similar to: [LLVMdev] LLVM profiling

I am a student at the University of Alberta under the supervision of José Nelson Amaral, and I have been working on implementing path profiling into LLVM. I have completed my project and would like to submit it. We are looking for a reviewer for the path profiling implementation. We have sent previous requests to the llvmdev list but have so far been unsuccessful. Please see the attached

Thank you for your suggestions on the patch. If the patch is committed, I would be willing to maintain it, though I am not sure what is all involved or how I am made aware of changes that need to be made. The technical report https://www.cs.ualberta.ca/system/files/tech_report/2010/PreussPathProfLLVM.pdf contains my benchmarks relating to profiling overhead in LLVM. Over the next week I will

On Dec 3, 2010, at 11:21 AM, Adam Preuss wrote: > I am a student at the University of Alberta under the > supervision of José Nelson Amaral, and I have been working on > implementing path profiling into LLVM. I have completed my project > and would like to submit it. > > We are looking for a reviewer for the path profiling implementation. We > have sent previous requests

Alright, I'm ready to nuke it. Last chance to say stop. For context of others, this has come up repeatedly: no one we know of is using EdgeProfiling.cpp, PathProfiling.cpp, and the lib/Analysis/Profile*Pass.cpp collection of tools. They haven't been updated since 2012 when Alastair Murray looked into this stuff, and both current efforts towards PGO are essentially *totally* different

Dear All, I am using the release 33 of LLVM. This release supports -insert-edge-profiling option for opt. But it doesnt provide/supports the -dot-edge-numbers option. Where can I find the file implementing this option (e.g, the source file for edge profiling is located in lib/transforms/instrumentation)? Please help me out. Thanks Naveed Ul Mustafa

Dear Members, I am working on path profiling, but command llvm-prof cannot read path profile info. Making llvm-prof to be able to read PP info is so wonderful. But I cannot find the format of PP. Could anyone give me the document of path profile info format so that I could modify llvm-prof. Thank you in advance Linh Ho -------------- next part -------------- An HTML attachment was

Hi John, I have looked into the EmitAutoVarAlloca() in CGDecl.cpp. However, I could not figure out how to employ my custom attribute for code generation. For example, my custom attribute is visible in CGDecl.cpp but how can I generate based on my custom attribute if (D.hasAttr<myCustomAttri>()) { //What to do here? } What I wan in IR is something like below. Without Custom Attribute:

Hi Asit, thanks for the reply. But I guess I was not clear in my question. Actually, i dont want to use __ATTRIBUTE__((ANNOTATE("MOVIATTR"))), since in documentation it is stated that "This intrinsic allows annotation of local variables with arbitrary strings. This can be useful for special purpose optimizations that want to look for these annotations. These have no other

Hi All, I need your guidance about a custom attribute. I have defined one for variables. It is accepted in the source code (without any warnings from clang), for example in following snippet. #define NEWATTR __attribute__((moviAttr(1))) int main() { NEWATTR volatile unsigned int a = 5; volatile unsigned int *p; p = &a; return (a+*p); } and actually when I Dump the declaration, after

Hello devlopers, I request your guidance on how to lower the metadata attached with an instruction. Following is given the IR dump before Module verifier pass, and there is a string "Tile3" attached as metadata with instruction "%x = alloca i32, align 4, !Tile3 !1". My target is to transmit/propagate the string down to post RA-Scheduling pass. Is it possible? If yes, how

Hi Nick Thanks for you reply. CMAKE is very new to me. I complied using GNU WIN32 and got those errors. Is it possible to compile it using GNU WIN 32 and anything need to be modified? I managed to compile the run time library on a mac machine. Yafan On Fri, Apr 22, 2011 at 5:04 PM, Nick Lewycky <nicholas at mxc.ca> wrote: > yafan zhao wrote: > >> Hi All >> Thanks for

What version of LLVM are you using? The profiling framework is completely messed up in the newer versions of LLVM.. I used to work with profiling in 2.5 some time ago, and it seemed to work fine.. If you really need this to work quickly, you might want to just get the old version and get on with it.. The newer versions of LLVM need to get the profiling part fixed soon..It is messing up my work as

Dear all, I have already checked some related posted messages, such as: http://lists.cs.uiuc.edu/pipermail/llvmdev/2008-January/012315.html and http://lists.cs.uiuc.edu/pipermail/llvmdev/2008-February/012466.html After getting rid of some error messages, I was able to run the following commands: 1) opt -insert-path-profiling matmul.bc -o matmul.pp.bc 2) lli -load

Chandler Carruth wrote: >Alright, I'm ready to nuke it. Last chance to say stop. Stop. >For context of others, this has come up repeatedly: no one we know of is >using EdgeProfiling.cpp, PathProfiling.cpp, and the >lib/Analysis/Profile*Pass.cpp collection of tools. We've been actively using it since at least 2.8. True, we haven't been vocal about it. While I can see

Hello Everyone, Before I get started I just want to sincerely apologise for not getting feedback on this earlier. I've had an extremely busy week as I was presenting a paper at the CGO conference. If anyone is able to provide feedback in such a short time-frame then it will be gratefully received. If not, then I just hope the work described sounds useful. I have already submitted

Hello, I am planning on contributing path profiling to LLVM by the end of August. I have written a document of what the interface to the path profiles would look like at that time. If someone has any amendments, I can incorporate them. http://www.cs.ualberta.ca/~pejic/PathProfiling.html Slobodan Pejic

Summary: We need to find a reviewer for our implementation of Ball-Laurus path profiling. It is well known that path profiling generates more precise information about a program's behaviour than edge profiling. We are conducting a research project with the goal of developing a methodology to make feedback-directed optimization (FDO) more sound. We are developing combined profiles that enable

On 05/27/2015 11:13 AM, Duncan P. N. Exon Smith wrote: >> On 2015 May 27, at 07:42, Diego Novillo <dnovillo at google.com> wrote: >> >> On Tue, May 26, 2015 at 11:47 PM, Lee Hunt <leehu at exchange.microsoft.com> wrote: >> >>> For example, from reading different pages on how Clang PGO, it’s unclear if >>> it does “block reordering” (i.e. moving

> On 2015 May 27, at 07:42, Diego Novillo <dnovillo at google.com> wrote: > > On Tue, May 26, 2015 at 11:47 PM, Lee Hunt <leehu at exchange.microsoft.com> wrote: > >> For example, from reading different pages on how Clang PGO, it’s unclear if >> it does “block reordering” (i.e. moving unexecuted code blocks to a distant >> code page, leaving only ‘hot’

Dear Duncan, Thank you a lot for your feedback. I have a problem though. The branch weights counters overflow in some files and thus I get incorrect numbers. Is there any way to find a workaround for that? Is is supposed to be a known bug or is it something that needs configuration on my part? Again, thank you a lot for your reply. Best Regards, Georgios Zacharopoulos 2016-02-03 18:23