RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-03 10:54:42 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

ScalarEvolution: Compute exit counts for loops with a power-of-2 step.

Browse Source 
If we have a loop of the form
for (unsigned n = 0; n != (k & -32); n += 32) {}
then we know that n is always divisible by 32 and the loop must
terminate. Even if we have a condition where the loop counter will
overflow it'll always hold this invariant.

PR19183. Our loop vectorizer creates this pattern and it's also
occasionally formed by loop counters derived from pointers.

llvm-svn: 204728
This commit is contained in:
Benjamin Kramer 2014-03-25 16:25:12 +00:00
parent 1772c4217d
commit 79c500fdd4
2 changed files with 63 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lib/Analysis/ScalarEvolution.cpp
View File

@ -5744,6 +5744,16 @@ ScalarEvolution::HowFarToZero(const SCEV *V, const Loop *L, bool IsSubExpr) {
getUDivExpr(Distance, CountDown ? getNegativeSCEV(Step) : Step);
return ExitLimit(Exact, Exact, /*MustExit=*/false);
}
// If Step is a power of two that evenly divides Start we know that the loop
// will always terminate. Start may not be a constant so we just have the
// number of trailing zeros available. This is safe even in presence of
// overflow as the recurrence will overflow to exactly 0.
const APInt &StepV = StepC->getValue()->getValue();
if (StepV.isPowerOf2() &&
GetMinTrailingZeros(getNegativeSCEV(Start)) >= StepV.countTrailingZeros())
return getUDivExactExpr(Distance, CountDown ? getNegativeSCEV(Step) : Step);
// Then, try to solve the above equation provided that Start is constant.
if (const SCEVConstant *StartC = dyn_cast<SCEVConstant>(Start))
return SolveLinEquationWithOverflow(StepC->getValue()->getValue(),

53
test/Analysis/ScalarEvolution/trip-count-pow2.ll Normal file
View File

@ -0,0 +1,53 @@
; RUN: opt < %s -scalar-evolution -analyze | FileCheck %s
define void @test1(i32 %n) {
entry:
%s = mul i32 %n, 96
br label %loop
loop:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop ]
%i.next = add i32 %i, 32
%t = icmp ne i32 %i.next, %s
br i1 %t, label %loop, label %exit
exit:
ret void
; CHECK-LABEL: @test1
; CHECK: Loop %loop: backedge-taken count is ((-32 + (96 * %n)) /u 32)
; CHECK: Loop %loop: max backedge-taken count is ((-32 + (96 * %n)) /u 32)
}
; PR19183
define i32 @test2(i32 %n) {
entry:
%s = and i32 %n, -32
br label %loop
loop:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop ]
%i.next = add i32 %i, 32
%t = icmp ne i32 %i.next, %s
br i1 %t, label %loop, label %exit
exit:
ret i32 %i
; CHECK-LABEL: @test2
; CHECK: Loop %loop: backedge-taken count is ((-32 + (32 * (%n /u 32))) /u 32)
; CHECK: Loop %loop: max backedge-taken count is ((-32 + (32 * (%n /u 32))) /u 32)
}
define void @test3(i32 %n) {
entry:
%s = mul i32 %n, 96
br label %loop
loop:
%i = phi i32 [ 0, %entry ], [ %i.next, %loop ]
%i.next = add i32 %i, 96
%t = icmp ne i32 %i.next, %s
br i1 %t, label %loop, label %exit
exit:
ret void
; CHECK-LABEL: @test3
; CHECK: Loop %loop: Unpredictable backedge-taken count.
; CHECK: Loop %loop: Unpredictable max backedge-taken count.
}