diff options
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp | 5 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopUnroll/runtime-loop5.ll | 45 |
2 files changed, 47 insertions, 3 deletions
diff --git a/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp b/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp index 46570a11a4f..c8d47828eba 100644 --- a/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp +++ b/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp @@ -318,9 +318,8 @@ bool llvm::UnrollRuntimeLoopProlog(Loop *L, unsigned Count, LoopInfo *LI, return false; // This constraint lets us deal with an overflowing trip count easily; see the - // comment on ModVal below. This check is equivalent to `Log2(Count) < - // BEWidth`. - if (BEWidth < 64 && static_cast<uint64_t>(Count) > (1ULL << BEWidth)) + // comment on ModVal below. + if (Log2_32(Count) > BEWidth) return false; // If this loop is nested, then the loop unroller changes the code in diff --git a/llvm/test/Transforms/LoopUnroll/runtime-loop5.ll b/llvm/test/Transforms/LoopUnroll/runtime-loop5.ll new file mode 100644 index 00000000000..e8d51775ce1 --- /dev/null +++ b/llvm/test/Transforms/LoopUnroll/runtime-loop5.ll @@ -0,0 +1,45 @@ +; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=16 | FileCheck --check-prefix=UNROLL-16 %s +; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 | FileCheck --check-prefix=UNROLL-4 %s + +; Given that the trip-count of this loop is a 3-bit value, we cannot +; safely unroll it with a count of anything more than 8. + +define i3 @test(i3* %a, i3 %n) { +; UNROLL-16-LABEL: @test( +; UNROLL-4-LABEL: @test( +entry: + %cmp1 = icmp eq i3 %n, 0 + br i1 %cmp1, label %for.end, label %for.body + +; UNROLL-16-NOT: for.body.prol: +; UNROLL-4: for.body.prol: + +for.body: ; preds = %for.body, %entry +; UNROLL-16-LABEL: for.body: +; UNROLL-4-LABEL: for.body: + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %sum.02 = phi i3 [ %add, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds i3, i3* %a, i64 %indvars.iv + +; UNROLL-16-LABEL: for.body +; UNROLL-16-LABEL: getelementptr +; UNROLL-16-LABEL-NOT: getelementptr + +; UNROLL-4-LABEL: getelementptr +; UNROLL-4-LABEL: getelementptr +; UNROLL-4-LABEL: getelementptr +; UNROLL-4-LABEL: getelementptr + + %0 = load i3, i3* %arrayidx + %add = add nsw i3 %0, %sum.02 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i3 + %exitcond = icmp eq i3 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +; UNROLL-16-LABEL: for.end +; UNROLL-4-LABEL: for.end +for.end: ; preds = %for.body, %entry + %sum.0.lcssa = phi i3 [ 0, %entry ], [ %add, %for.body ] + ret i3 %sum.0.lcssa +} |
