Subscribe to EDN

Can FPGAs help speed the ASIC design cycle?

March 17, 2009

Something tells me that Kawasaki Microelectronics America Inc. may be more straightforward than other ASIC vendors in confronting FPGAs’ threats to ASICs. K-Micro has gone public with an effort to use FPGA-based boards in its CatsEye development system to help speed development of complex ASIC designs.

Yes, you heard right. K-Micro is offering boards that combine the Xilinx Virtex-4 with the K-Micro PCI Express physical-layer core. By modeling ASIC designs in FPGAs in early stages, the designer can raise the chance of first-pass success in the final ASIC. Of course, there’s always the chance that the Virtex customer will find the FPGA architecture preferable to the next step of ASIC implementation, but K-Micro is betting that most users of CatsEye will continue to see an advantage in footprint and cost for ASIC conversion.

K-Micro’s CatsEye is not just a massive sea of gates, but a complex core-based ASIC with two MIPS32 24Kf cores and two Gigabit Ethernet MACs. There is no doubt an element of risk and a certain sense of “If you can’t beat them, join them,” in offering an ASIC development environment based on FPGAs. But I have to hand it to K-Micro for not hiding their collective heads in the sand on the role of FPGAs in displacing ASICs.

Posted by Loring Wirbel on March 17, 2009 | Comments (3)

April 16, 2010
In response to: Can FPGAs help speed the ASIC design cycle?
Buy Cialis commented:

cloning legendi deprive collegiate deride relieve bifilar felaalrl checklists shubhi refined


March 20, 2009
In response to: Can FPGAs help speed the ASIC design cycle?
Garry commented:

Adding to andy's comments its far from a simple convertion.


March 17, 2009
In response to: Can FPGAs help speed the ASIC design cycle?
Andy T commented:

In our green-pressured world, the excess power dissipation of FPGAs vs ASICs will likely go the route you've highlighted here, Loring - prototype using massive FPGA-based engines like those from K-Micro, Dini Group, and others, then straight to either a structured ASIC or ASIC-proper for manufacturing. I think the applications where FPGAs will most likely entrench themselves and displace ASICs are plays in 1) reconfigurability 2) fickle, untried, markets or where standards are not set in stone 3) fast time to market 4) power-indifferent applications (which are rare these days) 5) low volume markets where the NRE of an ASIC adds major money to unit cost

POST A COMMENT
Display Name
captcha

Before submitting this form, please type the characters displayed above. Note the letters are case sensitive:

Advertisement
Advertisement
Advertisement
About EDN   |   Site Map   |   Contact Us   |   Subscription   |   RSS
© 2012 UBM Electronics. All rights reserved.
Use of this Web site is subject to its Terms of Use | Privacy Policy

Please visit these other UBM Canon sites

UBM Canon | Design News | Test & Measurement World | Packaging Digest | EDN | Qmed | Pharmalive | Appliance Magazine | Plastics Today | Powder Bulk Solids | Canon Trade Shows