NVIDIA® Tesla™ GPU Computing Solutions

Trenton brings over thirty years of design, manufacturing and system engineering experience to the world of High-Performance GPU Computing. Our in-depth knowledge of high-speed bus technology, system BIOS, power requirements and shock, vibration and thermal characteristics is incorporated into every integrated computer system, single board computer, backplane and embedded motherboard. As a member of the NVIDIA Tesla Preferred Partner (TPP) program Trenton is now creating computing solutions supporting NVIDIA's Tesla GPU 20-series computing products and CUDA™ GPU architecture.

Advantages of working with Trenton to build a Tesla GPU-based computing solution!

	Trenton designs and manufactures a range of PCI Express Gen2 backplanes that are ideal for high-performance GPU computing applications		Trenton single board computers, backplanes and embedded motherboards are designed and manufactured in the United States
	Trenton designs rugged computing solutions to satisfy the most demanding application-specific system requirements		Trenton single board computers, backplanes and embedded motherboards carry a 5-year factory warranty
	Trenton maintains complete BIOS control and provides modifications in support of complex integrated systems		Trenton board-level products are designed with long-life components to provide our customers with 7+ year product availability

Integrated systems designed for high-peformance NVIDIA 20-series GPU processors:


TCS4501 Rackmount Computer	Tesla 20-Series GPU Processor

Trenton's integrated computer systems, single board computers, PCI Express backplanes and embedded motherboards are engineered to work alongside NVIDIA's Tesla GPU Computing Processors, creating supercomputing platforms targeted at mission critical applications within industries such as government & defense, industrial automation, video processing and medical research. Call on Trenton's in-house design, manufacturing and integration expertise to build a customer-driven solution tailored to your specifications, from backplane configuration to BIOS or system features.

For more information about NVIDIA's approach to GPU Computing, download the NVIDIA Tesla GPU Computing Brochure.

"Trenton's design, engineering and integration capabilities are ideal for customers who require a high-performance computing solution based on industry-specific system requirements," said Shanker Trivedi, vice president of sales, NVIDIA Professional Solutions Group. "These industry solutions are ideal platforms for implementing NVIDIA's Tesla computing processors and CUDA GPU architecture."

The next generation CUDA architecture, code named "Fermi", is the most advanced GPU computing architecture ever built. With over three billion transistors and featuring up to 512 CUDA cores, Fermi delivers supercomputing features and performance at 1/10th the cost and 1/20th the power of traditional CPU-only servers.