diff --git a/lib/Target/README.txt b/lib/Target/README.txt
index 4e374e59d6d..f047d087cbf 100644
--- a/lib/Target/README.txt
+++ b/lib/Target/README.txt
@@ -414,14 +414,6 @@ this construct.
 
 //===---------------------------------------------------------------------===//
 
-[LOOP RECOGNITION]
-
-viterbi speeds up *significantly* if the various "history" related copy loops
-are turned into memcpy calls at the source level.  We need a "loops to memcpy"
-pass.
-
-//===---------------------------------------------------------------------===//
-
 [LOOP OPTIMIZATION]
 
 SingleSource/Benchmarks/Misc/dt.c shows several interesting optimization
diff --git a/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
index e9394cd5c02..84e33f062b0 100644
--- a/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -126,11 +126,6 @@ static void DeleteDeadInstruction(Instruction *I, ScalarEvolution &SE) {
 bool LoopIdiomRecognize::runOnLoop(Loop *L, LPPassManager &LPM) {
   CurLoop = L;
   
-  // We only look at trivial single basic block loops.
-  // TODO: eventually support more complex loops, scanning the header.
-  if (L->getBlocks().size() != 1)
-    return false;
-  
   // The trip count of the loop must be analyzable.
   SE = &getAnalysis<ScalarEvolution>();
   if (!SE->hasLoopInvariantBackedgeTakenCount(L))
@@ -142,6 +137,11 @@ bool LoopIdiomRecognize::runOnLoop(Loop *L, LPPassManager &LPM) {
   TD = getAnalysisIfAvailable<TargetData>();
   if (TD == 0) return false;
   
+  // TODO: We currently only scan the header of the loop, because it is the only
+  // part that is known to execute and we don't want to make a conditional store
+  // into an unconditional one in the preheader.  However, there can be diamonds
+  // and other things in the loop that would make other blocks "always executed"
+  // we should get the full set and scan each block.
   BasicBlock *BB = L->getHeader();
   DEBUG(dbgs() << "loop-idiom Scanning: F[" << BB->getParent()->getName()
                << "] Loop %" << BB->getName() << "\n");
diff --git a/test/Transforms/LoopIdiom/basic.ll b/test/Transforms/LoopIdiom/basic.ll
index 8929fe48015..589fea4f3a3 100644
--- a/test/Transforms/LoopIdiom/basic.ll
+++ b/test/Transforms/LoopIdiom/basic.ll
@@ -21,6 +21,30 @@ for.end:                                          ; preds = %for.body, %entry
 ; CHECK-NOT: store
 }
 
+; This is a loop that was rotated but where the blocks weren't merged.  This
+; shouldn't perturb us.
+define void @test1a(i8* %Base, i64 %Size) nounwind ssp {
+bb.nph:                                           ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %bb.nph, %for.body
+  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body.cont ]
+  %I.0.014 = getelementptr i8* %Base, i64 %indvar
+  store i8 0, i8* %I.0.014, align 1
+  %indvar.next = add i64 %indvar, 1
+  br label %for.body.cont
+for.body.cont:
+  %exitcond = icmp eq i64 %indvar.next, %Size
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+; CHECK: @test1a
+; CHECK: call void @llvm.memset.p0i8.i64(i8* %Base, i8 0, i64 %Size, i32 1, i1 false)
+; CHECK-NOT: store
+}
+
+
 define void @test2(i32* %Base, i64 %Size) nounwind ssp {
 entry:
   %cmp10 = icmp eq i64 %Size, 0