From 269112230203d28dd04beab3ecc09dbab4c75b6e Mon Sep 17 00:00:00 2001
From: Anna Thomas <anna@azul.com>
Date: Tue, 12 Sep 2017 16:32:45 +0000
Subject: [PATCH] [LV] Clamp the VF to the trip count

Summary:
When the MaxVectorSize > ConstantTripCount, we should just clamp the
vectorization factor to be the ConstantTripCount.
This vectorizes loops where the TinyTripCountThreshold >= TripCount < MaxVF.

Earlier we were finding the maximum vector width, which could be greater than
the trip count itself. The Loop vectorizer does all the work for generating a
vectorizable loop, but in the end we would always choose the scalar loop (since
the VF > trip count). This allows us to choose the VF keeping in mind the trip
count if available.

This is a fix on top of rL312472.

Reviewers: Ayal, zvi, hfinkel, dneilson

Reviewed by: Ayal

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D37702

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313046 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Transforms/Vectorize/LoopVectorize.cpp    | 19 +++++++++-----
 .../LoopVectorize/X86/vector_max_bandwidth.ll | 26 +++++++++++++++++++
 2 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index fac76ba643c..5267a2a3f19 100644
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1960,7 +1960,7 @@ public:
 private:
   /// \return An upper bound for the vectorization factor, larger than zero.
   /// One is returned if vectorization should best be avoided due to cost.
-  unsigned computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount = 0);
+  unsigned computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount);
 
   /// The vectorization cost is a combination of the cost itself and a boolean
   /// indicating whether any of the contributing operations will actually
@@ -6161,8 +6161,9 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
     return None;
   }
 
+  unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
   if (!OptForSize) // Remaining checks deal with scalar loop when OptForSize.
-    return computeFeasibleMaxVF(OptForSize);
+    return computeFeasibleMaxVF(OptForSize, TC);
 
   if (Legal->getRuntimePointerChecking()->Need) {
     ORE->emit(createMissedAnalysis("CantVersionLoopWithOptForSize")
@@ -6175,7 +6176,6 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
   }
 
   // If we optimize the program for size, avoid creating the tail loop.
-  unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
   DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
 
   // If we don't know the precise trip count, don't try to vectorize.
@@ -6236,15 +6236,20 @@ LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
   DEBUG(dbgs() << "LV: The Widest register is: " << WidestRegister
                << " bits.\n");
 
+  assert(MaxVectorSize <= 64 && "Did not expect to pack so many elements"
+                                " into one vector!");
   if (MaxVectorSize == 0) {
     DEBUG(dbgs() << "LV: The target has no vector registers.\n");
     MaxVectorSize = 1;
   } else if (ConstTripCount && ConstTripCount < MaxVectorSize &&
-             isPowerOf2_32(ConstTripCount))
+             isPowerOf2_32(ConstTripCount)) {
+    // We need to clamp the VF to be the ConstTripCount. There is no point in
+    // choosing a higher viable VF as done in the loop below.
+    DEBUG(dbgs() << "LV: Clamping the MaxVF to the constant trip count: "
+                 << ConstTripCount << "\n");
     MaxVectorSize = ConstTripCount;
-
-  assert(MaxVectorSize <= 64 && "Did not expect to pack so many elements"
-                                " into one vector!");
+    return MaxVectorSize;
+  }
 
   unsigned MaxVF = MaxVectorSize;
   if (MaximizeBandwidth && !OptForSize) {
diff --git a/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll b/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
index a32cc46e913..4e7880d09d6 100644
--- a/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
+++ b/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
@@ -46,3 +46,29 @@ for.body:
   %exitcond = icmp eq i64 %indvars.iv.next, 1000
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
+
+; We should not choose a VF larger than the constant TC.
+; VF chosen should be atmost 16 (not the max possible vector width = 32 for AVX2)
+define void @not_too_small_tc(i8* noalias nocapture %A, i8* noalias nocapture readonly %B) {
+; CHECK-LABEL: not_too_small_tc
+; CHECK-AVX2: LV: Selecting VF: 16.
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i8, i8* %B, i64 %indvars.iv
+  %l1 = load i8, i8* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %arrayidx2 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv
+  %l2 = load i8, i8* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %add = add i8 %l1, %l2
+  store i8 %add, i8* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 16
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
+
+for.end:
+  ret void
+}
+!3 = !{!3}
+!4 = !{!4}
-- 
2.50.0