Gael Guennebaud
b3151bca40
Implement pmadd for float and double to make it consistent with the vectorized path when FMA is available.
2016-08-23 14:24:08 +02:00
Benoit Jacob
40a16282c7
Remove now-unused protate PacketMath func
2016-05-24 11:01:18 -04:00
Benoit Steiner
bfb3fcd94f
Optimized implementation of the tanh function for SSE
2016-02-10 08:52:30 -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
ae87f094eb
Fix "," in non SSE4 mode
2015-11-05 12:08:36 +01:00
Alexandre Avenel
d46e2c10a6
Add round, ceil and floor for SSE4.1/AVX (Bug #70 )
2015-11-01 10:49:27 +01:00
Gael Guennebaud
6163db814c
bug #1085 : workaround gcc default ABI issue
2015-10-10 22:38:55 +02:00
Gael Guennebaud
f047ecc36a
_mm_hadd_epi32 is for SSSE3 only (and not SSE3)
2015-10-07 15:48:35 +02:00
Gael Guennebaud
2c676ddb40
Handle various TODOs in SSE vectorization (remove splitted storeu, enable SSE3 integer vectorization, plus minor tweaks)
2015-10-06 15:43:27 +02:00
Gael Guennebaud
6245591349
Fix prototype of plset and generalize linspace functor.
2015-08-07 19:27:59 +02:00
Gael Guennebaud
ce57dbd937
Let unpacket_traits<> exposes the required alignment and make use of it everywhere
2015-08-07 10:44:01 +02:00
Benoit Steiner
f41b1f1666
Added support for fast reciprocal square root computation.
2015-02-26 09:42:41 -08:00
Benoit Jacob
9bd8a4bab5
bug #955 - Implement a rotating kernel alternative in the 3px4 gebp path
...
This is substantially faster on ARM, where it's important to minimize the number of loads.
This is specific to the case where all packet types are of size 4. I made my best attempt to minimize how dirty this is... opinions welcome.
Eventually one could have a generic rotated kernel, but it would take some work to get there. Also, on sandy bridge, in my experience, it's not beneficial (even about 1% slower).
2015-02-18 15:03:35 -05:00
Gael Guennebaud
159fb181c2
Disable __m128* wrappers when compiling with AVX and -fabi-version=4
2015-02-17 16:27:20 +01:00
Gael Guennebaud
91ab2489dd
Fix compilation with GCC/AVX (workaround __m128 and __m256 being the same type with default ABI)
2015-02-17 16:08:07 +01:00
Gael Guennebaud
45cbb0bbb1
The usage of DenseIndex is deprecated, so let's replace DenseIndex by Index
2015-02-16 15:05:41 +01:00
Gael Guennebaud
0918c51e60
merge Tensor module within Eigen/unsupported and update gemv BLAS wrapper
2015-02-12 21:48:41 +01:00
Gael Guennebaud
fe25f3b8e3
FMA has been wrongly disabled
2015-02-10 23:11:35 +01:00
Benoit Steiner
c739102ef9
Pulled the latest changes from the trunk
2015-02-06 05:25:03 -08:00
Benoit Jacob
0f21613698
bug #936 , patch 2/3: Remove EIGEN_VECTORIZE_FMA, was redundant with EIGEN_HAS_SINGLE_INSTRUCTION_MADD
2015-01-30 17:44:26 -05:00
Benoit Jacob
340b8afb14
bug #936 , patch 1.5/3: rename _FUSED_ macros to _SINGLE_INSTRUCTION_,
...
because this is what they are about. "Fused" means "no intermediate rounding
between the mul and the add, only one rounding at the end". Instead,
what we are concerned about here is whether a temporary register is needed,
i.e. whether the MUL and ADD are separate instructions.
Concretely, on ARM NEON, a single-instruction mul-add is always available: VMLA.
But a true fused mul-add is only available on VFPv4: VFMA.
2015-01-31 14:15:57 -05:00
Gael Guennebaud
ee06f78679
Introduce unified macros to identify compiler, OS, and architecture. They are all defined in util/Macros.h and prefixed with EIGEN_COMP_, EIGEN_OS_, and EIGEN_ARCH_ respectively.
2014-11-04 21:58:52 +01:00
Benoit Steiner
16047c8d4a
Pulled in the latest changes from the Eigen trunk
2014-08-13 22:25:29 -07:00
Gael Guennebaud
b47ef1431f
Fix many long to int implicit conversions
2014-07-08 16:47:11 +02:00
Benoit Steiner
29aebf96e6
Created the pblend packet primitive and implemented it using SSE and AVX instructions.
2014-06-06 20:18:44 -07:00
Gael Guennebaud
450d0c3de0
Make sure that calls to broadcast4 are 16 bytes aligned
2014-04-25 22:25:48 +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
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
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
Gael Guennebaud
10aa14592a
Add a mechanism to recursively access to half-size packet types
2014-03-28 10:18:04 +01:00
Benoit Steiner
8a94cb3edd
Implemented the SSE version of the gather and scatter packet primitives.
2014-03-27 18:29:01 -07:00
Benoit Steiner
a419cea4a0
Created the ptranspose packet primitive that can transpose an array of N packets, where N is the number of words in each packet. This primitive will be used to complete the vectorization of the gemm_pack_lhs and gemm_pack_rhs functions.
...
Implemented the primitive using SSE instructions.
2014-03-26 19:03:07 -07:00
Benoit Steiner
cc73164aa8
Merged latest updates from the parent branch
2014-03-26 15:23:59 -07:00
Gael Guennebaud
bc401eb6fa
Implement new 1 packet x 8 gebp kernel
2014-03-26 18:53:00 +01:00
Gael Guennebaud
b286a1e75c
add pbroadcast2/4 generic intrinsics
2014-03-26 16:46:36 +01:00
Benoit Steiner
db7d49efbb
Added support for FMA instructions
2014-02-24 13:45:32 -08:00
Benoit Steiner
64a85800bd
Added support for AVX to Eigen.
2014-01-29 11:43:05 -08:00
Gael Guennebaud
a7621809fe
Remove useless register keyword, and optimize predux_min/max for SSE4
2014-01-25 16:54:13 +01:00
Gael Guennebaud
01fd880424
Revert previous change and introduce a new workaround regarding gcc generating a shufps instruction instead of the more efficient pshufd instruction.
...
The trick consists in introducing a new pload1 function to be used in low level product kernels for which bug #203 does not apply.
Indeed, it turned out that using inline assembly prevents gcc of doing a good job at instructtion reordering.
2014-03-20 16:03:46 +01:00
Gael Guennebaud
c39a3fa7a1
Makes gcc to generate a pshufd instruction for pset1
2014-03-20 10:14:26 +01:00
Gael Guennebaud
d4dd6aaed2
Fix bug #642 : add vectorization of sqrt for doubles, and make sqrt really safe if EIGEN_FAST_MATH is disabled
2013-08-19 16:02:27 +02:00
Gael Guennebaud
b3adc4face
Add missing pconj specializations
2013-05-17 17:25:29 +02:00
Gael Guennebaud
d63712163c
Add SSE4 min/max for integers
2013-03-20 18:28:40 +01:00
Gael Guennebaud
e8aa1f00c5
add SSE pexp function for double, make use of _mm_floor_p* for pexp with SSE4.1
2012-07-27 23:40:04 +02:00
Benoit Jacob
69124cfca2
Automatic relicensing to MPL2 using Keirs script. Manual fixup follows.
2012-07-13 14:42:47 -04:00
Jitse Niesen
3c412183b2
Get rid of include directives inside namespace blocks (bug #339 ).
2012-04-15 11:06:28 +01:00
Gael Guennebaud
634fedaf68
proper C++ casting
2012-01-31 18:56:25 +01:00
Gael Guennebaud
9c86ee2695
fix static inline versus inline static issues (the former is the correct order)
2012-01-31 12:58:52 +01:00