feature article
Subscribe Now

Persistent Precision

Mentor Synthesis Makes Steady, Stealthy Progress

Probably the most under-lauded product in the FPGA landscape is Mentor Graphics’s Precision synthesis.  Precision has been around in various incarnations for the better part of a decade now, quietly turning HDL into FPGA-bound netlists around the world with little fanfare or controversy.  

You’ll just about never see Precision in public – it prefers to keep a low profile.  It mainly hangs out on large distributed networks in the worlds’ largest electronics companies, helping to turn their experiments, prototypes, and products into FPGA reality.  Precision’s loyal fans tend to keep to themselves – helping the shy, shade-wearing synthesis tool maintain its modest mode of operation and its traditional aura of mystery and intrigue.

Precision has an interesting history. If you go deep into the chronicles of FPGA synthesis technology, you’ll find its grandfather — Leonardo — which was a product of then start-up Exemplar Logic. Leonardo was the primary contender for the 1990s third-party FPGA synthesis championship, along with Synplicity’s Synplify.  Synplicity went public, and Exemplar was acquired by Mentor Graphics, taking the contest from the domain of startup-versus-startup to the arena of newly-minted-public-company versus confused-acquisition-of-large-diverse-EDA-company.  Newly-minted-public-company won.  Synplicity gained a massive market share advantage while Exemplar/Mentor tried in vain to figure out just what to do with the technology.

Eventually, however, Mentor got it sorted out, and Leonardo evolved into “Leonardo Spectrum” and then finally to “Precision”.  Counter to appearances, Precision never really went head-to-head with Synplify.  Synplicity marketed Synplify aggressively to the broad base of FPGA designers – ranging from “Fred-in-the-shed” low-budget startup companies and consultants through mid-sized systems houses.  Mentor, on the other hand, kept Precision on a tight leash – aiming instead at the “big 25” largest electronics companies that provide the lion’s share of the “big-3” EDA companies’ revenue.  Synplify was sold in the trenches to engineers who were trying to eek out the last few nanoseconds from the critical path so their FPGA-based PCI block would run at 33 MHz instead of 32.999.  Precision was sold on the golf course to CAD-group executives of mega-companies as part of complex, multi-million-dollar multi-year deals involving a wide spectrum of EDA tools – with Precision included in the mix much like the benzoic acid in soda pop.  You don’t make the purchase because it’s there — you may not even realize you have it, but it’s good that it was included by the supplier.  

Apparently, some of the engineers at some of those mega-companies started using the product eventually, and kinda’ liked it.  They must have started calling up Mentor’s support line, making suggestions and providing feedback, and first thing you know – Mentor had a real tool on its hands.  Over the ensuing several years, Mentor has slowly evolved and improved the tool – increasing the range of FPGA coverage, improving the quality of results, and improving the stability in the way that only years of real-world, real-project use can. 

Recently, Mentor has made some interesting improvements to the world’s quietest design tool – giving it some unique differentiators not found in any other product.  Following (apparently) the guidance of some of their military, aerospace, and medical customers, the company has added some impressive features for radiation-tolerant and high-reliability design.  

As many of you know first-hand, radiation is not particularly a good friend to logic design.  Those annoying neutrons flying around in space can slam into just the right part of your circuit – changing a randomly selected zero into a one, or vice versa.  If that memory element was part of a state register – your state machine just ended up in another state.  If it was part of your configuration logic, your circuit may now be connected in a different way than you intended.  As with any random phenomenon – the possibilities are almost endless.

There is only so much the FPGA companies can do to mitigate the effects of radiation on FPGAs.  They can scrub the configuration periodically and take other process precautions to reduce the likelihood of a single-event-upset (SEU) or single-event-transient (SET).  There are, however, a number of things you can do in your logic design to help, but doing so is a tricky proposition with most synthesis tools.  You can triplicate all your registers and add voting circuitry to create triple-module-redundancy (TMR), you can encode your state machines in a “safe” way so that a single-state bit flip won’t land you in too much trouble… you get the idea.  You can create lots of extra safety with lots of extra design work.

Precision can now automate most of that extra design work for you – automatically synthesizing the structures you need for solid, radiation-tolerant design.  The new product, called “Precision Rad-Tolerant” adds significant capability to the stock synthesis tool for high-rel design.  Mentor says the product was developed “in conjunction with NASA” – which is an over-worked marketing claim, considering it puts your product in with the likes of Tang, upside-down-writing pens, and memory-foam mattresses.  What Mentor SHOULD have explained is that the product was developed with advice from the likes of Melanie Berg of MEI Technologies, NASA/GSFC Radiation Effects and Analysis Group – one of the world’s leading black-belt samurai experts on mitigating radiation effects in logic design.  

With Precision Rad-Tolerant, you can dial-in your own level and type of mitigation – including TMR and safe state-machine synthesis as well as other proven strategies like replicating critical sequential and combinational logic paths.  Mentor’s tool is multi-vendor and multi-technology, supporting devices from Actel and XIlinx – the only two FPGA vendors to aggressively market to the mil-aero community.  

In addition to reliability-specific features like radiation mitigation, Mentor has recently added other capabilities to Precision — like low-power synthesis — that are very important to the space-bound electronics crowd.  With the ability to put lower-power, more radiation-tolerant FPGAs in orbit or at altitude, Precision now fills a high-value niche in the FPGA design space.

Mil/Aero designs aren’t the only ones that can benefit from radiation mitigation strategies, however.  Random effects like SEUs can occur (albeit much less frequently) at ground level as well.  Companies developing high-reliability FPGA-based systems with substantial uptime requirements frequently run into SEUs as limiting factors in time-between-failures of large systems like network switches, or in safety-critical systems like some medical devices.  Precision Rad-Tolerant may find some happy customers in those markets as well.

Of course, as we mentioned, Precision is pretty shy, so you may have a hard time getting Mentor to tell you about it.  Be persistent, though – the results could be worth your effort.

Leave a Reply

featured blogs
Nov 25, 2020
It constantly amazes me how there are always multiple ways of doing things. The problem is that sometimes it'€™s hard to decide which option is best....
Nov 25, 2020
[From the last episode: We looked at what it takes to generate data that can be used to train machine-learning .] We take a break from learning how IoT technology works for one of our occasional posts on how IoT technology is used. In this case, we look at trucking fleet mana...
Nov 25, 2020
It might seem simple, but database units and accuracy directly relate to the artwork generated, and it is possible to misunderstand the artwork format as it relates to the board setup. Thirty years... [[ Click on the title to access the full blog on the Cadence Community sit...
Nov 23, 2020
Readers of the Samtec blog know we are always talking about next-gen speed. Current channels rates are running at 56 Gbps PAM4. However, system designers are starting to look at 112 Gbps PAM4 data rates. Intuition would say that bleeding edge data rates like 112 Gbps PAM4 onl...

featured video

Improve SoC-Level Verification Efficiency by Up to 10X

Sponsored by Cadence Design Systems

Chip-level testbench creation, multi-IP and CPU traffic generation, performance bottleneck identification, and data and cache-coherency verification all lack automation. The effort required to complete these tasks is error prone and time consuming. Discover how the Cadence® System VIP tool suite works seamlessly with its simulation, emulation, and prototyping engines to automate chip-level verification and improve efficiency by ten times over existing manual processes.

Click here for more information about System VIP

featured paper

Top 9 design questions about digital isolators

Sponsored by Texas Instruments

Looking for more information about digital isolators? We’re here to help. Based on TI E2E™ support forum feedback, we compiled a list of the most frequently asked questions about digital isolator design challenges. This article covers questions such as, “What is the logic state of a digital isolator with no input signal?”, and “Can you leave unused channel pins on a digital isolator floating?”

Click here to download the whitepaper

Featured Chalk Talk

Mom, I Have a Digital Twin? Now You Tell Me?

Sponsored by Cadence Design Systems

Today, one engineer’s “system” is another engineer’s “component.” The complexity of system-level design has skyrocketed with the new wave of intelligent systems. In this world, optimizing electronic system designs requires digital twins, shifting left, virtual platforms, and emulation to sort everything out. In this episode of Chalk Talk, Amelia Dalton chats with Frank Schirrmeister of Cadence Design Systems about system-level optimization.

Click here for more information