rCUDA presented at ISC'14 at Leipzig, Germany
| 
| Hits: 2495
/ 0
The rCUDA technology has been presented at #ISC14. On the one hand, a talk titled "Increasing the efficiency of your GPU-enabled cluster with rCUDA" was given by Federico Silla at the HPC Advisory Council European Conference 2014, on June 22nd. On the other hand, two different live demos comparing the performance of CUDA and rCUDA on real time were concurrently running at the Mellanox Technologies booth.
Visit us at the Mellanox Technologies booth at ISC'14
| | Hits: 3067
New rCUDA 4.2 version to be released next week
| | Hits: 2641
New rCUDA 4.1 version available
| | Hits: 2399
/ 7
The rCUDA Team is pleased to announce the release of the new rCUDA 4.1 version. In addition to fix some bugs related with asynchronous memory transfers, the new release provides support for:
-CUDA 5.5 Runtime API
-Mellanox Connect-IB network adapters
-Dynamic Parallelism
-cuFFT and cuBLAS libraries
Paper on the use of remote GPU virtualization mechanisms along with low-power processors presented at the Fourth ENERGY Conference
| | Hits: 2138
/ 0
The rCUDA team is glad to announce that its last research results were presented at the Fourth ENERGY Conference celebrated in Chamonix (France). The presented paper, titled "On the Use of Remote GPUs and Low-Power Processors for the Acceleration of Scientific Applications", showed the possibilities that remote GPU virtualization technologies offer when used with low-power processors. The paper was awarded with the Best Paper Award.
rCUDA achieves maximum performance with the new Mellanox Connect-IB cards
| | Hits: 2386
/ 0
The performance tests carried out by the rCUDA team leveraging the new Connect-IB cards, along with the new NVIDIA Tesla K40 GPU, revealed that rCUDA is able to provide almost the same bandwidth as original CUDA. Our testbed was composed of two Ivy Bridge Xeon based computers equipped with the new dual-port Mellanox Connect-IB cards and a K40 Tesla GPU installed in one of the systems. In this hardware configuration, the maximum data transfer rate achieved by the bandwidthTest benchmark from the NVIDIA CUDA Samples when using local CUDA was 10.06GB/s. In the case of using rCUDA to transfer data from main memory of one computer to the GPU installed in the other computer, the same bandwidthTest benchmark achieved a maximum data transfer rate of 9.91GB/s. This means that rCUDA is able to attain 98.5% of CUDA’s bandwidth, thus introducing a negligible performance loss.
rCUDA presented at HPC Advisory Council Switzerland Conference 2014
| | Hits: 2558
/ 0
rCUDA was presented last week at Lugano (Switzerland) in the HPC Advisory Council Conference that took place from 31st March to 3rd April. In addition to the presentation, a hands on session about rCUDA was also provided. You can additionally find the videos of the presentation and hands on session here.
