[llvm] r309758 - [SCEV/IndVars] Always compute loop exiting values if the backedge count is 0

[Hans Wennborg via llvm-commits]

On Tue, Aug 1, 2017 at 4:47 PM, Hans Wennborg <hans at chromium.org> wrote:
> On Tue, Aug 1, 2017 at 4:12 PM, Sanjoy Das
> <sanjoy at playingwithpointers.com> wrote:
>> Hi,
>>
>> On Tue, Aug 1, 2017 at 3:45 PM, Davide Italiano <davide at freebsd.org> wrote:
>>> Sanjoy, Hans, can we backport this one to 5.0?
>>
>> SGTM, but I'd like to bake this in tree for a day or two before we do that.
>
> Sounds good to me too.

Merged in r310538.

>>>
>>> Thanks,
>>>
>>> --
>>> Davide
>>>
>>> On Tue, Aug 1, 2017 at 3:37 PM, Sanjoy Das via llvm-commits
>>> <llvm-commits at lists.llvm.org> wrote:
>>>> Author: sanjoy
>>>> Date: Tue Aug  1 15:37:58 2017
>>>> New Revision: 309758
>>>>
>>>> URL: http://llvm.org/viewvc/llvm-project?rev=309758&view=rev
>>>> Log:
>>>> [SCEV/IndVars] Always compute loop exiting values if the backedge count is 0
>>>>
>>>> If SCEV can prove that the backedge taken count for a loop is zero, it does not
>>>> need to "understand" a recursive PHI to compute its exiting value.
>>>>
>>>> This should fix PR33885.
>>>>
>>>> Modified:
>>>>     llvm/trunk/lib/Analysis/ScalarEvolution.cpp
>>>>     llvm/trunk/test/Transforms/IndVarSimplify/exit_value_test2.ll
>>>>
>>>> Modified: llvm/trunk/lib/Analysis/ScalarEvolution.cpp
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Analysis/ScalarEvolution.cpp?rev=309758&r1=309757&r2=309758&view=diff
>>>> ==============================================================================
>>>> --- llvm/trunk/lib/Analysis/ScalarEvolution.cpp (original)
>>>> +++ llvm/trunk/lib/Analysis/ScalarEvolution.cpp Tue Aug  1 15:37:58 2017
>>>> @@ -7597,6 +7597,25 @@ const SCEV *ScalarEvolution::computeSCEV
>>>>              const SCEV *BackedgeTakenCount = getBackedgeTakenCount(LI);
>>>>              if (const SCEVConstant *BTCC =
>>>>                    dyn_cast<SCEVConstant>(BackedgeTakenCount)) {
>>>> +
>>>> +              // This trivial case can show up in some degenerate cases where
>>>> +              // the incoming IR has not yet been fully simplified.
>>>> +              if (BTCC->getValue()->isZero()) {
>>>> +                Value *InitValue = nullptr;
>>>> +                bool MultipleInitValues = false;
>>>> +                for (unsigned i = 0; i < PN->getNumIncomingValues(); i++) {
>>>> +                  if (!LI->contains(PN->getIncomingBlock(i))) {
>>>> +                    if (!InitValue)
>>>> +                      InitValue = PN->getIncomingValue(i);
>>>> +                    else if (InitValue != PN->getIncomingValue(i)) {
>>>> +                      MultipleInitValues = true;
>>>> +                      break;
>>>> +                    }
>>>> +                  }
>>>> +                  if (!MultipleInitValues && InitValue)
>>>> +                    return getSCEV(InitValue);
>>>> +                }
>>>> +              }
>>>>                // Okay, we know how many times the containing loop executes.  If
>>>>                // this is a constant evolving PHI node, get the final value at
>>>>                // the specified iteration number.
>>>>
>>>> Modified: llvm/trunk/test/Transforms/IndVarSimplify/exit_value_test2.ll
>>>> URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/IndVarSimplify/exit_value_test2.ll?rev=309758&r1=309757&r2=309758&view=diff
>>>> ==============================================================================
>>>> --- llvm/trunk/test/Transforms/IndVarSimplify/exit_value_test2.ll (original)
>>>> +++ llvm/trunk/test/Transforms/IndVarSimplify/exit_value_test2.ll Tue Aug  1 15:37:58 2017
>>>> @@ -3,15 +3,14 @@
>>>>
>>>>  ; Check IndVarSimplify should not replace exit value because or else
>>>>  ; udiv will be introduced by expand and the cost will be high.
>>>> -;
>>>> -; CHECK-LABEL: @_Z3fooPKcjj(
>>>> -; CHECK-NOT: udiv
>>>>
>>>>  declare void @_Z3mixRjj(i32* dereferenceable(4), i32)
>>>>  declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture)
>>>>  declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
>>>>
>>>>  define i32 @_Z3fooPKcjj(i8* nocapture readonly %s, i32 %len, i32 %c) {
>>>> +; CHECK-LABEL: @_Z3fooPKcjj(
>>>> +; CHECK-NOT: udiv
>>>>  entry:
>>>>    %a = alloca i32, align 4
>>>>    %tmp = bitcast i32* %a to i8*
>>>> @@ -50,3 +49,26 @@ while.end:
>>>>    call void @llvm.lifetime.end.p0i8(i64 4, i8* %tmp)
>>>>    ret i32 %tmp4
>>>>  }
>>>> +
>>>> +define i32 @zero_backedge_count_test(i32 %unknown_init, i32* %unknown_mem) {
>>>> +; CHECK-LABEL: @zero_backedge_count_test(
>>>> +entry:
>>>> +  br label %loop
>>>> +
>>>> +loop:
>>>> +  %iv = phi i32 [ 0, %entry], [ %iv.inc, %loop ]
>>>> +  %unknown_phi = phi i32 [ %unknown_init, %entry ], [ %unknown_next, %loop ]
>>>> +  %iv.inc = add i32 %iv, 1
>>>> +  %be_taken = icmp ne i32 %iv.inc, 1
>>>> +  %unknown_next = load volatile i32, i32* %unknown_mem
>>>> +  br i1 %be_taken, label %loop, label %leave
>>>> +
>>>> +leave:
>>>> +; We can fold %unknown_phi even though the backedge value for it is completely
>>>> +; unknown, since we can prove that the loop's backedge taken count is 0.
>>>> +
>>>> +; CHECK: leave:
>>>> +; CHECK: ret i32 %unknown_init
>>>> +  %exit_val = phi i32 [ %unknown_phi, %loop ]
>>>> +  ret i32 %exit_val
>>>> +}
>>>>
>>>>
>>>> _______________________________________________
>>>> llvm-commits mailing list
>>>> llvm-commits at lists.llvm.org
>>>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>>
>>>
>>>
>>> --
>>> Davide
>>>
>>> "There are no solved problems; there are only problems that are more
>>> or less solved" -- Henri Poincare