[LoopUnroll] Enable option to peel remainder loop

On some targets, the penalty of executing runtime unrolling checks
and then not the unrolled loop can be significantly detrimental to
performance. This results in the need to be more conservative with
the unroll count, keeping a trip count of 2 reduces the overhead as
well as increasing the chance of the unrolled body being executed. But
being conservative leaves performance gains on the table.

This patch enables the unrolling of the remainder loop introduced by
runtime unrolling. This can help reduce the overhead of misunrolled
loops because the cost of non-taken branches is much less than the
cost of the backedge that would normally be executed in the remainder
loop. This allows larger unroll factors to be used without suffering
performance loses with smaller iteration counts.

Differential Revision: https://reviews.llvm.org/D36309

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@310824 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Analysis/TargetTransformInfo.h b/include/llvm/Analysis/TargetTransformInfo.h
index df96bcf1534df663535b08723ebacb831a0a9910..8696f080fd7a48b69c2aa43e359f8383c73f4e67 100644 (file)
--- a/include/llvm/Analysis/TargetTransformInfo.h
+++ b/include/llvm/Analysis/TargetTransformInfo.h
@@ -382,6 +382,8 @@ public:
     bool UpperBound;
     /// Allow peeling off loop iterations for loops with low dynamic tripcount.
     bool AllowPeeling;
+    /// Allow unrolling of all the iterations of the runtime loop remainder.
+    bool UnrollRemainder;
   };
 
   /// \brief Get target-customized preferences for the generic loop unrolling

diff --git a/include/llvm/Transforms/Utils/UnrollLoop.h b/include/llvm/Transforms/Utils/UnrollLoop.h
index a3115ad16914da94ecc73e6f8731b2676fcc2855..8e3e12620e8ae00e2c204d1fdde0da58178f8bf1 100644 (file)
--- a/include/llvm/Transforms/Utils/UnrollLoop.h
+++ b/include/llvm/Transforms/Utils/UnrollLoop.h
@@ -42,14 +42,18 @@ const Loop* addClonedBlockToLoopInfo(BasicBlock *OriginalBB,
 bool UnrollLoop(Loop *L, unsigned Count, unsigned TripCount, bool Force,
                 bool AllowRuntime, bool AllowExpensiveTripCount,
                 bool PreserveCondBr, bool PreserveOnlyFirst,
-                unsigned TripMultiple, unsigned PeelCount, LoopInfo *LI,
-                ScalarEvolution *SE, DominatorTree *DT, AssumptionCache *AC,
-                OptimizationRemarkEmitter *ORE, bool PreserveLCSSA);
+                unsigned TripMultiple, unsigned PeelCount, bool UnrollRemainder,
+                LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT,
+                AssumptionCache *AC, OptimizationRemarkEmitter *ORE,
+                bool PreserveLCSSA);
 
 bool UnrollRuntimeLoopRemainder(Loop *L, unsigned Count,
                                 bool AllowExpensiveTripCount,
-                                bool UseEpilogRemainder, LoopInfo *LI,
+                                bool UseEpilogRemainder, bool UnrollRemainder,
+                                LoopInfo *LI,
                                 ScalarEvolution *SE, DominatorTree *DT,
+                                AssumptionCache *AC,
+                                OptimizationRemarkEmitter *ORE,
                                 bool PreserveLCSSA);
 
 void computePeelCount(Loop *L, unsigned LoopSize,

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index a6d7849010cac5ca0e9b3f8ecd1a092915bbb000..fb50a3562accbb2eee4ddb7067330d643b940587 100644 (file)
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -115,6 +115,10 @@ static cl::opt<bool>
                        cl::desc("Allows loops to be peeled when the dynamic "
                                 "trip count is known to be low."));
 
+static cl::opt<bool> UnrollUnrollRemainder(
+  "unroll-remainder", cl::Hidden,
+  cl::desc("Allow the loop remainder to be unrolled."));
+
 // This option isn't ever intended to be enabled, it serves to allow
 // experiments to check the assumptions about when this kind of revisit is
 // necessary.
@@ -153,6 +157,7 @@ static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
   UP.Partial = false;
   UP.Runtime = false;
   UP.AllowRemainder = true;
+  UP.UnrollRemainder = false;
   UP.AllowExpensiveTripCount = false;
   UP.Force = false;
   UP.UpperBound = false;
@@ -188,6 +193,8 @@ static TargetTransformInfo::UnrollingPreferences gatherUnrollingPreferences(
     UP.UpperBound = false;
   if (UnrollAllowPeeling.getNumOccurrences() > 0)
     UP.AllowPeeling = UnrollAllowPeeling;
+  if (UnrollUnrollRemainder.getNumOccurrences() > 0)
+    UP.UnrollRemainder = UnrollUnrollRemainder;
 
   // Apply user values provided by argument
   if (UserThreshold.hasValue()) {
@@ -1034,7 +1041,8 @@ static bool tryToUnrollLoop(
   // Unroll the loop.
   if (!UnrollLoop(L, UP.Count, TripCount, UP.Force, UP.Runtime,
                   UP.AllowExpensiveTripCount, UseUpperBound, MaxOrZero,
-                  TripMultiple, UP.PeelCount, LI, &SE, &DT, &AC, &ORE,
+                  TripMultiple, UP.PeelCount, UP.UnrollRemainder,
+                  LI, &SE, &DT, &AC, &ORE,
                   PreserveLCSSA))
     return false;
 

diff --git a/lib/Transforms/Utils/LoopUnroll.cpp b/lib/Transforms/Utils/LoopUnroll.cpp
index f2527f89e83e5fabf43b792ff15a1a00680b98cc..835f43993320b7b54153d3760ad69742736abb7e 100644 (file)
--- a/lib/Transforms/Utils/LoopUnroll.cpp
+++ b/lib/Transforms/Utils/LoopUnroll.cpp
@@ -295,7 +295,8 @@ static bool isEpilogProfitable(Loop *L) {
 bool llvm::UnrollLoop(Loop *L, unsigned Count, unsigned TripCount, bool Force,
                       bool AllowRuntime, bool AllowExpensiveTripCount,
                       bool PreserveCondBr, bool PreserveOnlyFirst,
-                      unsigned TripMultiple, unsigned PeelCount, LoopInfo *LI,
+                      unsigned TripMultiple, unsigned PeelCount,
+                      bool UnrollRemainder, LoopInfo *LI,
                       ScalarEvolution *SE, DominatorTree *DT,
                       AssumptionCache *AC, OptimizationRemarkEmitter *ORE,
                       bool PreserveLCSSA) {
@@ -418,7 +419,8 @@ bool llvm::UnrollLoop(Loop *L, unsigned Count, unsigned TripCount, bool Force,
 
   if (RuntimeTripCount && TripMultiple % Count != 0 &&
       !UnrollRuntimeLoopRemainder(L, Count, AllowExpensiveTripCount,
-                                  EpilogProfitability, LI, SE, DT,
+                                  EpilogProfitability, UnrollRemainder,
+                                  LI, SE, DT, AC, ORE,
                                   PreserveLCSSA)) {
     if (Force)
       RuntimeTripCount = false;

diff --git a/lib/Transforms/Utils/LoopUnrollRuntime.cpp b/lib/Transforms/Utils/LoopUnrollRuntime.cpp
index 2631255d64c8e3b56df2c7a13b84a26affd8e6cc..cd5e977c2a39f022a8aff17e9fe3c676c3123251 100644 (file)
--- a/lib/Transforms/Utils/LoopUnrollRuntime.cpp
+++ b/lib/Transforms/Utils/LoopUnrollRuntime.cpp
@@ -294,7 +294,8 @@ static void ConnectEpilog(Loop *L, Value *ModVal, BasicBlock *NewExit,
 /// Return the new cloned loop that is created when CreateRemainderLoop is true.
 static Loop *
 CloneLoopBlocks(Loop *L, Value *NewIter, const bool CreateRemainderLoop,
-                const bool UseEpilogRemainder, BasicBlock *InsertTop,
+                const bool UseEpilogRemainder, const bool UnrollRemainder,
+                BasicBlock *InsertTop,
                 BasicBlock *InsertBot, BasicBlock *Preheader,
                 std::vector<BasicBlock *> &NewBlocks, LoopBlocksDFS &LoopBlocks,
                 ValueToValueMapTy &VMap, DominatorTree *DT, LoopInfo *LI) {
@@ -413,10 +414,13 @@ CloneLoopBlocks(Loop *L, Value *NewIter, const bool CreateRemainderLoop,
     }
 
     LLVMContext &Context = NewLoop->getHeader()->getContext();
-    SmallVector<Metadata *, 1> DisableOperands;
-    DisableOperands.push_back(MDString::get(Context, "llvm.loop.unroll.disable"));
-    MDNode *DisableNode = MDNode::get(Context, DisableOperands);
-    MDs.push_back(DisableNode);
+    if (!UnrollRemainder) {
+      SmallVector<Metadata *, 1> DisableOperands;
+      DisableOperands.push_back(MDString::get(Context,
+                                              "llvm.loop.unroll.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.
@@ -525,8 +529,11 @@ static bool canProfitablyUnrollMultiExitLoop(
 bool llvm::UnrollRuntimeLoopRemainder(Loop *L, unsigned Count,
                                       bool AllowExpensiveTripCount,
                                       bool UseEpilogRemainder,
+                                      bool UnrollRemainder,
                                       LoopInfo *LI, ScalarEvolution *SE,
-                                      DominatorTree *DT, bool PreserveLCSSA) {
+                                      DominatorTree *DT, AssumptionCache *AC,
+                                      OptimizationRemarkEmitter *ORE,
+                                      bool PreserveLCSSA) {
   DEBUG(dbgs() << "Trying runtime unrolling on Loop: \n");
   DEBUG(L->dump());
 
@@ -739,7 +746,8 @@ bool llvm::UnrollRuntimeLoopRemainder(Loop *L, unsigned Count,
   BasicBlock *InsertBot = UseEpilogRemainder ? LatchExit : PrologExit;
   BasicBlock *InsertTop = UseEpilogRemainder ? EpilogPreHeader : PrologPreHeader;
   Loop *remainderLoop = CloneLoopBlocks(
-      L, ModVal, CreateRemainderLoop, UseEpilogRemainder, InsertTop, InsertBot,
+      L, ModVal, CreateRemainderLoop, UseEpilogRemainder, UnrollRemainder,
+      InsertTop, InsertBot,
       NewPreHeader, NewBlocks, LoopBlocks, VMap, DT, LI);
 
   // Insert the cloned blocks into the function.
@@ -883,6 +891,15 @@ bool llvm::UnrollRuntimeLoopRemainder(Loop *L, unsigned Count,
       formDedicatedExitBlocks(remainderLoop, DT, LI, PreserveLCSSA);
   }
 
+  if (remainderLoop && UnrollRemainder) {
+    UnrollLoop(remainderLoop, /*Count*/Count - 1, /*TripCount*/Count - 1,
+               /*Force*/false, /*AllowRuntime*/false,
+               /*AllowExpensiveTripCount*/false, /*PreserveCondBr*/true,
+               /*PreserveOnlyFirst*/false, /*TripMultiple*/1,
+               /*PeelCount*/0, /*UnrollRemainder*/false, LI, SE, DT, AC, ORE,
+               PreserveLCSSA);
+  }
+
   NumRuntimeUnrolled++;
   return true;
 }

diff --git a/test/Transforms/LoopUnroll/runtime-unroll-remainder.ll b/test/Transforms/LoopUnroll/runtime-unroll-remainder.ll
new file mode 100644 (file)
index 0000000..ccfb323
--- /dev/null
+++ b/test/Transforms/LoopUnroll/runtime-unroll-remainder.ll
@@ -0,0 +1,74 @@
+; RUN: opt < %s -S -loop-unroll -unroll-runtime=true -unroll-count=4 -unroll-remainder -instcombine | FileCheck %s
+
+; CHECK-LABEL: unroll
+define i32 @unroll(i32* nocapture readonly %a, i32* nocapture readonly %b, i32 %N) local_unnamed_addr #0 {
+entry:
+  %cmp9 = icmp eq i32 %N, 0
+  br i1 %cmp9, label %for.cond.cleanup, label %for.body.lr.ph
+
+for.body.lr.ph:
+  %wide.trip.count = zext i32 %N to i64
+  br label %for.body
+
+for.cond.cleanup:
+  %c.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  ret i32 %c.0.lcssa
+
+; CHECK-LABEL: for.body.lr.ph
+; CHECK: [[COUNT:%[a-z.0-9]+]] = add nsw i64 %wide.trip.count, -1
+; CHECK: %xtraiter = and i64 %wide.trip.count, 3
+; CHECK: [[CMP:%[a-z.0-9]+]] = icmp ult i64 [[COUNT]], 3
+; CHECK: br i1 [[CMP]], label %[[CLEANUP:.*]], label %for.body.lr.ph.new
+
+; CHECK-LABEL: for.body.lr.ph.new:
+; CHECK: %unroll_iter = sub nsw i64 %wide.trip.count, %xtraiter
+; CHECK: br label %for.body
+
+; CHECK: [[CLEANUP]]:
+; CHECK: [[MOD:%[a-z.0-9]+]] = icmp eq i64 %xtraiter, 0
+; CHECK: br i1 [[MOD]], label %[[EXIT:.*]], label %[[EPIL_PEEL0_PRE:.*]]
+
+; CHECK: [[EPIL_PEEL0_PRE]]:
+; CHECK: br label %[[EPIL_PEEL0:.*]]
+
+; CHECK: [[EPIL_PEEL0]]:
+; CHECK: [[PEEL_CMP0:%[a-z.0-9]+]] = icmp eq i64 %xtraiter, 1
+; CHECK: br i1 [[PEEL_CMP0]], label %[[EPIL_EXIT:.*]], label %[[EPIL_PEEL1:.*]],
+
+; CHECK: [[EPIL_EXIT]]:
+; CHECK: br label %[[EXIT]]
+
+; CHECK: [[EXIT]]:
+; CHECK: ret i32
+
+; CHECK-LABEL: for.body:
+; CHECK: [[INDVAR0:%[a-z.0-9]+]] = phi i64 [ 0, %for.body.lr.ph
+; CHECK: [[ITER:%[a-z.0-9]+]] = phi i64 [ %unroll_iter
+; CHECK: or i64 [[INDVAR0]], 1
+; CHECK: or i64 [[INDVAR0]], 2
+; CHECK: or i64 [[INDVAR0]], 3
+; CHECK: add nsw i64 [[INDVAR0]], 4
+; CHECK: [[SUB:%[a-z.0-9]+]] = add i64 [[ITER]], -4
+; CHECK: [[ITER_CMP:%[a-z.0-9]+]] = icmp eq i64 [[SUB]], 0
+; CHECK: br i1 [[ITER_CMP]], label %[[LOOP_EXIT:.*]], label %for.body
+
+; CHECK: [[EPIL_PEEL1]]:
+; CHECK: [[PEEL_CMP1:%[a-z.0-9]+]] = icmp eq i64 %xtraiter, 2
+; CHECK: br i1 [[PEEL_CMP1]], label %[[EPIL_EXIT]], label %[[EPIL_PEEL2:.*]],
+
+; CHECK: [[EPIL_PEEL2]]:
+; CHECK: br label %[[EXIT]]
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %c.010 = phi i32 [ 0, %for.body.lr.ph ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
+  %arrayidx2 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %1 = load i32, i32* %arrayidx2, align 4
+  %mul = mul nsw i32 %1, %0
+  %add = add nsw i32 %mul, %c.010
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}