similar to: Working on FP SCEV Analysis

> On May 16, 2016, at 5:35 PM, Hal Finkel via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > ----- Original Message ----- >> From: "Sanjoy Das via llvm-dev" <llvm-dev at lists.llvm.org> >> To: escha at apple.com >> Cc: "llvm-dev" <llvm-dev at lists.llvm.org>, "Michael V Zolotukhin" <michael.v.zolotukhin at

[+CC Andy] Hi Elena, I don't have any fundamental issues with teaching SCEV about floating point types, but given this will be a major change, I think a high level roadmap should be discussed on llvm-dev before we start reviewing and committing changes. Here are some issues that I think are worth discussing: - Core motivation: why do we even care about optimizing floating point

Hi Escha, via llvm-dev wrote: > One thought I’ve had about this in the past — > > SCEV is useful for proving two expressions are equivalent (in general, > not just specifically for loop induction variables). This gets a little > bit trickier with fast-math; for example, suppose two expressions are > equivalent, but *only* with reassociativity allowed? This isn't too

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

Adding support for FP inductions through isInductionPHI() is certainly possible, I have a relatively small local patch that does exactly that for simple fp add-recurrence cases, along with changes to the vectorizer to make it aware of FP inductions. It won't get give you the powerful reasoning capabilities of SCEV, but for the B-like cases it should work. Amara On 20 May 2016 at 19:31, Adam

Hi Hideki, I like this summary overall, thanks. More below. > On May 20, 2016, at 10:04 AM, Saito, Hideki <hideki.saito at intel.com> wrote: > > > To the best of my experience, handling case B (secondary induction) is must-have, and if I’m not mistaken, > people aren’t opposed to that. > > For me, handling case A (primary induction) is “why not?”, but I certainly

To the best of my experience, handling case B (secondary induction) is must-have, and if I’m not mistaken, people aren’t opposed to that. For me, handling case A (primary induction) is “why not?”, but I certainly admit that that can be very naïve thinking coming from lack of good understanding on SCEV and their proper usages. Now, let’s assume we can postpone discussion about case A. What is the

>What situations are they common in? ICC Vectorizer made a paradigm shift a while ago. If there aren’t a clear reason why something can’t be vectorized, we should try our best to vectorize. The rest is a performance modeling (and priority to implement) question, not a capability question. We believe this is a good paradigm to follow in a vectorizer development. It was a big departure from

> One option would be to extend InductionDescriptor::isInductionPHI in the vectorizer to directly analyze the PHIs without SCEV support as Sanjoy suggested. I *think* that that could be sufficient to handle case B. I implemented this with FP SCEV and the code looks very structured, including SCEVExpander. Extending the existing structures without implementing FP SCEV will be problematic. And

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

On Tue, May 17, 2016 at 8:49 PM Owen Anderson <resistor at mac.com> wrote: > > On May 16, 2016, at 2:42 PM, Sanjoy Das via llvm-dev < > llvm-dev at lists.llvm.org> wrote: > > - Core motivation: why do we even care about optimizing floating > point induction variables? What situations are they common in? Do > programmers _expect_ compilers to optimize them

Demikhovsky, Elena wrote: > > Even then, I'd personally want to see further evidence of why the > correct solution is to model the floating point IV in SCEV rather than > find a more powerful way of converting the IV to an integer that models > > the non-integer values taken on by the IV. As an example, if the use > case is the following code with appropriate flags to

Hi Fellows, The goal is to find the induction variable for a loop, where the induction variable increments with the multiplication, division or shift operations, like this one: sz = 8; do { ... ... sz = sz / 2; } while (sz) Is SCEV capable of detecting the induction variable 'sz' in this case? The code snippet I am using to solve the problem is for each basic-block in a

Hi Tobi, I would like to remove the SCEVRewriter code and replace it with a call to SCEVAddRec::apply (see attached a patch that adds just this function). More precisely I want to add another function called apply_map that applies a map (loop -> expr) on a given scev. This is the apply function on a multi-variate polynomial. So here is an overview of how I would like the scev code generator

I would like to nominate Sanjoy Das as code owner of Scalar Evolution and Induction Variable Simplification. Scalar Evolution has never had an official code owner, but does regularly need in depth review. Over the past year and a half, Sanjoy has made fantastic contributions to SCEV and has been responsive reviewing patches. He is clearly the authority at this point. Induction variable

Tobias Grosser wrote: > You create a map from the old_loop to a symbolic expression. What type would > this symbolic expression have? Would it be a SCEVExpr? evaluateAtIteration takes a scev, so apply will take a scev, or a map (loop->scev). You can always build a ScevUnknown from an SSA name and use that in the apply. > At the moment, we calculate at the beginning of each >

Hi all, I’ve most recently been grappling with a difficult to reproduce bug. I’ve traced the source of the difficulty in reproduction to the IVUsers analysis pass that is used by Loop Strength Reduction. Specifically, the IVUsers pass’s output is very sensitive to both the use list ordering of the instructions that it is looking at and the ordering of the Phi nodes in the header block of the loop

On Fri, Nov 30, 2012, at 08:46 PM, Sebastian Pop wrote: > Hi Tobi, > > I would like to remove the SCEVRewriter code and replace it with a call > to > SCEVAddRec::apply (see attached a patch that adds just this function). > More > precisely I want to add another function called apply_map that applies a > map > (loop -> expr) on a given scev. This is the apply

Thank you for your thoughts, Hal. More information below... On Sep 13, 2017, at 5:43 PM, Hal Finkel <hfinkel at anl.gov<mailto:hfinkel at anl.gov>> wrote: On 09/13/2017 01:01 PM, Daniel Neilson via llvm-dev wrote: … snip For example, the following IR will produce different sets of IV users if either: i) The order of the PHI nodes in the %loop block are reordered; or ii) The

----- Original Message ----- > From: "Andrew Trick via llvm-dev" <llvm-dev at lists.llvm.org> > To: "llvm-dev" <llvm-dev at lists.llvm.org> > Sent: Wednesday, May 25, 2016 6:17:54 PM > Subject: [llvm-dev] SCEV/IndVars Code Owner Nomination > > I would like to nominate Sanjoy Das as code owner of Scalar Evolution > and Induction Variable