The question most teams ask is simple:
“At what volume does ASIC become cheaper than FPGA?”
The problem is that the question is usually asked too late, and answered too simplistically. There is no single magic number where ASIC suddenly becomes the obvious choice. The real break-even point
Most ASIC schedules fail quietly.
Not because of one catastrophic mistake, but because they were planned as if silicon behaved like software: linear progress, easy reversals, and unlimited iteration. In reality, ASIC development is constrained by physics, manufacturing, and verification effort. Late changes are expensive, and uncertainty compounds quickly.
Read More
For many teams, the term “ASIC NRE” is enough to stop the conversation.
It sounds like a single, large, opaque number that appears late in the process and instantly kills the business case. In reality, NRE is not one thing, and it is rarely as arbitrary as it feels.
Read More
Most teams don’t decide to move from FPGA to ASIC.
They get pushed there.
At the beginning of a product’s life, FPGA feels like freedom: fast iteration, low upfront cost, and a clear path to demos and early customers. But once a product starts shipping, the rules change.
As PCIe 5.0 and 6.0 dominate headlines in the semiconductor industry, it’s tempting for every SoC design team to reach for the newest protocol available. But not every application needs blazing-fast 32GT/s throughput—and not every market segment can afford the power, complexity, and cost penalties that come with bleeding-edge PHYs.
Read More
As factories, process plants, and robotics platforms become increasingly intelligent and interconnected, the demand for stable, low-latency data links has pushed Ethernet deeper into embedded systems. However, since designing Ethernet connectivity into industrial chips comes with its technical and logistical hurdles, engineers may face challenges when implementing Ethernet in industrial
Read More