Rocketick to showcase the power of GPUs for accelerating chip design verification at NVIDIA’s GPU Technology Conference
GPU Technology Conference 2010 (GTC), San Jose, Calif. - Sep. 20, 2010 – Rocketick Technologies LTD., a pioneer in GPU-based simulation acceleration for chip verification, will showcase its technology at the NVIDIA GPU Technology Conference. The conference will take place at the San Jose Convention Center in San Jose, California.
Rocketick CEO Uri Tal will deliver a “CEO on Stage” presentation on Wed., Sept. 22 during the GTC Emerging Companies Summit, an event for developers, entrepreneurs, industry analysts, investors and other professionals.
Rocketick’s development solves a known and pressing challenge in chip design verification. The ever-growing chip density and complexity of chips impacts the time it takes verification simulators to complete each run. When each simulation takes days to complete, either the product’s time-to-market is affected or in some cases teams tape-out early with less confidence.
Rocketick’s technology realizes NVIDIA’s GPU computing vision, by which computing is evolving from "central processing" on the CPU to "co-processing" on the CPU and GPU. Rocketick’s product, RocketSim™, solves chip design verification bottlenecks by solution that offers 10x faster simulations for highly complex designs. It serves as a “co-processor” to the CPU-based simulator, offloading most time-consuming calculations to an ultra-fast GPU-based engine.
“After only two days of ramping up RocketSim with one of our designs, we were able to accelerate our simulations by an order of magnitude,” said Dan Smith, Director of Hardware Engineering at NVIDIA. “No doubt Rocketick has made a significant step into this emerging market by introducing RocketSim.”
“This is exactly the kind of solution that the semiconductor market has been waiting for. I’m confident that in the future we’ll be seeing our GPUs entering all types of EDA applications,” said Jeff Herbst, VP of Business Development at NVIDIA.
CEO Uri Tal said: “Chip simulation can be accelerated by GPUs, but it is far from being trivial. To achieve that, Rocketick has developed unique algorithms that exploit inherent parallelism in complex graphs. NVIDIA’s CUDA parallel computing architecture facilitated this development. ”
Copyright© 2016 NVIDIA Corporation. All rights reserved. All company and/or product names may be trade names, trademarks, and/or registered trademarks of the respective owners with which they are associated. Features, pricing, availability, and specifications are subject to change without notice.
Note to editors: If you are interested in viewing additional information on NVIDIA, please visit the NVIDIA Press Room at http://www.nvidia.com/page/press_room.html