Aspen
Oakridge Top Right
HPCwire

Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them

Language Flags

Visit additional Tabor Communication Publications

Datanami
Digital Manufacturing Report
HPC in the Cloud
Green Computing Report

Tabor Communications
Corporate Video

The Microsoft of FPGAs


HPC and modern computing in general has a seemingly insatiable demand for more performance, better efficiency and scalability. Now with the expansion of computing to practically every commercial and non-commercial endeavor, an additional requirement is to apply these attributes to a much wider range of applications.

"So there's a need there for more types of processing," says Jeff Jussel, vice president of marketing and general manager of the Americas for Celoxica. "There's a number of ways the industry is addressing that -- with massively parallel processing (MPP) and with all sorts of different types of co-processors. At Celoxica, we believe that the FPGA represents a huge opportunity for co-processing, because it can deliver the massive parallelization, with the advantages of custom hardware, but in a way that is programmable."

But there are three things that you need in order for FPGAs to really take off:

  1. Capable hardware: You've got to have the FPGAs that are powerful enough to handle the load, and do something interesting. Today that's not a problem. For example, even the standard technology Xilinx Virtex 4 (90nm) devices have the capability to run workloads from the financial services, oil and gas, and life science spaces with much higher performance than conventional scalar processors.

  2. High performance interconnects: You can't just use a PCI bus to communicate with the processor to provide the level of bandwidth and latency required to offload anything very interesting. But with PCI Express and HyperTransport, that level of interconnect performance is now available.

  3. Programmability: You can't expect software developers on Wall Street to understand RTL (register transfer level) technology to program the hardware. Familiar software tools and programming models need to be available. This is the biggest challenge for FPGAs today.

"That's where the tools that Celoxica provides comes in," says Jussel. "That's our mission in life -- to make that FPGA programming transparent. And in doing so, enable FPGA use for the high performance computing market."

As part of this strategy, this week Celoxica announced a new off-the-shelf hardware and software compiler design bundle for high performance computing using HyperTransport (HTX) slots. The HTX bundle combines an intellectual property (IP) core for HTX connectivity, an FPGA-based HTX acceleration card and a software programming environment. The solution is designed to allow users to accelerate applications in Opteron-based computing systems with FPGA co-processing and HyperTransport technology. The bundle provides compilers that map C code onto FPGA hardware, a run-time OS (RTOS) for FPGA computing, and FPGA hardware that plugs into a host server system.

The hardware consists of the RCHTX acceleration card, which includes two Xilinx Virtex 4 FPGAs devices (in the future it will support more advanced Virtex 5 devices), 24 MB of QDR SRAM, and a range of I/O. The main co-processor FPGA is a 16 million gate device that is meant to run the user algorithms. The second FPGA is configured as a bridge, containing an HTX IP core developed by Celoxica. The bridge FPGA and IP provide the HyperTransport interconnect between the FPGA co-processor and the host processor system and memory space.

The software component consists of the DK Design Suite, which includes a C compiler for programming the FPGA co-processor, a board support package (BSP) and data communications drivers for the RCHTX card, a basic floating point library (single and double precision) and the software API which provides the interfaces.

The idea is not for the user to port their whole application to the FPGAs, just the compute-intensive algorithms that represent the workload bottlenecks. For example FFT calculations, a Black Scholes algorithm or wave migration calculations can be offloaded to the FPGA to take advantage of the parallel hardware resources.

The user replaces the algorithm loop in the original FORTRAN or C source with a Celoxica API call, which calls the C code that will be compiled into the FPGA. Jussel says the original algorithm needs to be "tweaked" somewhat to insert parallelism, but they've tried to simplify this as much as possible. The FPGA C compiler brings in the appropriate run-time pieces to make it work in its new hardware environment. At execution time, the data communication between the host processor and the FPGA is done across the HyperTransport connection, but this is transparent to the user.

Jussel notes that the product announced this week represents the first FPGA solutions that uses the HTX slot. DRC Computer Corporation has a somewhat similar solution, where its FPGA uses an Opteron socket to directly connect to HyperTransport. As it turns out, DRC is an OEM partner with Celoxica and makes use of the same C compiler technology.

Celoxica's current (beta) customers for the HTX solution are in the financial services, oil & gas, and life sciences industries. With this particular product, users have achieved a 200X performance improvement for the application (offloading a Black Scholes algorithm to the FPGA).

"We've done enough with the finance industry to know that the metric we need to hit is about a 10X price-performance benefit," says Jussel. "If we hit that 10X factor then it's worth it for them to invest in new technology. And we've been able to show quite a bit greater than 10X for all these applications."

Even though this HTX product includes the FPGA card, hardware is not Celoxica's main focus. The company's real goal is to be the leader in compilers and the run-time support for FPGAs. Jussel says that compared to other FPGA compiler companies, Celoxica is quite a bit larger and more established, having developed and matured its software technology over the past 10 years. It provides the compiler for the SGI RASC RC100 system as well as Cray FPGA systems, not to mention its large customer base in the embedded computing space -- still the majority of their business. But because FPGAs have this unique aspect of reconfigurability and high performance, the company believes that these devices will become ubiquitous throughout computing. And Celoxica wants to be there with their software.

Says Jussel: "We really want to be the Microsoft of FPGA computing. We want to provide the compilers and RTOS for that solution."

Sponsored Links

Accelerate your science with Seneca
One of the first HPC providers installing a 4X NVIDIA Kepler K-20 cluster. Invites you to a free evaluation on Seneca’s NVIDIA K20 Kepler cluster, pre-loaded with AMBER, NAMD, LAMMPS

High-Performance Computing in Action
Businesses that want to be on the cutting edge of their industries are increasingly turning to high-performance computing (HPC) solutions to handle complex compute processes and speed up their rate of innovation. Download this Executive Brief to see how businesses in energy, life sciences and entertainment put HPC solutions to work in their operations.

Webinar: Programming Heterogeneous X64+GPU Systems Using OpenACC
Join Michael Wolfe as he compares the advantages and costs of using both low-level models and the directive-based OpenACC model for programming accelerated heterogeneous systems. Registration is free.

May 20, 2013

May 17, 2013

May 16, 2013

May 15, 2013

May 14, 2013

May 13, 2013

May 10, 2013

May 09, 2013

May 08, 2013


Most Read Features

Most Read Around the Web

Most Read This Just In

Supermicro

Short Takes

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

Computing the Physics of Bubbles

May 15, 2013 | Supercomputers at the Department of Energy’s National Energy Research Scientific Computing Center (NERSC) have worked on important computational problems such as collapse of the atomic state, the optimization of chemical catalysts, and now modeling popping bubbles.
Read more...

Internet2 Awards Program Seeks Innovative Applications

May 10, 2013 | Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
Read more...

Floating Funding to Exascale Island

May 09, 2013 | The Japanese government has revealed its plans to best its previous K Computer efforts with what they hope will be the first exascale system...
Read more...

HPC and the True Cost of Cloud

May 08, 2013 | For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Progress in Parallel: the Bull Parallel Programming Center

04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.

Sponsored Multimedia

SGI DMF ZeroWatt Disk Solution

In this demonstration of SGI DMF ZeroWatt disk solution, Dr. Eng Lim Goh, SGI CTO, discusses a function of SGI DMF software to reduce costs and power consumption in an exascale (Big Data) storage datacenter.

Cray CS300-AC Cluster Supercomputer Air Cooling Technology Video

The Cray CS300-AC cluster supercomputer offers energy efficient, air-cooled design based on modular, industry-standard platforms featuring the latest processor and network technologies and a wide range of datacenter cooling requirements.

SC12 Editorial Feature HPCwire Soundbite sponsored by ISC

HPC Job Bank


Featured Events


  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States





HPCwire Events