56 Commits

Author SHA1 Message Date
Rory Mitchell
24f527a1c0
AVX gradients (#2878)
* AVX gradients

* Add google test for AVX

* Create fallback implementation, remove fma instruction

* Improved accuracy of AVX exp function
2017-11-27 08:56:01 +13:00
Vadim Khotilovich
74db9757b3 [R package] GPU support (#2732)
* [R] MSVC compatibility

* [GPU] allow seed in BernoulliRng up to size_t and scale to uint32_t

* R package build with cmake and CUDA

* R package CUDA build fixes and cleanups

* always export the R package native initialization routine on windows

* update the install instructions doc

* fix lint

* use static_cast directly to set BernoulliRng seed

* [R] demo for GPU accelerated algorithm

* tidy up the R package cmake stuff

* R pack cmake: installs main dependency packages if needed

* [R] version bump in DESCRIPTION

* update NEWS

* added short missing/sparse values explanations to FAQ
2017-09-28 18:15:28 -05:00
Rory Mitchell
530f01e21c [GPU-Plugin] Add load balancing search to gpu_hist. Add compressed iterator. (#2504) 2017-07-11 22:36:39 +12:00
Rory Mitchell
e939192978 Cmake improvements (#2487)
* Cmake improvements
* Add google test to cmake
2017-07-06 18:05:11 +12:00
Rory Mitchell
48f3003302 [GPU-Plugin] Change GPU plugin to use tree_method parameter, bump cmake version to 3.5 for GPU plugin, add compute architecture 3.5, remove unused cmake files (#2455) 2017-06-29 16:19:45 +12:00
PSEUDOTENSOR / Jonathan McKinney
41efe32aa5 [GPU-Plugin] Multi-GPU for grow_gpu_hist histogram method using NVIDIA NCCL. (#2395) 2017-06-12 05:06:08 +12:00