Markets & Applications

SRC’s powerful reconfigurable computing products offer benefits for a variety of compute-intensive markets and applications. SRC has demonstrated significant increases in performance for applications in the defense/national security, scientific and academic research, medical imaging, and financial sectors.

 

Defense, Intelligence & National Security

 

 

[Photos courtesy of the Department of Defense]

 

 

Airborne Signal Data Processor
80 lbs, 21"x17"x10.5"
2 mP, 4 MAPs, 5 Common Memory banks

 

Overview & Challenges

The U.S. military and intelligence agencies have tremendous demand for a large range of solutions including real-time Synthetic Aperture Radar (SAR) image processing, real-time HDTV image processing, real-time target recognition, and real-time biometric recognition, just to name a few. Powerful processing resources are necessary to handle these highly compute-intensive visualization applications and quickly provide decision-makers with reliable timely information.

 

The job of safeguarding borders, airspace and seas, both at home and in combat, becomes exponentially more challenging as the amount of data increases from these sources. Raw data and intelligence must be fused in a format that is easily understandable and actionable. 

 

Defense applications face additional hurdles due to deployment on a variety of platforms such as Unmanned Aerial Vehicles (UAVs), Unmanned Ground Vehicles (UGVs), traditional military aircraft and helicopters, as well as ground vehicle and portable implementations. There is one commonality among all these platforms; they are generally constrained by weight, power, physical space, and computational time requirements

 

SRC Solutions

For airborne or mobile applications, SRC’s Signal Data Processing solutions, Portable MAPstations™, 2U solutions and custom embedded solutions provide powerful computing in small form factors for real-time, compute-intensive processing.

 

For ground-based applications, SRC’s MAPstation™ workstations harness the performance of large multi-rack servers into a single desktop unit. And if even more computing power is needed, Scalable Systems & Servers can replace traditional commodity clusters for orders of magnitude increases in processing performance in a smaller footprint with lower power, cooling and support costs.

 

Performance Gains

  Speedup* Relative to 2.8 GHz Xeon Processor   
Application SRC-6 Series E MAP® SRC-7 Series H MAP
Target recognition  357x >535x
Backprojection 75x >200x
Radar signal processing 304x >456x
Visual/IR Image Processing 240x >360x

Scientific & Academic Research

 

Overview & Challenges

Scientific discoveries in academic research and the life sciences are often driven by the speed and power of high performance computing. For this reason, the scientific and academic communities have been strong supporters of high performance computing for many decades and have traditionally relied on large clusters for their computing needs..

 

However, the low efficiency-per-CPU of modern commodity compute clusters typically forces industrial and academic compute centers to install many systems in order to meet the needs of their users.

 

SRC Solutions

SRC’s MAPstations and Scalable Systems & Servers provide high performance computing that is affordable for the scientific, academic and commercial markets alike. The IMPLICIT+EXPLICIT™ Architecture accelerates applications by enabling computational efficiency and allows SRC’s systems to provide the same level of performance in less space with lower power and cooling costs of a typical commodity compute cluster.

 

SRC’s solutions support applications such as bioinformatics, data visualization, molecular modeling, and genomics as well as more industrial and commercial based applications such as computational fluid dynamics, simulation, modeling, and seismic tomography.

 

Performance Gains

  Speedup* Relative to 2.8 GHz Xeon Processor   
Application SRC-6 Series E MAP® SRC-7 Series H MAP
Molecular dynamics  15x  
Cosmology 50x  >75x
Gravitational force 90x  >135x
Deconvolution 30x 50x

Medical Imaging

 

Overview & Challenges

The medical imaging market has grown significantly in recent years due to vast improvements in imaging technology. There are several extremely compute-intensive imaging techniques, or modalities, that require the use of image processing and reconstruction such as Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI).

 

Too often, a software application’s computational intensity limits the imaging details available to the medical professional. This problem is compounded as volumetric imaging fuses multiple modalities.

 

SRC Solutions

The performance gains provided by SRC’s MAPstations and Scalable Systems & Servers enable higher image resolution in less time for medical visualization applications.

 

Performance Gains

  Speedup* Relative to 2.8 GHz Xeon Processor   
Application SRC-6 Series E MAP® SRC-7 Series H MAP
Visual/IR image processing  240x >360x
CT scanner image reconstruction 131x  >578x
Optics correction 30x 50x

Finance

 

Overview & Challenges

The popular phrase “time is money,” rings no truer than in the financial world. The speed at which market analysis, risk management and data mining research need to take place are critical to this industry and to individual firms’ competitive advantage. Computationally intensive financial applications such as these have historically run on large grids or clusters requiring high power, cooling and IT support costs.

 

SRC Solutions

SRC’s MAPstation and Scalable Systems & Servers can greatly accelerate transaction applications, data mining and data encryption for financial sector applications. SRC is currently developing solutions for the financial sector based on the powerful cost-effective Series I MAP processor.

 

Performance Gains

  Speedup* Relative to 2.8 GHz Xeon Processor   
Application SRC-6 Series E MAP® SRC-7 Series I MAP SRC-7 Series H MAP
Black-Scholes  32x 46x >92x
Brodie-Glasserman 49x    

 

* Speedup numbers include all overhead and data movement.

 

For more information on any of the above performance gains, please visit the White Papers section of this website.

 

back to top