search for: ball94

...rom http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-July/023569.html http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-July/023602.html http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-July/023642.html This patch introduces an implementation of the ProfileInfo that estimates a profile as proposed in [Ball94]. (It distributes incoming flow in an block equally to the successor edges and assumes an loop iteration count of 10.) Andi [Ball94] Thomas Ball, James R. Larus: "Optimally profiling and tracing programs" ACM TOPLAS, Volume 16, Issue 4, 1994 http://portal.acm.org/citation.cfm?id=183527

Hi all, as proposed in http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-February/020396.html I implemented the algorithm presented in [Ball94]. It only instruments the minimal number of edges necessary for edge profiling. The main changes introduced by this patch are: *) a interface compatible rewrite of ProfileInfo *) a cleanup of ProfileInfoLoader (some functionality in ProfileInfoLoader was duplicated in ProfileInfo or Profil...

Hi all, I plan to improve the existing profiling support in LLVM for my master thesis. The goal is threefold: a) Implement more efficient instrumentation along the lines of [Ball94]. b) Implement and experiment with heuristic estimators as proposed in [Wu94]. c) Make profile information available in the backend machinery. We have a preliminary patch that achieves this by maintaining profiles during instruction selection and CFG modifications. This might be useful for...

...efore the unified profiling infrastructure was in place. It seems that the code was removed from trunk post LLVM 3.3. Current Implementation : + HashTable based + Static overflow checks (64 bit counters) at instrumentation time with fallback to APInt counters + Implements efficient event counting [Ball94] to reduce instrumentation overheads + Context sensitive counters if no 64-bitoverflow (i.e. supports path profiling across recursion) + Optimizations for use cases with very large number of executed paths + Used to analyse C/C++ benchmarks from SPECCPU2006 Proposed Integration : + Support library...

Hello all, I would like to participate in this year's Google Summer of Code and I am sending you a short description of my proposal. I have written the formal proposal already and if someone is interested I can send him the pdf. One of the open projects in the LLVM list is to enhance LLVM with static profiling capabilities. LLVM already provides a unified structure for writing pro

...Int::getSigned(llvm::Type::Int32Ty, -1); On Mon, Jun 29, 2009 at 6:34 AM, Andreas Neustifter<e0325716 at student.tuwien.ac.at> wrote: > Hi all, > > as proposed in > http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-February/020396.html > I implemented the algorithm presented in [Ball94]. It only instruments > the minimal number of edges necessary for edge profiling. > > The main changes introduced by this patch are: > *) a interface compatible rewrite of ProfileInfo > *) a cleanup of ProfileInfoLoader >   (some functionality in ProfileInfoLoader was duplicated i...

Hi Daniel, Daniel Dunbar wrote: > Hi Andreas, > > First, thanks again for undertaking this work and submitting it back. There is a > lot of good stuff here and it would be great to see it get back into the tree. Thanks for taking the time to review this, I know its a huge patch. I still have a few questions on how you would like this patch to be re-factored and split up. > [...]

...amount of instrumentation required is not exponential. For example, every if-condition in a routine will increase the number of paths by X2, but the instrumentation points required to disambiguate between each side of the branch is only 1. Furthermore, we reduce the amount of instrumentation using [Ball94] which is proven to be optimal. > > Path profiles enable precise enumeration of the sequence of basic blocks executed in order for a particular path. Using path profiles has been demonstrated by [Young98] to perform better global scheduling than edge profiles. > I haven't had time...