<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Wed, Sep 25, 2013 at 1:15 PM, Andrew Trick <span dir="ltr"><<a href="mailto:atrick@apple.com" target="_blank">atrick@apple.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div style="word-wrap:break-word"><br><div><div>
<div>On Sep 24, 2013, at 7:59 PM, Liu Xin <<a href="mailto:navy.xliu@gmail.com" target="_blank">navy.xliu@gmail.com</a>> wrote:</div><br><blockquote type="cite"><div dir="ltr">Hi, Andrew, <div><br></div><div>Thank you for answering my question. </div>
<div><br></div><div>What's the status of misched? is it experimental? I found it is disabled by default for all architectures(3.4svn). I also don't understand the algorithm. Could you point to me more papers or text materials about your approach? it seems that you want to balance register pressure and ILP in misched. </div>
</div></blockquote><div><br></div></div><div>It has been used in production for a year. It’s currently enabled on trunk for PPC, R600, and Hexagon. If there are no objections I’d like to move x86 and armv7 ASAP. Leaving it disabled is becoming more of a maintenance burden.</div>
<div><br></div></div></div></blockquote><div><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex">
<div style="word-wrap:break-word"><div><div></div><div>Please see my llvm-dev list messages to Ghassan yesterday. MI Scheduler is pass that just provides a place to do scheduling and a large toolbox to do it with. ScheduleDAGMI is a list scheduler driver, and the GenericScheduler strategy attempts to balance register pressure with latency. In my opinion getting the right register pressure vs latency balance is easy to do at a given point in time for a small benchmark suite, but very, very hard to do in general with a design that works across microarchitectures and is resilient to changes to incoming IR. GenericScheduler doesn’t magically solve this problem, but it should never do anything too terrible either.</div>
<div><br></div></div></div></blockquote><div>Sorry, I have a false statement above. I tried x86/arm/mips and found no misched in use. you means misched is just like a framework. Backend can configure TargetConfigaPass to run misched both pre-RA and post-RA, right? </div>
<div><br></div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div style="word-wrap:break-word"><div><div><blockquote type="cite">
<div dir="ltr">
<div><div class="gmail_extra"><div class="gmail_quote">On Tue, Sep 24, 2013 at 4:07 PM, Andrew Trick <span dir="ltr"><<a href="mailto:atrick@apple.com" target="_blank">atrick@apple.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div><br>
On Sep 21, 2013, at 8:02 PM, Liu Xin <<a href="mailto:navy.xliu@gmail.com" target="_blank">navy.xliu@gmail.com</a>> wrote:<br>
<br>
> hi, LLVM,<br>
><br>
> I found there is a flag DisableHazardRecognizer in TargetInstrImpl.cpp. I still don't understand how llvm detects data hazard in pre-RA-sched. pre-RA-sched is based on SDNode and all operands are vregs. Even you can calculate the operators of SDNodes, the data hazard in vreg are not same as physical register data hazard. Is it useful to optimize processor pipeline?<br>
<br>
</div>The hazard recognizer enforces the instruction itineraries that are defined for some subtargets. The itineraries specify resource usage at each pipeline stage and latency. The "hazards" being recognized are resource conflicts, like two independent instructions using the FP unit, or read after write latency. It does not deal with WAR physical register hazards.<br>
<br>
(Targets are migrating to a more flexible and efficient machine model now that does not use the hazard recognizer.)<br>
<br></blockquote><div>I don't understand this statement. what's the meaning of "more flexible & efficient machine model". I know intel x86 processors are featured with aggressive out of order function, but arm and mips don't have it. Server processor can have, embedded processor will not. Compiler writers still need to consider instruction pipeline and multiple issue. </div>
<div><br></div><div>Our processor still uses mips-like multiple-stage pipeline, almost same as what textbook taught me. We suffer from pipeline stalls and manager to improve issue rate using instruction scheduling. by now, I use post-RA-sched because It can build graph whose edges are dependencies. the dependencies are real basing on physical register and instruction attributes. Because misched happens before register allocation, I don't think I can make use of it to resolve data hazard. am I right? <br>
</div></div></div></div></div></blockquote><br></div></div><div>The old itineraries allow specifying which resources are used in each pipeline stage. It’s a full matrix.</div><div><br></div><div>In the new machine model, you only specify the resources and number of cycles. It can be implemented with simple counters. This works in practice because it’s almost always the case that different instructions begin using a given resource at the same time relative to when the instruction is executed. Even the VLIW implementation I’ve seen in trunk could have used the new model.</div>
<div><br></div><div>It’s efficient because the scheduler doesn’t need to manage a reservation table or build a state machine.</div><div><br></div><div>It’s more flexible because predicates allow instructions to be modeled differently based on opcode extensions or immediate values.</div>
<div><br></div></div></blockquote><div style>I got it. I do feel the scoreboard state-tracker is not that useful except for software pipelining. I have resolved my instruction pipeline stall using existing post-RA-Sched(TD). I will investigate the new misched approach later. Ghassan mentioned llvm performance regression in previous thread. Do you measure perf impact of compiler using llvm-test-suite ? As you said, there's no absolutely one good algorithm for instruction scheduler , so I have to learn measure my changes. </div>
<div style> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;padding-left:1ex"><div style="word-wrap:break-word"><div>
</div><div>The postRA hazard that your talking about is the job of the dependence graph builder. That is the same for both post-RA and MI sched. When the DAG builder runs before regalloc, it also has to handle virtual registers, that’s the only difference.</div>
<div><br></div><div>The best way for me to explain how to define a machine model for an in-order processor would be to work with someone who is ready to migrate mips or a simple ppc, arm, or x86 (atom) implementation and improve the docs along the way.</div>
<div><br></div><div>We’re also lacking a model for AVX!</div><div><br></div><div>-Andy</div></div></blockquote></div></div><div class="gmail_extra"><br></div><div class="gmail_extra">thanks,</div><div class="gmail_extra" style>
--lx</div></div>