search for: benchmarking

Hi all, I've started looking at the GlobalMerge pass, enabled by default on ARM and AArch64. I think we should reconsider that, at least for AArch64. As is, the pass just merges all globals together, in groups of 4KB (AArch64, 128B on ARM). At the time it was enabled, the general thinking was "it's almost free, it doesn't affect performance much, we might as well use it".

Hello; I was able to build and install llvm(3.0) under Ubuntu 11.10 (using the ./configure script found under llvm source, and then make and make install). While configuring, I gave --prefix as a directory where I would like llvm to be installed. I did not give --with-llvmgccdir and the --enable-optimized argument to configure. Because 3.0 doesn't come with llvmgcc source/binaries and I

...16.04.1 - Linux core: 4.13.0-37 - test-suite SVN rev: 328330 2018-03-23 08:58:41 -0700 (Fri, 23 Mar 2018) - LLVM SVN rev: 329926 2018-04-12 10:01:46 -0700 (Thu, 12 Apr 2018) - clang SVN rev: 329924 2018-04-12 09:41:55 -0700 (Thu, 12 Apr 2018) I followed these useful tips: https://www.llvm.org/docs/Benchmarking.html. I used only a shell, no GUI, no other services, with 2 CPUs isolated from other processes and used only for testing. Test-suite source files were moved to a ramdisk (because some tests use some input files from the source folder), and 3 builds were made in separate folders on the ramdisk wit...

Perhaps you noticed that LLVM gained a new optimizing register allocator yesterday (r130568). Linear scan is going away, and RAGreedy is the new default for optimizing builds. Hopefully, you noticed because your binaries were suddenly 2% smaller and 10% faster*. Some noticed because LLVM started crashing or miscompiling their code. Greedy replaces a fairly big chunk of the code generator, so

This nightly tester is now using an llvm-g++ that produces the new ODR linkage types. This means that many more functions are being considered by the inter-procedural optimization passes (for example, "linkonce" functions defined in a header). The result seems to be pretty huge swings (both good and bad) in the C++ tests in the testsuite, see below. Note that this tester is often

G'Day Tanya, Is it too late to bring in the following patches to fix some major brokenness in the AuroraUX tool chain for 2.6? http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Tools.cpp?r1=84468&r2=84469&view=diff&pathrev=84469 http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/Driver/Tools.cpp?r1=84265&r2=84266&view=diff&pathrev=84266

Hi Tanya, > 1) Compile llvm from source and untar the llvm-test in the projects > directory (name it llvm-test or test-suite). Choose to use a > pre-compiled llvm-gcc or re-compile it yourself. I compiled llvm and llvm-gcc with separate objects directories. Platform is x86_64-linux-gnu. > 2) Run make check, report any failures (FAIL or unexpected pass). Note > that you need to

Hi, Sean: I'm sorry I lie. I didn't mean to lie. I did try to avoid making a *BIG* change to the IPO pass-ordering for now. However, when I make a minor change to populateLTOPassManager() by separating module-pass and non-module-passes, I saw quite a few performance difference, most of them are degradations. Attacking these degradations one by one in a piecemeal manner is wasting

On Oct 20, 2009, at 6:02 AM, Duncan Sands wrote: > Hi Tanya, > >> 1) Compile llvm from source and untar the llvm-test in the projects >> directory (name it llvm-test or test-suite). Choose to use a pre- >> compiled llvm-gcc or re-compile it yourself. > > I compiled llvm and llvm-gcc with separate objects directories. > Platform is x86_64-linux-gnu. > Ok.

Target: FreeBSD 6.2-STABLE on i386 autoconf says: configure:2122: checking build system type configure:2140: result: i386-unknown-freebsd6.2 [...] configure:2721: gcc -v >&5 Using built-in specs. Configured with: FreeBSD/i386 system compiler Thread model: posix gcc version 3.4.6 [FreeBSD] 20060305 [...] objdir != srcdir, for both llvm and gcc. Release build. llvm-gcc 4.2 from source.

Hi, LLVM 2.1-pre1 test results: Linux (SUSE) on x86 (P4) Release mode, but with assertions enabled LLVM srcdir == objdir # of expected passes 2250 # of expected failures 5 I ran the llvm-test suite on my desktop while I was also working on that PC, so don't put too much trust in the timing info. Especially during the "spiff" test the machine was swapping

LLVMers, The 2.2 prerelease is now available for testing: http://llvm.org/prereleases/2.2/ If anyone can help test this release, I ask that you do the following: 1) Build llvm and llvm-gcc (or use a binary). You may build release (default) or debug. You may pick llvm-gcc-4.0, llvm-gcc-4.2, or both. 2) Run 'make check'. 3) In llvm-test, run 'make TEST=nightly report'. 4) When

Hi, LLVM’s SLP-vectorizer is a new pass that combines similar independent instructions in a straight-line code. It is currently not enabled by default, and people who want to experiment with it can use the clang command line flag “-fslp-vectorize”. I ran LLVM’s test suite with and without the SLP vectorizer on a Sandybridge mac (using SSE4, w/o AVX). Based on my performance measurements

Andy and I briefly discussed this the other day, we have not yet got chance to list a detailed pass order for the pre- and post- IPO scalar optimizations. This is wish-list in our mind: pre-IPO: based on the ordering he propose, get rid of the inlining (or just inline tiny func), get rid of all loop xforms... post-IPO: get rid of inlining, or maybe we still need it, only

Hi Tanya, Here's my second attempt on Fedora Core 5. The changes this time are: 1. Using GCC 4.0.3 as the compiler 2. Building everything from source (no pre-built binaries used) BUILD LLVM WITH GCC 4.0.3 * No issues, just the usual warnings. BUILD LLVM-GCC WITH GCC 4.0.3 * No issues RUN LLVM-TEST WITH GCC 4.0.3 * The following failures were encountered. Some of them are

On Fri, Sep 14, 2007 at 11:42:18PM -0700, Tanya Lattner wrote: > The 2.1 pre-release (version 1) is available for testing: > http://llvm.org/prereleases/2.1/version1/ > > [...] > > 2) Download llvm-2.1, llvm-test-2.1, and the llvm-gcc4.0 source. > Compile everything. Run "make check" and the full llvm-test suite > (make TEST=nightly report). > > Send

Target: FreeBSD 7.0-RC1 on amd64. autoconf says: configure:2122: checking build system type configure:2140: result: x86_64-unknown-freebsd7.0 [...] configure:2721: gcc -v >&5 Using built-in specs. Target: amd64-undermydesk-freebsd Configured with: FreeBSD/amd64 system compiler Thread model: posix gcc version 4.2.1 20070719 [FreeBSD] [...] objdir != srcdir, for both llvm and gcc. Release

Tanya, Here's the results for GNU/Linux, 2.6.18-1.2200.fc5smp (Fedora Core 5) HIGH LEVEL COMMENTS * The llvm-1.9.tar.gz file unpacks to a dir named "llvm". Shouldn't that be llvm-1.9? * LLVM was built in Release mode in all cases * I don't think this is ready for release. In particular the llvm-gcc4 binary seg faults on FC 5 for most of llvm-test programs. *

LLVMers, 2.6 pre-release2 is ready to be tested by the community. http://llvm.org/prereleases/2.6/ If you have time, I'd appreciate anyone who can help test the release. To test llvm-gcc: 1) Compile llvm from source and untar the llvm-test in the projects directory (name it llvm-test or test-suite). Choose to use a pre- compiled llvm-gcc or re-compile it yourself. 2) Run make check,

LLVMers, The LLVM 1.9 Prerelease is available for testing: http://llvm.org/prereleases/1.9/ If anyone can spare some time, please download the appropriate tarballs for your platform and test the release (at least with make check). I'd also appreciate any documentation reviews. Please note that llvm-gcc3 on x86 may not have a clean dejagnu run. You should see one XPASS for