LoopVectorize: MaxVF should not be larger than the loop trip count

Summary:
Improve how MaxVF is computed while taking into account that MaxVF should not be larger than the loop's trip count.

Other than saving on compile-time by pruning the possible MaxVF candidates, this patch fixes pr34438 which exposed the following flow:
1. Short trip count identified -> Don't bail out, set OptForSize:=True to avoid tail-loop and runtime checks.
2. Compute MaxVF returned 16 on a target supporting AVX512.
3. OptForSize -> choose VF:=MaxVF.
4. Bail out because TripCount = 8, VF = 16, TripCount % VF !=0 means we need a tail loop.

With this patch step 2. will choose MaxVF=8 based on TripCount.

Reviewers: Ayal, dorit, mkuper, hfinkel

Reviewed By: hfinkel

Subscribers: hfinkel, llvm-commits

Differential Revision: https://reviews.llvm.org/D37425

llvm-svn: 312472

Author: Zvi Rackover

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1960,7 +1960,7 @@ class LoopVectorizationCostModel {
 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 computeFeasibleMaxVF(bool OptForSize, unsigned ConstTripCount = 0);
 
   /// The vectorization cost is a combination of the cost itself and a boolean
   /// indicating whether any of the contributing operations will actually
@@ -6187,7 +6187,7 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
     return None;
   }
 
-  unsigned MaxVF = computeFeasibleMaxVF(OptForSize);
+  unsigned MaxVF = computeFeasibleMaxVF(OptForSize, TC);
 
   if (TC % MaxVF != 0) {
     // If the trip count that we found modulo the vectorization factor is not
@@ -6208,7 +6208,9 @@ Optional<unsigned> LoopVectorizationCostModel::computeMaxVF(bool OptForSize) {
   return MaxVF;
 }
 
-unsigned LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize) {
+unsigned
+LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize,
+                                                 unsigned ConstTripCount) {
   MinBWs = computeMinimumValueSizes(TheLoop->getBlocks(), *DB, &TTI);
   unsigned SmallestType, WidestType;
   std::tie(SmallestType, WidestType) = getSmallestAndWidestTypes();
@@ -6237,7 +6239,9 @@ unsigned LoopVectorizationCostModel::computeFeasibleMaxVF(bool OptForSize) {
   if (MaxVectorSize == 0) {
     DEBUG(dbgs() << "LV: The target has no vector registers.\n");
     MaxVectorSize = 1;
-  }
+  } else if (ConstTripCount && ConstTripCount < MaxVectorSize &&
+             isPowerOf2_32(ConstTripCount))
+    MaxVectorSize = ConstTripCount;
 
   assert(MaxVectorSize <= 64 && "Did not expect to pack so many elements"
                                 " into one vector!");

llvm/test/Transforms/LoopVectorize/X86/pr34438.ll

@@ -0,0 +1,35 @@
+; PR34438
+; Loop has a short trip count of 8 iterations. It should be vectorized because no runtime checks or tail loop are necessary.
+; Two cases tested AVX (MaxVF=8 = TripCount) and AVX512 (MaxVF=16 > TripCount)
+
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=skylake-avx512 -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+define void @small_tc(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
+; CHECK-LABEL: @small_tc
+; CHECK:    load <8 x float>, <8 x float>*
+; CHECK:    fadd fast <8 x float>
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
+  %0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
+  %1 = load float, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %add = fadd fast float %0, %1
+  store float %add, float* %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, 8
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
+
+for.end:
+  ret void
+}
+
+!3 = !{!3}
+!4 = !{!4}