New release of the rCUDA middleware
| 
| Hits: 470
/ 0
The rCUDA Team is happy to announce the new release of the rCUDA remote GPU virtualization middleware. This new release is a beta version with lots of new functionality although performance is not optimized yet. The new release includes, among other characteristics, a new architecture of the rCUDA server, which has been renewed from scratch in order to provide full support to multi-threaded applications. Additionally, the rCUDA daemon now makes a better use of the GPU memory, allowing more memory for applications. Support for Deep Learning frameworks such as TensorFlow (v1.2 and v1.3) or Caffe has been introduced. Moreover, rendering programs such as Blender are now supported. New libraries, such as cuSOLVER, cuBLAS-XT and NVGRAPH, are also supported, whereas partial support is provided for the NPP library.
rCUDA tutorial at the HiPEAC conference next week
| | Hits: 981
/ 0
A tutorial on rCUDA will be given next week in the context of the HiPEAC 2018 conference that will take place next week in Manchester, UK. More information at https://sites.google.com/site/rcudatutorial/home
Come to see the live rCUDA demo at SC17
| | Hits: 1156
/ 0
If you are attending SC17 at Denver, CO, please feel free to come to the Mellanox booth and check out the new rCUDA demo about TensorFlow.
A new tutorial on rCUDA given at HPC Advisory Council Spain Conference
| | Hits: 1138
/ 0
Carlos Reaño and Federico Silla gave a tutorial on rCUDA on 29th September 2017 in the context of the 6th Annual HPC Advisory Council Spain Conference, which took place in Santiago de Compostela, Spain. The tutorial included a practical demonstration about how to install and use rCUDA.
rCUDA live demos at SC17 in Denver, CO
| | Hits: 1080
/ 0
rCUDA Tutorial given in PACT Conference in Portland, OR, USA
| | Hits: 1035
/ 0
Carlos Reaño and Federico Silla gave a tutorial on rCUDA during the latest edition of the PACT conference, which took place in Portland, Oregon, USA from 9 to 13 September 2017. The tutorial, which was titled "Boosting the performance of hybrid CPU-GPU clusters with rCUDA", included a practical demonstration about how to install and use rCUDA as well as several guided exercises to be carried out by attendees.
rCUDA presented at the HPC Advisory Council China Workshop 2017
| | Hits: 945
/ 1
The rCUDA technology was presented last 18th October at Hefei, China, as part of the HPC Advisory Council China Workshop 2017. You can find a copy of the slides here.
