[llvm-dev] loop unrolling introduces conditional branch

Marcello Maggioni via llvm-dev llvm-dev at lists.llvm.org
Sat Aug 22 09:09:31 PDT 2015


If you do -print-after-all you can see after which pass the IRs start to diverge.

Then I guess you can debug that pass and why it is doing the transformation differently or why it is not doing it at all

Marcello

Sent from my iPhone

> On Aug 22, 2015, at 8:53 AM, Xiangyang Guo via llvm-dev <llvm-dev at lists.llvm.org> wrote:
> 
> Actually, My code to generate the IR is really simple. I attach the code here for reference. 
> 
> I appreciate it if you can give me any suggestion about this loop-unrolling thing.
> 
> Regards,
> 
> Xiangyang
> 
>> On Sat, Aug 22, 2015 at 11:36 AM, Mehdi Amini <mehdi.amini at apple.com> wrote:
>> 
>>> On Aug 22, 2015, at 7:27 AM, Xiangyang Guo <xguo6 at ncsu.edu> wrote:
>>> 
>>> Hi, Mehdi,
>>> 
>>> For example, I have this very simple source code:
>>> void foo( int n, int array_x[])
>>> {
>>>     for (int i=0; i < n; i++)
>>> 	    array_x[i] = i; 
>>> }
>>> 
>>> After I use "clang -emit-llvm -o bc_from_clang.bc -c try.cc", I get bc_from_clang.bc. With my code (using LLVM IRbuilder API), I get bc_from_api.bc. Attachment please find thse two files. I also past the IR here.
>>> ******************************** Clang Generate IR Start ***********************************************************
>>> ; ModuleID = 'bc_from_clang.bc'
>>> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>>> target triple = "x86_64-unknown-linux-gnu"
>>> 
>>> ; Function Attrs: nounwind uwtable
>>> define void @_Z3fooiPi(i32 %n, i32* %array_x) #0 {
>>>   %1 = alloca i32, align 4
>>>   %2 = alloca i32*, align 8
>>>   %i = alloca i32, align 4
>>>   store i32 %n, i32* %1, align 4
>>>   store i32* %array_x, i32** %2, align 8
>>>   store i32 0, i32* %i, align 4
>>>   br label %3
>>> 
>>> ; <label>:3                                       ; preds = %13, %0
>>>   %4 = load i32, i32* %i, align 4
>>>   %5 = load i32, i32* %1, align 4
>>>   %6 = icmp slt i32 %4, %5
>>>   br i1 %6, label %7, label %16
>>> 
>>> ; <label>:7                                       ; preds = %3
>>>   %8 = load i32, i32* %i, align 4
>>>   %9 = load i32, i32* %i, align 4
>>>   %10 = sext i32 %9 to i64
>>>   %11 = load i32*, i32** %2, align 8
>>>   %12 = getelementptr inbounds i32, i32* %11, i64 %10
>>>   store i32 %8, i32* %12, align 4
>>>   br label %13
>>> 
>>> ; <label>:13                                      ; preds = %7
>>>   %14 = load i32, i32* %i, align 4
>>>   %15 = add nsw i32 %14, 1
>>>   store i32 %15, i32* %i, align 4
>>>   br label %3
>>> 
>>> ; <label>:16                                      ; preds = %3
>>>   ret void
>>> }
>>> 
>>> attributes #0 = { nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
>>> 
>>> !llvm.ident = !{!0}
>>> 
>>> !0 = !{!"clang version 3.8.0 (trunk 245730) (llvm/trunk 245727)"}
>>> 
>>> ******************************** Clang Generate IR End  ***********************************************************
>>> 
>>> ******************************** API Generate IR Start     ***********************************************************
>>> ; ModuleID = 'bc_from_api.bc'
>>> target triple = "x86_64-unkown-linux-gnu"
>>> 
>>> ; Function Attrs: nounwind
>>> define void @_Z3fooiPi(i32 %n, i32* %array_x) #0 {
>>> entry:
>>>   %n.addr = alloca i32, align 4
>>>   %array_x.addr = alloca i32*, align 8
>>>   %i = alloca i32, align 4
>>>   store i32 %n, i32* %n.addr, align 4
>>>   store i32* %array_x, i32** %array_x.addr, align 8
>>>   store i32 0, i32* %i, align 4
>>>   br label %for.cond
>>> 
>>> for.cond:                                         ; preds = %for.inc, %entry
>>>   %0 = load i32, i32* %i, align 4
>>>   %1 = load i32, i32* %n.addr, align 4
>>>   %cmp = icmp slt i32 %0, %1
>>>   br i1 %cmp, label %for.body, label %for.end
>>> 
>>> for.body:                                         ; preds = %for.cond
>>>   %2 = load i32, i32* %i, align 4
>>>   %3 = load i32, i32* %i, align 4
>>>   %idxprom = sext i32 %3 to i64
>>>   %4 = load i32*, i32** %array_x.addr, align 8
>>>   %arrayidx = getelementptr inbounds i32, i32* %4, i64 %idxprom
>>>   store i32 %2, i32* %arrayidx, align 4
>>>   br label %for.inc
>>> 
>>> for.inc:                                          ; preds = %for.body
>>>   %5 = load i32, i32* %i, align 4
>>>   %inc = add i32 %5, 1
>>>   store i32 %inc, i32* %i, align 4
>>>   br label %for.cond
>>> 
>>> for.end:                                          ; preds = %for.cond
>>>   ret void
>>> }
>>> 
>>> attributes #0 = { nounwind }
>>> 
>>> ******************************** API Generate IR End      ***********************************************************
>>> 
>>> Then I use "opt file.bc -mem2reg -loops -loop-simplify -loop-rotate -lcssa -indvars -loop-unroll -unroll-count=4 -irce -simplifycfg -S" to run both .bc files.
>>> The first .bc file give me this:
>>> 
>>> ***************************** Clang Generate IR with LoopUnrolling Start**********************************************
>>> ; ModuleID = 'bc_from_clang.bc'
>>> target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
>>> target triple = "x86_64-unknown-linux-gnu"
>>> 
>>> ; Function Attrs: nounwind uwtable
>>> define void @_Z3fooiPi(i32 %n, i32* %array_x) #0 {
>>>   %1 = icmp slt i32 0, %n
>>>   br i1 %1, label %.lr.ph, label %._crit_edge
>>> 
>>> .lr.ph:                                           ; preds = %0
>>>   %2 = add i32 %n, -1
>>>   %xtraiter = and i32 %n, 3
>>>   %lcmp.mod = icmp ne i32 %xtraiter, 0
>>>   br i1 %lcmp.mod, label %3, label %.lr.ph.split
>>> 
>>> ; <label>:3                                       ; preds = %3, %.lr.ph
>>>   %indvars.iv.prol = phi i64 [ 0, %.lr.ph ], [ %indvars.iv.next.prol, %3 ]
>>>   %prol.iter = phi i32 [ %xtraiter, %.lr.ph ], [ %prol.iter.sub, %3 ]
>>>   %4 = getelementptr inbounds i32, i32* %array_x, i64 %indvars.iv.prol
>>>   %5 = trunc i64 %indvars.iv.prol to i32
>>>   store i32 %5, i32* %4, align 4
>>>   %indvars.iv.next.prol = add nuw nsw i64 %indvars.iv.prol, 1
>>>   %lftr.wideiv.prol = trunc i64 %indvars.iv.next.prol to i32
>>>   %exitcond.prol = icmp ne i32 %lftr.wideiv.prol, %n
>>>   %prol.iter.sub = sub i32 %prol.iter, 1
>>>   %prol.iter.cmp = icmp ne i32 %prol.iter.sub, 0
>>>   br i1 %prol.iter.cmp, label %3, label %.lr.ph.split, !llvm.loop !1
>>> 
>>> .lr.ph.split:                                     ; preds = %3, %.lr.ph
>>>   %indvars.iv.unr = phi i64 [ 0, %.lr.ph ], [ %indvars.iv.next.prol, %3 ]
>>>   %6 = icmp ult i32 %2, 3
>>>   br i1 %6, label %._crit_edge, label %.lr.ph.split.split
>>> 
>>> .lr.ph.split.split:                               ; preds = %.lr.ph.split, %.lr.ph.split.split
>>>   %indvars.iv = phi i64 [ %indvars.iv.next.3, %.lr.ph.split.split ], [ %indvars.iv.unr, %.lr.ph.split ]
>>>   %7 = getelementptr inbounds i32, i32* %array_x, i64 %indvars.iv
>>>   %8 = trunc i64 %indvars.iv to i32
>>>   store i32 %8, i32* %7, align 4
>>>   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
>>>   %lftr.wideiv = trunc i64 %indvars.iv.next to i32
>>>   %9 = getelementptr inbounds i32, i32* %array_x, i64 %indvars.iv.next
>>>   %10 = trunc i64 %indvars.iv.next to i32
>>>   store i32 %10, i32* %9, align 4
>>>   %indvars.iv.next.1 = add nuw nsw i64 %indvars.iv.next, 1
>>>   %lftr.wideiv.1 = trunc i64 %indvars.iv.next.1 to i32
>>>   %11 = getelementptr inbounds i32, i32* %array_x, i64 %indvars.iv.next.1
>>>   %12 = trunc i64 %indvars.iv.next.1 to i32
>>>   store i32 %12, i32* %11, align 4
>>>   %indvars.iv.next.2 = add nuw nsw i64 %indvars.iv.next.1, 1
>>>   %lftr.wideiv.2 = trunc i64 %indvars.iv.next.2 to i32
>>>   %13 = getelementptr inbounds i32, i32* %array_x, i64 %indvars.iv.next.2
>>>   %14 = trunc i64 %indvars.iv.next.2 to i32
>>>   store i32 %14, i32* %13, align 4
>>>   %indvars.iv.next.3 = add nuw nsw i64 %indvars.iv.next.2, 1
>>>   %lftr.wideiv.3 = trunc i64 %indvars.iv.next.3 to i32
>>>   %exitcond.3 = icmp ne i32 %lftr.wideiv.3, %n
>>>   br i1 %exitcond.3, label %.lr.ph.split.split, label %._crit_edge
>>> 
>>> ._crit_edge:                                      ; preds = %.lr.ph.split, %.lr.ph.split.split, %0
>>>   ret void
>>> }
>>> 
>>> attributes #0 = { nounwind uwtable "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
>>> 
>>> !llvm.ident = !{!0}
>>> 
>>> !0 = !{!"clang version 3.8.0 (trunk 245730) (llvm/trunk 245727)"}
>>> !1 = distinct !{!1, !2}
>>> !2 = !{!"llvm.loop.unroll.disable"}
>>> 
>>> ******************************Clang Generate IR with LoopUnrolling End***********************************************
>>> 
>>> The second .bc file gives me this:
>>> ******************************API Generate IR with LoopUnrolling Start*************************************************
>>> ; ModuleID = 'bc_from_api.bc'
>>> target triple = "x86_64-unkown-linux-gnu"
>>> 
>>> ; Function Attrs: nounwind
>>> define void @_Z3fooiPi(i32 %n, i32* %array_x) #0 {
>>> entry:
>>>   %cmp.1 = icmp slt i32 0, %n
>>>   br i1 %cmp.1, label %for.body, label %for.end
>>> 
>>> for.body:                                         ; preds = %entry, %for.body.3
>>>   %i.02 = phi i32 [ %inc.3, %for.body.3 ], [ 0, %entry ]
>>>   %idxprom = sext i32 %i.02 to i64
>>>   %arrayidx = getelementptr inbounds i32, i32* %array_x, i64 %idxprom
>>>   store i32 %i.02, i32* %arrayidx, align 4
>>>   %inc = add nuw nsw i32 %i.02, 1
>>>   %cmp = icmp slt i32 %inc, %n
>>>   br i1 %cmp, label %for.body.1, label %for.end
>>> 
>>> for.end:                                          ; preds = %for.body, %for.body.1, %for.body.2, %for.body.3, %entry
>>>   ret void
>>> 
>>> for.body.1:                                       ; preds = %for.body
>>>   %idxprom.1 = sext i32 %inc to i64
>>>   %arrayidx.1 = getelementptr inbounds i32, i32* %array_x, i64 %idxprom.1
>>>   store i32 %inc, i32* %arrayidx.1, align 4
>>>   %inc.1 = add nuw nsw i32 %inc, 1
>>>   %cmp.1.3 = icmp slt i32 %inc.1, %n
>>>   br i1 %cmp.1.3, label %for.body.2, label %for.end
>>> 
>>> for.body.2:                                       ; preds = %for.body.1
>>>   %idxprom.2 = sext i32 %inc.1 to i64
>>>   %arrayidx.2 = getelementptr inbounds i32, i32* %array_x, i64 %idxprom.2
>>>   store i32 %inc.1, i32* %arrayidx.2, align 4
>>>   %inc.2 = add nuw nsw i32 %inc.1, 1
>>>   %cmp.2 = icmp slt i32 %inc.2, %n
>>>   br i1 %cmp.2, label %for.body.3, label %for.end
>>> 
>>> for.body.3:                                       ; preds = %for.body.2
>>>   %idxprom.3 = sext i32 %inc.2 to i64
>>>   %arrayidx.3 = getelementptr inbounds i32, i32* %array_x, i64 %idxprom.3
>>>   store i32 %inc.2, i32* %arrayidx.3, align 4
>>>   %inc.3 = add nuw nsw i32 %inc.2, 1
>>>   %cmp.3 = icmp slt i32 %inc.3, %n
>>>   br i1 %cmp.3, label %for.body, label %for.end
>>> }
>>> 
>>> attributes #0 = { nounwind }
>>> ******************************API Generate IR with LoopUnrolling End**************************************************
>>> 
>>> Sorry I post two many code here. Can you give me any suggestion?
>> 
>> Yes, use an online service like pastebin :)
>> 
>> You don’t have defined the DataLayout in the API cases, it should help to do so.
>> 
>>>> Mehdi
> 
> <main.cpp>
> _______________________________________________
> LLVM Developers mailing list
> llvm-dev at lists.llvm.org
> https://urldefense.proofpoint.com/v2/url?u=http-3A__lists.llvm.org_cgi-2Dbin_mailman_listinfo_llvm-2Ddev&d=BQIGaQ&c=eEvniauFctOgLOKGJOplqw&r=THu9ANfN9LYlQTYNQdmA7D-MsdMl2OioTAKXjMfn7i4&m=4L5QqBZnU-6JQoZ9JEaLTj_PmayQ49lOLETQL8yLA9I&s=MM8ySnofSnRJB2G1YBZPmxFwpIYUXZV04h6iDb9KrqI&e= 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20150822/19d75ebc/attachment.html>


More information about the llvm-dev mailing list