The Defense Advanced Research Projects Agency, also known as DARPA, just signed an agreement to work with Flex Logix, a semiconductor start-up, to develop the young company’s EFLX embedded FPGA technology for use by any company or government agency designing integrated circuits for the U.S. government.
FPGAs have been widely used in systems since the 1980s and, at the system level, provide flexibility and programmability different from what processors can do. Many years ago, ARM took the idea of a processor chip and offered a processor architecture, which could be embedded in chips. Although it took time, embedded processors are now nearly ubiquitous. Flex Logix is doing the same for embedded FPGAs.
As part of the agreement, Flex Logix will make available EFLX arrays in the TSMC 16FFC process node from 2.5K to 122.5K LUTs so that companies and agencies can reconfigure RTL at any point during the design process. This flexibility enables chip designers to increase performance, reduce power, and lower the size and weight of their critical systems. The EFLX platform will also allow companies to customize one chip in software for numerous applications or even upgrade the chip when already deployed in the field.
“DARPA’s agreement with Flex Logix enables any company or organization to easily use embedded FPGA in TSMC 16FFC for any IC that is used by the U.S. government,” said CEO of Flex Logix, Geoff Tate. “Making the agreement public is the easiest way for DARPA to communicate this to all of the suppliers to the U.S. government. DARPA believes that embedded FPGA will become a widely used building block in government ICs.”
The technology that Flex Logix is developing under its agreement with DARPA isn’t just available for government chips, but for any commercial company.
“We are working with other companies and organizations doing commercial applications who do not want to be publicly known until they go into production,” said Tate. “They don’t want their competitors to realize what they are doing; they want a competitive advantage.”
According to Tate, the EFLX embedded FPGA is an architecture that benefits chips across a wide range of applications and process nodes. Some examples include:
- Extending battery life in IoT applications by offloading receptive monitoring algorithms from the processor and by doing these algorithms using less energy.
- Enabling chips to be customized for customers by programming an EFLX embedded FPGA rather than doing multiple, increasingly expensive mask set variations. An example is Serial I/O interfaces in which a microcontroller must have dozens of versions because different customers want different standards in different numbers.
- 1-GHz+ programmable protocol logic for chips that are coming into demand from data centers to have programmable, not hardwired, protocols.
- High-speed large arrays (500 MHz+) for wireless base stations.
Companies Flex Logix is working with are in the following sectors:
- Networking & data centers.
- Wireless base stations.
- Microcontrollers.
- IoT.
- Defense electronics.
- A range of various SoC and ASIC chips for other applications.
Long considered the holy grail of chip design, embedded FPGAs are now available to provide chip designers the flexibility to quickly, easily, and cost-effectively update or change RTL after fabrication, even in-system.
“As every chip designer knows, having to change the RTL blocks at any point in the design process could easily cost multiple millions of dollars and add three to six months to the design schedule,” said Tate. “With embedded FPGAs, this risk can now be eliminated, providing designers with a higher level of confidence when undertaking a new SoC/MCU project.”
Learn more about Electronic Products Magazine