Market Leaders Collaborate with Synopsys to Realize Gains of Generative...
MCUs come in a broad range of flavors, meaning you can pick the best one for the application with the right performance, feature set, peripherals, memory, and software programmability. So, then, why do many systems also use FPGAs next to the MCUs? Usually, it’s because there’s not a “perfect” MCU for their application. MCUs by definition are built to be generic for a wide variety of applications, or in the case of applications specific standard parts (ASSPs), targeting particular market segments. Customization is done with software. FPGAs come into play where embedded CPUs can’t execute the required workload efficiently and some level of hard logic is needed to process proprietary algorithms, support unique interface requirements or enable future system upgradability.
FPGA companies have integrated processors, but these solutions are much more expensive than an MCU – what is needed is an MCU with a modest amount of FPGA at a low price. There are a few MCUs on the market that have a small amount of reconfigurable logic (LUTs) to give product designers some level of MCU personalization for their particular application. However, available LUT capacities are very limited because the intent was to support very basic functions that use 10’s of LUTs. While their products provide useful, but limited changes , it leaves the product designer who needs more capability no choice but to use a separate FPGA chip.
That no longer needs to be the case. Over the last few years, third party, silicon proven FPGA IP has become available from a number of suppliers on various process nodes that can dramatically increase the personalization and customization of MCUs for applications such as motor control, proprietary communication channels, encryption, or AI at the very edge using binary neural networks. For MCU companies, adding a small amount of eFPGA does increase the die area, but also increases their serviceable market with fewer SKUs and provide their customers system savings even though the MCU price might be slightly higher.
If you are one of the system designers who have heavily invested in software development around a favorite MCU family but want a more integrated solution to lower system cost, lower power, improved performance and have the ability to have a semi-custom chip at MCU volume prices, ask for eFPGA with your favorite MCU.
System companies are taking a more proactive role in codesigning their hardware and software roadmaps, so it’s no surprise that…
Expanding the possibilities in the processor subsystem.
2-1/2 Months from IP delivery on a FinFET Process
Join our community of thousands of semiconductor professionals. Keep up to date with all latest news and activities. Don’t miss out!