similar to: [LLVMdev] [llvm-testresults] bwilson__llvm-gcc_PROD__i386 nightly tester results

Yes, they are real. I re-ran the two tests with the biggest execution time regressions, and the results were completely reproducible. On Oct 12, 2011, at 1:24 AM, Duncan Sands wrote: > Hi Bob, are these performance regressions real? They look pretty serious. > > Ciao, Duncan. > > On 10/12/11 09:40, llvm-testresults at cs.uiuc.edu wrote: >> >>

A big compile time regression. Any ideas? Ciao, Duncan. On 22/07/11 19:13, llvm-testresults at cs.uiuc.edu wrote: > > bwilson__llvm-gcc_PROD__i386 nightly tester results > > URL http://llvm.org/perf/db_default/simple/nts/253/ > Nickname bwilson__llvm-gcc_PROD__i386:4 > Name curlew.apple.com > > Run ID Order Start Time End Time > Current 253 0 2011-07-22 16:22:04

On Jul 24, 2011, at 3:02 AM, Duncan Sands wrote: > A big compile time regression. Any ideas? > > Ciao, Duncan. False alarm. For some reason that I have not yet been able to figure out, these tests run significantly more slowly when I run them during the daytime, which I did for that run. I checked a few of the worst regressions reported here and they all recovered in subsequent

Hi Bob, >> A big compile time regression. Any ideas? >> >> Ciao, Duncan. > > False alarm. For some reason that I have not yet been able to figure out, these tests run significantly more slowly when I run them during the daytime, which I did for that run. I checked a few of the worst regressions reported here and they all recovered in subsequent runs. here is a crazy

Are these 225 compile time regressions real? It sure looks bad! Ciao, Duncan. On 01/12/11 09:39, llvm-testresults at cs.uiuc.edu wrote: > > bwilson__llvm-gcc_PROD__i386 nightly tester results > > URL http://llvm.org/perf/db_default/simple/nts/380/ > Nickname bwilson__llvm-gcc_PROD__i386:4 > Name curlew.apple.com > > Run ID Order Start Time End Time > Current 380

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".

In lto+pgo some (5 out of 12 with usual suspect like perlbench and gcc among them using -flto -Wl,-mllvm,-use-cfl-aa -Wl,-mllvm,-use-cfl-aa-in-codegen) the CINT2006 benchmarks don’t compile. Has the implementation been tested with lto? If not, please stress the implementation more. Do we know reasons for gains? Where did you expect the biggest gains? Some of the losses will likely boil down to

Hello everyone, One of Google's summer interns, George Burgess IV, created an implementation of the CFL pointer-aliasing analysis algorithm, and this has now been added to LLVM trunk. Now we should determine whether it is worthwhile adding this to the default optimization pipeline. For ease of testing, I've added the command line option -use-cfl-aa which will cause the CFL analysis to be

On CINT2006 ARM64/ref input/lto+pgo I practically measure no performance difference for the 7 benchmarks that compile. This includes bzip2 (although different source base than in CINT2000), mcf, hmmer, sjeng, h364ref, astar, xalancbmk On Sep 15, 2014, at 11:59 AM, Hal Finkel <hfinkel at anl.gov> wrote: > ----- Original Message ----- >> From: "Gerolf Hoflehner"

----- Original Message ----- > From: "Gerolf Hoflehner" <ghoflehner at apple.com> > To: "Hal Finkel" <hfinkel at anl.gov> > Cc: "LLVM Dev" <llvmdev at cs.uiuc.edu>, "Jiangning Liu" <liujiangning1 at gmail.com>, "George Burgess IV" > <george.burgess.iv at gmail.com> > Sent: Monday, September 15, 2014

Most of libc++ doesn't have explicit template instantiations, which leads to a pretty significant build time and code size cost when using libc++, since a large number of common templates will be emitted by the compiler and coalesced by the linker. Notably, in include/__config, we have: #ifndef _LIBCPP_EXTERN_TEMPLATE #define _LIBCPP_EXTERN_TEMPLATE(...) #endif whereas before

Hi folks, Moving the discussion to llvm.dev. None of the changes we talked earlier help. Find attached the C source code that you can use to reproduce the issue. clang --target=aarch64-linux-gnu -c -mcpu=cortex-a57 -Ofast -fno-math-errno test.c -S -o test.s -mllvm -debug-only=licm LICM hoisting to while.body.lr.ph: %21 = load double** %arrayidx8, align 8, !tbaa !5 LICM hoisting to

Can you send me actual LLVM IR or a preprocessed source from using -E? I don't have a machine handy that has headers that target that arch. On Tue Jan 13 2015 at 4:33:29 PM Daniel Berlin <dberlin at dberlin.org> wrote: > Anything other than noalias or mustalias should be getting passed down the > stack, so either that is not happening or CFL aa is giving better answers > and

On 13 January 2015 at 22:11, Daniel Berlin <dberlin at dberlin.org> wrote: > This is caused by CFLAA returning PartialAlias for a query that BasicAA > can prove is NoAlias. > One of them is wrong. Which one? I'm not sure from your description that this is a chaining issue. PartialAlias doesn't chain and isn't supposed to, it's a final answer just like NoAlias and

Inline - George > On Jan 14, 2015, at 10:49 AM, Daniel Berlin <dberlin at dberlin.org> wrote: > > > >> On Tue, Jan 13, 2015 at 11:26 PM, Nick Lewycky <nlewycky at google.com> wrote: >>> On 13 January 2015 at 22:11, Daniel Berlin <dberlin at dberlin.org> wrote: >>> This is caused by CFLAA returning PartialAlias for a query that BasicAA can

Hi Ahmed, Yes. I'd share with Kristof and Renato's concerns, and the impact/dependence upon link-time tool should be clarified before disabling this pass. On the other hand, actually the test on our hardware shows disabling this pass without LTO considered, some spec benchmarks would have big regressions, (positive is bad) spec.cpu2000.ref.253_perlbmk 3.27% spec.cpu2000.ref.254_gap

Oh, sorry, i didn't rebase it when i changed the fix, you would have had to apply the first on top of the second. Here is one against HEAD On Wed, Jan 14, 2015 at 12:32 PM, Ana Pazos <apazos at codeaurora.org> wrote: > Daniel, your patch does not apply cleanly. Are you on the tip? > > The code I see there is no line if (QueryResult == MayAlias|| QueryResult == PartialAlias)

Yes. I've attached an updated patch that does the following: 1. Fixes the partialalias of globals/arguments 2. Enables partialalias for cases where nothing has been unified to a global/argument 3. Fixes that select was unifying the condition to the other pieces (the condition does not need to be processed :P). This was causing unnecessary aliasing. 4. Adds a regression test to

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

On 26 February 2015 at 00:57, Ahmed Bougacha <ahmed.bougacha at gmail.com> wrote: > -- A way forward > One obvious way to improve it is: look at uses of globals, and try to > form sets of globals commonly used together. The tricky part is to > define heuristics for "commonly". Also, the pass then becomes much > more expensive. I'm currently looking into