17 Commits

Author SHA1 Message Date
Benoit Steiner
1a47844529 Preserve the ability to vectorize the evaluation of an expression even when it involves a cast that isn't vectorized (e.g fp16 to float) 2016-05-26 14:37:09 -07:00
Benoit Steiner
2d7ed54ba2 Made the static storage class qualifier come first. 2016-05-25 22:16:15 -07:00
Rasmus Munk Larsen
235e83aba6 Eigen cost model part 1. This implements a basic recursive framework to estimate the cost of evaluating tensor expressions. 2016-04-14 13:57:35 -07:00
Benoit Steiner
7d5b17087f Added missing EIGEN_DEVICE_FUNC to the tensor conversion code. 2016-04-07 20:01:19 -07:00
Benoit Steiner
e09eb835db Decoupled the packet type definition from the definition of the tensor ops. All the vectorization is now defined in the tensor evaluators. This will make it possible to relialably support devices with different packet types in the same compilation unit. 2016-03-08 12:07:33 -08:00
Benoit Steiner
257b640463 Fixed compilation warning generated by clang 2016-02-21 22:43:37 -08:00
Benoit Steiner
96a24b05cc Optimized casting of tensors in the case where the casting happens to be a no-op 2016-02-21 11:16:15 -08:00
Benoit Steiner
cd042dbbfd Fixed a bug in the tensor type converter 2016-02-19 15:03:26 +00:00
Benoit Steiner
f535378995 Added support for vectorized type casting of int to char. 2016-02-03 18:58:29 -08:00
Benoit Steiner
5b7713dd33 Record whether the underlying tensor storage can be accessed directly during the evaluation of an expression. 2016-01-19 17:05:10 -08:00
Benoit Steiner
33cbdc2d15 Added more missing EIGEN_DEVICE_FUNC 2015-11-06 09:29:59 -08:00
Benoit Steiner
73b8e719ae Removed bogus assertion 2015-10-20 11:42:34 -07:00
Benoit Steiner
f5c1587e4e Fixed a bug in the tensor conversion op 2015-10-20 11:37:44 -07:00
Gael Guennebaud
aec4814370 Many files were missing in previous changeset. 2015-07-29 11:11:23 +02:00
Benoit Steiner
b0f2b6f297 Updated the tensor type casting code as follow: in the case where TgtRatio < SrcRatio, disable the vectorization of the source expression unless is has direct-access. 2015-03-02 10:11:40 -08:00
Benoit Steiner
d9cb604a5d Disabled the use of aligned memory loads when converting a tensor from float to doubles since alignment can't always be guaranteed. 2015-03-02 09:41:36 -08:00
Benoit Steiner
573b377110 Added support for vectorized type casting of tensors 2015-02-27 08:46:04 -08:00