search for: scevs

Hi, I was looking at some bugs to play with, and I started with http://llvm.org/bugs/show_bug.cgi?id=18606 As I commented there, a loop is unrolled and exhibit this pattern: %mul.1 = mul i32 %mul, %mul %mul.2 = mul i32 %mul.1, %mul.1 .... With an unroll factor of 32, the last multiply has 2^32 terms in its SCEV expression. (I mean I expect it would have those terms if I was patient

On 2/7/14, 10:24 AM, Andrew Trick wrote: > > On Feb 5, 2014, at 12:54 AM, Mehdi Amini <mehdi.amini at silkan.com > <mailto:mehdi.amini at silkan.com>> wrote: > >> Hi, >> >> I was looking at some bugs to play with, and I started with >> http://llvm.org/bugs/show_bug.cgi?id=18606 >> >> As I commented there, a loop is unrolled and exhibit

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

...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 equivalence suppose we have SCEV cse rules. The reassociated order of generated SCEVs seems more consistent. For C= A1 + A2 + B above, the SCEV corresponding to A1 + A2 has the same computation sequence with the SCEV corresponding to A (A1, A2 and A are all complex SCEV themselves). However, during expansion, the cost of searching existing IR, convert them to SCEV and see if they ar...

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>,

> 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,

...dedAccesses) pass by marking both of these passes as preserving the ScalarEvolution analysis. Unfortunately, when this change is made, LSR will generate different code. One of the root causes seems to be that SCEV will return different nsw/nuw flags for the same Value, depending on what order the SCEVs are computed, due to the fact that the SCEV object unique-ing doesn't take the nsw/nuw flags into account. Since LoopDataPrefetch computes SCEVs in a different order than LSR, the nsw/nuw flags seen by LSR will differ based on whether the SCEVs are preserved from LoopDataPrefetch. >> &gt...

...ccesses) pass by marking both of these passes as preserving the ScalarEvolution analysis. Unfortunately, when this change is made, LSR will generate different code. One of the root causes seems to be that SCEV will return different nsw/nuw flags for the same Value, depending on what order the SCEVs are computed, due to the fact that the SCEV object unique-ing doesn't take the nsw/nuw flags into account. Since LoopDataPrefetch computes SCEVs in a different order than LSR, the nsw/nuw flags seen by LSR will differ based on whether the SCEVs are preserved from LoopDataPrefetch. I belie...

...need the nsw/nuw info, vs. simply propagating the flags. Can those reductions in turn be pulled out of as some high level analysis? I think sign-extend elimination would need some serious thought. But the current situation with reducing truncations/extensions in SCEV is not good anyway. It defeats SCEVs canonical form—you can get different answers depending on the order of reductions. > > -Andy I can’t help to ask. Why not define a wrapping nsw instruction as UB, instead of “delayed UB” aka poison? I believe we have the notion of poison solely to ease the movement of instructions. In my ex...

Hi, I'm new to ScalarEvolution and wanted to explore its capabilities. I have following few questions: 1) How to compare SCEV expressions. I have a situation to compare two SCEV to find the min among them. Found an existing function(getMinFromExprs) in LoopAccessAnalysis which compares two SCEVs. getMinFromExprs function finds the diff between two SCEV's and then checks for the negative value to find the minimum. While checking the negative value it specifically look for SCEVConstant. Do we have anything to find the min in case of NON-SCEVConstant (with some additional information), i...

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 exprs so that existing cleanup passes cannot remove them. https://llvm.org/bugs/show_bug.cgi?id=24920 https://llvm.org/bugs/show_bug.cgi?id=24442 https://reviews.llvm.org/D12090 and https://reviews.llvm.org/D21313 already relieved the

Hi Geoff, On Wed, Aug 9, 2017 at 8:58 AM, Geoff Berry <gberry at codeaurora.org> wrote: > On 8/8/2017 8:38 PM, Sanjoy Das wrote: >> >> Hi, >> >> On Tue, Aug 8, 2017 at 12:58 PM, Friedman, Eli <efriedma at codeaurora.org> >> wrote: >>> >>> Oh, I see... yes, we do stupid things involving mutating NoWrap flags >>> after

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

> On Aug 14, 2017, at 7:35 AM, Geoff Berry <gberry at codeaurora.org> wrote: > > Hi Sanjoy, > > [adding Adam since I believe he added the original FIXME to preserve SCEV > in LoopDataPrefetch] For record, that wasn’t me. It was there from the beginning when Hal added the PPC-specific pass. Adam > > On 8/14/2017 1:36 AM, Sanjoy Das wrote: >> Hi Geoff,

...nted to explore its capabilities. > > I have following few questions: > > 1) How to compare SCEV expressions. > > I have a situation to compare two SCEV to find the min among them. > > Found an existing function(getMinFromExprs) in LoopAccessAnalysis > which compares two SCEVs. > > getMinFromExprs function finds the diff between two SCEV’s and then > checks for the negative value to find the minimum. > > While checking the negative value it specifically look for SCEVConstant. > > Do we have anything to find the min in case of NON-SCEVConstant (with...

...ybe Chris, Andy or Dan can chime in here), but I personally am in > the "make the cleanup passes smarter" camp. We can also try to make > SCEV expansion smarter -- not by putting more things in SCEVExpander > (it is already complex enough!), but by splitting out a dedicated > SCEVSimplifier that you invoke on code generated from SCEVExpander to > strength reduce it. SCEVSimplifier can then internally use routines > in SCEV, so that it is "as smart as" SCEV in most cases. > > — Sanjoy SCEV is super useful as an analysis without SCEVExpander. The only r...

My response to this patch is below, but adding a floating-point feature to SCEV should really be hashed out on the llvm-dev list first. I would like to get the attention of floating-point experts on the design review. I’d like to see a small design proposal justifying the feature and defending it’s soundness. My concern is that the approach may not be sound, but providing this core API would

...anted to explore its capabilities. > > I have following few questions: > > 1) How to compare SCEV expressions. > > I have a situation to compare two SCEV to find the min among them. > > Found an existing function(getMinFromExprs) in LoopAccessAnalysis which > compares two SCEVs. > > getMinFromExprs function finds the diff between two SCEV’s and then checks > for the negative value to find the minimum. > > While checking the negative value it specifically look for SCEVConstant. > > Do we have anything to find the min in case of NON-SCEVConstant (with s...

...lvm::Instruction. a2) SCEV must be in sync with IR. One way to sync them is to delete invalidate SCEV, and force SE to recompute based on most recent IR. SCEVUnknonw is invalidated if its corresponding llvm::Instruction is deleted. However, it dose not invalidate those SCEVs that depends on it as well. a3) SCEV is hierarchically structured. So, if a SCEVUnknown is invalidated, the compiler needs to figure out who depends on this invalidated SCEVUnknown, and invalidate them accordingly. To enforce the consistency between SCEV and IR, curren...

For reference, the case with a variable loop count is filed as PR27894: https://llvm.org/bugs/show_bug.cgi?id=27894 And the case with a constant loop count is filed as PR27899: https://llvm.org/bugs/show_bug.cgi?id=27899 On Thu, Jun 2, 2016 at 7:48 AM, Demikhovsky, Elena via llvm-dev < llvm-dev at lists.llvm.org> wrote: > I implemented IV simplification with FP SCEV and uploaded a new