search for: aguha

...dy lowered into libgomp calls before leaving DragonEgg. It's been awhile since I've loooked at it though. If you use the PTX back-end and have any issues, please don't hesitate to post to the list and cc: me at jholewinski at nvidia.com On Thu, Nov 8, 2012 at 8:05 AM, Apala Guha <aguha at uchicago.edu> wrote: > Hi,**** > > ** ** > > Is it possible to translate an OpenMP program to CUDA using LLVM? I read > that dragonegg has a OpenMP front-end and LLVM has a PTX back-end. I don’t > know how mature these tools are. Please let me know. Thanks.**** > &gt...

Hi, Is there any way to analyze library functions using LLVM, in the same manner as source code functions? Thanks. -Apala

...tructure in place to do so ,One way to accomplish this by implementing decompiler to convert library functions to LLVM IR and run the LLVM analyze pass over converted LLVM IR ,Then revert back from LLVM IR to your library format. Thanks ~Umesh On Thu, Oct 4, 2012 at 9:47 PM, apala guha <aguha at uchicago.edu> wrote: > Hi, > > Is there any way to analyze library functions using LLVM, in the same > manner as source code functions? > > Thanks. > -Apala > ______________________________**_________________ > LLVM Developers mailing list > LLVMdev at cs.uiuc.e...

...gonegg has a OpenMP front-end and LLVM has a PTX back-end. I don't know how mature these tools are. Please let me know. Thanks. -Apala Postdoctoral Scholar Department of Computer Science, University of Chicago Computation Institute, Argonne National Laboratory http://sites.google.com/site/apalaguha/home/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20121108/c32289b1/attachment.html>

Hi, Is there a way to count branch frequencies using LLVM infrastructure? Thanks. -Apala Postdoctoral Scholar Department of Computer Science, University of Chicago Computation Institute, Argonne National Laboratory http://sites.google.com/site/apalaguha/home/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20120907/55acf933/attachment.html>

Hi, I am trying to link archives built by llvm-ar with other bitcode files, using llvm-link. But llvm-link seems unable to read files produced by llvm-ar. Also, clang seems unable to read files produced by llvm-ar. Am I doing something wrong or is this the expected behavior? Is there any work-around? Thanks. -Apala

On Dec 5, 2012, at 8:15 PM, apala guha <aguha at uchicago.edu> wrote: > I am trying to link archives built by llvm-ar with other bitcode files, using llvm-link. But llvm-link seems unable to read files produced by llvm-ar. Also, clang seems unable to read files produced by llvm-ar. Am I doing something wrong or is this the expected beha...

Hi, Is it possible to generate the PDG of a function using LLVM? I did not find much documentation on it online. Thanks. -Apala Postdoctoral Scholar Department of Computer Science, University of Chicago Computation Institute, Argonne National Laboratory http://sites.google.com/site/apalaguha/home/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20120820/c5640ae0/attachment.html>

Hi, Is there any way to print the source file and line number for loops and functions in the LLVM IR (assuming everything has been compiled with -g option)? Thanks. -Apala

Hi, I am seeing some strange function calls in the LLVM IR, such as, 'call llvm.lifetime.start'. What are these functions and why are they appearing in the IR? Thanks. -Apala

Hi, I had asked about LLVM debug information a while back, but was told that it is not well-maintained. Is there any way I can IR functions and loops with their source code positions? Thanks -Apala

Hi, The profiler pass currently uses 'unsigned' (32b) counters. These counters are not large enough for some of the programs I am profiling. I want to re-write the profiling tools for 64b counters. How much of an effort will that be? Thanks. -Apala

Hi, How can I pass arguments to the loop unroll pass? I want to pass the unroll factor to it. thanks. -Apala

Hi Tim, This is C++ indeed. Basically, I am profiling the code. So, these edges that cannot be resolved at compile time present a problem. Where can I find these devirtualization optimizations that you mentioned? Thanks. -Apala On 01/01/2013 12:18 PM, Tim Northover wrote: > > Hi, > > > For example: call void %1608(%"struct.LRT::RGBAucharFrameBuffer"* > > %1604)

Hi, I am using the profiling feature of LLVM 3.1. Mostly, it works well, but seems to be wrong in a few cases. For example, I have found that the number of times a function executed is reported as less than the number of times that the basic block calling this function executed (the difference was about 25x!). I am copying out the exact functions below. The relevant parts are in bold font:

I am coming up against a lot of function pointers in the IR, although the corresponding source code does not have indirect calls. For example: call void %1608(%"struct.LRT::RGBAucharFrameBuffer"* %1604) How can I resolve the targets of these? Also, why are they appearing as indirect calls in the IR, when they are direct calls in the source? Thanks. -Apala

...t; > >> -Apala > >> > >> Postdoctoral Scholar > >> > >> Department of Computer Science, University of Chicago > >> > >> Computation Institute, Argonne National Laboratory > >> > >> http://sites.google.com/site/apalaguha/home/ > >> > >> > >> > >> _______________________________________________ > >> LLVM Developers mailing list > >> LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu > >> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev > &gt...

Hi, According to the LLVM website, the pass-print-dbginfo should print : Pass that prints instructions, and associated debug info: * source/line/col information * original variable name * original type name But the following is the output I get. It has no source file names. It does not print any instructions. It only prints function and variable names: function main : ; %2 is

Another issue is with ProfileInfo::getExecutionCount(Function* F). Looking at the source code and results, I am seeing that it always returns the execution count of the entry basic block of the function. If the entry basic block is part of a loop, its execution count does not match the function invocation count. Is my assumption wrong, that ProfileInfo::getExecutionCount(Function* F) is

Thanks everyone for the replies. After some experimentation, I found that the order in which the passes are specified matters: opt -O3 -profile-loader matmult.bc -o matmult.opt.bc (works) opt -profile-loader -O3 matmult.bc -o matmult.opt.bc (does not work) Also, I am able to avoid the inconsistency warning only for optimization levels -O3 and -O2. I get that warning when using -O1 and