clumsy methods

fix for complex numbers
 2009-08-31 22:26:15 -04:00
Benoit Jacob
29c6b2452d simplifications 2009-08-31 22:09:44 -04:00
Benoit Jacob
5339db6164 add VERIFY_IS_UNITARY 2009-08-31 22:08:43 -04:00
Gael Guennebaud
a16599751f fix Matrix::stride for vectors, add a unit test for Block::stride 
and make use of it where it was relevant
 2009-08-31 17:39:56 +02:00
Hauke Heibel
ab6eb6a1a4 Adaptions from .lazy() towards .noalias(). 
Added missing casts.
 2009-08-31 17:29:37 +02:00
Hauke Heibel
0a0a805569 Fixed a cast warning in scaleAndAddTo. 
Fixed lazyness in umeyama.
Added a few missing casts.
 2009-08-31 15:34:57 +02:00
John Smith
aacada1662 Force release builds on Windows machines in the test suite. 
Added an IGNORE_CVS flag to the test suite (allows submitting local and modified repositories).
Fixed the EI_OFLAG for MSVC.
 2009-08-28 20:14:18 +02:00
Benoit Jacob
191d5275a7 modernize HouseholderQR too, uniformize all that stuff, update tests 2009-08-24 13:46:14 -04:00
Benoit Jacob
0eb142f559 bring the modern comfort also to ColPivotingHouseholderQR 
+ some fixes in FullPivotingHouseholderQR
 2009-08-24 11:11:41 -04:00
Benoit Jacob
b8106e97b4 add logAbsDeterminant() 
move log and exp functors from Array to Core
update documentation
 2009-08-24 09:46:17 -04:00
Benoit Jacob
f31b5a7114 add test for absDeterminant() 2009-08-24 00:35:42 -04:00
Benoit Jacob
c9a307f330 give FullPivotingHouseholderQR all the modern comfort 2009-08-24 00:23:35 -04:00
Benoit Jacob
154bdac9f4 small improvements 2009-08-24 00:09:01 -04:00
Benoit Jacob
97bc1af1f1 add ColPivotingHouseholderQR 
rename RRQR to fullPivotingHouseholderQR
 2009-08-23 18:04:33 -04:00
Benoit Jacob
a848ed02ad let createRandomMatrixOfRank support fixed-size! 2009-08-23 17:33:31 -04:00
Benoit Jacob
37dede6077 fix typo 2009-08-22 10:40:39 -04:00
Benoit Jacob
7bedf5e9cb add initial, rough, full-pivoting RRQR decomposition 
lots of room for improvement!
and add Gael a (c) line in Householder.h
 2009-08-22 01:13:21 -04:00
Marcus D. Hanwell
ef582933c1 Proper fix for linking to the Qt libraries (and others) 
My initial fix was incorrect, the libraries must be quoted when being
passed to the add test macro, but must be unquoted when passed to the
target_link_libraries function.
 2009-08-21 14:04:17 -04:00
Benoit Jacob
c7ae261ac0 adapt to API changes 2009-08-20 01:29:38 -04:00
Gael Guennebaud
ff0f005d4c change the make householder algorithm so that the remaining coefficient 
is real, and make Tridiagonalization use it
 2009-08-17 17:04:32 +02:00
Gael Guennebaud
737bed19c1 make HouseholderQR uses the Householder module 2009-08-16 19:22:15 +02:00
Benoit Jacob
03c1e79f35 svd: sort in decreasing order, remove unused code 2009-08-15 19:20:48 -04:00
Gael Guennebaud
239ada95b7 add overloads of lazyAssign to detect common aliasing issue with 
transpose and adjoint
 2009-08-15 22:19:29 +02:00
Gael Guennebaud
50c703f0c7 As proposed on the list: 
- rename EvalBeforeAssignBit to MayAliasBit
- make .lazy() remove the MayAliasBit only, and mark it as deprecated
- add a NoAlias pseudo expression, and MatrixBase::noalias() function
Todo:
- we have to decide whether += and -= assume no aliasing by default ?
- once we agree on the API: update the Sparse module and the unit tests respectively.
 2009-08-15 18:35:51 +02:00
Gael Guennebaud
109a4f650b fix a couple of warnings 2009-08-15 10:20:01 +02:00
Gael Guennebaud
846e8b49ba fix compilation of unit tests 2009-08-15 10:18:05 +02:00
Gael Guennebaud
afbd73b5cd overload operartor* with a ProductBase such that "scalar * (mat * mat)" is optimized 
as one could naturally expect
 2009-08-11 15:15:06 +02:00
Gael Guennebaud
9822493aaf fixes in determinant and homogeneous 2009-08-06 16:54:55 +02:00
Gael Guennebaud
3ac01b1400 compilation fix in EigenSolver, 
bugfix in PartialLU
 2009-08-06 16:41:54 +02:00
Gael Guennebaud
1d4fea48b5 fix a couple of compilations issues 2009-08-06 14:10:02 +02:00
Gael Guennebaud
56d00779db more product refactoring 2009-08-06 12:20:02 +02:00
Gael Guennebaud
88147e0a91 big refactoring in Product.h: 
- all specialized products now inherits ProductBase
- the default product evaluated by Assign is still here,
  but it is currently enabled for small fixed sizes only
- => this significantly speed up compilation for large matrices
- I left the OuterProduct specialization empty as an exercise...
 2009-08-05 15:23:35 +02:00
Gael Guennebaud
7d607048a9 implement a ProductBase class and, as a proof of concept, update TriangularProduct 
and SelfAdjointMatrixProduct to take advantage of it => fewer LOC
 2009-08-04 16:54:17 +02:00
Gael Guennebaud
2089a263f8 merge 2009-08-04 11:31:25 +02:00
Gael Guennebaud
4bec101470 implement two levels of blocking in PartialLU => high speedup 2009-08-04 11:28:02 +02:00
Benoit Jacob
523cdedf58 make the dot product linear in the second variable, not the first variable 2009-08-03 17:20:45 +02:00
Gael Guennebaud
912da9fade merge with special_matrix branch 2009-08-03 16:17:32 +02:00
Gael Guennebaud
a8f943127c merge 2009-08-03 16:11:30 +02:00
Benoit Jacob
d10c710b15 add new Householder module 2009-08-03 16:06:57 +02:00
Gael Guennebaud
ce1dc1ab16 implements a blocked version of PartialLU 2009-08-03 12:11:18 +02:00
Gael Guennebaud
0103de8512 bugfix in trsm 2009-08-02 15:32:43 +02:00
Benoit Jacob
cd49780143 apply patch from Marcus Hanwell: Improved quoting of tests when added to the build 2009-08-02 15:09:34 +02:00
Gael Guennebaud
48fc64458c add blocked LLT, and bugfix in trsm asserts 2009-08-01 23:42:51 +02:00
Gael Guennebaud
18429156a1 add selfadjointView from a trinagularView 2009-07-31 17:35:55 +02:00
Gael Guennebaud
864171df5c fix a couple of issues related to recent products 2009-07-28 18:11:30 +02:00
Gael Guennebaud
54804eb626 synch with main branch 2009-07-28 17:35:07 +02:00
Gael Guennebaud
264fe82c65 add a debug mechanism to compute the number of intermediate evaluations (only for dynamic size) 2009-07-28 17:13:13 +02:00
Gael Guennebaud
5f3606bce9 bug fix in inverse for 1x1 matrix, 
some compilation fixes in sparse_solvers
 2009-07-27 18:09:56 +02:00
Gael Guennebaud
94cc30180e compilation fixes 2009-07-27 13:50:23 +02:00
Gael Guennebaud
0590c18555 various compilation and bug fixes in selfadjoint stuff 2009-07-27 13:17:39 +02:00
Gael Guennebaud
f95b77be62 trmm is now fully working and available via TriangularView::operator* 2009-07-27 11:42:54 +02:00
Gael Guennebaud
f3fde74695 finalize trsm: works in all situations, and it is now used by solve() and solveInPlace() 2009-07-26 13:01:37 +02:00
Gael Guennebaud
82c5438c95 split and add unit tests for symm and syrk, 
the .rank*update() functions now returns a reference to *this
 2009-07-23 21:22:51 +02:00
Gael Guennebaud
713c92140c improve SYMV it is now faster and ready for use 2009-07-23 14:20:45 +02:00
Gael Guennebaud
ddb3ac98a2 addd matrix * self adjoint high level API 2009-07-23 10:05:38 +02:00
Gael Guennebaud
f696efc00e bugfix in SYMM 2009-07-22 23:48:42 +02:00
Gael Guennebaud
0cb4f32e12 implement high level API for SYMM and fix a couple of bugs related to complex 2009-07-22 23:12:22 +02:00
Gael Guennebaud
d6627d540e * refactoring of the matrix product into multiple small kernels 
* started an efficient selfadjoint matrix * general matrix product
  based on the generic kernels ( => need a very little LOC)
 2009-07-21 16:58:35 +02:00
Gael Guennebaud
afa8f2ca95 * various fixes related to sub diagonals and band matrix 
* allows 0 sized objects in Block/Map
 2009-07-21 11:19:52 +02:00
Gael Guennebaud
4375c043ac minor compilation fixes for Sun CC and ICC 2009-07-20 13:27:41 +02:00
Gael Guennebaud
a551107cce bugfix for a = a * b; when a has to be resized 2009-07-20 10:35:47 +02:00
Gael Guennebaud
32b08ac971 re-implement stableNorm using a homemade blocky and 
vectorization friendly algorithm (slow if no vectorization)
 2009-07-17 16:22:39 +02:00
Gael Guennebaud
34490f1493 * bugfixes in Product, and test/product_selfadjoint 
* speed up in the extraction of the matrix Q in Tridiagonalization
 2009-07-16 00:03:17 +02:00
Gael Guennebaud
97c9445c60 synch with main devel branch 2009-07-15 19:54:31 +02:00
Gael Guennebaud
df6561a73f change the implementation of BandMatrix to follow the BLAS/LAPACK storage scheme 2009-07-15 17:00:49 +02:00
Gael Guennebaud
1578421ed1 fix issue #25 : the problem was that we assumed Dynamic was a multiple of a packet size 
(also disable the test of blueNorm)
 2009-07-15 14:20:45 +02:00
Gael Guennebaud
587029a612 started an implementation of BandMatrix: at least the read/write access 
to the main/sub/super diagonals seems to work well.
 2009-07-14 23:27:37 +02:00
Gael Guennebaud
8120a5cecd synch with main devel branch 2009-07-14 23:06:25 +02:00
Gael Guennebaud
7a9519a9be fix typo in blue norm 2009-07-14 23:00:53 +02:00
Gael Guennebaud
f5d2317b12 add a blueNorm() function implementing the Blues's stable norm 
algorithm. it is currently provided for experimentation
purpose only.
 2009-07-13 21:14:47 +02:00
Gael Guennebaud
1e7b1a8a85 add a SparseNestByValue expression and fix issue in sparse adjoint evaluation 2009-07-13 14:55:03 +02:00
Gael Guennebaud
a2cf7ba955 add triangular * vector product 2009-07-13 13:17:55 +02:00
Gael Guennebaud
a2087cd7a3 Add an efficient rank2 update function (like the level2 blas xSYR2 routine). 
Note that it is already used in Tridiagonalization.
 2009-07-11 21:14:59 +02:00
Gael Guennebaud
ec5c608aa3 Set of fixes and workaround to make sun studio more happy. 
Still remains the problem of alignment and vectorization.
 2009-07-10 16:10:03 +02:00
Gael Guennebaud
b47dea8b7a add a meta unroller for the triangular solver (only for vectors as rhs) 2009-07-10 11:30:46 +02:00
Gael Guennebaud
1a1b2e9f27 finally directly calling the low-level products is faster 2009-07-10 10:41:26 +02:00
Gael Guennebaud
fa60c72398 started to simplify the triangular solvers 2009-07-09 17:11:03 +02:00
Gael Guennebaud
96e7d9f896 ok now all the complex mat-mat and mat-vec products involving conjugate, 
adjoint, -, and scalar multiple seems to be well handled. It only remains
the simpler case: C = alpha*(A*B) ... for the next commit
 2009-07-08 18:24:37 +02:00
Gael Guennebaud
13b2dafb50 conjugate expressions are now properly caught by Product 
=> significant speedup in expr. like a.adjoint() * b,
   for complex scalar type (~ x3)
 2009-07-07 21:30:20 +02:00
Gael Guennebaud
79877a9917 * take advantage of new possibilies in LLT (mat -= product) 
* fix Block::operator+= product which was not optimized
* fix some compilation issues
 2009-07-07 15:32:21 +02:00
Gael Guennebaud
92a35c93b2 * extended the cache friendly products to support C = alpha * A * M and C += alpha * A * B 
* this allows to optimize xpr like C -= lazy_product, still have to catch "scalar_product_of_lazy_product"
* started to support conjugate in cache friendly products (very useful to evaluate A * B.adjoint() without
  evaluating B.adjoint() into a temporary
* compilation fix
 2009-07-07 11:39:19 +02:00
Gael Guennebaud
1aea45335f * bybye Part, welcome TriangularView and SelfAdjointView. 
* move solveTriangular*() to TriangularView::solve*()
* move .llt() to SelfAdjointView
* add a high level wrapper to the efficient selfadjoint * vector product
* improve LLT so that we can specify which triangular part is meaningless
=> there are still many things to do (doc, cleaning, improve the matrix products, etc.)
 2009-07-06 23:43:20 +02:00
Benoit Jacob
e093b43b2c * rename QR to HouseholderQR because really that impacts the API, not just the impl. 
* rename qr() to householderQr(), for same reason.
* clarify that it's non-pivoting, non-rank-revealing, so remove all the rank API, make solve() be void instead of bool, update the docs/test, etc.
* fix warning in SVD
 2009-07-06 17:12:10 +02:00
Gael Guennebaud
0c2232e5d9 quick reimplementation of SVD from the numeral recipes book: 
this is still not Eigen style code but at least it works for
n>m and it is more accurate than the JAMA based version. (I needed
it now, this is why I did that)
 2009-07-06 13:47:41 +02:00
Manuel Yguel
c398d0edcf another test in the non invertible case 2009-07-04 14:55:25 +02:00
Gael Guennebaud
08e419dcb1 * update sparse module wrt new diagonal matrix impl 
* fix a bug is SparseMatrix
 2009-07-04 11:16:27 +02:00
Benoit Jacob
7b750182f2 * polish computeInverseWithCheck to share more code, fix documentation, fix coding style 
* add snippet for computeInverseWithCheck documentation
* expand unit-tests to cover computeInverseWithCheck
 2009-06-29 22:07:37 +02:00
Benoit Jacob
2de9b7f537 fully vectorize DiagonalProduct 
(it used to be partially vectorized and that had been lost in the big changes from the previous commit)
 2009-06-29 04:01:31 +02:00
Benoit Jacob
6809f7b1cd new implementation of diagonal matrices and diagonal matrix expressions 2009-06-28 21:27:37 +02:00
Gael Guennebaud
627595ad19 * rename PartialRedux to VectorwiseOp 
* add VectorwiseOp's +, -, +=, -= operators
 2009-06-10 11:20:30 +02:00
Benoit Jacob
ee92009fd8 make Umeyama, and its unit-test, work for me on gcc 4.3 2009-05-27 23:10:24 +02:00
Hauke Heibel
4d1e492c00 * Umeyama has now similar performance for RowMajor and ColMajor layouts. 
* Fixed a bug in umeyama for fixed size matrices.
* Fixed the umeyama unit test for fixed size matrices.
* Added XprHelper::ei_plain_matrix_type_row_major.
 2009-05-27 19:24:05 +02:00
Hauke Heibel
db5647abae Added Umeyama implementation. 2009-05-26 19:22:25 +02:00
Benoit Jacob
7667a93cbe merge 2009-05-22 20:31:26 +02:00
Benoit Jacob
6347b1db5b remove sentence "Eigen itself is part of the KDE project." 
it never made very precise sense. but now does it still make any?
 2009-05-22 20:25:33 +02:00
Hauke Heibel
c7303a876f Oops, here the actual LLT and LDLT patch. 2009-05-22 15:58:20 +02:00
Hauke Heibel
0523b64fe9 Eigensolver decomposition interface unification. 
Added default ctor and public compute method as
well as safe-guards against uninitialized usage.
Added unit tests for the safe-guards.
 2009-05-22 14:27:58 +02:00
Hauke Heibel
2c247fc8a8 LU and PartialLU decomposition interface unification. 
Added default ctor and public compute method as well
as safe-guards against uninitialized usage.
Added unit tests for the safe-guards.
 2009-05-22 14:27:58 +02:00
Hauke Heibel
5c5789cf0f QR and SVD decomposition interface unification. 
Added default ctor and public compute method as
well as safe-guards against uninitialized usage.
Added unit tests for the safe-guards.
 2009-05-22 14:27:58 +02:00
Gael Guennebaud
dd45c4805c * add a writable generic coeff wise expression (CwiseUnaryView) 
* add writable .real() and .imag() functions
 2009-05-20 15:41:23 +02:00
Gael Guennebaud
f47c4b5da8 update cdash testsuite file to use mercurial 2009-05-19 09:24:22 +02:00
Gael Guennebaud
e186728867 fix #1 : need to nest by value the affine part in homogeneous product 2009-05-18 17:55:50 +02:00
Jitse Niesen
e3d64cb418 Fix compilation error in createRandomMatrixOfRank() 2009-05-17 21:17:45 +01:00
Hauke Heibel
6358c12998 * introduced method createRandomMatrixOfRank (R = U*D*V where U,V unitary, D r-by-c diag. with rank non-zero values) 
* switched lu/qr tests to be using createRandomMatrixOfRank
* removed unused methods doSomeRankPreservingOperations
* removed NOTE about doSomeRankPreservingOperations
 2009-05-17 16:07:12 +02:00
Gael Guennebaud
877c3c00a2 enable testing of complex numbers for taucs 2009-05-12 13:43:40 +00:00
Gael Guennebaud
f5b5571a5a compilation fixes 2009-05-12 07:32:34 +00:00
Gael Guennebaud
9b256d997e various minor updates of some unit tests 2009-05-11 11:09:41 +00:00
Benoit Jacob
9afd1324fd constant Diagonal ---> DiagonalBits 
introduce ei_is_diagonal to check for it
DiagonalCoeffs ---> Diagonal and allow Index to by Dynamic
-> add MatrixBase::diagonal(int) with unittest and doc
 2009-05-10 16:24:39 +00:00
Benoit Jacob
eac79b6d2e CREDIT Hauke Heibel, fix MSVC warnings 2009-05-09 03:41:17 +00:00
Benoit Jacob
4f0af00e51 *add missing overloads of setZero, etc... that were mentioned in the tutorial 
--->they go into Matrix as they resize.
*add isConstant() alias to isApproxToConstant()
*extend unit-test
*change an assert into a static assert
 2009-05-06 21:40:24 +00:00
Gael Guennebaud
1e286464ab * compilation fixes for gcc 3.3 
* test Part::swap
 2009-05-06 08:43:38 +00:00
Benoit Jacob
2b2f0c0220 fix linearRegression, fix doc, add unit test (it was untested since the change 
making fitHyperplane no longer use it)
 2009-05-05 16:50:58 +00:00
Gael Guennebaud
2829314284 new simplified API to fill sparse matrices (the old functions are 
deprecated). Basically there are now only 2 functions to set a
coefficient:
1) mat.coeffRef(row,col) = value;
2) mat.insert(row,col) = value;
coeffRef has no limitation, insert assumes the coeff has not already
been set, and raises an assert otherwise.
In addition I added a much lower level, but more efficient filling
mechanism for
internal use only.
 2009-05-04 14:25:12 +00:00
Gael Guennebaud
469b8aa380 "forgot to commit the required changes in stdvector unit test" 2009-05-03 15:39:37 +00:00
Benoit Jacob
95bda5e6ab let the user disable alignment altogether by #defining EIGEN_DONT_ALIGN. 
Until now, the user had to edit the source code to do that.
Internally, add EIGEN_ALIGN that takes into account both EIGEN_DONT_ALIGN.and
EIGEN_ARCH_WANTS_ALIGNMENT. From now on, only EIGEN_ALIGN should be used to
test whether we want to align.
 2009-05-03 13:50:56 +00:00
Benoit Jacob
746079f75d gni, forgot to call the new subtest 2009-04-29 17:01:10 +00:00
Benoit Jacob
8b1e7c2792 add cast<>() tests. including a vectorization_logic test that currently fails (casting to same type should not prevent vectorization) 2009-04-29 14:51:19 +00:00
Gael Guennebaud
804a239d30 patch from Moritz Lenz to allow solving transposed problem with superlu 2009-04-10 19:54:43 +00:00
Gael Guennebaud
22edf77470 add a 4x4 inverse case which is not handled by the current 
ei_compute_inverse_in_size4_case (reported by mikola on IRC)
 2009-04-09 21:55:29 +00:00
Gael Guennebaud
5b1d0cebc5 sparse module: new API proposal for triangular solves and experimental 
solver support with a sparse matrix as the rhs.
 2009-04-05 16:30:10 +00:00
Benoit Jacob
2f45eeb0c6 More Cholesky fixes. 
* Cholesky decs are NOT rank revealing so remove all the rank/isPositiveDefinite etc stuff.
* fix bug in LLT: s/return/continue/
* introduce machine_epsilon constants, they are actually needed for Higman's formula determining
  the cutoff in Cholesky. Btw fix the page reference to his book (chat with Keir).
* solve methods always return true, since this isn't a rank revealing dec. Actually... they already did always return true!! Now it's explicit.
* updated dox and unit-test
 2009-04-01 00:21:16 +00:00
Benoit Jacob
bf596d0b3a add adjointInPlace() and add documentation warnings on adjoint() and transpose() about aliasing effects. 2009-03-31 13:55:40 +00:00
Benoit Jacob
a1ba995f05 Many improvements in LLT and LDLT: 
* in LDLT, support the negative semidefinite case
* fix bad floating-point comparisons, improves greatly the accuracy of methods like
  isPositiveDefinite() and rank()
* simplifications
* identify (but not resolve) bug: claim that only triangular part is used, is inaccurate
* expanded unit-tests
 2009-03-30 21:45:45 +00:00
Gael Guennebaud
49fc1e3e84 add vectorization of sqrt for float 2009-03-27 14:41:46 +00:00
Gael Guennebaud
17860e578c add SSE2 versions of sin, cos, log, exp using code from Julien 
Pommier. They are for float only, and they return exactly the same
result as the standard versions in about 90% of the cases. Otherwise the max error
is below 1e-7. However, for very large values (>1e3) the accuracy of sin and cos
slighlty decrease. They are about 3 or 4 times faster than 4 calls to their respective
standard versions. So, is it ok to enable them by default in their respective functors ?
 2009-03-25 12:26:13 +00:00
Gael Guennebaud
f4cf5e9b26 split and extend eigen-solver tests 2009-03-23 14:38:59 +00:00
Gael Guennebaud
fbf415c547 add vectorization of unary operator-() (the AltiVec version is probably 
broken)
 2009-03-20 10:03:24 +00:00
Gael Guennebaud
b8f46090ff add optimized cross3 function (code from Rohit Garg) 2009-03-11 14:20:36 +00:00
Gael Guennebaud
3f80c68be5 add the vectorization of abs 2009-03-09 18:40:09 +00:00
Gael Guennebaud
3ac42fed94 big rework of the Transform class: 
* add Projective and AffineCompact modes as an optional third template
  argument
* extend Transform::operator* to support more use cases
 2009-03-08 11:35:30 +00:00
Gael Guennebaud
fa9f7708d4 add efficient matrix product specializations for Homogeneous 2009-03-05 16:40:56 +00:00
Gael Guennebaud
0be89a4796 big addons: 
* add Homogeneous expression for vector and set of vectors (aka matrix)
  => the next step will be to overload operator*
* add homogeneous normalization (again for vector and set of vectors)
* add a Replicate expression (with uni-directional replication
  facilities)
=> for all of them I'll add examples once we agree on the API
* fix gcc-4.4 warnings
* rename reverse.cpp array_reverse.cpp
 2009-03-05 10:25:22 +00:00
Gael Guennebaud
40774c625e add a proof of concept autodiff jacobian helper class based on adolc 
with unit test and FindAdolc cmake module
 2009-02-27 16:19:13 +00:00