eFPGA LUTs Will Outship FPGA LUTs Later This Decade
By Geoff Tate, CEO of Flex Logix
EETimes (February 28, 2022)
FPGAs have become a strategic technology. It used to be a “poor man’s ASIC” and provided a customized IC for lower-volume applications. While it is still used this way in many systems, it has also become strategically important to two very big, high-growth applications:
- Cloud data centers: networking, storage and security
- Communications systems: base stations and 5G, etc.
In fact, FPGAs are so strategic for the data center that it caused Intel to buy Altera and more recently AMD to buy Xilinx. This is because processor workloads in many cases are shifting to FPGAs.
Data centers use FPGAs in volume to provide the parallel programmability a processor cannot achieve (one customer calls it “programmability at the speed of hardware”). These FPGAs are paired with dedicated function ICs such as NICs (network interface chips) and network switch chips. Each data center has different workloads and needs so a standard product for all doesn’t work, and each data center has the volumes and capital to optimize for their needs.
Communications systems have long used FPGAs to handle hundreds of national frequency bands and protocols. Now with 5G, FPGAs are used to manage the complexity and evolving standards such as O-RAN.
While FPGA programmability is very valuable as described above, the power and size of FPGAs is another story. As a result, today data center and communication companies want to integrate their FPGAs into SoCs to reduce size and power.
To read the full article, click here
Related Semiconductor IP
- eFPGA IP — Flexible Reconfigurable Logic Acceleration Core
- Heterogeneous eFPGA architecture with LUTs, DSPs, and BRAMs on GlobalFoundries GF12LP
- eFPGA on GlobalFoundries GF12LP
- eFPGA Hard IP Generator
- Radiation-Hardened eFPGA
Related Articles
- The end of the smartphone era: What will be the technology battlegrounds of the next decade?
- An 800 Mpixels/s, ~260 LUTs Implementation of the QOI Lossless Image Compression Algorithm and its Improvement through Hilbert Scanning
- What This Year May Well Bring for the eFPGA
- LUTstructions: Self-loading FPGA-based Reconfigurable Instructions
Latest Articles
- Closer in the Gap: Towards Portable Performance on RISC-V Vector Processors
- TTP: A Hardware-Efficient Design for Precise Prefetching in Ray Tracing
- Heterogeneous SoC Integrating an Open-Source Recurrent SNN Accelerator for Neuromorphic Edge Computing on FPGA
- A Reconfigurable Multiplier Architecture for Error-Resilient Applications in RISC-V Core
- ObfAx: Obfuscation and IP Piracy Detection in Approximate Circuits