TotalView Technologies, a provider of interactive analysis and debugging tools for serial and parallel codes, announced its port of the TotalView debugger to the CUDA architecture — the parallel computing foundation of NVIDIA graphics processing units (GPUs). TotalView Technologies and NVIDIA have established a technical and marketing alliance which is promoting the broad adoption of the TotalView debugger. Early Access Release of the TotalView debugger for NVIDIA GPUs will be available Q1, 2010. TotalView Technologies also announced that it has launched the GPU Computing track of the Early Experience Program. This program gives participants an early view of new products and an opportunity to provide input into their development. The GPU Computing track will focus on the CUDA C language and runtime and the OpenCL API, and possible techniques and interfaces for a port of TotalView to NVIDIA GPUs. Several dozen customers are currently enrolled in this program.
"TotalView has a long tradition of helping scientists, engineers, and developers write and debug cutting-edge code. Our customers are constantly looking for their applications to deliver more functionality, performance, and scalability. Many of them see GPU Computing on NVIDIA as a very attractive way to achieve their goals. We are proud to announce our collaboration with NVIDIA in a forthcoming version of TotalView specifically for CUDA developers," said Rich Collier, CEO and President at TotalView Technologies.
NVIDIA is a global corporation that invented the GPU and their product lines include GeForce for gaming, Quadro for computer-aided design and digital content creation and the Tesla product line, designed specifically for the high performance and enterprise computing market.
"It is critical that high quality development tools are available to help developers easily port existing applications to the CUDA architecture or develop new applications that can take advantage of the power of Tesla products. We are pleased to be working closely with TotalView Technologies to make their TotalView solution available for developers," said Sanford Russell, general manager, GPU Computing software at NVIDIA.
TotalView is a comprehensive source code analysis and memory error detection tool that dramatically enhances developer productivity by simplifying the process of debugging parallel, data-intensive, multi-process, multi-threaded or network-distributed applications. Built to handle the complexities of the world’s most demanding applications, TotalView offers a number of advanced features that help speed development and eliminate bugs quickly, and is capable of scaling from one to thousands of processes or threads with applications distributed over multiple machines or processors. TotalView has proven successful at helping users make sense of heterogeneous and distributed systems with asynchronously interacting components.