similar to: [LLVMdev] SCEV cannot derive number of loop iterations

[+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

Andy, et al., If I start with C code like this: void foo(long k, int * restrict a, int * restrict b, int * restrict c) { if (k > 0) { for (int i = 0; i < 2047; i++) { a[i] = a[i + k] + b[i] * c[i]; } } } Clang -O3 will produce code like this: entry: %cmp = icmp sgt i64 %k, 0 br i1 %cmp, label %for.body.preheader, label %if.end for.body.preheader: br label

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 > a SCEV is created. (grep for setNoWrapFlags in ScalarEvolution.cpp.) That's really a compile time hack -- we defer some expensive tricks to prove nsw/nuw on an add recurrences to when we've been asked to

----- Original Message ----- > > On Oct 31, 2013, at 1:24 PM, Hal Finkel <hfinkel at anl.gov> wrote: > > > Andy, et al., > > > > If I start with C code like this: > > > > void foo(long k, int * restrict a, int * restrict b, int * restrict > > c) { > > if (k > 0) { > > for (int i = 0; i < 2047; i++) { > > a[i] =

On Oct 31, 2013, at 1:24 PM, Hal Finkel <hfinkel at anl.gov> wrote: > Andy, et al., > > If I start with C code like this: > > void foo(long k, int * restrict a, int * restrict b, int * restrict c) { > if (k > 0) { > for (int i = 0; i < 2047; i++) { > a[i] = a[i + k] + b[i] * c[i]; > } > } > } > > Clang -O3 will produce code like

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 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,

Thanks for the feedback, Sanjoy. > SCEV is fairly conservative around PHI nodes that aren't recurrences and aren't obviously equivalent to a min-max branch-phi idiom. Is that the limitation you're running into here? Yes, that's exactly the problem. The problematic PHI nodes (%bc.resume.val and %bc.resume.val1) aren't either recurrences or related to min-max idioms. I

On 8/8/2017 1:37 PM, Friedman, Eli wrote: > On 8/8/2017 10:22 AM, Geoff Berry via llvm-dev wrote: >> Hi all, >> >> I'm looking into resolving a FIXME in the LoopDataPrefetch (and FalkorMarkStridedAccesses) 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

Hello, I assumed SCEV purpose was to be a normal form, but then I wondered which one of those is the normal form: (zext i16 (trunc i32 %a to i16) to i32) vs (-((%a /u 65536) *u 65536) + %a) The first one is nice for interval analysis, and known bit analysis. The second one is nice when plugged into gep of 2d arrays. -- *Alexandre Isoard* -------------- next part -------------- An HTML

Note that there is a slight difficulty due to the fact that we "sink" the trunc: (zext i16 {0,+,1}<%bb> to i32) + (65536 * ({0,+,1}<nuw><%bb> /u 65536) Here the recurrence lost it's <nuw> and got reduced to a i16 (on the left), but not on the right. But we can prove: - that (zext i16 {0,+,1}<%bb> to i32) has the same 16 LSB than (i32

Is there a document describing the guts of SCEV anywhere? I have a simple question. When looking at a linear SCEVAddRecExpr with a constant step recurrence (that is, getStepRecurrence returns SCEVConstant), is the constant in terms of bytes or in terms of "index," in that the byte offset is calculated by taking the step and multiplying it by the data size of any memory operation its

Hi Sanjoy, thanks for your thoughts on this. On Sat, Jun 27, 2015 at 12:16 AM, Sanjoy Das <sanjoy at playingwithpointers.com > wrote: > > First of all, going by the "poison causes UB only when observed", SCEV > does not do the right thing currently: [...] > > That seems like a bug? There's also bug 23527 for GEP. Sounds like there might be more such bugs. One

Hi, > Is there a document describing the guts of SCEV anywhere? If you're looking for theoretical background of SCEV (chains of recurrences algebra), you may take a look at this article: http://citeseer.ist.psu.edu/vanengelen00symbolic.html I'm not aware of any LLVM-specific document describing SCEV. > I have a simple question. When looking at a linear SCEVAddRecExpr > with a

On Tue, Sep 18, 2012 at 10:59 PM, Andrew Trick <atrick at apple.com> wrote: > > On Sep 18, 2012, at 8:21 PM, Preston Briggs <preston.briggs at gmail.com> > wrote: > > Given the following SCEV, > > *(sext i32 {2,+,1}<nw><%for.body> to i64)* > > > from the following C source, > > *void strong3(int *A, int *B, int n) {* > * for (int i =

Given the following SCEV, *(sext i32 {2,+,1}<nw><%for.body> to i64)* from the following C source, *void strong3(int *A, int *B, int n) {* * for (int i = 0; i < n; i++) {* * A[i + 2] = i;* * ...* * }* *}* Since the No-Wrap flag is set on the addrec, can't I safely rewrite it as *{2,+,1}<nw><%for.body>* If I can, why isn't the SCEV package

Hello Everyone, I want to raise a discussion about reasonability of late setting of nsw/nuw/nw flags to SCEV AddRecs through setNoWrapFlags method. A discussion about this have already happened in August last year, there was a concern about different no-wrap flags that come from different sequences of SCEV flags invocations. It was mentioned there that late setting of flags is actually a hack 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 Max, On Wed, Jan 24, 2018 at 10:03 PM, Maxim Kazantsev via llvm-dev <llvm-dev at lists.llvm.org> wrote: > I want to raise a discussion about reasonability of late setting of > nsw/nuw/nw flags to SCEV AddRecs through setNoWrapFlags method. A discussion > about this have already happened in August last year, there was a concern > about different no-wrap flags that come from

On Sep 19, 2012, at 2:18 PM, Preston Briggs <preston.briggs at gmail.com> wrote: > On Tue, Sep 18, 2012 at 10:59 PM, Andrew Trick <atrick at apple.com> wrote: > > On Sep 18, 2012, at 8:21 PM, Preston Briggs <preston.briggs at gmail.com> wrote: > >> Given the following SCEV, >> >> (sext i32 {2,+,1}<nw><%for.body> to i64) >>