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
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
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
Benoit Steiner
3b2321e3ab
Updated the geo_parametrizedline_2 test for AVX.
2014-04-04 17:08:47 -07:00
Benoit Steiner
b446ff037e
Deleted some dead code.
2014-04-04 14:12:24 -07:00
Benoit Steiner
aecc78325a
Pulled the latest updates from the eigen trunk.
2014-04-01 22:07:05 -07:00
Christoph Hertzberg
1cb8de1250
Make some actual verifications inside the autodiff unit test
2014-04-01 17:44:48 +02:00
Florian George
56c4851323
Fixed typo: symmretric -> symmetric
2014-04-01 15:52:25 +02:00
Gael Guennebaud
ceae5b4145
Fix lapack build
2014-04-01 11:52:23 +02:00
Gael Guennebaud
ec65e6648c
bug #775 : propagate generator when workingaround cmake bug #9220
2014-04-01 11:45:43 +02:00
Gael Guennebaud
d992634fbc
Fix bug #776 : it seems that mingw does not support weak linking
2014-04-01 11:31:21 +02:00
Benoit Steiner
5e8622477b
Rename the vector() factories defined in blas/common.h into make_vector() to prevent a possible name conflict with std::vector.
2014-04-01 11:23:28 +02:00
Gael Guennebaud
1221dd90aa
Fix no newline at end of file warning
2014-04-01 11:21:14 +02:00
Gael Guennebaud
93870d95b7
BTL: add blaze
2014-03-31 10:59:55 +02:00
Gael Guennebaud
f603823ef3
BTL: fix warnings and extend to 5k matrices, update GotoBlas to OpenBlas, etc.
2014-03-31 10:58:30 +02:00
Gael Guennebaud
8d0441052e
Finally, prefetching seems to help getting more stable performance
2014-03-31 10:42:19 +02:00
Gael Guennebaud
82c8163067
Enable repetition in mixing type unit test
2014-03-31 10:41:40 +02:00
Gael Guennebaud
1c0728043a
Workaround alignment warnings
2014-03-30 22:43:47 +02:00
Gael Guennebaud
e497a27ddc
Optimize gebp kernel:
...
1 - increase peeling level along the depth dimention (+5% for large matrices, i.e., >1000)
2 - improve pipelining when dealing with latest rows of the lhs
2014-03-30 21:57:05 +02:00
Benoit Steiner
ad59ade116
Vectorized the loop peeling of the inner loop of the block-panel matrix multiplication code. This speeds up the multiplication of matrices which size is not a multiple of the packet size.
2014-03-28 12:11:23 -07:00
Benoit Steiner
39bfbd43f0
Properly align the input data to prevent false failures of the packetmath.cpp test.
2014-03-28 12:00:08 -07:00
Gael Guennebaud
10aa14592a
Add a mechanism to recursively access to half-size packet types
2014-03-28 10:18:04 +01:00
Gael Guennebaud
8d2bb2c20d
merge with default branch
2014-03-28 09:24:18 +01:00
Gael Guennebaud
c94fde118a
Enable vectorization of gemv for PacketSize>4 through unaligned loads (still better than no vectorization)
2014-03-28 09:11:06 +01:00
Benoit Steiner
51e85c936d
Merged latest changes from parent.
2014-03-27 18:32:15 -07:00
Benoit Steiner
8a94cb3edd
Implemented the SSE version of the gather and scatter packet primitives.
2014-03-27 18:29:01 -07:00
Benoit Steiner
7f3162f707
Implemented the AVX version of the gather and scatter packet primitives.
2014-03-27 17:42:25 -07:00
Benoit Steiner
ee86679096
Introduced pscatter/pgather packet primitives. They will be used to optimize the loop peeling code of the block-panel matrix multiplication kernel.
2014-03-27 16:03:03 -07:00
Gael Guennebaud
58fe2fc2b2
enforce the use of vfmadd231ps for pmadd (gcc and clang stupidely generates the other fmadd variants plus some register moves...)
2014-03-27 23:38:50 +01:00
Benoit Steiner
729363114f
Fixed compilation error when FMA instructions are enabled.
2014-03-27 11:20:41 -07:00
Benoit Steiner
1697d7a179
Silenced "unused variable" warnings when compiling with FMA.
2014-03-27 11:00:47 -07:00
Benoit Steiner
3e1fe8e416
Vectorized the packing of a col-major matrix used as the right hand side argument in a matrix-matrix product when AVX instructions are used. No vectorization takes place when SSE instructions are used, however this doesn't seem to impact performance.
2014-03-27 10:38:41 -07:00
Benoit Steiner
b776458ccb
Vectorized the packing of a row-major matrix used as the left hand side argument in a matrix-matrix product.
2014-03-27 10:02:24 -07:00
