Commit Graph

5406 Commits

Author SHA1 Message Date
Gael Guennebaud
7388fdf560 pbroadcast4/2 assume aligned memory 2014-04-25 02:46:22 -07:00
Gael Guennebaud
c9788d55b9 Disable 3pX4 kernel on Altivec: despite this platform has 32 registers, this version seems significantly slower. 2014-04-25 11:48:22 +02:00
Gael Guennebaud
ae4d9434e2 Add unit test for pbroadcast4/2 2014-04-25 11:21:18 +02:00
Gael Guennebaud
4def7b1fa5 Fix ptranspose overload prototypes for NEON 2014-04-25 11:15:13 +02:00
Gael Guennebaud
c79bd4b64b Minor optimizations in product kernel:
- use pbroadcast4 (helpful when AVX is not available)
- process all remaining rows at once (significant speedup for small matrices)
2014-04-25 11:06:03 +02:00
Gael Guennebaud
cf7eaed38d Avoid blocking-size mismatch in unit tests calling Eigen's blas interface. 2014-04-25 11:04:02 +02:00
Gael Guennebaud
3d8d0f6269 Enable vectorization of pack_rhs with a column-major RHS.
Rename and generalize Kernel<*> to PacketBlock<*,N>.
2014-04-25 10:56:18 +02:00
Gael Guennebaud
b0e19db1cf Enable fused madd for Altivec 2014-04-24 23:17:18 +02:00
Gael Guennebaud
8d85ce88e1 Implement ptranspose on altivec and fix pgather/pscatter 2014-04-24 05:47:53 -07:00
Benoit Steiner
4eb92e5647 Fixed the NEON implementation of predux_max<Packet4i>. 2014-04-23 18:23:07 -07:00
Benoit Steiner
ccb4dec719 Created a NEON version of the ptranspose packet primitives 2014-04-23 18:22:10 -07:00
Gael Guennebaud
82b09fcb91 Add Altivec implementation of pgather/pscatter (not tested) 2014-04-23 13:09:26 +02:00
Gael Guennebaud
ecbd67a15a Fix EIGEN_MAKE_UNALIGNED_ARRAY_ASSERT macro 2014-04-22 17:03:57 +02:00
Gael Guennebaud
934ce93886 merge with default branch 2014-04-22 17:00:38 +02:00
Gael Guennebaud
5c5231ab71 Workaround gcc's default ABI not being able to distinghish between vector types of different sizes. 2014-04-22 16:03:19 +02:00
Gael Guennebaud
2606abed53 Fix 128bit packet size assumptions in unit tests. 2014-04-18 21:14:40 +02:00
Gael Guennebaud
a7d20038df Fix alignment assertion. 2014-04-18 17:06:31 +02:00
Gael Guennebaud
3454b4e5f1 Fix calls to lazy products (lazy product does not like matrices with 0 length) 2014-04-18 17:06:03 +02:00
Gael Guennebaud
94684721bd Smarter block size computation 2014-04-18 15:35:34 +02:00
Gael Guennebaud
1388f4f9fd Fix typo (was working with clang\!) 2014-04-18 11:43:13 +02:00
Gael Guennebaud
6d665d446b Fixes for fixed sizes and non vectorizable types 2014-04-17 23:26:34 +02:00
Gael Guennebaud
2c3c95990d merge 2014-04-17 22:50:49 +02:00
Benoit Steiner
6d6df90c9a Implemented the pgather/pscatter packet primitives for the arm/NEON architecture 2014-04-17 12:28:01 -07:00
Gael Guennebaud
c354bd47f7 Make our gemm bench a little more powerful. 2014-04-17 21:03:26 +02:00
Gael Guennebaud
9777a5ca60 Various minor fixes in BTL 2014-04-17 21:01:45 +02:00
Gael Guennebaud
9746396d1b Optimize AVX pset1 for complexes and ploaddup 2014-04-17 20:51:04 +02:00
Benjamin Chretien
e5d0cb54a5 Fix typo in Reductions tutorial. 2014-04-17 18:49:23 +02:00
Gael Guennebaud
1dd015fea6 Reduce block sizes in unit tests. 2014-04-17 16:27:58 +02:00
Gael Guennebaud
45a4aad572 add unit tests for ploadquad and predux4, and split packetmath unit test wrt real/complex 2014-04-17 16:27:22 +02:00
Gael Guennebaud
e1d461352e Extend mixingtype unit test to check transposed cases. 2014-04-17 16:26:35 +02:00
Gael Guennebaud
11fbdcbc38 Fix and optimize mixed products 2014-04-17 16:04:30 +02:00
Gael Guennebaud
0fa8290366 Optimize ploaddup for AVX 2014-04-17 16:02:27 +02:00
Gael Guennebaud
d936ddc3d1 Fallback to lazy products for very small ones. 2014-04-16 23:15:42 +02:00
Gael Guennebaud
de8336a9bc Enable alloca on MAC OSX 2014-04-16 23:14:58 +02:00
Gael Guennebaud
d5a795f673 New gebp kernel handling up to 3 packets x 4 register-level blocks. Huge speeup on Haswell.
This changeset also introduce new vector functions: ploadquad and predux4.
2014-04-16 17:05:11 +02:00
Mark Borgerding
e0dbb68c2f Check IMKL version for compatibility with Eigen 2014-04-15 13:57:03 -04:00
Gael Guennebaud
20c840be15 Merged in benoitsteiner/eigen-fixes/nvcc_fixes (pull request PR-56)
Fixed a typo in CXX11Meta.h
2014-04-15 10:38:25 +02:00
Benoit Steiner
1afd50e0f3 Fixed a typo in CXX11Meta.h 2014-04-14 14:26:30 -07:00
Gael Guennebaud
3c66bb136b bug #793: detect NaN and INF in EigenSolver instead of aborting with an assert. 2014-04-14 22:00:27 +02:00
Gael Guennebaud
7098e6d976 Add isfinite overload for complexes. 2014-04-14 21:57:49 +02:00
Benoit Steiner
feaf7c7e6d Optimized SSE unaligned loads and stores when compiling a 64bit target with a recent version of gcc (ie gcc 4.8). 2014-04-14 10:44:17 -07:00
Gael Guennebaud
d567e3b893 Merged in benoitsteiner/eigen-fixes (pull request PR-55)
CUDA fixes
2014-04-14 14:33:50 +02:00
Gael Guennebaud
148acf8e4f bug #790: fix overflow in real_2x2_jacobi_svd 2014-04-14 13:52:16 +02:00
Gael Guennebaud
0587db8bf5 bug #793: fix overflow in EigenSolver and add respective regression unit test 2014-04-14 11:43:08 +02:00
Benoit Steiner
7903d3f27b Updated the compiler flags to enable nvcc to work with clang. 2014-04-12 23:39:37 -07:00
Benoit Steiner
a803ff18a9 Fixed a typo in cuda_basic.cu 2014-04-12 20:24:05 -07:00
Freddie Witherden
91288e9bf9 Add include LevenbergMarquardt in CMakeLists.txt.
This fixes bug #768.
2014-04-12 12:53:09 +01:00
Jitse Niesen
fbd5eac7cf Merged in benoitsteiner/eigen-fixes/nvcc_fixes (pull request PR-53)
Silenced a compilation warning produced by nvcc.
2014-04-11 14:16:08 +01:00
Benoit Steiner
1b333c89c9 Updated my previous fix to avoid introducing a compilation warning on ARM platforms. 2014-04-10 17:43:13 -07:00
Benoit Steiner
a1fcf599fa Silenced a compilation warning produced by nvcc. 2014-04-10 11:19:37 -07:00