PRESS RELEASE

MPC-X series

Maxeler Technologies has launched the MPC-X series for deployment of dataflow computing to complement standard servers. The MPC-X1000 provides eight dataflow engines with the equivalent performance of 40 to 60 multicore x86 servers and power consumption comparable to a single high-end server. A 1U rack-mount system that supports dual redundant power supplies and IPMI-compatible remote management, a single MPC-X1000 has 384GB of memory and over 16TB of memory in a single rack.

Resources within the MPC-X1000, including dynamic allocation of dataflow engines to CPU threads and processes, and balancing demands on the cluster at runtime to maximise overall performance, are managed by Maxeler’s software. With a Linux RPM installation, any CPU server in the cluster can be quickly upgraded to benefit from dataflow computing.

The MPC-X series dataflow appliances provide multiple dataflow engines as shared resources on the network, allowing them to be used by applications running anywhere in a cluster. The MPC-X series combines dual FDR/QDR Infiniband connectivity with unique RDMA technology that provides direct memory to dataflow engine transfers without inefficient memory copies. In one key benchmark, the MPC-X1000's hardware-enabled RDMA delivered 40 per cent speedup over a software-only framework for remote execution over a network.

Feature

For functionality and security for externalised research, software providers have turned to the cloud, writes Sophia Ktori

Feature

Robert Roe looks at the latest simulation techniques used in the design of industrial and commercial vehicles

Feature

Robert Roe investigates the growth in cloud technology which is being driven by scientific, engineering and HPC workflows through application specific hardware

Feature

Robert Roe learns that the NASA advanced supercomputing division (NAS) is optimising energy efficiency and water usage to maximise the facility’s potential to deliver computing services to its user community

Feature

Robert Roe investigates the use of technologies in HPC that could help shape the design of future supercomputers