similar to: Fwd: Strength reduction in loops

Hi Raghavan, I concur no specific docs. What do you want to know specifically? Cheers, -Quentin > On Jul 5, 2017, at 11:16 PM, Madhur Amilkanthwar via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > AFAIK, no official doc. > You can probably get better help if you ask specific questions (which part of the code you don't understand). > > On Thu, Jul 6, 2017 at 9:53

Hi, Sorry I took a long time to reply as it took me some time to get some understanding of the code even to ask some specific questions (I have a test case in which LSR does not kick in and wanted to understand the code to figure out why it was not kicking in). Here are some specific questions I have: 1) It appears that LSR works only for the inner-most loop. Is this correct? Can you tell

Dear Momchil, Thanks a lot for your prompt reply and kindly suggestion. The code will truly lead to some automatic unrolling with GCC and increase the number of operations in the assembly code. However, I am focus on the the IR optimization and the calculation of the array element offest, which may need multiplication if the IR instruction GEP is lowered to arithmetic operations. The

I am attempting to implement a minor loop strength reduction optimization for targets that support compare and jump fusion, specifically TTI::canMacroFuseCmp(). My approach might be wrong; however, I am soliciting the idea for feedback, so that I can implement this correctly. My plan is to add a Supplemental LSR formula to LoopStrengthReduce.cpp that optimizes the following case, but perhaps

> cmpq %rbx, %r14 > jne .LBB0_1 > > LLVM can perform compare-jump fusion, it already does in certain cases, but > not in the case above. We can remove the cmp above if we were to perform > the following transformation: Do you mean branch-fusion (https://en.wikichip.org/wiki/macro-operation_fusion)? Is there any more limitation why these two or not fused? > -----Original

Hi, My name is Venugopal Raghavan and I work in AMD. I was trying to understand the code in the file LoopStrengthReduce.cpp but I am making very slow progress. Is there any additional documentation available that would help me understand the code, like a PPT presentation or a design document or maybe a paper? I did not find anything on the Internet. There are comments interspersed in the code

Chris Lattner wrote: > On Mon, 21 Feb 2005, Jeff Cohen wrote: > >> Sorry, I thought I was running selection dag isel but I screwed up >> when trying out the really big array. You're right, it does clean it >> up except for the multiplication. >> >> So LoopStrengthReduce is not ready for prime time and doesn't >> actually get used? > >

Hi Andrew, The issue below refers to LSR, so I'll appreciate your feedback. It also refers to instruction combining and might impact backends other than X86, so if you know of others that might be interested you are more than welcome to add them. Thanks, Anat _____________________________________________ From: Shemer, Anat Sent: Tuesday, February 18, 2014 15:07 To: 'llvmdev at

Dear all, Hi! Recently, I try to combine the passes SeparateConstOffsetFromGEP and LoopStrengthReduction to transform the multiplication in the lowered GEP IRs into addition. However, it seems LoopStrengthReduction is unable to remove all the multiplications for the element offset calculation. My test code is shown below and thanks a lot in advance for your time and suggestion!

This is related to an issue in loop strength reduction [1] that I've been trying to fix on and off for a while. [1] has a more detailed description of the issue and an example, but briefly put, I want LSR to consider formulae that have "Zext T" as base and/or scale registers, and to appropriately rate such formulae. My first attempt[2] at fixing this was buggy and had to be

Vikram S. Adve wrote: >> The only way to make preselection or lowermultidimrefs work is to >> duplication all of the knowledge of how the instruction selector will >> select the code (e.g. the advice about allowing constant indices to >> be grouped together). > > > This is why you need a separate, low-level optimization framework - > the kind you were

Hello, I was wondering if we had a way to strength reduce getelementptr today. For the following code: void func(float (&A)[132][140]) { > for (int i = 0; i < 132; ++i) > for (int j = 0; j < 140; ++j) > A[i][j] += 1; > } We will generate: (annotated with SCEV) define void @func([132 x [140 x float]]* nocapture dereferenceable(73920)) local_unnamed_addr #0 {

On Mon, 21 Feb 2005, Jeff Cohen wrote: >>> trying out the really big array. You're right, it does clean it up except >>> for the multiplication. >>> >>> So LoopStrengthReduce is not ready for prime time and doesn't actually get >>> used? >> >> >> I don't know what the status of it is. You could try it out, and see

On Mon, 21 Feb 2005, Jeff Cohen wrote: > Sorry, I thought I was running selection dag isel but I screwed up when > trying out the really big array. You're right, it does clean it up except > for the multiplication. > > So LoopStrengthReduce is not ready for prime time and doesn't actually get > used? I don't know what the status of it is. You could try it out,

+CC llvm-dev On Tue, May 8, 2018 at 2:34 AM, Gal Zohar <Gal.Zohar at ceva-dsp.com> wrote: > I noticed that SCEV, when trying to perform strength reduction, doesn’t use > the ability to prove an induction variable does not signed/unsigned wrap due > to infinite loops. > > Is there an easy way to use the isAddRecNeverPoison function when > determining if strength reduction

Here is the patch for the new Operator Strength Reduction optimization pass that I have written. The bulk of the code is in lib/Transforms/Scalar/OperatorStrengthReduce.cpp The optimization is based on the algorithm described within the paper that can be found here: http://portal.acm.org/citation.cfm?id=504709.504710 Keith D. Cooper , L. Taylor Simpson , Christopher A. Vick, Operator strength

Hi Geoff, Firstly, I think it will be great if you have a small reproducer of this issue (which I can make fail after re-applying D18001 to ToT). > I’ve run into what appears to be a bug in ScalarEvolution, but I’m not sure > if it is instead caused by me missing an implicit assumption between LSR and > SCEV. > > This issue is caused by the change D18001, which is an attempt to

Hi, I would like some help regarding the LSR pass. It seems that it likes to duplicate address calculations as in the case above, which is highly undesirable on my target. I wonder if there is any way to tell LSR to not duplicate the code in cases like this? Or could I perhaps run CSE after LSR again? What is the logic behind this transformation? It seems that a LSR pass should not insert a

Hi All, I've run into what appears to be a bug in ScalarEvolution, but I'm not sure if it is instead caused by me missing an implicit assumption between LSR and SCEV. This issue is caused by the change D18001 <http://reviews.llvm.org/D18001> , which is an attempt to increase SCEV-inserted instruction re-use by picking a more canonical insertion position in the case where a new

> Of course, and the point is that, for example, on x86_64, the zext here is free. I'm still trying to understand the problem... > > In the example you provided in your previous e-mail, we choose the solution: > > `GEP @Global, zext(V)` -> `GEP (@Global + zext VStart), {i64 0,+,1}` > `V` -> `trunc({i64 0,+,1}) + VStart` > > instead of the actually-better