Benoit Steiner
393b7c4959
Merged in ncluehr/eigen/float2half-fix (pull request PR-349)
...
Replace __float2half_rn with __float2half
2017-12-01 00:29:51 +00:00
nluehr
aefd5fd5c4
Replace __float2half_rn with __float2half
...
The latter provides a consistent definition for CUDA 8.0 and 9.0.
2017-11-28 10:15:46 -08:00
Gael Guennebaud
d0b028e173
clarify Pastix requirements
2017-11-27 22:11:57 +01:00
Gael Guennebaud
3587e481fb
silent MSVC warning
2017-11-27 21:53:02 +01:00
Benoit Steiner
3a327cd3c7
Merged in ncluehr/eigen/predux_fp16_fix (pull request PR-348)
...
Fix incorrect integer cast in half2 predux.
2017-11-21 21:11:45 +00:00
nluehr
dd6de618c3
Fix incorrect integer cast in predux<half2>().
...
Bug corrupts results on Maxwell and earlier GPU architectures.
2017-11-21 10:47:00 -08:00
Gael Guennebaud
3dc6ff73ca
Handle PGI compiler
2017-11-17 22:54:39 +01:00
Zvi Rackover
599a88da27
Disable gcc-specific workaround for Clang to allow build with AVX512
...
There is currently a workaround for an issue in gcc that requires invoking gcc with the -fabi-version flag. This workaround is not needed for Clang and moreover is not supported.
2017-11-16 19:53:38 +00:00
Gael Guennebaud
672bdc126b
bug #1479 : fix failure detection in LDLT
2017-11-16 17:55:24 +01:00
zhouzhaoping
912e9965ef
a small mistake QuickReference.dox edited online with Bitbucket
2017-11-09 08:49:01 +00:00
Gael Guennebaud
4c03b3511e
Fix issue with boost::multiprec in previous commit
2017-11-08 23:28:01 +01:00
Gael Guennebaud
e9d2888e74
Improve debugging tests and output in BDCSVD
2017-11-08 10:26:03 +01:00
Gael Guennebaud
e8468ea91b
Fix overflow issues in BDCSVD
2017-11-08 10:24:28 +01:00
Benoit Steiner
3949615176
Merged in JonasMu/eigen (pull request PR-329)
...
Added an example for a contraction to a scalar value to README.md
Approved-by: Jonas Harsch <jonas.harsch@gmail.com>
2017-10-27 07:27:46 +00:00
Christoph Hertzberg
11ddac57e5
Merged in guillaume_michel/eigen (pull request PR-334)
...
- Add support for NEON plog PacketMath function
2017-10-23 13:22:22 +00:00
Benoit Steiner
a6d875bac8
Removed unecesasry #include
2017-10-22 08:12:45 -07:00
Benoit Steiner
f16ba2a630
Merged in LaFeuille/eigen-1/LaFeuille/typo-fix-alignmeent-alignment-1505889397887 (pull request PR-335)
...
Typo fix alignmeent ->alignment
2017-10-21 01:59:55 +00:00
Benoit Steiner
ee6ad21b25
Merged in henryiii/eigen/henryiii/device (pull request PR-343)
...
Fixing missing inlines on device functions for newer CUDA cards
2017-10-21 01:58:22 +00:00
Henry Schreiner
9bb26eb8f1
Restore __device__
2017-10-21 00:50:38 +00:00
Henry Schreiner
4245475d22
Fixing missing inlines on device functions for newer CUDA cards
2017-10-20 03:20:13 +00:00
Benoit Steiner
8eb4b9d254
Merged in benoitsteiner/opencl (pull request PR-341)
2017-10-17 16:39:28 +00:00
Rasmus Munk Larsen
2dd63ed395
Merge
2017-10-13 15:58:52 -07:00
Rasmus Munk Larsen
f349507e02
Specialize ThreadPoolDevice::enqueueNotification for the case with no args. As an example this reduces binary size of an TensorFlow demo app for Android by about 2.5%.
2017-10-13 15:58:12 -07:00
Benoit Steiner
688451409d
Merged in mehdi_goli/upstr_benoit/ComputeCppNewReleaseFix (pull request PR-16)
...
Changes required for new ComputeCpp CE version.
2017-10-13 20:56:01 +00:00
Konstantinos Margaritis
0e6e027e91
check both z13 and z14 arches
2017-10-12 15:38:34 -04:00
Konstantinos Margaritis
6c3475f110
remove debugging
2017-10-12 15:34:55 -04:00
Konstantinos Margaritis
df7644aec3
Merged eigen/eigen into default
2017-10-12 22:23:13 +03:00
Konstantinos Margaritis
98e52cc770
rollback 374f750ad4
2017-10-12 15:22:10 -04:00
Konstantinos Margaritis
c4ad358565
explicitly set conjugate mask
2017-10-11 11:05:29 -04:00
Konstantinos Margaritis
380d41fd76
added some extra debugging
2017-10-11 10:40:12 -04:00
Konstantinos Margaritis
d0b7b9d0d3
some Packet2cf pmul fixes
2017-10-11 10:17:22 -04:00
Konstantinos Margaritis
df173f5620
initial pexp() for 32-bit floats, commented out due to vec_cts()
2017-10-11 09:40:49 -04:00
Konstantinos Margaritis
3dcae2a27f
initial pexp() for 32-bit floats, commented out due to vec_cts()
2017-10-11 09:40:45 -04:00
Konstantinos Margaritis
c2a2246489
fix predux_mul for z14/float
2017-10-10 13:38:32 -04:00
Konstantinos Margaritis
374f750ad4
eliminate 'enumeral and non-enumeral type in conditional expression' warning
2017-10-09 16:56:30 -04:00
Konstantinos Margaritis
bc30305d29
complete z14 port
2017-10-09 16:55:10 -04:00
Gael Guennebaud
0e85a677e3
bug #1472 : fix warning
2017-09-26 10:53:33 +02:00
Gael Guennebaud
8579195169
bug #1468 (1/2) : add missing std:: to memcpy
2017-09-22 09:23:24 +02:00
Gael Guennebaud
f92567fecc
Add link to a useful example.
2017-09-20 10:22:23 +02:00
Gael Guennebaud
7ad07fc6f2
Update documentation for aligned_allocator
2017-09-20 10:22:00 +02:00
LaFeuille
7c9b07dc5c
Typo fix alignmeent ->alignment
2017-09-20 06:38:39 +00:00
Mehdi Goli
2062ac9958
Changes required for new ComputeCpp CE version.
2017-09-18 18:17:39 +01:00
Christoph Hertzberg
23f8b00bc8
clang provides __has_feature(is_enum) (but not <type_traits>) in C++03 mode
2017-09-14 19:26:03 +02:00
Christoph Hertzberg
0c9ad2f525
std::integral_constant is not C++03 compatible
2017-09-14 19:23:38 +02:00
Rasmus Munk Larsen
1b7294f6fc
Fix cut-and-paste error.
2017-09-08 16:35:58 -07:00
Rasmus Munk Larsen
94e2213b38
Avoid undefined behavior in Eigen::TensorCostModel::numThreads.
...
If the cost is large enough then the thread count can be larger than the maximum
representable int, so just casting it to an int is undefined behavior.
Contributed by phurst@google.com .
2017-09-08 15:49:55 -07:00
Gael Guennebaud
6d42309f13
Fix compilation of Vector::operator()(enum) by treating enums as Index
2017-09-07 14:34:30 +02:00
Benoit Steiner
ea4e65bf41
Fixed compilation with cuda_clang.
2017-09-07 09:13:52 +00:00
Gael Guennebaud
a91918a105
Merged in infinitei/eigen (pull request PR-328)
...
bug #1464 : Fixes construction of EulerAngles from 3D vector expression.
Approved-by: Tal Hadad <tal_hd@hotmail.com>
Approved-by: Abhijit Kundu <abhijit.kundu@gatech.edu>
2017-09-06 08:42:14 +00:00
Gael Guennebaud
9c353dd145
Add C++11 max_digits10 for half.
2017-09-06 10:22:47 +02:00
