similar to: -mllvm -inline-threshold no longer honored?

Thanks Easwaran. This is what we've observed as well, where the old PM inliner was only looking hot/cold callee information, which have signficantly smaller boosts/penalties compared to callsite information. Teresa, do you know if there is some documentation/video/presentation on how PGO information is represented in LLVM and what information is passed via the IR? I'm finding some

> On Apr 18, 2016, at 2:07 PM, Hal Finkel via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > ----- Original Message ----- >> From: "Easwaran Raman" <eraman at google.com> >> To: "via llvm-dev" <llvm-dev at lists.llvm.org> >> Cc: "Chandler Carruth" <chandlerc at gmail.com>, "Hal Finkel" <hfinkel at

On Wed, Jun 24, 2015 at 2:35 PM, David Blaikie <dblaikie at gmail.com> wrote: > > > On Wed, Jun 24, 2015 at 2:20 PM, Easwaran Raman <eraman at google.com> wrote: >> >> On Wed, Jun 24, 2015 at 2:10 PM, Robinson, Paul >> <Paul_Robinson at playstation.sony.com> wrote: >> >> -----Original Message----- >> >> From: Easwaran Raman

On Wed, Jun 24, 2015 at 2:10 PM, Robinson, Paul <Paul_Robinson at playstation.sony.com> wrote: >> -----Original Message----- >> From: Easwaran Raman [mailto:eraman at google.com] >> Sent: Wednesday, June 24, 2015 1:27 PM >> To: Xinliang David Li >> Cc: Robinson, Paul; Xinliang David Li; <llvmdev at cs.uiuc.edu> List >> Subject: Re: [LLVMdev] Inline

I'm reviving this thread after a while and CCing cfe-commits as suggested by David Blaikie. I've also collected numbers building chrome (from chromium, on Linux) with and without this patch as suggested by David. I've re-posted the proposed patch and performance/size numbers collected at the top to make it easily readable for those reading it through cfe-commits. The proposed patch

On Mon, Apr 18, 2016 at 3:20 PM Easwaran Raman <eraman at google.com> wrote: > On Mon, Apr 18, 2016 at 3:00 PM, Chandler Carruth via llvm-dev < > llvm-dev at lists.llvm.org> wrote: > >> On Mon, Apr 18, 2016 at 2:48 PM Hal Finkel <hfinkel at anl.gov> wrote: >> >>> >>> >>> ------------------------------ >>> >>>

(Resending after removing llvmdev at cs.uiuc.edu and using llvm-dev at lists.llvm.org) On Mon, Dec 7, 2015 at 3:08 PM, Easwaran Raman <eraman at google.com> wrote: > Hi Philip, > > Is there any update on this? I've been sending patches to get rid of the > callee hotness based inline hints from the frontend and move the logic to > the inliner. The next step is to use

On Thu, Dec 17, 2015 at 9:21 AM, Andy Ayers <andya at microsoft.com> wrote: > While your bb count distribution is extremely likely to be some kind of power-law like distribution, it's not guaranteed. > > Also you might think about operations that can amplify (rerolling) or appear to amplify (TRE) or diminish BB counts, and how you'd go about reclassifying block hotness. yes

On Wed, Jun 24, 2015 at 2:35 PM, David Blaikie <dblaikie at gmail.com> wrote: > > > On Wed, Jun 24, 2015 at 2:20 PM, Easwaran Raman <eraman at google.com> wrote: >> >> On Wed, Jun 24, 2015 at 2:10 PM, Robinson, Paul >> <Paul_Robinson at playstation.sony.com> wrote: >> >> -----Original Message----- >> >> From: Easwaran Raman

The method to identify functions with in-class definitions is one part of my question. Even if there is a way to do that without passing the hint, I'm interested in getting feedback on treating it at-par with functions having the inline hint in inline cost analysis. Thanks, Easwaran On Wed, Jun 24, 2015 at 12:56 PM, Xinliang David Li <xinliangli at gmail.com> wrote: > The problem

On 04/18/2016 04:05 PM, Easwaran Raman via llvm-dev wrote: > > > On Mon, Apr 18, 2016 at 3:25 PM, Chandler Carruth <chandlerc at gmail.com > <mailto:chandlerc at gmail.com>> wrote: > > On Mon, Apr 18, 2016 at 3:20 PM Easwaran Raman <eraman at google.com > <mailto:eraman at google.com>> wrote: > > On Mon, Apr 18, 2016 at 3:00 PM,

Hi, After r256521 - which removes InlineCostAnalysis class - I think there is no strong reason for InlineCost.cpp to be part of the Analysis library. Is it fine to make it part of TransformUtils? I submitted r266477 (which has now been reverted) that made Analysis depend on ProfileData in order to obtain ProfileSummary for the module, but there is an existing dependency of ProfileData on

----- Original Message ----- > From: "Sean Silva" <chisophugis at gmail.com> > To: "llvm-dev" <llvm-dev at lists.llvm.org> > Cc: "Chris Lattner" <clattner at apple.com>, "Rafael Ávila de Espíndola" <rafael.espindola at gmail.com>, "Michael Spencer" > <bigcheesegs at gmail.com>, "Chandler Carruth"

On Mon, Apr 18, 2016 at 2:18 PM, Chandler Carruth <chandlerc at gmail.com> wrote: > The difference between Analysis and Transforms is *not* about passes, but > about what the code *does*. > > Code for mutating the IR should be in Transforms, and code that analyzes > the IR without mutating it should be in Analysis. This is why, for example, > InstructionSimplify is in

On Wed, Jun 24, 2015 at 2:10 PM, Robinson, Paul <Paul_Robinson at playstation.sony.com> wrote: >> -----Original Message----- >> From: Easwaran Raman [mailto:eraman at google.com] >> Sent: Wednesday, June 24, 2015 1:27 PM >> To: Xinliang David Li >> Cc: Robinson, Paul; Xinliang David Li; <llvmdev at cs.uiuc.edu> List >> Subject: Re: [LLVMdev] Inline

Sorry for misinterpreting, but what is the basis for the simple fact you mentioned? David On Wed, Jun 24, 2015 at 2:43 PM, Robinson, Paul <Paul_Robinson at playstation.sony.com> wrote: >> -----Original Message----- >> From: Xinliang David Li [mailto:davidxl at google.com] >> Sent: Wednesday, June 24, 2015 2:17 PM >> To: Robinson, Paul >> Cc: Easwaran Raman;

On Wed, Dec 16, 2015 at 6:00 PM, Andy Ayers <andya at microsoft.com> wrote: > I’ve done similar rankings with profile data and found it worked out pretty > well. > > > > In my case it was ranking function hotness but the idea was similar: sort by > weight, compute various percentile cutoff points, and use those to classify. > I put in some compensation for truly

On Thu, Dec 10, 2015 at 4:51 PM, Philip Reames <listmail at philipreames.com> wrote: > > > On 12/10/2015 04:29 PM, Xinliang David Li wrote: >> >> On Thu, Dec 10, 2015 at 4:00 PM, Philip Reames >> <listmail at philipreames.com> wrote: >>> >>> Given I didn't get any response to my original query, I chose not to >>> invest

On Thu, Dec 10, 2015 at 4:00 PM, Philip Reames <listmail at philipreames.com> wrote: > Given I didn't get any response to my original query, I chose not to invest > time in this at the time. I am unlikely to get time for this in the near > future. > > On 12/07/2015 03:13 PM, Easwaran Raman wrote: > > (Resending after removing llvmdev at cs.uiuc.edu and using >

On Tue, Oct 3, 2017 at 1:46 PM, Teresa Johnson via llvm-dev < llvm-dev at lists.llvm.org> wrote: > > > On Tue, Oct 3, 2017 at 1:38 PM, Graham Yiu <gyiu at ca.ibm.com> wrote: > >> Hi Teresa, >> >> Actually, enabling the new pass manager manually seems to have solved >> this issue, so this problem is only valid for the old pass manager. >> >