HOME    COMMUNITY    BLOGS & FORUMS    Breaking The Three Laws
Breaking The Three Laws
 
  • About

    Breaking the Three Laws is dedicated to discussing technically challenging ASIC prototyping problems and sharing solutions.
  • About the Author

    Michael (Mick) Posner joined Synopsys in 1994 and is currently Director of Product Marketing for Synopsys' DesignWare USB Solutions. Previously, he was the Director of Product Marketing for Physical (FPGA-based) Prototyping and has held various product marketing, technical marketing manager and application consultant positions at Synopsys. He holds a Bachelor Degree in Electronic and Computer Engineering from the University of Brighton, England.

Archive for the 'In-System Software Validation' Category

Prototyping Low Power Functions Using UPF

Posted by Michael Posner on 19th December 2015

Regardless of the market segment your product targets you are being required to build it with the lowest power operation to either compete, differentiate or just be more green. This week I ran into a customer who unfortunately had to re-spin their chip due to a low power mode of operation issue. The software was able to put the chip into a low power mode but due to a bug, they were unable to get the chip out of the low power mode cleanly without a system reset. This customer wanted to better verify the low power modes before tape-out this time around.

UPF (IEEE 1801-2009 ― Unified Power Format) is the industry standard for design and verification of low power integrated circuits. As noted above, these low power modes are a mix of hardware capabilities under software control and to verify the operation the two must be run together which poses a challenge for the verification and software engineers. Physical, FPGA-based prototyping would seem like the logical solution to this problem as you are running a high performance, cycle accurate model of the design against the real software. But there is a problem, FPGA’s are not ASIC’s .

FPGA’s are volatile

  • No power islands or partial turn off
  • Configuration file loaded from external memory

Multi-voltage cells are not present

  • Only user configurable cells

A single power and single ground

  • VCC, GND for user mapping

Click picture for full size render.

Low power intent view in ASIC

But will you cannot test the exact power domain capabilities of your design there are still many capabilities which can be modeled in the Physical Prototype which will result in higher test coverage of the designs low power capabilities. To make this process easy the Synopsys ProtoCompiler tool can read your UPF and implement a number of lower power capabilities as part of the HAPS physical prototype. This enables the software that controls these lower power modes to be more fully verified pre-silicon.

Some of the key low power capabilities which can be inferred directly from the UPF through the ProtoCompiler for HAPS flow are:-

Verify/validate logical of the islands and control manager

  • Isolation behavior
  • Retention behavior
  • Power Management Unit (PMU) connections and control

Click picture for full size render

Low power modes modeled through ProtoCompiler for HAPS

With this low power logic modeled in HAPS the design’s low power modes can be more extensively tested. The isolation and retention behavior is a mix of hardware functions controlled by software which can now both be tested together. ProtoCompiler’s implementation of the UPF directives modeled in the HAPS systems the designs inferred low power modes enables the hardware and software engineers to expand the low power mode verification resulting in lower rick risk of post-silicon issues.

To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says.

I’m taking a personal break over this holiday period so no blog for a couple of weeks. I would hope that no one is around or bored enough to want to read this blog over the break period anyway so no one will really notice.

I grew a beard for the winter break, (see below) not because I’m hip and trendy but because I like to ski/snowboard/mountain climb during the break and a beard protects your face from the wind. I’ll shave it off in January and then post a comparison picture. I like a beard for the technical reasons listed but I really don’t think it suits me.

Mick grew a beard

Posted in ASIC Verification, Bug Hunting, Early Software Development, HAPS-80, HW/SW Integration, In-System Software Validation, System Validation, UltraScale, Use Modes | Comments Off

Fastest Time to Productivity using DesignWare IP, HAPS with ProtoCompiler & Hybrid Prototyping

Posted by Michael Posner on 12th December 2015

Hybrid IP Prototyping Kit

While traveling this week I found myself explaining the value of Hybrid Prototyping when used with DesignWare IP or your own IP blocks and RTL code. Simply put, using Hybrid Prototyping you can immerse the IP in the context of the SoC without needing to have RTL for the whole SoC. Hybrid Prototyping enables a Pre-RTL SoC representation to be rapidly created (using off the shelf Virtualizer Development kits as a starting point) and incorporating the block(s) under test modeled in HAPS Physical Prototype. This Hybrid Prototype is used for early software development in the case of the DesignWare IP and can be used in the same way for your own blocks in addition to increasing the verification of the design(s) under test.

Rather than writing an lengthy explanation I suggest you watch the Hybrid IP Prototyping Kits video which explains the key benefits of Hybrid Prototyping. Watch how the DesignWare Hybrid IP Prototyping Kits combine the benefits of virtual prototyping (Virtualizer) and FPGA-based prototyping (HAPS with ProtoCompiler) to speed development of DesignWare IP in 64-bit ARM-based designs

To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says.

Can you guess where I was last week from this picture?

What Was Mick Last Week?

This is a picture explaining the perils of business travel

This explains my weight gain

Happy Holidays!

Posted in Debug, DWC IP Prototyping Kits, Early Software Development, Hybrid Prototyping, In-System Software Validation, IP Validation, Man Hours Savings, Use Modes | Comments Off

Customer experiences with ProtoCompiler for HAPS

Posted by Michael Posner on 4th September 2015

Censorship is ............

Last week I posted some anonymous results from ProtoCompiler for HAPS usage on real customer designs. While I had removed the customer names and replace them with names like, consumer electronics company, which in my opinion could have implied hundreds of different HAPS customers across the globe, the greater powers in Synopsys felt the data was still too close to the customer. I should point out that Synopsys treats customer information with the highest confidentiality and I personally did not think any confidential information was being shared. I pulled the data off my blog. Anyway, this is the first and I hope last time that Synopsys has to step in and censor my blog.

So just in case you missed the data the first time around, here it is again, this time just the data points. These two examples are from existing HAPS and Certify users and I define both customers as experienced in FPGA-based prototyping. Results of ProtoCompiler run on their designs.

I can't tell you who this customer was

This first case you can see that ProtoCompiler identified a partition solution in an automated fashion which resulted in a more optimized prototype. In this case shrinking the design from three FPGA’s to two. It’s typically understood that as you consolidate a design into less FPGA’s you can achieve higher performance. The customer will realize the effect of this performance with a reduction in test runtime.

Now the second case below is an example of how ProtoCompiler can be used again to identify more optimum prototype. In this case the solution was not to shrink the design into less FPGA’s but to partition the design at other points in the design spreading it out to four FPGA’s vs. the original three FPGA version. ProtoCompiler was able to utilize HSTDM, high speed pin-multiplexing to improve the overall system performance. A byproduct of the new partition was that compile, synthesis and Xilinx place and route times were halved.

Different customer but I still can't tell you who this is either

To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says

I’ve been dropping “easter eggs” all through my blogs for the last couple of months. If you noticed them drop me a note or comment below on where you found the easter egg. If you don’t know what the term easter egg is then look here: https://en.wikipedia.org/wiki/Easter_egg_(media)

Posted in ASIC Verification, Early Software Development, In-System Software Validation, Man Hours Savings, Performance Optimization, Project management | Comments Off

Prototype ready IP for immediate productivity

Posted by Michael Posner on 7th August 2015

MIPI CSI DWC IP Prototyping Kit as seen at SNUG Israel. Hi, thats me, Mick

Back in 2011 I had a vision, a vision for how users of both IP and FPGA-Based Prototypes could be more productive. The problems these users faced was not to do with bugs or lack of capabilities in the products but from the fact that the usage crossed between the two products. IP users traditionally are not experienced prototypers and prototypers lacked IP specific knowledge. Of course this was not helped by the fact that the IP did not document it’s prototyping specific needs. For example, the IP is optimized for ASIC deployment and when you prototype it the clocking, reset and rams sometimes need to be modified to fit into a FPGA environment. Another issue is that as it’s ASIC IP not all configurations can be physically supported in FPGA. For example while the IP might support up to 16 IO ports on the prototype you might only be physically implement up to 4.

So back in 2011 I presented this slide as part of a larger proposal. (Don’t worry, it’s not confidential at this point)

DesignWare IP on HAPS for the Win presentation back from 2011

Eventually this proposal turned into part of Synopsys’ IP Accelerated initiative, the DesignWare IP Prototyping kits. Well I like to think that this was the source of inspiration which lead to the DesignWare IP Prototyping kits. Others “claim” the idea and I’m happy for them to have the glory as they put far more effort taking a vision to reality that I did. It’s still a nice feeling to know that I identified the original need.

Fast forward and there are eight IP protocols supported with over seventeen different configuration varieties including Hybrid IP Prototyping Kit versions.

While at SNUG in Israel recently, the technical marketing manager and I met in front of the MIPI CSI DesignWare IP Prototyping Kit. The picture at the top of the blog is me in front of the demonstration, below is the TMM in front of it.

Hi from the TMM for DesignWare IP Prototyping kits

The funny thing is that this is not really a demo, it’s the actual execution of the DesignWare IP Prototyping kit. This highlights the huge benefit the kits bring to it’s users.

The DesignWare IP Prototyping Kits include the following:

  • Synopsys’ HAPS-DX FPGA-based prototyping system with pre-configured IP and SoC integration logic
  • PHY daughter board
  • Simulation testbench DesignWare ARC-based software development platform running Linux, or PCI Express connection to PC, or Virtualizer Development Kit
  • Reference drivers Application examples

Finally, below is a picture of my favorite coffee mug. Trust me when I say you don’t want to talk to be before I reach the bottom of the mug. I like to say never talk to Mick B.C, Before Coffee. Others within Synopsys have worked out that this is very true but have reduced the quote to “Never talk to Mick”………………. You folks are soooooo funny……

How fast do you run your prototypes? Make a comment and let me know.

To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says

I love coffee

Posted in DWC IP Prototyping Kits, Early Software Development, HW/SW Integration, In-System Software Validation, IP Validation, Man Hours Savings, Real Time Prototyping | Comments Off

Prototyping a PowerVR Series6XT GPU using an optimized flow from Synopsys

Posted by Michael Posner on 24th July 2015

Block diagram on Imagination PowerVR Series6XT GPU

I ran across this blog on Imaginations website which covers details on prototyping the PowerVR Series6XT on HAPS: http://blog.imgtec.com/powervr/prototyping-a-powervr-series6xt-gpu-using-an-optimized-flow-from-synopsys

I highly recommend reviewing the material as it provides insight into not only how to prototype large GPU’s but also how to quickly scale multi-FPGA prototypes.

Short blog this week as I’m off to do a little camping and when I camp I like to camp in style.

Tepui tent installed on top of my Toyota truck

I love my little retro-style teardrop camper and my tent on top of my truck. Enjoy.

Posted in Early Software Development, HW/SW Integration, In-System Software Validation, IP Validation, Man Hours Savings, Performance Optimization, Project management, Real Time Prototyping, System Validation, Use Modes | Comments Off

Intel’s FPGA-Based Prototyping presentations from SNUG Israel

Posted by Michael Posner on 27th June 2015

Recently at  SNUG in Israel I was lucky enough to attend two presentations created and delivered by Intel teams on their use of FPGA-based prototyping. The first: “Methodology and Best Practices deployed by Intel for FPGA-based prototyping” discussed various technics they employ to streamline the creation of an FPGA-based prototype. It’s like a mini methodology guide so I highly recommend you review the material.

http://www.synopsys.com/community/snug/pages/proceedingLp.aspx?loc=Israel&locy=2015

Intel presentation from SNUG Israel on FPGA-based Prototyping of SoC's

The second paper titles  “Large Scale IP Prototyping” is a great example of multi-FPGA designs using Synopsys’ HAPS/ProtoCompiler solution and specifically the HAPS High Speed Time Domain Multiplexing to pass ~25K signals between FPGA’s. The material presents Intel’s usage and results and again I recommend downloading and reviewing the material.

http://www.synopsys.com/community/snug/pages/proceedingLp.aspx?loc=Israel&locy=2015

Intel presentation on Large IP Prototyping using HAPS and ProtoCompiler

Oh, you need to have a Synopsys SolvNet ID to download….. Oh#2, I just noticed the proceedings are not posted yet. I am reliably informed that they will be posted shortly.

Many of you know that I travel internationally on business on a regular basis and have asked how I cope with the constant time changes. I employ two simply methods to manage jet lag, #1 No alcohol while traveling at all. This helps when you are only getting 3-5 hours of sleep and #2 Coffee

Best jet lag #2 Coffeeeeee

Luckily while in the UK they serve up vats/buckets of coffee that require two handles to hold the weight. This is a six shot “eye opener”

To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says.

Posted in ASIC Verification, Debug, Early Software Development, FPGA-Based Prototyping, FPMM Methods, Getting Started, HW/SW Integration, In-System Software Validation, IP Validation, Man Hours Savings, Milestones, Performance Optimization, Project management, System Validation, Technical, Tips and Traps, Use Modes | Comments Off

Comparison of Prototyping bridge vs. Hybrid Prototypes

Posted by Michael Posner on 1st May 2015

DesignWare Hybrid IP Prototyping Kits

This week Synopsys’ announced the availability of the DesignWare Hybrid IP Prototyping Kits: http://www.synopsys.com/IP/ip-accelerated/Pages/hybrid-ip-prototyping-kits.aspx The Synopsys DesignWare® Hybrid IP Prototyping Kits pre-integrate a Virtualizer™ Development Kit (VDK) and a DesignWare IP Prototyping Kit to accelerate IP prototyping, software development and integration of DesignWare IP in 64-bit ARM®-based designs. Hybrid IP Prototyping Kits enable designers to accelerate hardware/software integration and full system validation, thus reducing the overall product design cycle. The included Linaro® Linux® software stack, reference drivers, and pre-verified DesignWare IP reference design allow users to start implementing and validating IP in an SoC context in minutes.

Now I’ve spoken about Hybrid Prototyping a number of times, the most recent was Valuable Software Driven Validation where I discussed how users are deploying Hybrid Prototyping to accelerate IP validation. The DesignWare Hybrid IP Prototyping Kit of course comes with validated IP, Synopsys does that work, but many IP’s required customized drivers which are application specific. It’s this software development, within the context of a CPU subsystem, which the kit focuses on accelerating.

I was asked a question this week which I think is important to clarify, what is the difference between a prototyping bridge and Hybrid Prototyping. A prototyping bridge is a native PCIe host to prototype physical connection with standard interfaces such as AMBA AXI to connect to the user design under test in the hardware. This is what I have previously called a memory mapped interface. Synopsys provides such a prototyping bridge example, you can find it in SolvNet buried in the HAPS documentation

HAPS Prototyping bridge example on SolvNet

A prototyping bridge like this is good for test cases where you want to stream data to a design under test on the prototyping hardware. You will need to write a customized PCIe driver, which is memory mapped on the host workstation, which you build on top of to create the custom application test code.

HAPS PCIe Prototyping Bridge example

Within the small context of this need the prototyping bridge works well. However its usefulness reduces very quickly due to the following limited capabilities

  • Only provides  1x AXI master and 1x AXI slave interface, what happens if you need more?
  • No support for mixing with other AMBA protocols or sideband signals (interrupt, GPIO, etc.)
  • No control over the AMBA protocol parameters (you get what you get through the PCIe interface)
  • Manually effort to instantiate into design (Might require changes in golden RTL to fix interfaces offered)

I’m not saying there is not a place for this type of prototyping bridge, our own DesignWare USB IP team use such a bridge to enable the standard, off the shelf PCIe based USB host drivers to be tested against the IP. It’s a standalone environment and as the driver is PCIe based it’s not directly reusable when the IP is integrated into a  the end ARM/ARC/MIPS/Tensilica/Other SoC.

Enter Hybrid Prototyping from Synopsys. Hybrid has none of the restrictions as noted above with a prototyping bridge. You can insert multiple transactors into a design, configure them to your direct need in an automated fashion. With Hybrid the software that you are running is the same as the end SoC software, as in in the example of an ARM-based SoC you are executing ARM code.

Hybrid Prototyping design with CPU subsystem and RTL design

The key to Hybrid Prototyping is the transactors. A transactor translate between the Virtual SystemC abstract level across to cycle accurate protocol specific pin level interface. Synopsys delivers off the shelf transactors for the AMBA protocols and more. There are two sides of a transactors, the software side and the RTL hardware side.

HAPS high level view of Hybrid Prototyping transactors

On the software side, the interface which is exposed to the user is the abstracted SystemC level interface, read/write etc. This is what software engineers understand, the transactor looks just like the software that they are used to coding against. All the nitty gritty engineering of the transactors is done by Synopsys so the user can become immediately productive.

HAPS Transactor, Software side

On the hardware side, the interface is RTL, again all the deep protocol stuff is done by Synopsys so the engineers instantiate the transactor into their design just like any other AMBA based design block.

HAPS Transactor Hardware side

The HAPS ProtoCompiler flow automatically understands the transactors and seamlessly connects up the physical interface, UMRBus, with no user intervention.

The Virtualizer environment delivers amazing software debug as well, here is a view of the software debug capabilities which the DesignWare Hybrid IP Prototyping kit delivers.

VPExplorer, amazing software debug

So in a comparison of a prototyping bridge and Hybrid Prototyping, Hybrid wins hands down.

  • Predefined environment, fully supported, configurable, automatic hook-up in user design
  • Runs SoC specific software which can be directly run on the final product
  • Multiple protocols, multiple instances per design
  • Amazing software debug, especially for multi-core

In most cases a Hybrid Prototyping environment can replace the use of a prototyping bridge because it can also be driven via a C/C++ or native TCL interface, just like what you would do with the prototyping bridge. The additional advantage is that the same environment can easily be expanded to a full Hybrid Prototype with Virtual Prototype connection without having to change the design.

Posted in ASIC Verification, Debug, DWC IP Prototyping Kits, Early Software Development, HW/SW Integration, Hybrid Prototyping, In-System Software Validation, IP Validation, Use Modes | Comments Off

SYNOPSYS SETS NEW STANDARDS FOR FPGA-BASED PROTOTYPING WITH COMPLETE PROTOTYPING PLATFORM

Posted by Michael Posner on 23rd April 2015

SYNOPSYS SETS NEW STANDARDS FOR FPGA-BASED PROTOTYPING WITH COMPLETE PROTOTYPING PLATFORM…. Yes, we did this way back in 2010 with the launch of the HAPS-60 complete solution, and then raised the bar in 2012 with the launch of the evolutionary HAPS-70 complete solution. Synopsys HAPS is a proven integrated solution delivering the fastest time to operational prototype, highest system performance, superior debug and advanced capabilities including Hybrid Prototyping and global server farm access.

HAPS Solution

This week I’m feeling feisty so my blog is going to be a little more edgy than normal. The launch of the HAPS-60 series in 2010 delivered the first integrated FPGA-Based prototyping solution with key capabilities such as automated deployment of unique HAPS High Speed Time-Domain Multiplexing (pin-multiplexing) schemes in Synopsys’ Certify. Host connected, globally accessible hardware with the HAPS Universal Multi-Resource Bus, UMRBus, as well as advanced data streaming and platform connectivity. The solution included integrated superior debug visualization for bug hunting. Yes, in 2010, over 5 years ago, Synopsys set the new standard for FPGA-based prototyping with a comprehensive prototyping platform. Since then, our solution has rapidly evolved delivering far greater value.

HAPS-70 hardware, just becuase I like the picture

The HAPS-70 (which, by the way, was selected as Electronic Design http://electronicdesign.com/ “Best of 2012” recipient) with fully integrated HAPS ProtoCompiler, the prototyping implementation environment, accelerated the deployment of prototypes by providing advances in automation including time to first prototyping modes and timing biased partitioning.

HAPS ProtoCompiler, the leading FPGA-based prototyping implementation tool

Synopsys has always been the leader in debug visibility and the HAPS integrated debug capabilities enables at speed debug across multiple-FPGA’s in addition to integration with the leading Synopsys Verdi debug visualization software.

HAPS Debug, superiour debug visualization

The HAPS UMRBus has for multiple generations enabled the hardware to be a globally accessible resource for server farm and multi-user scenarios in addition to enabling data streaming modes and Hybrid Prototyping capabilities.

HAPS UMRBus, global access, farm usage, advanced data streaming modes

At about the same time as the HAPS-70, Synopsys launched the first commercial Hybrid Prototyping solution. HAPS Hybrid Prototyping enables HAPS to be connected with Virtualizer, Virtual Prototype delivering early prototyping capabilities, IP and in context validation scenarios.

HAPS Hybrid Prototyping, accellerating the availability of prototypes

Talking of IP, Synopsys is the leader in interface IP and offers DesignWare IP Prototyping kits for immediate software development and prototyping of key IP titles.

DesignWare IP Prototyping Kits, immediate availability

All this wrapped with the global expert support, eco-system of HAPS Connect partners, professional services. This is how we define a complete solution. What I am trying to illustrate is that Synopsys is now, and will continue to be the technology leader in FPGA-based prototyping. Synopsys continues to invest and the HAPS next generation solution will raise the bar again ensuring that our integrated FPGA-based prototyping products meet your requirements today and way into the future.

Posted in Admin and General, ASIC Verification, Bug Hunting, DWC IP Prototyping Kits, Early Software Development, HW/SW Integration, Hybrid Prototyping, In-System Software Validation, IP Validation, Man Hours Savings, Milestones, Performance Optimization, Real Time Prototyping, Support, System Validation, Use Modes | 1 Comment »

Reduce WNS by up to 60%, sometime more

Posted by Michael Posner on 17th April 2015

Bats with White Nose Syndrome. Please help reduce the spread of this and wash boots, clothes and equipment between caves

The WNS I am talking about is Worst Case Negative Slack and not White Nose Syndrome, a disease in North American bats which, as of 2012, was associated with at least 5.7 million to 6.7 million bat deaths. Please help and stop the spread of this nasty disease. Poor little bats have no defense against it. The WNS I’m going to talk about is Worst Case Negative Slack of a prototyping design, reduce WNS and prototype execution performance increases.

A couple of weeks back I blogged on Timing Biased Partitioning and received a number of follow up questions and comments. This blog is to hopefully answer those and provide more information on the Synopsys capabilities to optimize for the highest system performance on your HAPS-based prototype.

The first question, actually statement was from one of the Synopsys engineers who correctly pointed out that my blog title only covers a fraction of what HAPS ProtoCompiler does in the area of prototype performance optimization. In addition to reducing the number of multi-hop paths during the automated partition stage, ProtoCompiler can also reduce the path length and automatically use a lower pin mux ration on multi-hop paths. The combination of these result in the highest performance prototype. In essence timing biased capabilities cross the partition, system route and system generate stages of the prototyping design flow.

Something that I did not mention in the previous blog was the recommendations for pin mux ratios for optimized performance, so here they are.

  • All paths are not critical
    • Some paths don’t need to be fast
    • False paths and asynchronous clock crossing
    • Slow clocks and debug paths
  • Some paths are just fast, pipeline paths with little logic
  • Don’t use one HAPS HSTDM ratio everywhere
    • Lower ratios on critical paths
    • Higher ratios on non-critical path
    • HAPS ProtoCompiler supports ratios up to 128:1
  • HAPS Hardware Traces are precious
    • High ratios on non-critical paths, frees up traces for critical paths (HAPS flexible interconnect)
  • No cost to mixing ratios with HAPS HSTDM
    • Source sync clock is shared across ratios
    • No overhead of mixing ratios

Much of this is automated in HAPS ProtoCompiler but the 2nd question was why these timing biased capabilities are not default “ON”. The answer is that typically the goal at the start of the project is Time to First Prototype (TTFP), and you sacrifice performance optimization to get a valid solution in the least amount of time. Optimization for performance, while automated, increases the runtime of the tool. The recommendation is that you utilize the HAPS ProtoCompiler TTFP mode to generate a feasible solution and hand this off to your developers. While it might not be performance optimized your developers will thank you as you delivered it very quickly. They can be very productive debugging the initial HW/SW integration, board support software and completing initial OS boot procedures. With your developers busy and happy you have an extra day or so to optimize the platform for performance. Now you turn on timing biased capabilities as you can afford the slightly longer runtime to a feasible solution. This is an iterative process as you play with partition, route and physical interconnect on the HAPS systems.

The results of HAPS ProtoCompiler timing biased capabilities are astonishing and I was able to get my hands on the results of these capabilities from a suite of test designs. This suite of designs consist of real customer designs which we have gather over time (with permission). The goal of this testing was to judge the automated capabilities of the tools.

HAPS & ProtoCompiler test suite of designs for timing bias optimization benchmarks

First the “hop” reduction with multi_hop_path optimization enabled is amazing. It’s hard to see in the picture but all designs yielded multi-hop path reduction with the capability enabled.

HAPS ProtoCompiler multi-hop reduction. Less hops = higher system execution performance

Second, the effect to worse case negative slack showed up to 60% reduction. Reduce WNS and performance is improved !!!!

HAPS ProtoCompiler timing bias optimization WNS reduction yields up to 60% execution performance improvement

The funny thing is that the effect on runtime is not huge so while above we recommend a TTFP flow first and then a timing optimized flow you can be successful in generating a timing optimized solution right out of the starting gate. Well at least a version where you have enabled the capabilities but spend no time analyzing the output. Remember, to get the most out of the HAPS solution you should tailor the HAPS hardware flexible interconnect to the SoC partition needs.

I’ve not had much time for projects recently and the next couple of months are busy, busy, busy with business stuff but I have been making slow progress on my new gaming console in a briefcase. Below you can see pictures of the custom controllers, I had to make them small to ensure they fit inside a briefcase. The second picture is a mock up of the monitor and controllers in the briefcase. You open the case and the monitor pulls up and can be rotated for vertical and horizontal play. The whole system is powered by two 7 ah 12v sealed batteries which based on the current draw should enable 5 hours of play before needing to be charged. There are 912 games installed, all the old school favorites like pacman, donkey kong, street fighter, 1945 etc…

If you like this or other previous posts, send this URL to your friends and tell them to Subscribe to this Blog.To SUBSCRIBE use the Subscribe link in the left hand navigation bar.

Another option to subscribe is as follows:

• Go into Outlook

• Right click on “RSS Feeds”

• Click on “Add a new RSS Feed”

• Paste in the following “http://feeds.feedburner.com/synopsysoc/breaking”

• Click on “Accept” or “Yes” or whatever the dialogue box says.

Mick Built Toys, new gaming console in a briefcase controllers

Mick Built Toys, prototype of monitor and controllers in a briefcase

Posted in ASIC Verification, Early Software Development, HW/SW Integration, In-System Software Validation, Man Hours Savings, Mick's Projects, Milestones, Performance Optimization, Project management, System Validation, Use Modes | Comments Off

Prototyping Over 700 Million ASIC Gates Using Xilinx Virtex-7 2000T FPGAs

Posted by Michael Posner on 10th April 2015

HAPS Super Chain Testing at Synopsys HAPS Lab, 64 FPGA's operating together

You read the title correctly, this blog discusses prototyping over 700 Million ASIC gates using the Xilinx Virtex-7 2000T FPGA’s. To get to this capacity you need to utilize sixty four (64) FPGA’s. The picture above was taken in the Synopsys HAPS lab and shows part of our Super Chain testing. As noted previously, HAPS documented seamless deployable capacity is 288 Million ASIC gates, which is six HAPS-70 (four) FPGA systems chained together, a total of twenty four (24) FPGA’s. However we have customers where this is not enough. The HAPS solution is modular and scalable with base building blocks of x1, x2 and x4 FPGA systems and supported with a HAPS-Aware design tool flow.

The HAPS capabilities and software infrastructure enables the solution to scale with ease but Synopsys does not claim support for capabilities until they have been tested and validated. Once the HAPS systems are configured in the Super Chain they act as one unified massive prototyping system. Thanks to our synchronized clocking capabilities the prototyped design still utilizes the HAPS High Speed Time-Domain Pin Multiplexing, HSTDM, which enables the highest system performance. The above picture super chain models sixty four FPGA’s operating synchronously with HSTDM between all FPGA’s ensuring the highest system performance. That’s over 700 Million ASIC gates (12 million ASIC gates per FPGA)…

While HAPS can scale to these huge systems that does not mean that users of just x1, x2, x4 or x8 FPGA’s do not benefit from this testing. Testing of such large systems ensures that the communication, clock synchronization, HSTDM and other capabilities are bullet proof which benefits the smaller system usage ensuring maximum reliability and uptime when used in server farms or on the user’s desk.

Off subject, while visiting Mountain View CA I noticed that one of our creative R&D engineers had come in over the weekend and decorated their Cube space for Easter

Easter Cube decoration

Absolutely amazing don’t you think! Anyway I introduced myself to the R&D engineer and congratulated them. Apparently they do this once in a while and shared a couple of pictures of their previous cube creations.

Cube decoration Cube2 Cube3 Cube4

Crazy cool right!!! I also think that this R&D engineer might have just a little too much time on their hands. Or maybe they are just like me and maximizes every second or every day. I personally think there is a business here, cubicle decoration in a box…. Would you buy a box of decorations to jazz up your cube?

Posted in ASIC Verification, Debug, Early Software Development, Humor, HW/SW Integration, In-System Software Validation, Man Hours Savings, Project management, Support | Comments Off