similar to: persuading licm to do the right thing

On some targets with limited addressing modes, getting that 64-bit relocatable but loop-invariant value into a register requires several instructions. I'd like those several instruction outside the loop, where they belong. Yes, my experience is that something (I assume instcombine) recanonicalizes. Thanks, Preston On Tue, Dec 8, 2015 at 11:21 PM, Mehdi Amini <mehdi.amini at

I'm trying to make the IR "better", in a machine-independent fashion, without having to do any lowering. I've written code that rewrites GEPs as simple adds and multiplies, which helps a lot, but there's still some sort of re-canonicalization that's getting in my way. Is there perhaps a way to suppress it? Thanks, Preston On Wed, Dec 9, 2015 at 7:47 AM, Mehdi Amini

I suppose your view is reasonable, and perhaps common. My own "taste" has always preferred machine-independent code that is as simple as possible, so GEPs reduced to nothing more than an add, etc, i.e., quite risc-like. Then optimize it to reduce the total number of operations (as best we can), then raise the level during instruction selection, taking advantage of available instructions.

A GEP can represent a potentially large tree of instructions. Seems like all the sub-trees are hidden from optimization; that is, I never see licm or value numbering doing anything with them. If I rewrite the GEPs as lots of little adds and multiplies, then opt will do a better job (I speculate this happens during lowering). One of the computations that's hidden in the GEP in my example is

I understand that GEPs do not access memory. They do a (possibly expensive) address calculation, perhaps adding a few values to a label and leaving the result in a register. Getting a label into a register is (to me) just like loading a 64-bit integer value into a register. It can happen in many places and it can cost a few instructions and several bytes. I'd like to see such things commoned

Hi I have this program in which fooBuf can only take on NULL or the address of local_fooBuf, and fooBuf and local_fooBuf have scope of the foo function. Therefore there is no way for the fooPtr argument to alias with fooBuf. However, LLVM basicaa and globalsmodref-aa say the 2 pointers may alias. I am thinking whether i should implement a limited form of point-to alias on the fooBuf pointer in

Hi the appended IR code does not optimize to my liking :) this is the interesting part in x86_64, that got produced via clang -Os: --- movq -16(%r12), %rax movl -4(%rax), %ecx andl $2298949, %ecx ## imm = 0x231445 cmpq $2298949, (%rax,%rcx) ## imm = 0x231445 leaq 8(%rax,%rcx), %rax cmovneq %r15, %rax movl $2298949, %esi ## imm = 0x231445 movq %r12, %rdi movq %r14,

Hello Has there been any progress on this topic ? The 3.9 optimizer output is still the same as I just looked. https://llvm.org/bugs/show_bug.cgi?id=24448 Ciao Nat! Sanjay Patel schrieb: > [cc'ing Zia] > > We have this transform with -Os for some cases after: > http://reviews.llvm.org/rL244601 > http://reviews.llvm.org/D11363 > > but something in this example is

Here is original C code: void topup(int a[], unsigned long i) { for (; i < 16; i++) { a[i] = 1; } } Here is the IR before the pass where I expect SCEV to return trip-count value ; Function Attrs: nofree norecurse nounwind uwtable writeonly define dso_local void @topup(i32* nocapture %a, i64 %i) local_unnamed_addr #0 { entry: %cmp3 = icmp ult i64 %i, 16 br i1

----- Original Message ----- > From: "Hal Finkel" <hfinkel at anl.gov> > To: "Chandler Carruth" <chandlerc at google.com> > Cc: llvmdev at cs.uiuc.edu > Sent: Thursday, July 16, 2015 1:58:02 AM > Subject: Re: [LLVMdev] Improving loop vectorizer support for loops > with a volatile iteration variable > ----- Original Message ----- > >

Hi Gerolf, I think we have several (perhaps separable) issues here: 1. Do we have a canonical form for loops, preserved through the optimizer, that allows naturally-constructed loop nests to remain separable? 2. Do we forbid non-lowering transformations that turn vectorizable loops into non-vectorizable loops? 3. How do we detect cases where transformations cause a negative answer to either

Hello, I am first time paying with SCEV codebase. I am trying to find out why ScalarEvolution is not able to give correct back edge taken count for an expression. So in my case flow reaches to howFarToZero() and in that function, I have following expressions as SCEV Start = (15 + (-1 * %i) (which is set to Distance SCEV) Step = 1 now, first of all, should I expect Start as ConstantSCEV (15)

Hi all, I have investigated the 6X extra compile-time overhead when Polly compiles the simple nestedloop benchmark in LLVM-testsuite. (http://188.40.87.11:8000/db_default/v4/nts/31?compare_to=28&baseline=28). Preliminary results show that such compile-time overhead is resulted by the complicated polly-dependence analysis. However, the key seems to be the polly-prepare pass, which introduces

Hi, I've prepared patches for both LLVM and Clang to change the datalayout for R600. This may seem like a bold move, but I think it is warranted. R600/SI is a strange architecture in that it uses 64bit pointers but does not support 64 bit arithmetic except for load/store operations that roughly map onto getelementptr. The current datalayout for r600 includes n32:64, which is odd

On Wed, Sep 2, 2015 at 5:36 AM, James Molloy <james at jamesmolloy.co.uk> wrote: > Hi, > > Coremark really isn't a good enough test - have you run the LLVM test suite > with this patch, and what were the performance differences? For the test suite single source benches, the 235 tests improved performance, 2 regressed and 705 were unchanged. That seems very optimistic.

Hi, When I write various test cases and explore how they're handled by the code in LoopDependenceAnalysis::analysePair, I'm surprised. This loop collects pairs of subscripts from the source and destination refs. * // Collect GEP operand pairs (FIXME: use GetGEPOperands from BasicAA), adding* * // trailing zeroes to the smaller GEP, if needed.* * GEPOpdsTy destOpds, srcOpds;* *

----- Original Message ----- > From: "Chandler Carruth" <chandlerc at google.com> > To: "Hal Finkel" <hfinkel at anl.gov> > Cc: "Hyojin Sung" <hsung at us.ibm.com>, llvmdev at cs.uiuc.edu > Sent: Thursday, July 16, 2015 1:06:03 AM > Subject: Re: [LLVMdev] Improving loop vectorizer support for loops > with a volatile iteration

Hi, InstCombine canonicalizes index operands (unless they are into struct types) to pointer size. The comment says: "If we are using a wider index than needed for this platform, shrink it to what we need. If narrower, sign-extend it to what we need. This explicit cast can make subsequent optimizations more obvious.". For our architecture, the canonicalization is a bit

----- Original Message ----- > From: "Chandler Carruth" <chandlerc at google.com> > To: "Hyojin Sung" <hsung at us.ibm.com>, llvmdev at cs.uiuc.edu > Sent: Wednesday, July 15, 2015 7:34:54 PM > Subject: Re: [LLVMdev] Improving loop vectorizer support for loops > with a volatile iteration variable > On Wed, Jul 15, 2015 at 12:55 PM Hyojin Sung

On Fri, Mar 31, 2017 at 10:23 AM, Sanjoy Das <sanjoy at playingwithpointers.com > wrote: > Hi Piotr, > > On March 31, 2017 at 9:07:42 AM, Piotr Padlewski > (piotr.padlewski at gmail.com) wrote: > > Hi all, > > I have a question about dereferenceable metadata on load instruction. I > > have a patch (https://reviews.llvm.org/D31539) for LICM that hoists >