similar to: [LLVMdev] [RFC] BlockFrequency is the wrong metric; we need a new one

On Sun, Feb 2, 2014 at 6:18 PM, Andrew Trick <atrick at apple.com> wrote: > > On Feb 2, 2014, at 2:13 AM, Chandler Carruth <chandlerc at gmail.com> wrote: > > > Right now, all profile information is funneled through two analysis > passes prior to any part of the optimizer using it. > > > > First, we have BranchProbabilityInfo, which provides a simple

On Feb 3, 2014, at 12:13 AM, Andrew Trick <atrick at apple.com> wrote: > On Feb 2, 2014, at 6:55 PM, Chandler Carruth <chandlerc at gmail.com> wrote: > >> On Sun, Feb 2, 2014 at 6:18 PM, Andrew Trick <atrick at apple.com> wrote: >> >> On Feb 2, 2014, at 2:13 AM, Chandler Carruth <chandlerc at gmail.com> wrote: >> >> > Right now,

On Feb 4, 2014, at 4:36 PM, Andrew Trick <atrick at apple.com> wrote: > > On Feb 4, 2014, at 4:07 PM, Duncan P. N. Exon Smith <dexonsmith at apple.com> wrote: > >> >> On Feb 3, 2014, at 12:13 AM, Andrew Trick <atrick at apple.com> wrote: >> >>> On Feb 2, 2014, at 6:55 PM, Chandler Carruth <chandlerc at gmail.com> wrote: >>>

On Feb 2, 2014, at 6:18 PM, Andrew Trick <atrick at apple.com> wrote: >> The result of such a system would produce weights for every block in the above CFG as '1.0', or equivalent to the entry block weight. This to me is a really useful metric -- it indicates that no block in the CFG is really more or less likely than any other. Only *biases* in a specific direction would

On Thu, Oct 20, 2011 at 10:53 AM, Jakob Stoklund Olesen <stoklund at 2pi.dk>wrote: > > On Oct 20, 2011, at 9:56 AM, Chandler Carruth wrote: > > > A new patch is attached that is *much* less of a rough draft. Sorry for > any confusion due to the early state of the patch. > > Thanks, Chandler. This is great stuff. > > > Still, I never intended this to be

David Is this true for static heuristics as well ? If the bb freqs are scaled wrt to the entry block freq and a) use such scaled freqs for the bb's that have calls b) propagate this info topologically over the call graph, how representative will be the info if one just wants to use in a comparative sense ? -Dibyendu Sent from my Windows Phone ________________________________ From: Xinliang

On Oct 20, 2011, at 11:53 PM, Chandler Carruth wrote: > On Thu, Oct 20, 2011 at 10:53 AM, Jakob Stoklund Olesen <stoklund at 2pi.dk> wrote: > On Oct 20, 2011, at 9:56 AM, Chandler Carruth wrote: > > > A new patch is attached that is *much* less of a rough draft. Sorry for any confusion due to the early state of the patch. > > Thanks, Chandler. This is great stuff. >

In PR 22718, we are looking at issues with long running applications producing non-representative frequencies. For example, in these two loops: int g = 0; __attribute__((noinline)) void bar() { g++; } extern int printf(const char*, ...); int main() { int i, j, k; for (i = 0; i < 1000000; i++) bar(); printf ("g = %d\n", g); g = 0; for (i = 0; i < 500000; i++)

The BlockFrequency analysis has been useful for machine block placement, register allocation and other function-level optimizations. How could we extend it for use in an inter-procedural (whole-program) context? For example, if we would like to compare the hotness of two call sites in different functions, or calculate the hotness of two global variables referenced in multiple functions. If the

Hello, I'm working on an application that would benefit from knowing the weight of a basic block, as in "fraction of the program's execution time spent in this block". Currently, I'm computing this using the block's frequency from BlockFrequencyInfo, relative to the function's entry block frequency, and scaled by the function's entry count. This is also the

On Mon, Sep 18, 2017 at 1:16 PM, Andrew Trick <atrick at apple.com> wrote: > > On Sep 14, 2017, at 6:53 PM, Kyle Butt via llvm-dev < > llvm-dev at lists.llvm.org> wrote: > > I plan on rewriting the block placement algorithm to proceed by traces. > > A trace is a chain of blocks where each block in the chain may fall > through to > the successor in the chain.

(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 01/07/2015 05:33 PM, Chandler Carruth wrote: > > On Wed, Jan 7, 2015 at 5:19 PM, Philip Reames > <listmail at philipreames.com <mailto:listmail at philipreames.com>> wrote: > > I've been playing with approaches to getting better optimization > of loops which contain infrequently executed slow paths. I've > gotten as far as throwing together

I tried getting profile data from LLVM 3.1, using the method mentioned below. I tried it out on a simple matrix multiplication program. However, I noticed the following problems: 1. There is a warning message: "WARNING: profile information is inconsistent with the current program!" 2. The basic block counts (obtained from ProfileInfo::getExecutionCount(const BasicBlock*)) are

Thanks Alastair. Is it possible to associate the branch frequency counts with the basic blocks in the intermediate representation? (e.g. Can I access basic block frequencies in runOnFunction()?) Also, I was able to produce a 'llvmprof.out' file. What is the format of this file? How can I parse it? Thanks. -Apala > > > On 09/07/2012 01:25 PM, Alastair Murray wrote: >

> On Sep 18, 2017, at 5:17 PM, Kyle Butt <iteratee at google.com> wrote: > > > > On Mon, Sep 18, 2017 at 1:16 PM, Andrew Trick <atrick at apple.com <mailto:atrick at apple.com>> wrote: > >> On Sep 14, 2017, at 6:53 PM, Kyle Butt via llvm-dev <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> wrote: >> >> I plan on

On Wed, Jun 12, 2013 at 3:10 PM, Jakob Stoklund Olesen <stoklund at 2pi.dk>wrote: > It predates the block frequency interface. It just needs to be hooked up, > patches welcome. It would also be nice to remove the floating point > computations from the spill placement code. Cool, if Diego doesn't beat me to it, I may send you a patch as that seems easy and obviously

Hi, I have a three dimensional array, e.g., my.array = array(0, dim=c(2,3,4), dimnames=list( d1=c("A1","A2"), d2=c("B1","B2","B3"), d3=c("C1","C2","C3","C4")) ) what I would like to get is then a dataframe: d1 d2 d3 value A1 B1 C1 0 A2 B1 C1 0 . . . A2 B3 C4 0 I'm sure there is one function to do

Hi, I am trying to aggregate the sum of my test data.frame as follow: testDF <- data.frame(v1 = c("a", "a", "a", "a", "a", "b", "b", "b", "b", "b", "c", "c", "c", "c", "c", "d", "d", "d", "d",

Hello, I have an unbalanced panel dataset and would like to exclude all objects that don't appear at least x times. Therefore, I would like to include a column indicating for every line how many periods are available, e.g. id, year, number 1, 2000, 3 1, 2001, 3 1, 2002, 3 2, 2001, 1 3, ..., ... This would allow me to exclude companies by setting "subset=number>=x". However, I