LoopVectorizer: Truncate i64 trip counts of i32 phis if necessary

In signed arithmetic we could end up with an i64 trip count for an i32 phi.
Because it is signed arithmetic we know that this is only defined if the i32
does not wrap. It is therefore safe to truncate the i64 trip count to a i32
value.

Fixes PR18049.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@195787 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index 79f80f37eeaf8c989e8d3f2d90205b792b919365..874db9ff15263cb3c0b61fe85cbeb8bd9eb779f8 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1537,6 +1537,15 @@ InnerLoopVectorizer::createEmptyLoop(LoopVectorizationLegality *Legal) {
   const SCEV *ExitCount = SE->getBackedgeTakenCount(OrigLoop);
   assert(ExitCount != SE->getCouldNotCompute() && "Invalid loop count");
 
+  // The exit count might have the type of i64 while the phi is i32. This can
+  // happen if we have an induction variable that is sign extended before the
+  // compare. The only way that we get a backedge taken count is that the
+  // induction variable was signed and as such will not overflow. In such a case
+  // truncation is legal.
+  if (ExitCount->getType()->getPrimitiveSizeInBits() >
+      IdxTy->getPrimitiveSizeInBits())
+    ExitCount = SE->getTruncateOrNoop(ExitCount, IdxTy);
+
   ExitCount = SE->getNoopOrZeroExtend(ExitCount, IdxTy);
   // Get the total trip count from the count by adding 1.
   ExitCount = SE->getAddExpr(ExitCount,

diff --git a/test/Transforms/LoopVectorize/X86/tripcount.ll b/test/Transforms/LoopVectorize/X86/tripcount.ll
new file mode 100644 (file)
index 0000000..6b38bac
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/tripcount.ll
@@ -0,0 +1,39 @@
+; RUN: opt -S -loop-vectorize -force-vector-width=2 -force-vector-unroll=1 -mcpu=prescott < %s | FileCheck %s
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32-S128"
+target triple = "i386-unknown-freebsd11.0"
+
+@big = external global [0 x i32]
+
+; PR18049
+; We need to truncate the exit count to i32. This is legal because the
+; arithmetic is signed (%inc is nsw).
+
+; CHECK-LABEL: tripcount
+; CHECK: trunc i64 %count to i32
+
+define void @tripcount(i64 %count) {
+entry:
+  %cmp6 = icmp sgt i64 %count, 0
+  br i1 %cmp6, label %for.body.preheader, label %for.end
+
+for.body.preheader:
+  br label %for.body
+
+for.body:
+  %i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+  %arrayidx = getelementptr inbounds [0 x i32]* @big, i32 0, i32 %i.07
+  %0 = load i32* %arrayidx, align 4
+  %neg = xor i32 %0, -1
+  store i32 %neg, i32* %arrayidx, align 4
+  %inc = add nsw i32 %i.07, 1
+  %conv = sext i32 %inc to i64
+  %cmp = icmp slt i64 %conv, %count
+  br i1 %cmp, label %for.body, label %for.end.loopexit
+
+for.end.loopexit:
+  br label %for.end
+
+for.end:
+  ret void
+}