search for: naryreassoci

...015 at 4:45 PM Daniel Berlin <dberlin at dberlin.org> > wrote: > >> > >> Whoops, forgot llvmdev > >> > >> > >> On Mon, May 4, 2015 at 4:12 PM, Daniel Berlin <dberlin at dberlin.org> > wrote: > >> > So i started by looking at naryreassociate, whose pass > >> > description/reason listed for doing it is actually describes bug in > >> > reassociate, and discovered that, in fact, reassociate seems broken, > >> > and should be doing the right thing on most of your testcases. > >> > > &gt...

Whoops, forgot llvmdev On Mon, May 4, 2015 at 4:12 PM, Daniel Berlin <dberlin at dberlin.org> wrote: > So i started by looking at naryreassociate, whose pass > description/reason listed for doing it is actually describes bug in > reassociate, and discovered that, in fact, reassociate seems broken, > and should be doing the right thing on most of your testcases. > > Let's take nary-add.ll, left_reassociate > > ; RU...

...example to *x = a + b; *y = (a + b) + 2; Jingyue On Mon, May 4, 2015 at 4:45 PM Daniel Berlin <dberlin at dberlin.org> wrote: > Whoops, forgot llvmdev > > > On Mon, May 4, 2015 at 4:12 PM, Daniel Berlin <dberlin at dberlin.org> wrote: > > So i started by looking at naryreassociate, whose pass > > description/reason listed for doing it is actually describes bug in > > reassociate, and discovered that, in fact, reassociate seems broken, > > and should be doing the right thing on most of your testcases. > > > > Let's take nary-add.ll, left_r...

...> Jingyue > > On Mon, May 4, 2015 at 4:45 PM Daniel Berlin <dberlin at dberlin.org> wrote: >> >> Whoops, forgot llvmdev >> >> >> On Mon, May 4, 2015 at 4:12 PM, Daniel Berlin <dberlin at dberlin.org> wrote: >> > So i started by looking at naryreassociate, whose pass >> > description/reason listed for doing it is actually describes bug in >> > reassociate, and discovered that, in fact, reassociate seems broken, >> > and should be doing the right thing on most of your testcases. >> > >> > Let's take...

Hi, As you may have noticed, since last year, we (Google's CUDA compiler team) have contributed quite a lot to the effort of optimizing LLVM for CUDA programs. I think it's worthwhile to write some docs to wrap them up for two reasons. 1) Whoever wants to understand or work on these optimizations has some detailed docs instead of just source code to refer to. 2) RFC on how to improve

...on the > straight-line scalar optimizations. I will send out more docs on other > optimizations later. Please feel free to comment. > > Thanks, > Jingyue > > > Out of curiosity, is there any plan to make the NVPTX-originated passes > (separateconstantoffsetfromgep, slsr, naryreassociate) more generic? They > seem very specialized for the nVidia GPU addressing modes despite the > generic names, and in my tests tend to pessimize our target more often than > not for that reason. > > It’d be really nice to have something more generic, and I might look into > helpi...

On Wed, Aug 24, 2016 at 3:07 PM, Daniel Berlin <dberlin at dberlin.org> wrote: > > > On Fri, Aug 19, 2016 at 3:57 PM, Wei Mi via llvm-dev > <llvm-dev at lists.llvm.org> wrote: >> >> SCEV expansion sometimes generates redundent expr even if there is an >> available expr which can be reused. The redundent exprs can be a lot >> different from existing

...l (not just for scev expansion). From my current experience, a large part of expansion redundency uncleaned is caused by some weakness of reassociation, especially the problem mentioned in http://lists.llvm.org/pipermail/llvm-dev/2015-May/085406.html and problem related with multiple getelementptr. NaryReassociate solved some common problems but there are more. The paper mentioned in Pact08 may be worthy to try. By the way, to answer Andy's question. I did some experiment using the testcase in PR29065 to see if we regenerate SCEV for existing and expanded IR, whether it will be easier to check equiva...

...r' llvm[4]: Compiling X86AsmInstrumentation.cpp for Release+Asserts build llvm[3]: Compiling MergedLoadStoreMotion.cpp for Release+Asserts build llvm[3]: Compiling InstCombineSelect.cpp for Release+Asserts build llvm[3]: Compiling ErlangGCPrinter.cpp for Release+Asserts build llvm[3]: Compiling NaryReassociate.cpp for Release+Asserts build llvm[4]: Compiling X86AsmParser.cpp for Release+Asserts build llvm[3]: Compiling OcamlGCPrinter.cpp for Release+Asserts build llvm[3]: Compiling InstCombineShifts.cpp for Release+Asserts build llvm[3]: Compiling PartiallyInlineLibCalls.cpp for Release+Asserts build...