Is there a reason why existing buildbots are not generating LNT results? On 2013-01-28, at 11:37 AM, David Blaikie wrote: They're just build bots running LNT - check the build bot configuration code in the zorg llvm project repository. You'll probably need to do some work to get a machine quiet enough to have reliable/useful performance results, though On Jan 28, 2013 8:33 AM, "Redmond, Paul" <paul.redmond at intel.com<mailto:paul.redmond at intel.com>> wrote: Hi, What is involved in adding new perf machines? Are these machines separate from the buildbots? paul _______________________________________________ LLVM Developers mailing list LLVMdev at cs.uiuc.edu<mailto:LLVMdev at cs.uiuc.edu> http://llvm.cs.uiuc.edu<http://llvm.cs.uiuc.edu/> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
On Jan 28, 2013, at 8:57 AM, "Redmond, Paul" <paul.redmond at intel.com> wrote:> Is there a reason why existing buildbots are not generating LNT results?Performance machines should be configured differently. For example, when you run performance measurements you need to disable Turbo to get stable results. On the other hand when you check for the correctness of the compiler you want to compile and test as fast as you can and Turbo can give you a 20% boost. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20130128/b285a2df/attachment.html>
On Mon, Jan 28, 2013 at 8:57 AM, Redmond, Paul <paul.redmond at intel.com> wrote:> Is there a reason why existing buildbots are not generating LNT results?Those running LNT should be/are: http://llvm.org/perf/db_default/v4/nts/recent_activity Shows all 3 of the lab.llvm.org machines that run LNT ( http://lab.llvm.org:8011/buildslaves - you can see these 3 macminis run "-nt" builder variations (-O3, -O3 vectorized, -O0 -g))> > On 2013-01-28, at 11:37 AM, David Blaikie wrote: > > They're just build bots running LNT - check the build bot configuration code > in the zorg llvm project repository. You'll probably need to do some work to > get a machine quiet enough to have reliable/useful performance results, > though > > On Jan 28, 2013 8:33 AM, "Redmond, Paul" <paul.redmond at intel.com> wrote: >> >> Hi, >> >> What is involved in adding new perf machines? Are these machines separate >> from the buildbots? >> >> paul >> _______________________________________________ >> LLVM Developers mailing list >> LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu >> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev > >
Is O3-vectorize redundant now that the loop vectorizer is enabled by default? On 2013-01-28, at 12:25 PM, David Blaikie wrote:> On Mon, Jan 28, 2013 at 8:57 AM, Redmond, Paul <paul.redmond at intel.com> wrote: >> Is there a reason why existing buildbots are not generating LNT results? > > Those running LNT should be/are: > > http://llvm.org/perf/db_default/v4/nts/recent_activity > > Shows all 3 of the lab.llvm.org machines that run LNT ( > http://lab.llvm.org:8011/buildslaves - you can see these 3 macminis > run "-nt" builder variations (-O3, -O3 vectorized, -O0 -g)) > >> >> On 2013-01-28, at 11:37 AM, David Blaikie wrote: >> >> They're just build bots running LNT - check the build bot configuration code >> in the zorg llvm project repository. You'll probably need to do some work to >> get a machine quiet enough to have reliable/useful performance results, >> though >> >> On Jan 28, 2013 8:33 AM, "Redmond, Paul" <paul.redmond at intel.com> wrote: >>> >>> Hi, >>> >>> What is involved in adding new perf machines? Are these machines separate >>> from the buildbots? >>> >>> paul >>> _______________________________________________ >>> LLVM Developers mailing list >>> LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu >>> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev >> >>