rCUDA is designed to provide the best performance. In the plot you can see a comparison among the performance of P2P memory copies (data copies among GPUs) carried out with CUDA using the PCIe link within a single node and the performance attained by rCUDA when both GPUs are located in different remote servers and connected by InfiniBand. Three different GPU generations are considered. As you can see, using rCUDA does not mean a performance degradation.

The rCUDA Team is showing a live demo of the new rCUDA version at Mellanox booth at ISC 2018 in Frankfurt, Germany. If you are attending ISC, you are welcome to come to the Mellanox booth ant talk to the creators of the rCUDA technology.

 Federico Silla presented rCUDA last week in the High Performance Container Workshop held in conjunction with ISC 2018 in Frankfurt, Germany. You can find a copy of the slides here.

Federico Silla and Carlos Reaño presented a tutorial on rCUDA during HPC ADMINTECH 2018, which took place in Valencia, Spain, between 9 and 11 May 2018. The focus of the tutorial was the use of rCUDA in ARM-based systems. A copy of the slides can be found here.

You are welcome to watch the live rCUDA demo at Mellanox booth at ISC 2018. Come!!