feature article
Subscribe Now

Xilinx Goes Retro

Moving Ahead by Looking Back

All the FPGA action these days is in the new, emerging markets right? As we’ve all discussed for awhile, CPLDs are a nice steady market with slow growth, and networking apps (the ones that built the FPGA industry to where it is today) took a nose-dive a few years back and are out of favor.

According to the world’s largest programmable logic company, this line of reasoning is a bit short-sighted. While Xilinx agrees that there are new and exciting emerging markets out there, they are pointing out, with two announcements this week, that some of the new and exciting opportunities are built right on top of the old, boring ones.

For example, the world is filled with circuit boards that still use old, near obsolete discrete logic components. For the companies that manufacture products that use these boards, there is an enormous opportunity for saving cost, power, and board complexity by consolidating groups of these assorted components into CPLDs. The problem is that the logic designers that created these masterpieces of old are not exactly hanging around waiting for the opportunity to cost-reduce their work from 10 years ago. The people who actually care the most about the problem, the purchasing managers, are generally ill-equipped to make a case for taking action.

Xilinx is here to give that purchasing manager a little mutually-beneficial helping hand. Their Logic Consolidator introduced this week (press release) is a “convenient tool for quickly and accurately estimating the number of discrete logic devices that can be integrated into a single CPLD.” Design engineers beware! The purchasing department just got new super-powers. No longer can you weasel out of looking at that old design because the folks on the third floor just don’t know any better. When they come down and tell you “Hey, George, we’ve just noticed that we can replace 52 devices in our digital hyper-ventilator board with a single XC9500XL CPLD,” you can’t just brush them off with the “nah – incompatible supply voltages” argument again. They’ve got Xilinx on their side, and this time it’s even worse. They hold the dreaded bean-counter’s weapon of choice. The Logic Consolidator works in an Excel spreadsheet.

While designers are running for their professional lives, they might try escaping temporarily to SUPERCOMM in Chicago where they’ll see Xilinx demonstrating 10Gbps performance across an off-the-shelf AdvancedTCA (ATCA) backplane (press release). This proves a point beyond the usual haze of marketing-megahertz and dog-gates. You can really do 10Gbps yourself using a few handy items you probably have around the house (assuming your household includes an ATCA backplane, and one of the new Xilinx ATCA line-card development platforms.)

Here again, Xilinx returns to “dance with the one that brought them” as ATCA has the potential to be a huge market with its pernicious price/performance ratios and widespread applicability. The performance of Xilinx’s ATCA implementation will make high-end telecom designers reconsider proprietary backplane design, as the design time and complexity using the standard will likely be dramatically less for comparable performance.

According to Xilinx’s announcement the ATCA market has the potential to grow to over $20 billion by the end of 2007. Xilinx is well poised to take advantage of that growth. With their Virtex II Pro X devices (now you know what those embedded PowerPCs are for) and their recently introduced line card development boards, they have a huge lead in offering fast time-to-market for ATCA designers with minimal risk and overhead. Once those designs speed their way to market and go into production, they’ll be eating up large quantities of Xilinx FPGAs, and everyone will be smiling. Everyone, perhaps, except those among us that mistakenly thought that the FPGA telecom market was passé…

Leave a Reply

featured blogs
Feb 28, 2021
Using Cadence ® Specman ® Elite macros lets you extend the e language '”€ i.e. invent your own syntax. Today, every verification environment contains multiple macros. Some are simple '€œsyntax... [[ Click on the title to access the full blog on the Cadence Comm...
Feb 27, 2021
New Edge Rate High Speed Connector Set Is Micro, Rugged Years ago, while hiking the Colorado River Trail in Rocky Mountain National Park with my two sons, the older one found a really nice Swiss Army Knife. By “really nice” I mean it was one of those big knives wi...
Feb 26, 2021
OMG! Three 32-bit processor cores each running at 300 MHz, each with its own floating-point unit (FPU), and each with more memory than you than throw a stick at!...
Feb 25, 2021
Learn how ASIL-certified EDA tools help automotive designers create safe, secure, and reliable Advanced Driver Assistance Systems (ADAS) for smart vehicles. The post Upping the Safety Game Plan for Automotive SoCs appeared first on From Silicon To Software....

featured video

Silicon-Proven Automotive-Grade DesignWare IP

Sponsored by Synopsys

Get the latest on Synopsys' automotive IP portfolio supporting ISO 26262 functional safety, reliability, and quality management standards, with an available architecture for SoC development and safety management.

Click here for more information

featured paper

Making it easier to design with mmWave radar sensors using the TI third-party ecosystem

Sponsored by Texas Instruments

If you are new to radar or interested in replacing your existing sensing technology with radar, there can be a significant learning curve to both designing your product and ramping to production. In order to lower this barrier, Texas Instruments created a third-party ecosystem of radar experts who can provide solutions no matter how much help you need.

Click here to download the whitepaper

Featured Chalk Talk

TensorFlow to RTL with High-Level Synthesis

Sponsored by Cadence Design Systems

Bridging the gap from the AI and data science world to the RTL and hardware design world can be challenging. High-level synthesis (HLS) can provide a mechanism to get from AI frameworks like TensorFlow into synthesizable RTL, enabling the development of high-performance inference architectures. In this episode of Chalk Talk, Amelia Dalton chats with Dave Apte of Cadence Design Systems about doing AI design with HLS.

More information