Current-generation CPU cores can process approximately 16 million DES key operations per second. A GPU card such as the GTX-295 can be programmed to process approximately 250 million such operations per second.
When using a Pico FPGA cluster, however, each FPGA is able to perform 1.6 billion DES operations per second. A cluster of 176 FPGAs, installed into a single server using standard PCI Express slots, is capable of processing more than 280 billion DES operations per second. This means that a key recovery that would take years to perform on a PC, even with GPU acceleration, could be accomplished in less than three days on the FPGA cluster.
HPCWire reports - computing. The reason that FPGAs are so adept at these types of applications, from both a performance and power consumption point of view, is their ability to morph their hardware structures to match operators and data types for a given algorithm. This is especially true when the underlying algorithms are not based on typical integer or floating point data types.
In genomics applications, for example, a lot of algorithms are based on the four fundamental nucleoside bases (adenine, thymine, guanine, cytosine) that make up RNA and DNA. Thus a nucleoside data type would only be two bits wide. And unlike CPUs and GPUs, you can map FPGA resources to match that data size exactly. "You don't need full 32-bit or 64-bit data paths and operators," explains David Pellerin, Pico's director of strategic marketing. "It's wasteful." That's why some applications that get 100-fold acceleration from a GPU can get 1,000-fold from an FPGA, when compared to a CPU.