db45746821
Loop peeling is currently performed as part of UnrollLoop(). Outside test scenarios, it is always performed with an unroll count of 1. This means that unrolling doesn't actually do anything apart from performing post-unroll simplification. When testing, it's currently possible to specify both an explicit peel count and an explicit unroll count. This doesn't perform any sensible operation and may result in miscompiles, see https://bugs.llvm.org/show_bug.cgi?id=45939. This patch moves peeling from UnrollLoop() into tryToUnrollLoop(), so that peeling does not also perform a susequent unroll. We only run the post-unroll simplifications. Specifying both an explicit peel count and unroll count is forbidden. In the future, we may want to support both (non-PGO) peeling a loop and unrolling it, but this needs to be done by first performing the peel and then recalculating unrolling heuristics on a now possibly analyzable loop. Differential Revision: https://reviews.llvm.org/D103362
23 lines
819 B
LLVM
23 lines
819 B
LLVM
; RUN: not --crash opt -loop-unroll -unroll-peel-count=2 -unroll-count=2 -S < %s 2>&1 | FileCheck %s
|
|
|
|
; CHECK: LLVM ERROR: Cannot specify both explicit peel count and explicit unroll count
|
|
|
|
@a = global [8 x i32] zeroinitializer, align 16
|
|
|
|
define void @test1() {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* @a, i64 0, i64 %indvars.iv
|
|
%0 = trunc i64 %indvars.iv to i32
|
|
store i32 %0, i32* %arrayidx, align 4
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp ne i64 %indvars.iv.next, 8
|
|
br i1 %exitcond, label %for.body, label %for.exit
|
|
|
|
for.exit: ; preds = %for.body
|
|
ret void
|
|
}
|