ACADEMIA
Xilinx Powered SGI RASC Platform Accelerates Bioinformatics Application 900X
SGI Altix System with 70 Xilinx FPGAs Sets New Performance Record: Xilinx today announced that an SGI RASC (Reconfigurable Application Specific Computing) enabled SGI Altix system from Silicon Graphics (SGI), featuring Xilinx Virtex-4 high performance FPGAs, can accelerate the Blast-n (Basic Local Alignment Search Tool for nucleotides) bioinformatics application by more than 900 times compared to a traditional cluster. 
"The performance of Xilinx accelerated bioinformatics is truly astonishing and the price-performance of our RC100 based Blast-n appliance is extending the utility of this tool to many more customers and applications," said Bill Mannel, SGI director of marketing for servers. "We are seeing tremendous interest from commercial customers anxious to exploit this technology to competitive advantage." The benchmark test ran a standard Blast-n query to match 25 nucleotide base pairs against 600,000 queries. This application required approximately 3 weeks to complete on a 68-node AMD Opteron cluster compared to less than 33 minutes for the Virtex-4 FPGA accelerated SGI RASC platform: a total speed improvement of more than 900 times. The product used to set the Blast-n performance record was an SGI Altix 4700 system configured as a turn-key bioinformatics appliance with 64 Intel Itanium 2 processors and 35 RC100 RASC blades. The completed system fits into a single rack and runs a Mitrionics developed Blast-n engine to transparently accelerate a customer's Blast-n applications using the RC100 RASC blades. Each RC100 is tightly integrated into SGI NUMAflex architecture and features two Xilinx Virtex-4 LX200 FPGAs and 10 banks of local scratchpad memory, providing a total of 70 FPGAs and 840 GB per second of local memory bandwidth in the benchmarked configuration. Now in its 4th generation, Xilinx enabled RASC technology can scale performance across a broad range of data intensive algorithms such as those used in Blast-n, the world's most widely used bioinformatics application. Additional applications appropriate for RASC acceleration include oil and gas exploration, defense and intelligence, financial analytics, medical imaging and broadcast media encoding. "The SGI Blast-n appliance exemplifies the value FPGAs can bring to high performance computing and validates our investments in this market," said Ivo Bolsens, CTO of Xilinx. "With our newly announced Accelerated Computing Platform (ACP) for the Intel Front Side Bus, Xilinx is extending this value into the X86 platform space too." Last month, Xilinx began commercial licensing of the high-performance computing industry's first FPGA-based acceleration solution to interface with the Intel Front Side Bus (FSB). Enabled by the high-performance 65nm Virtex-5 platform FPGA and Intel QuickAssist Technology, the ACP M1 licensing package supports implementations capable of full 1066MHz FSB performance. The ACP M1 licensing package is available today to system integrators for developing solutions that accelerate the performance of Intel processor-based server platforms while minimizing power consumption and total cost of ownership. Customers and partners who wish to learn more about Xilinx in accelerated computing can contact ACP@Xilinx.com.
"The performance of Xilinx accelerated bioinformatics is truly astonishing and the price-performance of our RC100 based Blast-n appliance is extending the utility of this tool to many more customers and applications," said Bill Mannel, SGI director of marketing for servers. "We are seeing tremendous interest from commercial customers anxious to exploit this technology to competitive advantage." The benchmark test ran a standard Blast-n query to match 25 nucleotide base pairs against 600,000 queries. This application required approximately 3 weeks to complete on a 68-node AMD Opteron cluster compared to less than 33 minutes for the Virtex-4 FPGA accelerated SGI RASC platform: a total speed improvement of more than 900 times. The product used to set the Blast-n performance record was an SGI Altix 4700 system configured as a turn-key bioinformatics appliance with 64 Intel Itanium 2 processors and 35 RC100 RASC blades. The completed system fits into a single rack and runs a Mitrionics developed Blast-n engine to transparently accelerate a customer's Blast-n applications using the RC100 RASC blades. Each RC100 is tightly integrated into SGI NUMAflex architecture and features two Xilinx Virtex-4 LX200 FPGAs and 10 banks of local scratchpad memory, providing a total of 70 FPGAs and 840 GB per second of local memory bandwidth in the benchmarked configuration. Now in its 4th generation, Xilinx enabled RASC technology can scale performance across a broad range of data intensive algorithms such as those used in Blast-n, the world's most widely used bioinformatics application. Additional applications appropriate for RASC acceleration include oil and gas exploration, defense and intelligence, financial analytics, medical imaging and broadcast media encoding. "The SGI Blast-n appliance exemplifies the value FPGAs can bring to high performance computing and validates our investments in this market," said Ivo Bolsens, CTO of Xilinx. "With our newly announced Accelerated Computing Platform (ACP) for the Intel Front Side Bus, Xilinx is extending this value into the X86 platform space too." Last month, Xilinx began commercial licensing of the high-performance computing industry's first FPGA-based acceleration solution to interface with the Intel Front Side Bus (FSB). Enabled by the high-performance 65nm Virtex-5 platform FPGA and Intel QuickAssist Technology, the ACP M1 licensing package supports implementations capable of full 1066MHz FSB performance. The ACP M1 licensing package is available today to system integrators for developing solutions that accelerate the performance of Intel processor-based server platforms while minimizing power consumption and total cost of ownership. Customers and partners who wish to learn more about Xilinx in accelerated computing can contact ACP@Xilinx.com.