On 1 July 2015 at 21:22, Frank Winter <fwinter at jlab.org> wrote:> there were two follow-up emails.I only got one... weird...> The issue is solved. The SLP vectorizer has > a magic number built into the code which determines the max. vector length > to search for. That was set to 128 bits. Increasing it to 256 bits solved > the issue.That looks like a simple fix. Is it upstream yet? :)> For inconsistency reasons it must be '--debug-only=SLP' and the output can > be found in one of the follow-up emails.Of course. Maybe we should mean "vectorize" as all of them? Anyway, that's unrelated. cheers, --renato
On 07/01/2015 04:29 PM, Renato Golin wrote:> On 1 July 2015 at 21:22, Frank Winter <fwinter at jlab.org> wrote: >> there were two follow-up emails. > I only got one... weird... > > >> The issue is solved. The SLP vectorizer has >> a magic number built into the code which determines the max. vector length >> to search for. That was set to 128 bits. Increasing it to 256 bits solved >> the issue. > That looks like a simple fix. Is it upstream yet? :)That's not up to me. There were concerns raised about an increased compile time. https://llvm.org/bugs/show_bug.cgi?id=17170#c8 Frank> > >> For inconsistency reasons it must be '--debug-only=SLP' and the output can >> be found in one of the follow-up emails. > Of course. Maybe we should mean "vectorize" as all of them? Anyway, > that's unrelated. > > cheers, > --renato
----- Original Message -----> From: "Renato Golin" <renato.golin at linaro.org> > To: "Frank Winter" <fwinter at jlab.org> > Cc: "LLVM Dev" <llvmdev at cs.uiuc.edu> > Sent: Wednesday, July 1, 2015 3:29:25 PM > Subject: Re: [LLVMdev] SLP vectorizer on AVX feature > > On 1 July 2015 at 21:22, Frank Winter <fwinter at jlab.org> wrote: > > there were two follow-up emails. > > I only got one... weird... > > > > The issue is solved. The SLP vectorizer has > > a magic number built into the code which determines the max. vector > > length > > to search for. That was set to 128 bits. Increasing it to 256 bits > > solved > > the issue. > > That looks like a simple fix. Is it upstream yet? :)The main concern here, as noted in the bug report, is compile-time cost. We need to characterize that. -Hal> > > > For inconsistency reasons it must be '--debug-only=SLP' and the > > output can > > be found in one of the follow-up emails. > > Of course. Maybe we should mean "vectorize" as all of them? Anyway, > that's unrelated. > > cheers, > --renato > _______________________________________________ > LLVM Developers mailing list > LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev >-- Hal Finkel Assistant Computational Scientist Leadership Computing Facility Argonne National Laboratory
----- Original Message -----> From: "Frank Winter" <fwinter at jlab.org> > To: "Renato Golin" <renato.golin at linaro.org> > Cc: "LLVM Dev" <llvmdev at cs.uiuc.edu> > Sent: Wednesday, July 1, 2015 3:33:18 PM > Subject: Re: [LLVMdev] SLP vectorizer on AVX feature > > On 07/01/2015 04:29 PM, Renato Golin wrote: > > On 1 July 2015 at 21:22, Frank Winter <fwinter at jlab.org> wrote: > >> there were two follow-up emails. > > I only got one... weird... > > > > > >> The issue is solved. The SLP vectorizer has > >> a magic number built into the code which determines the max. > >> vector length > >> to search for. That was set to 128 bits. Increasing it to 256 bits > >> solved > >> the issue. > > That looks like a simple fix. Is it upstream yet? :) > > That's not up to me. There were concerns raised about an increased > compile time. > https://llvm.org/bugs/show_bug.cgi?id=17170#c8The first step, likely, is to transform this bound into a command-line option for ease of benchmarking. I think that a patch that does that (along with a test case) would be nice. -Hal> > Frank > > > > > > >> For inconsistency reasons it must be '--debug-only=SLP' and the > >> output can > >> be found in one of the follow-up emails. > > Of course. Maybe we should mean "vectorize" as all of them? Anyway, > > that's unrelated. > > > > cheers, > > --renato > > > _______________________________________________ > LLVM Developers mailing list > LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev >-- Hal Finkel Assistant Computational Scientist Leadership Computing Facility Argonne National Laboratory