search for: tripcount

...(l != NULL) { l->dump(); errs() << "BB:\t" << BB->getNameStr() << "\n" ; errs() << "Is simplifyed loop?\t" << l->isLoopSimplifyForm() << "\n" ; errs() << "Tripcount " << l->getSmallConstantTripCount() << "\n" ; const PHINode* phi = l->getCanonicalInductionVariable(); errs() << "Induction variable: " << *phi << "\n"; } } } When I feed it with this program...

...ralInfo pass as mentioned below. 2: Decouple DependenceInfo object from pass and create two passes. Same as above. 3: Create the interface PolyhedralInfo, which will extract Memory Access wise dependence information from Polly and provide few simple interfaces like isParallel(), isVectorizable(), tripCount(Loop&). Please feel free to post your comments and suggestions on this. [1] https://docs.google.com/document/d/1QyUzL3OOwJSI91lDqr7VsvqUsFyTY9FlpAwbGSipUtw/edit# [2] https://groups.google.com/forum/#!topic/polly-dev/DuRxNmKfEnM Regards, Utpal Bora Ph.D. Scholar Computer Science & Engin...

...Threshold = OptSizeUnrollThreshold; As a result, the OptimizeForSize attribute is ignored when the pass calculating the reduced count, which is not I expected. Am i correct or i missed something? If i am correct, i am going to fix this. best regards ether ps: the code contains typo if (TripCount) { // Reduce unroll count to be modulo of TripCount for partial unrolling Count = CurrentThreshold / LoopSize; <--------------------------should use Threshold while (Count != 0 && TripCount%Count != 0) Count--; } else if (UnrollRuntime) {...

...http://reviews.llvm.org/D21124. The patch basically creates groups of references that would lie in the same cache line. Each group is then analysed with respect to innermost loops considering cache lines. Penalty for the reference is: a. 1, if the reference is invariant with the innermost loop, b. TripCount for non-unit stride access, c. TripCount / CacheLineSize for a unit-stride access. Loop Cost is then calculated as the sum of the reference penalties times the product of the loop bounds of the outer loops. This loop cost can then be used as a profitability measure for cache reuse related optimizat...

...ptimizer has no idea how to use this interface. If you just call this interface to disable unrolling, that would be overkill on some arch which has HW support, as on such arch HW-loop and unrolling are orthogonal. - hasLoopZeroCostTopology(Loop *L, unsigend TripCount) Why trip-count? It can be derived from the loop itself. Which optimizer will call this interface? I would suggest following interface: /// get unrolling factor of given *INNERMOST* loop from HW's perspective. /// Note: this interface is for innermost loop only. Gett...

...opt -indvars | opt -analyze -scalar-evolution" which led me to add the forgetLoop here. Ah, I tried the testcase, saw the crash, and assumed that was the bug you were aiming to fix. The forgetLoop() call shouldn't be necessary for correctness. But I do see how ScalarEvolution's cached tripcounts are sub-optimal in this case, because they retain the type of the loop's original induction variable, rather than the type that indvars has chosen for the new induction variable. So forgetLoop() makes sense there. Dan

.... > > The patch basically creates groups of references that would lie in the > same cache line. Each group is then analysed with respect to innermost > loops considering cache lines. Penalty for the reference is: > a. 1, if the reference is invariant with the innermost loop, > b. TripCount for non-unit stride access, > c. TripCount / CacheLineSize for a unit-stride access. > Loop Cost is then calculated as the sum of the reference penalties times > the product of the loop bounds of the outer loops. This loop cost can then > be used as a profitability measure for cache reu...

Thank you for your answer! I tested your example, yes, perhaps I should preserve some kind of tree to parse this start and end expressions for induction variable... I was surprised, that SCEV cannot compute the tripcount here. I thought, that all linear and maybe expressions with multiplication are suitable for analysis. 2017-08-10 19:30 GMT+02:00 Sanjoy Das <sanjoy at google.com>: > Hi Anastasiya, > > If you're looking for the exit value of a PHI node, please take a look > at what IndVarSim...

...mpler. I think we are going off-topic. I'm not proposing new llvm instructions to introduce hw loop semantics. What I'd like to do is to find a good interface between the loop unroller and targets to prevent loop unrolling. hasZeroCostLoop() and hasLoopZeroCostTopology(Loop *L, unsigend TripCount) has been proposed so far. Ivan > > Thanks > Shuxin > > On 11/22/2012 02:56 PM, Gang Yu wrote: >> Hi shuxin, >> >> Promote while-loop to do-loop is the job of loop induction >> recognized, not this transformation. The scalar transform for hwloop >> i...

hi, The loopinfo pass failed to recognize the Tripcount of a simple program constructed by me, can you help me to figure out why this happened? Thanks. The C program and corresponding .ll files are shown below. I used llvm1.7 to develop my own pass, and want to use the loop information. -Wei Test.c: #include "stdio.h" #define N 40 void...

On 19 January 2011 13:01, Dan Gohman <gohman at apple.com> wrote: > > On Jan 18, 2011, at 12:32 AM, Nick Lewycky wrote: > > > Hi, > > > > I tracked down a bug in indvars where we weren't updating SCEV properly. > The attached patch shows the fix to this bug with a testcase, but it also > causes five new test failures. > > Indvars isn't

...So, the hot part looks like this: for(y = 0..height) { for (x = 0..width) { val = 0 for (j = 0..5) { for (i = 0..5) { val += img[x+i,y+j] * weight[i,j] } } } } And ‘weight' is just a constant matrix with some coefficients. If we unroll the two internal loops (with tripcount 5), then we can replace weight[i,j] with concrete constant values. In this particular case, many of the coefficients are actually 0 or 1, which enables huge code simplifications later on. But currently we unroll only the innermost one, because unrolling both of them will exceed the threshold. When...

Hi, Gang: I don't want to discuss Open64 internal in LLVM mailing list. Let us only focus on the design per se. As your this mail and your previous mail combined give me a impression that : The only reason you introduce the specific operator for HW loop in Scalar Opt simply because you have hard time in figure out the trip count in CodeGen. This might be true for Open64's

...memcpy optimization for such cases, and found that LLVM LoopVectorizer successfully vectorizes and unrolls the inner loop. However, in order to take the fast path (vmovups) it must copy at least 32 ints, where as in this case we only do an 8int copy. ** Upon closer look, LoopVectorizer obtains the TripCount for the innerloop using getSmallConstantTripCount(Loop,...). This value is 0 for the loop with unknown trip count. Loop unrolling is disabled when TC > 0. Should this be changed to TC >= 0 (which does the job for this testcase)? Or is there a better way to disable loop unrolling for such triv...

Hi All, I am trying to unroll the below loop, but couldn't as SCEV returns TripCount as 0. void foo(int x) { int p, i = 1; int mat[6][6][6]; for (p = x+3 ; p<= x+6 ;p++) mat[x][p][i] = mat[x][p][i] + 5; } For a quick reference I have added the generated IR compiled with clang using -O3. Please let me know if this is an known issue in SCEV or I am missing something he...

...<sabre at nondot.org> To: "LLVM Developers Mailing List" <llvmdev at cs.uiuc.edu> Sent: Thursday, June 15, 2006 3:35 PM Subject: Re: [LLVMdev] problem with loopinfo > On Thu, 15 Jun 2006, Wei Jiang wrote: >> hi, >> The loopinfo pass failed to recognize the Tripcount of a simple >> program constructed by me, can you help me to figure out why this >> happened? Thanks. >> The C program and corresponding .ll files are shown below. I used >> llvm1.7 to develop my own pass, and want to use the loop information. > > What passes are...

On Thu, 15 Jun 2006, Wei Jiang wrote: > hi, > The loopinfo pass failed to recognize the Tripcount of a simple program constructed by me, can you help me to figure out why this happened? Thanks. > The C program and corresponding .ll files are shown below. I used llvm1.7 to develop my own pass, and want to use the loop information. What passes are you running before your pass? trip count...

...patch basically creates groups of references that would lie in the >> same cache line. Each group is then analysed with respect to innermost >> loops considering cache lines. Penalty for the reference is: >> a. 1, if the reference is invariant with the innermost loop, >> b. TripCount for non-unit stride access, >> c. TripCount / CacheLineSize for a unit-stride access. >> Loop Cost is then calculated as the sum of the reference penalties times >> the product of the loop bounds of the outer loops. This loop cost can then >> be used as a profitability measu...

...alues of the variables within the loop can't have been changed by this? I expected to find such a property based on my understanding of indvars, but when I looked through the code I couldn't convince myself of it. Can you make such an argument? But I do see how ScalarEvolution's cached tripcounts > are sub-optimal in this case, because they retain the type of the loop's > original induction variable, rather than the type that indvars has > chosen for the new induction variable. So forgetLoop() makes sense > there. > That's what I expected, and what I see in the test...

...pInstruction and > FoldBlockIntoPredecessor support functions there. > > Additionally, I've also moved the loop unrolling statistics into the > Utils file. Is > that a good idea? > > I've added two new methods to Loop (or LoopBase<> really): > getSmallConstantTripCount() and getSmallConstantTripMultiple(), > which return > the trip count and multiple as a normal unsigned value. > > There are a number of remaining issues, though. Firstly, I observe > some code > duplication. Every pass that performs loop unrolling, should depend > on the...