From 715b01e979aad41b1138fb21ed08601cc328159e Mon Sep 17 00:00:00 2001
From: Kevin Qin <Kevin.Qin@arm.com>
Date: Mon, 9 Mar 2015 06:14:18 +0000
Subject: Introduce runtime unrolling disable matadata and use it to mark the
 scalar loop from vectorization.

Runtime unrolling is an expensive optimization which can bring benefit
only if the loop is hot and iteration number is relatively large enough.
For some loops, we know they are not worth to be runtime unrolled.
The scalar loop from vectorization is one of the cases.

llvm-svn: 231631
---
 llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 54 ++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 2 deletions(-)

(limited to 'llvm/lib/Transforms/Vectorize')

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index ffa3fe13df5..781e224eef6 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -250,7 +250,7 @@ public:
       : OrigLoop(OrigLoop), SE(SE), LI(LI), DT(DT), DL(DL), TLI(TLI),
         VF(VecWidth), UF(UnrollFactor), Builder(SE->getContext()),
         Induction(nullptr), OldInduction(nullptr), WidenMap(UnrollFactor),
-        Legal(nullptr) {}
+        Legal(nullptr), AddedSafetyChecks(false) {}
 
   // Perform the actual loop widening (vectorization).
   void vectorize(LoopVectorizationLegality *L) {
@@ -264,6 +264,11 @@ public:
     updateAnalysis();
   }
 
+  // Return true if any runtime check is added.
+  bool IsSafetyChecksAdded() {
+    return AddedSafetyChecks;
+  }
+
   virtual ~InnerLoopVectorizer() {}
 
 protected:
@@ -443,6 +448,9 @@ protected:
   EdgeMaskCache MaskCache;
 
   LoopVectorizationLegality *Legal;
+
+  // Record whether runtime check is added.
+  bool AddedSafetyChecks;
 };
 
 class InnerLoopUnroller : public InnerLoopVectorizer {
@@ -893,7 +901,7 @@ private:
 
   ValueToValueMap Strides;
   SmallPtrSet<Value *, 8> StrideSet;
-  
+
   /// While vectorizing these instructions we have to generate a
   /// call to the appropriate masked intrinsic
   SmallPtrSet<const Instruction*, 8> MaskedOp;
@@ -1320,6 +1328,40 @@ struct LoopVectorize : public FunctionPass {
     return Changed;
   }
 
+  static void AddRuntimeUnrollDisableMetaData(Loop *L) {
+    SmallVector<Metadata *, 4> MDs;
+    // Reserve first location for self reference to the LoopID metadata node.
+    MDs.push_back(nullptr);
+    bool IsUnrollMetadata = false;
+    MDNode *LoopID = L->getLoopID();
+    if (LoopID) {
+      // First find existing loop unrolling disable metadata.
+      for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i) {
+        MDNode *MD = dyn_cast<MDNode>(LoopID->getOperand(i));
+        if (MD) {
+          const MDString *S = dyn_cast<MDString>(MD->getOperand(0));
+          IsUnrollMetadata =
+              S && S->getString().startswith("llvm.loop.unroll.disable");
+        }
+        MDs.push_back(LoopID->getOperand(i));
+      }
+    }
+
+    if (!IsUnrollMetadata) {
+      // Add runtime unroll disable metadata.
+      LLVMContext &Context = L->getHeader()->getContext();
+      SmallVector<Metadata *, 1> DisableOperands;
+      DisableOperands.push_back(
+          MDString::get(Context, "llvm.loop.unroll.runtime.disable"));
+      MDNode *DisableNode = MDNode::get(Context, DisableOperands);
+      MDs.push_back(DisableNode);
+      MDNode *NewLoopID = MDNode::get(Context, MDs);
+      // Set operand 0 to refer to the loop id itself.
+      NewLoopID->replaceOperandWith(0, NewLoopID);
+      L->setLoopID(NewLoopID);
+    }
+  }
+
   bool processLoop(Loop *L) {
     assert(L->empty() && "Only process inner loops.");
 
@@ -1475,6 +1517,12 @@ struct LoopVectorize : public FunctionPass {
       LB.vectorize(&LVL);
       ++LoopsVectorized;
 
+      // Add metadata to disable runtime unrolling scalar loop when there's no
+      // runtime check about strides and memory. Because at this situation,
+      // scalar loop is rarely used not worthy to be unrolled.
+      if (!LB.IsSafetyChecksAdded())
+        AddRuntimeUnrollDisableMetaData(L);
+
       // Report the vectorization decision.
       emitOptimizationRemark(
           F->getContext(), DEBUG_TYPE, *F, L->getStartLoc(),
@@ -2221,6 +2269,7 @@ void InnerLoopVectorizer::createEmptyLoop() {
   std::tie(FirstCheckInst, StrideCheck) =
       addStrideCheck(LastBypassBlock->getTerminator());
   if (StrideCheck) {
+    AddedSafetyChecks = true;
     // Create a new block containing the stride check.
     BasicBlock *CheckBlock =
         LastBypassBlock->splitBasicBlock(FirstCheckInst, "vector.stridecheck");
@@ -2245,6 +2294,7 @@ void InnerLoopVectorizer::createEmptyLoop() {
   std::tie(FirstCheckInst, MemRuntimeCheck) =
     Legal->getLAI()->addRuntimeCheck(LastBypassBlock->getTerminator());
   if (MemRuntimeCheck) {
+    AddedSafetyChecks = true;
     // Create a new block containing the memory check.
     BasicBlock *CheckBlock =
         LastBypassBlock->splitBasicBlock(FirstCheckInst, "vector.memcheck");
-- 
cgit v1.2.3