OoOE

You’re going to come across the phrase out-of-order execution (OoOE) a lot here, so let’s go through a quick refresher on what that is and why it matters.

At a high level, the role of a CPU is to read instructions from whatever program it’s running, determine what they’re telling the machine to do, execute them and write the result back out to memory.

The program counter within a CPU points to the address in memory of the next instruction to be executed. The CPU’s fetch logic grabs instructions in order. Those instructions are decoded into an internally understood format (a single architectural instruction sometimes decodes into multiple smaller instructions). Once decoded, all necessary operands are fetched from memory (if they’re not already in local registers) and the combination of instruction + operands are issued for execution. The results are committed to memory (registers/cache/DRAM) and it’s on to the next one.

In-order architectures complete this pipeline in order, from start to finish. The obvious problem is that many steps within the pipeline are dependent on having the right operands immediately available. For a number of reasons, this isn’t always possible. Operands could depend on other earlier instructions that may not have finished executing, or they might be located in main memory - hundreds of cycles away from the CPU. In these cases, a bubble is inserted into the processor’s pipeline and the machine’s overall efficiency drops as no work is being done until those operands are available.

Out-of-order architectures attempt to fix this problem by allowing independent instructions to execute ahead of others that are stalled waiting for data. In both cases instructions are fetched and retired in-order, but in an OoO architecture instructions can be executed out-of-order to improve overall utilization of execution resources.

The move to an OoO paradigm generally comes with penalties to die area and power consumption, which is one reason the earliest mobile CPU architectures were in-order designs. The ARM11, ARM’s Cortex A8, Intel’s original Atom (Bonnell) and Qualcomm’s Scorpion core were all in-order. As performance demands continued to go up and with new, smaller/lower power transistors, all of the players here started introducing OoO variants of their architectures. Although often referred to as out of order designs, ARM’s Cortex A9 and Qualcomm’s Krait 200/300 are mildly OoO compared to Cortex A15. Intel’s Silvermont joins the ranks of the Cortex A15 as a fully out of order design by modern day standards. The move to OoO alone should be good for around a 30% increase in single threaded performance vs. Bonnell.

Pipeline

Silvermont changes the Atom pipeline slightly. Bonnell featured a 16 stage in-order pipeline. One side effect to the design was that all operations, including those that didn’t have cache accesses (e.g. operations whose operands were in registers), had to go through three data cache access stages even though nothing happened during those stages. In going out-of-order, Silvermont allows instructions to bypass those stages if they don’t need data from memory, effectively shortening the mispredict penalty from 13 stages down to 10. The integer pipeline depth now varies depending on the type of instruction, but you’re looking at a range of 14 - 17 stages.

Branch prediction improves tremendously with Silvermont, a staple of any progressive microprocessor architecture. Silvermont takes the gshare branch predictor of Bonnell and significantly increased the size of all associated data structures. Silvermont also added an indirect branch predictor. The combination of the larger predictors and the new indirect predictor should increase branch prediction accuracy.

Couple better branch prediction with a lower mispredict latency and you’re talking about another 5 - 10% increase in IPC over Bonnell.

Introduction & 22nm Sensible Scaling: OoO Atom Remains Dual-Issue
POST A COMMENT

174 Comments

View All Comments

  • Ortanon - Monday, May 6, 2013 - link

    This. Reply
  • jamesb2147 - Monday, May 6, 2013 - link

    That's not an excuse for subjective fluff. Don't get me wrong, I particularly liked the Bulldozer performance reviews and analysis. The reason I liked them was the hard data used to develop ideas about possible use-case scenarios for the CPU's. This article is full of "IT'S GONNA BE AWESUMMMMMM!!!!!1!!!" and not so much nuanced, objective reporting on actual news. It has plenty of analysis, but without concrete evidence, it reads like one of those all-too-familiar forum rants from HardForum or the like, full of people with too much time and not enough to do.

    If Anandtech is evolving into one of those news outlets that has to keep writing articles to keep people engaged, then I'm not interested. And it's not just my loss, it's the readership's.
    Reply
  • wsw1982 - Tuesday, May 7, 2013 - link

    if the clover trail+ already has similar performance as the best ARM offer, and the silvermont is said to be 2 times better than clover trail+. What should be the most logic sentiment in your opinion? Reply
  • phoenix_rizzen - Tuesday, May 7, 2013 - link

    Well, you're comparing some future Intel SoC that no one has been allowed to actually touch/test (using only Intel's internal "benchmarking") against currently available ARM SoCs. Who knows what the performance will be like for ARM SoCs in 8-12 months, when these Intel SoCs are actually, physically able to be benchmarked.

    Cautious optimism is warranted. Not flat-out "OMG, THIS IS THE BESTEST EVAR!" fluff like this article spouts.
    Reply
  • Spunjji - Wednesday, May 8, 2013 - link

    Restrained optimism and a desire for further evidence. I can only assume Anand has already seen more than us, as his attitude is somewhat more positive than that. If he hasn't, well, I have expressed the opinion before that I find he treats Intel press releases rather lightly. Reply
  • cjb110 - Tuesday, May 7, 2013 - link

    tbh that's an OTT response, AnandTech have done a piece based on the info they have and their previous experience. Everything mentioned is reasoned out in a logical progression. You might not always agree with the reasoning but its most certainly isn't 'fluff'. There will be a data based analysis later, as always. Reply
  • Krysto - Monday, May 6, 2013 - link

    But not entirely unbiased. Making a detailed analysis and being biased aren't mutually exclusive. Reply
  • Krysto - Monday, May 6, 2013 - link

    See asymco.com (apple fanboi doing "indepth analysis" about Android and other competitors.. Guess what? They usually favor Apple). Reply
  • Homeles - Monday, May 6, 2013 - link

    I doubt there's a single human being on the face of the planet that is unbiased. What's your point? Reply
  • Thrill92 - Tuesday, May 7, 2013 - link

    Oh no, your going to have to do some critical thinking about the data and conclusions in media. What ever will you do? Reply

Log in

Don't have an account? Sign up now