Advertisement
News
EEtimes
News the global electronics community can trust
eetimes.com
power electronics news
The trusted news source for power-conscious design engineers
powerelectronicsnews.com
EPSNews
News for Electronics Purchasing and the Supply Chain
epsnews.com
elektroda
The can't-miss forum engineers and hobbyists
elektroda.pl
eetimes eu
News, technologies, and trends in the electronics industry
eetimes.eu
Products
Electronics Products
Product news that empowers design decisions
electronicproducts.com
Datasheets.com
Design engineer' search engine for electronic components
datasheets.com
eem
The electronic components resource for engineers and purchasers
eem.com
Design
embedded.com
The design site for hardware software, and firmware engineers
embedded.com
Elector Schematics
Where makers and hobbyists share projects
electroschematics.com
edn Network
The design site for electronics engineers and engineering managers
edn.com
electronic tutorials
The learning center for future and novice engineers
electronics-tutorials.ws
TechOnline
The educational resource for the global engineering community
techonline.com
Tools
eeweb.com
Where electronics engineers discover the latest toolsThe design site for hardware software, and firmware engineers
eeweb.com
Part Sim
Circuit simulation made easy
partsim.com
schematics.com
Brings you all the tools to tackle projects big and small - combining real-world components with online collaboration
schematics.com
PCB Web
Hardware design made easy
pcbweb.com
schematics.io
A free online environment where users can create, edit, and share electrical schematics, or convert between popular file formats like Eagle, Altium, and OrCAD.
schematics.io
Product Advisor
Find the IoT board you’ve been searching for using this interactive solution space to help you visualize the product selection process and showcase important trade-off decisions.
transim.com/iot
Transim Engage
Transform your product pages with embeddable schematic, simulation, and 3D content modules while providing interactive user experiences for your customers.
transim.com/Products/Engage
About
AspenCore
A worldwide innovation hub servicing component manufacturers and distributors with unique marketing solutions
aspencore.com
Silicon Expert
SiliconExpert provides engineers with the data and insight they need to remove risk from the supply chain.
siliconexpert.com
Transim
Transim powers many of the tools engineers use every day on manufacturers' websites and can develop solutions for any company.
transim.com

FPGAs in the Storm

By Lauro Rizzatti, consultant  04.30.2021 1

The 35-year-old field programmable gate array (FPGA) is one of the most impressive semiconductor devices ever created, short of the central processing unit (CPU). Today, it is more popular than ever before, reinvigorated by its intrinsic raw processing power and adaptability, a perfect match for accommodating the rapid evolution of the electronic industry. It does not show its age. Oddly, its very versatility is creating a dilemma for FPGA vendors.

Communications and networking stood out among applications that drove the FPGA’s early popularity because of frequent changes in their standards that necessitated field updates/grades, inconceivable with hard-wired ASIC implementations. In later years, a wide range of automotive, military, consumer and defense applications have been using FPGAs. Lately, the FPGA renaissance has been bolstered by progress in Artificial Intelligence (AI) technologies and proliferation of AI applications. Prominent among AI applications is deep-learning acceleration (DLA).

Figure 1: Today’s FPGA is a complex set of hardware blocks, including programmable logic, application and real-time processors and blocks of interface controllers that is more of an adaptive compute acceleration platform. (Source: Xilinx)

The Ages of the FPGA

An article by Stephen M. Trimberger, Ph.D. and Xilinx fellow, titled “The Three Ages of FPGAs: A Retrospective on the First Thirty Years of the FPGA Technology,” traces the evolution of the FPGA from its origin in 1984 to 2015.

Partner Content
View All
By Shingo Kojima, Sr Principal Engineer of Embedded Processing, Renesas Electronics  03.26.2024

Trimberger’s article, published in the March 2015 IEEE Proceedings, names three ages in this succession:

  1. Age of Invention (1984-1991)
  2. Age of Expansion (1992-1999)
  3. Age of Accumulation (2000-2007)

Following the “Age of Accumulation” through 2015, the author submits that FPGA technology entered the age of “No Longer Programmable Logic.” Ironically, the title contradicts the essence of the device as captured in its name, but it reflects the reality of its contents. In fact, calling it the age of “No Longer Programmable Logic” beyond 2015 may be appropriate. Actually, the structures of the latest FPGAs would be better served by renaming it the “Age of Artificial Intelligence.”

Certainly, the new Xilinx adaptive compute acceleration platform (ACAP), first implemented on the Versal family, reinforces the case for renaming it the “AI age.” According to Victor Peng, Xilinx’s president and CEO, the ACAP is an FPGA logic fabric that includes multiple levels of distributed memory, hardware-programmable digital signal processor (DSP) blocks, a multicore system on chip (SoC), one or more compute engines that are software programmable and hardware adaptable. Everything is connected via a low-latency, high-frequency on-chip network with arbitration and flow control. The platform also includes integrated RF-ADCs/DACs, support a High-Bandwidth Memory (HBM) stack, various generations of DDR, and advanced SerDes technology. See figure 1.

The block structures are brains of DLAs.

Show me the money

According to a market analysis by Barclays Research published in 2018, the DLA market can be broken in three buckets: machine learning training in the datacenter, inference in the datacenter, and inference at the edge (see the chart below).

The study predicted that until 2020, about two thirds of semiconductor sales would come from chips accelerating neural networks training, mostly from Nvidia GPUs. Beyond 2020, it projected a moderate growth in semiconductors for training neural networks with an explosive increase for inference in the data center and at the edge, reaching high double-digit growth in 2021 and keeping growing at the same rate. Specifically, Barclays anticipated that in 2021, edge inference would grow slightly faster than data center inference, since data at the edge would need local pre-processing to prevent the latency affecting data transfer to the data center for processing. From 2022 onward, inference would drive around 3.6X times as much semiconductor revenue as training would.

As for the technologies fueling DLA, such as CPUs, GPUs, FPGAs and ASICs, analysis after analysis consistently favor escalating growth in ASICs and GPUs, moderate growth for FPGAs and contraction for CPUs.

Obviously, FPGA vendors have been responding to the projections by stuffing more and more functional blocks to address DLA, trading off silicon area with traditional lookup tables (LUT). In the process, they are becoming more like re-programmable ASICs than FPGAs.

Figure 2: Deep learning acceleration could serve machine learning training in the data center, inference in the data center or inference at the edge. (Source: Barclays Research)

Arguably, the potential for driving DLAs with FPGAs motivated Intel to acquire Altera in 2015, and AMD to make an acquisition offer to Xilinx in 2020. Good news for Achronix, the new lion dominating the FPGA landscape.

FPGAs and hardware-assisted verification platforms

Assuming the trend will continue, it is sensible to ask what the future of hardware-assisted design verification tools based on commercial FPGAs will be.

Known as FPGA prototype platforms, they make extensive use of re-programmable logic provided by embedded LUTs to virtually map any design, regardless of size, architecture and target application. With design sizes reaching 10-billion ASIC-equivalent gates, prototyping vendors are designing cabinets loaded with several boards stuffed with vast arrays of the largest FPGAs in the quest to support massive amounts of LUTs.

This poses a dilemma for FPGA providers. To effectively support FPGA prototype platforms, FPGAs should trade off DSPs, SoCs and other embedded blocks and processors for LUT area. To serve the DLA market, however, FPGAs should trade off generic logic area for specialized silicon area. The two requirements are not reconcilable, leaving the FPGA vendor in quandary.

Should FPGA vendors create two distinct FPGA devices, one for less than one-billion dollars total available market of hardware-assisted verification platforms, and another to fully embrace the DLA venue and serve a several billion-dollar market (and growing)? In fact, they may have an opportunity to charge a premium for programmable devices targeting prototyping platforms.

Final thought

Since 1985, FPGAs evolved over five generations. In its present incarnation, its fabric is a far cry from its original structure. Today, it reflects the evolution of the electronic chip, from a monolithic construct that used to be well served by a sea of LUTs, to a hierarchical, multi-block assembly that calls for a mirror structural image.

Recently, Trimberger shared with me his thinking about the future of FPGAs, and elected to name it the “Age of Computation,” in expectation that software processing will play a fundamental role in them. In his words, “In today’s devices I/O communications infrastructure can consume over 50% of silicon area, in tomorrow’s over 50% could be consumed by software computation units.”

From my perspective, that future may or may not extend to prototyping platforms.

Lauro Rizzatti is a verification consultant and industry expert on hardware emulation. Rizzatti has held positions in management, product marketing, technical marketing and engineering.

1 comments
Post Comment
PA Investor   2021-05-04 14:18:07

Lauro, I enjoyed your column but you didn't mention the role of embedded FPGA's which is being promoted heavily by Achronix. It seems to me there are lots of use cases where a customer would like to build an ASIC for performance and cost reasons but still needs some flexibility to speed time to market and extend the product life. Xilinx and Intel are not offering that currently but it seems like this allows customers to get the right amount of flexibility for their needs without being forced to choose an off the shelf, higher volume part. You can also eliminate the additional cost of hardened IO that wouldn't be needed.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Articles