[llvm-dev] Working on FP SCEV Analysis

[Mikhail Zolotukhin via llvm-dev]

> On May 19, 2016, at 7:03 AM, Demikhovsky, Elena via llvm-dev <llvm-dev at lists.llvm.org> wrote:
> 
> > 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 end goal is to handle case *A*.
The problem isn't that the code will be bad, but that it might be unused. SCEV is already quite big, and extending it even further for no (stated so far) reason sounds questionable.

Owen mentioned an important use case where float is just used because integers are not supported at all - we definitely should be able to handle such cases, but it looks like promotion to int is the only thing we need for it. I looked into a simple example:
#define T float
void foo(T *buf) {
  T i = 0;
#pragma clang loop vectorize(enable)
  for (i = 0; i < 1000; i += 1) {
    buf[(int)i] = i;
  }
}

and we vectorize it now. That said, the generated code for integers is much cleaner, but I don't think and has anything to do with the IV, as it's been successfully promoted to an integer IV.

So, as far as I understand, your intention is to handle loops with non-integer step/start/end value. Why can't we focus on promotable to integer cases, which can and should be handled even now (if not, we'd rather fix it)?

Thanks,
Michael

PS: My old intel email address isn't accessible any more, so you probably should remove it from your contacts.

>  
>  
> -           Elena
>  
>  <>From: anemet at apple.com <mailto:anemet at apple.com> [mailto:anemet at apple.com <mailto:anemet at apple.com>] 
> Sent: Thursday, May 19, 2016 07:43
> To: Sanjoy Das <sanjoy at playingwithpointers.com <mailto:sanjoy at playingwithpointers.com>>
> Cc: Demikhovsky, Elena <elena.demikhovsky at intel.com <mailto:elena.demikhovsky at intel.com>>; Saito, Hideki <hideki.saito at intel.com <mailto:hideki.saito at intel.com>>; llvm-dev <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>>; Andrew Trick <atrick at apple.com <mailto:atrick at apple.com>>
> Subject: Re: [llvm-dev] Working on FP SCEV Analysis
>  
>  
> On May 18, 2016, at 12:17 PM, Sanjoy Das via llvm-dev <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> wrote:
>  
> 
> 
> 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 relax IEEE
> semantics so this looks like normal algabra etc:
> 
> > for (float f = 0.01f; f < 1.0f; f += 0.01f) ç **A**
> 
> ...
> 
> > I'd rather see us cleverly turn it into:
> 
> > float f = 0.01f;
> 
> > for (int i = 1; i < 100; i += 1, f += 0.01f) ç **B**
> 
> I can later try to enhance IndVarSimplify::handleFloatingPointIV() in
> order to convert**A** to **B**.
> 
> But **B** is exactly the case I’m starting from. The main IV “i” is
> integer. The variable “f” is also considered as IV in this loop.
> 
> And this loop is not vectorized because “f” is floating point.
> 
> I don’t think that the case **B** is uncommon.
> 
> If B is the case we actually care about, I'd say changing SCEV to work with floating points is an overkill.  How would you expect an SCEVFAddExpr to help vectorize B, other than tell you what the initial value and the increment is (and these can be found with a simple value analysis)?
>  
> 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.
>  
> Then if we find other pressing cases to handle we can rethink the strategy.
>  
> Also the current diagnostics is pretty bad for Hideki’s testcase with TTT as float.  This is what we currently report with -Rpass-analysis=loop-vectorize:
>  
> /tmp/sss.c:3:6: remark: loop not vectorized: value that could not be
>       identified as reduction is used outside the loop
>       [-Rpass-analysis=loop-vectorize]
>  
> I have no clue why we say that the value is used outside the loop.  I think this should just say that we have a loop-variant value that we couldn’t identify either as an induction or as a reduction.
>  
> Adam
> 
> 
> 
> If we're interested in handling complex variants of A directly: computing trip counts, proving away predicates etc. without translating the loops to use integer IVs (perhaps because we can't legally do so), then I can see FP-SCEV as a reasonable implementation strategy, but it looks like the general consensus is that such cases are rare and generally not worth optimizing?
> 
> -- Sanjoy
> 
> 
> 
> -*/Elena/*
> 
> ---------------------------------------------------------------------
> Intel Israel (74) Limited
> 
> This e-mail and any attachments may contain confidential material for
> the sole use of the intended recipient(s). Any review or distribution
> by others is strictly prohibited. If you are not the intended
> recipient, please contact the sender and delete all copies.
> 
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev <http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev>
>  
> ---------------------------------------------------------------------
> Intel Israel (74) Limited
> 
> This e-mail and any attachments may contain confidential material for
> the sole use of the intended recipient(s). Any review or distribution
> by others is strictly prohibited. If you are not the intended
> recipient, please contact the sender and delete all copies.
> 
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev <http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160519/69313f45/attachment-0001.html>