• About Jakob Engblom and this blog
Observations from Uppsala Computer Simulation, Virtual Platforms, Embedded Programming, Multicore and More (by Jakob Engblom)

Wind River Blog: Inside the Simics QSP – Additional Notes

2012 July 6 20:11 / Leave a Comment / Jakob

There is a new post at my Wind River blog, about the design and technical contents of the new Simics Quick Start Platforms, more widely known as the QSP. The blog describes the virtual-only hardware that forms part of the QSP, and how it was designed. It is interesting to note that the hardware ended up a bit more complex that I initially thought it would be, since an ideal virtual platform should be very simple. Right? Turns out an OS complicates things.

Basically, today’s operating systems contain many structures and design patterns for device drivers that have evolved together with hardware over the years. Thus, the least overall effort when taking virtual hardware design and driver development into account is typically not to make a totally green field design, but rather to look at what exists and simplify it. The Wind River blog post contains several examples, such as having transmit delays in serial ports and Ethernet MACs, along with the requisite transmit interrupts. This works much more easily with the given structure of Ethernet and serial drivers in general in OSes like VxWorks and Linux.

There are many other concepts around that are more or less similar to the QSP idea.

Several “Android simulators” out there start with some standard platform and add virtual-only devices that are just like QSP devices. However, these systems leave the interrupt controller and other common parts as they are from some real system, they are not synthetic all the way through. The end goal is pretty similar though, being the development of application code on a virtual platform without having to create a perfect model of a particular real phone.

Carbon Design Systems recently announced something they called the CPAK, Carbon Performance Analysis Kit, which is basically a core subsystem of an ARM-based SoC that is capable of running Linux. With this, Carbon customers can immediately start to do performance analysis of applications on Linux on various ARM processors, without first building a model of their own ASIC. It is not very clear what is included in a CPAK, but it seems mostly be a processor core, caches, and memory. I assume there are also interrupt controllers and timers, serial ports, and maybe other IO.

It is interesting to compare and contrast the Simics QSP and the Carbon CPAK. Where the goal of a QSP is to be purely virtual and not model any real hardware, the goal of the CPAK is to be very true to the real hardware. The use of compiled RTL models of processor cores, cache controllers, and bus systems is a key part of the value, as this provides a true view of the performance as it will be in a real hardware system. This means that while a single QSP can cover the needs for all ARM Cortex-A series processors, CPAKs will exist for each particular core. It also means that it is hard to make a CPAK more flexible than hardware, since it is by design limited to the scaling of existing cache coherency systems. Both ideas have merit, and both are needed, but for different users at different stages of the system design cycle.

 

Tweet
Posted in: virtual machines, Wind River Blog / Tagged: Android, Carbon, CPAK, QSP, Simics

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Post Navigation

← Previous Post
Next Post →

Recent Posts

  • Wind River Blog: Simics 4.8 is Here
  • A Few Electrons too Many
  • Wind River Blog: Visuality NQ CIFS Server on Simics
  • Everything in the Cloud?
  • Wind River Blog: TCF and Simics
  • Off-Topic: Moving Bad Piggies Save Games
  • Two Cores, Four Cores, Eight Cores – Mobile Variety
  • Bliss: Failing to Pivot for Ideology
  • Wind River Blog and Movie: Demo of Simics Debugging
  • Simulation vs Reality in Schlock Mercenary
  • Programming like Lego
  • Does ISA Matter for Performance?
  • Wind River Blog: Debugging Simics using Simics
  • Wind River Blog: Simics and Flying Piggies
  • Dragons can be Useful – when AT Models Make Sense

Categories

  • appearances (30)
  • articles (21)
  • blogging (10)
  • books (6)
  • business issues (31)
  • computer architecture (35)
  • conferences (34)
  • EDA (50)
    • ESL (35)
  • embedded (78)
    • embedded software (57)
    • embedded systeme (50)
  • general research (6)
  • history (32)
    • general history (7)
    • history of computing (26)
  • off-topic (94)
    • biking (5)
    • board games (1)
    • computer games (3)
    • desktop software (35)
    • food and drink (1)
    • funny (12)
    • gadgets (24)
    • Politics (3)
    • popular culture (5)
    • trains (5)
    • transportation (10)
    • travel (10)
    • websites (3)
  • parallel computing (92)
    • multicore computer architecture (51)
    • multicore debug (22)
    • multicore software (65)
  • programming (107)
  • review (8)
  • security (19)
  • teaching (7)
  • testing (9)
  • uncategorized (12)
  • virtual things (129)
    • computer simulation technology (68)
    • virtual machines (17)
    • virtual platforms (98)
    • virtualization (14)
  • Wind River Blog (40)

Tags

ARM blog commentary Cadence Checkpointing clock-cycle models Communications of the ACM computer architecture conference cycle accuracy debugging DML Domain-specific languages embedded freescale G900 heterogeneous homogeneous IBM Intel iPod lego linux mobile phones multicore off-topic office 2007 operating systems p4080 podcast commentary power architecture rant research reverse debugging reverse execution S4D SiCS Multicore days Simics simulation software tools Sun SystemC video virtualization Vista Windows

1

  • F-Secure Blog

Blogs and news

  • Andras Vajda's blog (on multicore)
  • Embedded in Academia (John Regehr)
  • Grant Martin
  • Jack Ganssle
  • My Wind River Blog
  • Security Now podcast
  • Secworks (Joachim Strömbergson)
  • Simon Kågström
  • Synopsys View from the Top
  • Worse Than Failure

Archives

  • May 2013 (2)
  • April 2013 (1)
  • March 2013 (4)
  • February 2013 (1)
  • January 2013 (3)
  • December 2012 (2)
  • November 2012 (2)
  • October 2012 (1)
  • September 2012 (6)
  • August 2012 (4)
  • July 2012 (4)
  • June 2012 (3)
  • May 2012 (4)
  • April 2012 (2)
  • March 2012 (3)
  • February 2012 (1)
  • January 2012 (6)
  • December 2011 (2)
  • November 2011 (3)
  • October 2011 (4)
  • September 2011 (5)
  • August 2011 (4)
  • July 2011 (3)
  • June 2011 (4)
  • May 2011 (7)
  • April 2011 (1)
  • March 2011 (3)
  • February 2011 (5)
  • January 2011 (1)
  • December 2010 (4)
  • November 2010 (3)
  • October 2010 (5)
  • September 2010 (5)
  • August 2010 (5)
  • July 2010 (6)
  • June 2010 (5)
  • May 2010 (3)
  • April 2010 (4)
  • March 2010 (3)
  • February 2010 (4)
  • January 2010 (7)
  • December 2009 (6)
  • November 2009 (6)
  • October 2009 (7)
  • September 2009 (6)
  • August 2009 (7)
  • July 2009 (11)
  • June 2009 (5)
  • May 2009 (10)
  • April 2009 (7)
  • March 2009 (8)
  • February 2009 (9)
  • January 2009 (12)
  • December 2008 (8)
  • November 2008 (9)
  • October 2008 (9)
  • September 2008 (10)
  • August 2008 (13)
  • July 2008 (12)
  • June 2008 (8)
  • May 2008 (9)
  • April 2008 (10)
  • March 2008 (7)
  • February 2008 (8)
  • January 2008 (5)
  • December 2007 (5)
  • November 2007 (7)
  • October 2007 (7)
  • September 2007 (12)
  • August 2007 (9)
  • July 2007 (2)
© Copyright 2013 - Observations from Uppsala
Infinity Theme by DesignCoral / WordPress