The main technology transition target for the Avalanche effort is commercial. Hewlett Packard is already a technology partner and is taking a keen interest in the effort. The injection point for HP is HP Laboratories and a group has been set up to monitor progress of the Avalanche effort and move it into the appropriate segment of the company. Close collaboration with Myricom is also underway and the PPE design should allow Myricom to improve on the latency component of their LaNai design in a significant manner. The PPE has higher performance but is less flexible than the LaNai so it is not expected that it will replace the LaNai but more likely will lead to increased interface options for Myricom. Since Myrinet is a technology choice for many ARPA sponsored projects the impact of this strategy is broader than direct connection with Myrinet users. Hopefully the use of Avalanche technology by HP will have an equally broad and significant impact on network of workstation projects as well.
This work was sponsored by the
Space and Naval Warfare Systems Command (SPAWAR) and
Advanced Research Projects Agency (ARPA),
Communication and Memory Architectures for
Scalable Parallel Computing,
ARPA order #B990 under SPAWAR contract #N00039-95-C-0018
Back to the
Avalanche Project Home Page,
or Computer Science Department Home Page.
Feedback to <avalanche@jensen.cs.utah.edu>.