How to build an ASIC that can adapt to many applications.
By exploiting Achronix Speedcore embedded FPGA (eFPGA) IP — IP proven in multiple ASIC designs for wireless, datacenter and high-performance computing (HPC) applications — designers of SoCs can now add logic programmability to their solution, resulting in a single ASIC that can adapt to many applications. While many system architects may already have strong ideas on how an eFPGA core could add value to their ASIC/SoC design even before having formulated a specific application, it may not be clear how to start an evaluation. Often the question foremost on a potential customer’s mind is “How can I assess Speedcore IP’s ability to solve my problem?”
Achronix refers to this pre-engagement stage as phase zero — an evaluation period where customers formulate application ideas and test them using tools and models. This paper presents a walk-through of phase zero, providing guidelines to customers who want to explore and refine ideas for employing a Speedcore eFPGA in their SoC.
To read more, click here.
30 facilities planned, including 10/7nm processes, but trade war and economic factors could slow progress.
Leaders of three R&D organizations, Imec, Leti and SRC, discuss the latest chip trends in AI, packaging and quantum computing.
Applied Materials’ VP looks at what’s next for semiconductor manufacturing and the impact of variation, new materials and different architectures.
What could make this memory type stand out from the next-gen memory crowd.
Researchers digging into ways around the von Neumann bottleneck.
Semiconductor devices face many hazards before and after manufacturing that can cause them to fail prematurely.
Chips will cost more to design and manufacture even without pushing to the latest node, but that’s not the whole story.
This will go down as a good year for the semiconductor industry, where new markets and innovation were both necessary and rewarded.
Experts at the Table, Part 1: Impact on the supply chain, who’s using advanced packaging, and the cost of packaging versus device scaling.
Companies battle it out to get artificial intelligence to the edge using various chip architectures as their weapons of choice.
Technology adds more granularity, but starting point for design shifts as architectures cope with greater volumes of data.
Bulk CMOS, FD-SOI and finFETs all on tap as big players vie for differentiation. But where will chipmakers go after 28nm?
30 facilities planned, including 10/7nm processes, but trade war and economic factors could slow progress.
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Leave a Reply