similar to: Speculation and control dependent no wrap flags

On 2016-09-27 02:28, Philip Reames wrote: > On 09/20/2016 12:05 PM, Matti Niemenmaa via llvm-dev wrote: >> I posted some questions related to implementing inference of nsw/nuw >> flags based on known icmp results to Bug 30428 ( >> https://llvm.org/bugs/show_bug.cgi?id=30428 ) and it was recommended >> that I engage a wider audience by coming here. The minimal context is

One of the arguments for doing this earlier is inline cost perception of the original pattern. Reading i32/i64 by bytes look much more expensive than it is and can prevent inlining of interesting function. Inhibiting other optimizations concern can be addressed by careful selection of the pattern we’d like to match. I limit the transformation to the case when all the individual have no uses other

Hi, Can I ask what is the status of load widening. It seems there is no load widening on IR at all. // Paweł On Wed, Oct 5, 2016 at 1:49 PM Artur Pilipenko via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Philip and I talked about this is person. Given the fact that load > widening in presence of atomics is irreversible transformation we agreed > that we don't want to do

Ok, thanks. Are there any plans to reintroduce it on the IR level? I'm not confident this is strictly necessary, but in some cases not having load widening ends up really bad. Like in the case where vectorizer tries to do something about it: https://godbolt.org/z/60RuEw https://bugs.llvm.org/show_bug.cgi?id=42708 At the current state I'm forced to use memset() to express uint64 load from

If we do load combining at the IR level, one thing we'll need to give some thought to is atomicity.  Combining two atomic loads into a wider (legal) atomic load is not a reversible transformation given our current specification. I've been thinking about a concept I've been tentatively calling "element wise atomicity" which would make this a reversible transform by

> On 29 Sep 2016, at 03:23, Sanjoy Das <sanjoy at playingwithpointers.com> wrote: > > Hi Artur, > > Artur Pilipenko via llvm-dev wrote: > > One of the arguments for doing this earlier is inline cost > > perception of the original pattern. Reading i32/i64 by bytes look much > > more expensive than it is and can prevent inlining of interesting > >

Hello. This question has come up in https://reviews.llvm.org/D70043 There, i'm teaching ConstantRange how no-wrap flags affect the range of `mul` instruction, with end goal of exploiting this in LVI/CVP. There are certain combinations of ranges and no-wrap flags that result in always-overflowing `mul`. For example, `mul nuw nsw i4 [2,0), [4,0)` always overflows:

Hi, I'm trying to optimize a pattern like this into a single i16 load: %1 = bitcast i16* %pData to i8* %2 = load i8, i8* %1, align 1 %3 = zext i8 %2 to i16 %4 = shl nuw i16 %3, 8 %5 = getelementptr inbounds i8, i8* %1, i16 1 %6 = load i8, i8* %5, align 1 %7 = zext i8 %6 to i16 %8 = shl nuw nsw i16 %7, 0 %9 = or i16 %8, %4 I came across load combine pass which is motivated

> On 29 Sep 2016, at 21:01, Sanjoy Das <sanjoy at playingwithpointers.com> wrote: > > Hi Artur, > > Artur Pilipenko wrote: > > > BTW, do we really need to emit an atomic load if all the individual > > components are bytes? > > Depends -- do you mean at the at the hardware level or at the IR > level? > > If you mean at the IR level, then I

Hi all, This is about a project I've been prototyping on-and-off for a while that has finally reached a point where I can claim it to be "potentially viable". I'd like to gather some input from the community before moving too far ahead. # The problem There is a representation issue within SCEV that prevents it from fully using information from nsw/nuw flags present in the

Hi Sanjoy, Any update on this? Are there plans to implement this proposal? Thanks, Pankaj -----Original Message----- Date: Fri, 23 Sep 2016 02:09:19 -0700 From: Sanjoy Das via llvm-dev <llvm-dev at lists.llvm.org> To: llvm-dev <llvm-dev at lists.llvm.org>, Andrew Trick <atrick at apple.com>, Dan Gohman <dan433584 at gmail.com>, Hal Finkel <hfinkel at anl.gov>,

Yes, I'm running all the existing passes that I know how to run. I didn't know they returned change-made. Thanks! On Mon, Dec 21, 2015 at 12:36 PM, Artur Pilipenko < apilipenko at azulsystems.com> wrote: > Are you going to run some of the existing passes? Why can’t you just use > the returned change-made value from the passes? > > Artur > > > On 20 Dec 2015, at

Hi, There are several optimizations where we try to load speculatively. There are also two similar functions to determine whether it's a safe transformation: * isSafeToLoadUnconditionally * isSafeToSpeculativelyExecute isSafeToLoadUnconditionally tries to take load alignment into account but fails to do this in some cases. It checks alignment for pointers derived from allocas and global

Masked load/store are overloaded intrinsics, the only generic type is the type of the value being loaded/stored. The signature of the intrinsic is generated based on this type. The type of the pointer argument is generated as a pointer to the return type with default addrspace. E.g.: declare <8 x i32> @llvm.masked.load.v8i32(<8 x i32>*, i32, <8 x i1>, <8 x i32>) The

On Sun, Feb 5, 2017 at 3:41 PM, Nuno Lopes <nunoplopes at sapo.pt> wrote: > Thanks for the answers! The plan makes sense to me. > > Regarding phis, what about diamonds, e.g.: > > > define i32 @f(i32 %x) { > br .., label %bb0, label %bb1 > bb0: > %cmp = icmp sge i32 %x, 0 ; x > 0 > br i1 %cmp, label %bb2, label %bb3 > bb1: > %x2 = add nsw

> On Aug 8, 2017, at 5:34 PM, Sanjoy Das <sanjoy at playingwithpointers.com> wrote: > > Hi Pankaj, > > IIRC there was pushback on this proposal so I did not proceed further. > Are you blocked on this? > > [+CC Andy, who I remember had some objections.] > > — Sanjoy Off the top of my head, my concern is that expression comparison is no longer constant time,

Hi Sanjay, Some time ago you implemented a sext(add_nsw(x, C)) --> add(sext(x), C_sext) transformation in X86ISelLowering https://reviews.llvm.org/D13757 Is there any reason why this transformation is limited to sexts and doesn’t support zexts? Thanks, Artur -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi, On 13 Jul 2015, at 15:59, Hal Finkel <hfinkel at anl.gov<mailto:hfinkel at anl.gov>> wrote: ----- Original Message ----- From: "Artur Pilipenko" <apilipenko at azulsystems.com<mailto:apilipenko at azulsystems.com>> To: llvmdev at cs.uiuc.edu<mailto:llvmdev at cs.uiuc.edu> Cc: "Hal Finkel" <hfinkel at anl.gov<mailto:hfinkel at

I agree. There’s implementation-defined behavior on the conversion of (arg*58) to int, but that shouldn’t be at issue here. The transform of (float)x + 1 => (float)(x + 1) is bogus. > On Mar 20, 2017, at 10:41 AM, Sanjay Patel via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Looks broken to me; I don't think there's UB in the original program. > > The fold in

Hi, Is it intentional that LazyValueInfo.getPredicateAt doesn't solve for the value and only takes assumptions into account? getPredicateAt gets lattice value from cache using getValueAt call: LVILatticeVal LazyValueInfoCache::getValueAt(Value *V, Instruction *CxtI) { ... LVILatticeVal Result; mergeAssumeBlockValueConstantRange(V, Result, CxtI); ... return Result; } Other