666 Commits

Author SHA1 Message Date
Benoit Steiner
b6a517c47d Added the ability to load fp16 using the texture path.
Improved the performance of some reductions on fp16
2016-05-11 21:26:48 -07:00
Benoit Steiner
518149e868 Misc fixes for fp16 2016-05-11 20:11:14 -07:00
Benoit Steiner
56a1757d74 Made predux_min and predux_max on fp16 less noisy 2016-05-11 17:37:34 -07:00
Benoit Steiner
9091351dbe __ldg is only available with cuda architectures >= 3.5 2016-05-11 15:22:13 -07:00
Benoit Steiner
02f76dae2d Fixed a typo 2016-05-11 15:08:38 -07:00
Benoit Steiner
70195a5ff7 Added missing EIGEN_DEVICE_FUNC 2016-05-11 14:10:09 -07:00
Benoit Steiner
09a19c33a8 Added missing EIGEN_DEVICE_FUNC qualifiers 2016-05-11 14:07:43 -07:00
Benoit Steiner
0b9e3dcd06 Added packet primitives to compute exp, log, sqrt and rsqrt on fp16. This improves the performance by 10 to 30%. 2016-05-10 11:05:33 -07:00
Benoit Steiner
8adf5cc70f Added support for packet processing of fp16 on kepler and maxwell gpus 2016-05-06 19:16:43 -07:00
Benoit Steiner
0451940fa4 Relaxed the dummy precision for fp16 2016-05-05 15:40:01 -07:00
Benoit Steiner
4c05fb03a3 Merged eigen/eigen into default 2016-05-03 13:15:00 -07:00
Benoit Steiner
6c3e5b85bc Fixed compilation error with cuda >= 7.5 2016-05-03 09:38:42 -07:00
Benoit Steiner
da50419df8 Made a cast explicit 2016-05-02 19:50:22 -07:00
Benoit Steiner
2b890ae618 Fixed compilation errors generated by clang 2016-04-29 18:30:40 -07:00
Benoit Steiner
07a247dcf4 Pulled latest updates from upstream 2016-04-29 13:41:26 -07:00
Benoit Steiner
fa5a8f055a Implemented palign_impl for AVX512 2016-04-29 13:30:13 -07:00
Benoit Steiner
ef3ac9d05a Fixed the AVX512 packet traits 2016-04-29 13:28:36 -07:00
Benoit Steiner
d7b75e8d86 Added pdiv packet primitives for avx512 2016-04-29 13:26:47 -07:00
Benoit Steiner
5e89ded685 Implemented preduxp for AVX512 2016-04-29 13:00:33 -07:00
Benoit Steiner
5f85662ad8 Implemented the pabs and preverse primitives for avx512. 2016-04-29 12:53:34 -07:00
Benoit Steiner
d37ee89ca8 Disabled some of the AVX512 primitives on compilers that don't support them 2016-04-29 12:50:29 -07:00
Konstantinos Margaritis
87294c84a6 define Packet2d constants with VSX only 2016-04-28 14:39:56 -03:00
Konstantinos Margaritis
6ed7a7281c remove accidentally pasted code 2016-04-28 14:35:55 -03:00
Konstantinos Margaritis
62f9093b31 improve state of MathFunctions as well 2016-04-28 14:33:09 -03:00
Konstantinos Margaritis
8ed26120c8 bring Altivec/VSX to a better state, implement some of the missing functions 2016-04-28 14:32:42 -03:00
Konstantinos Margaritis
950158f6d1 add name to copyrights 2016-04-28 14:32:11 -03:00
Konstantinos Margaritis
ee0459300b minor fix, add to copyright 2016-04-28 14:31:21 -03:00
Benoit Steiner
c61170e87d fpclassify isn't portable enough. In particular, the return values of the function are not available on all the platforms Eigen supportes: remove it from Eigen. 2016-04-27 14:22:20 -07:00
Benoit Steiner
25141b69d4 Improved support for min and max on 16 bit floats when running on recent cuda gpus 2016-04-27 12:57:21 -07:00
Benoit Steiner
6744d776ba Added support for fpclassify in Eigen::Numext 2016-04-27 12:10:25 -07:00
Konstantinos Margaritis
0e8fc31087 remove pgather/pscatter for std::complex<double> for s390x 2016-04-15 07:08:57 -04:00
Benoit Steiner
7718749fee Force the inlining of the << operator on half floats 2016-04-14 11:51:54 -07:00
Benoit Steiner
5379d2b594 Inline the << operator on half floats 2016-04-14 11:40:48 -07:00
Benoit Steiner
5c13765ee3 Added ability to printf fp16 2016-04-14 10:24:52 -07:00
Benoit Steiner
36f5a10198 Properly gate the definition of the error and gamma functions for fp16 2016-04-13 18:44:48 -07:00
Benoit Steiner
d6105b53b8 Added basic implementation of the lgamma, digamma, igamma, igammac, polygamma, and zeta function for fp16 2016-04-13 15:26:02 -07:00
Benoit Steiner
87ca15c4e8 Added support for sin, cos, tan, and tanh on fp16 2016-04-13 14:12:38 -07:00
Benoit Steiner
473c8380ea Added constructors to convert unsigned integers into fp16 2016-04-13 11:03:37 -07:00
Benoit Steiner
8bfe739cd2 Updated the AVX512 PacketMath to properly leverage the AVX512DQ instructions 2016-04-11 18:40:16 -07:00
Benoit Steiner
d6e596174d Pull latest updates from upstream 2016-04-11 17:20:17 -07:00
Benoit Steiner
833efb39bf Added epsilon, dummy_precision, infinity and quiet_NaN NumTraits for fp16 2016-04-11 11:03:56 -07:00
Benoit Steiner
995f202cea Disabled the use of half2 on cuda devices of compute capability < 5.3 2016-04-08 14:43:36 -07:00
Benoit Steiner
8d22967bd9 Initial support for taking the power of fp16 2016-04-08 14:22:39 -07:00
Benoit Steiner
3394379319 Fixed the packet_traits for half floats. 2016-04-08 13:33:59 -07:00
Benoit Jacob
cd2b667ac8 Add references to filed LLVM bugs 2016-04-08 08:12:47 -04:00
Benoit Steiner
737644366f Move the functions operating on fp16 out of the std namespace and into the Eigen::numext namespace 2016-04-07 11:40:15 -07:00
Benoit Steiner
df838736e2 Fixed compilation warning triggered by msvc 2016-04-06 20:48:55 -07:00
Benoit Steiner
14ea7c7ec7 Fixed packet_traits<half> 2016-04-06 19:30:21 -07:00
Benoit Steiner
532fdf24cb Added support for hardware conversion between fp16 and full floats whenever
possible.
2016-04-06 17:11:31 -07:00
Benoit Steiner
58c1dbff19 Made the fp16 code more portable. 2016-04-06 13:44:08 -07:00