Demo shows off FPGA-based supercomputing

Nallatech and Mitrionics have demonstrated an FPGA based HPC system hosted on a PowerPC showing a 10-30x improvement in performance over a conventional system.

FPGA Computing system expert Nallatech and FPGA programming specialist Mitrionics jointly demonstrated an FPGA based HPC system hosted on a PowerPC at the Power.org Community conference held at the MareNostrum in Barcelona earlier this month.

The demonstration showed the 10-30x improvement in performance achieved, at a lower size weight and power than a conventional system.

This was achieved by using Mitrionics' Mitrion software to port a protein analysis algorithm to Nallatech's FPGA hardware platform hosted in a PowerPC computer running Linux.

The demonstration system, based around the Xilinx Virtex 2VP70 FPGA, is scalable and each FPGA added to the system delivers an order of magnitude increase in processing throughput to the system, reducing runtime for analysis from days to hours for large data sets.

The protein analysis algorithm demonstrated is used to compare images of markers on 2D gels which show the protein content of samples.

The cross-referencing of differences in the positions and composition of the markers can be used to detect the presence of a disease or disorder.

This process is computationally intensive and presents a major bottleneck to life science research.

Commenting on the demonstration, Allan Cantle, President and CEO of Nallatech, said: "From the viewpoint of the electronics engineering community desktop machines with supercomputing like power is a reality, we have delivered this sort of power for several years".

"However, for the scientific user community to be able to harness the power of FPGA computing, we in the industry need to provide equipment and tools that will integrate with normal workflows".

"Our demonstration showed how an FPGA hardware platform can augment the capabilities of the type of PowerPC based equipment used in labs all over the world and how that hardware can be programmed by algorithm designers using Mitrion software".

Anders Dellson, CEO of Mitrionics, said: "Programmability is the key to adoption of FPGA computing in scientific research applications".

"Researchers in life sciences for example, don't want to learn how low level hardware design skills make their analysis algorithm run faster on a particular hardware platform; they just want to be able to use their existing computing skills and access the computing power available from FPGAs".

"Our solution completely abstracts the FPGA platform, in this case generating the 150,000 lines of VHDL code needed to programme the FPGA system from 180 lines of Mitrion-C to deliver a speed up of 10-30x per FPGA".

Back to top