[LoopUnroll] Allow unrolling if the unrolled size does not exceed loop size.

Summary:
In the following cases, unrolling can be beneficial, even when
optimizing for code size:
 1) very low trip counts
 2) potential to constant fold most instructions after fully unrolling.

We can unroll in those cases, by setting the unrolling threshold to the
loop size. This might highlight some cost modeling issues and fixing
them will have a positive impact in general.

Reviewers: vsk, efriedma, dmgreen, paquette

Reviewed By: paquette

Differential Revision: https://reviews.llvm.org/D60265

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@358586 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index c113e4d31667d6b71c937d440be1696a1be57c2d..53015d25842cd13aec34b035caf9c606c4bdc89b 100644 (file)
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -207,6 +207,7 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
   if (OptForSize) {
     UP.Threshold = UP.OptSizeThreshold;
     UP.PartialThreshold = UP.PartialOptSizeThreshold;
+    UP.MaxPercentThresholdBoost = 100;
   }
 
   // Apply any user values specified by cl::opt
@@ -993,6 +994,7 @@ static LoopUnrollResult tryToUnrollLoop(
   if (OnlyWhenForced && !(TM & TM_Enable))
     return LoopUnrollResult::Unmodified;
 
+  bool OptForSize = L->getHeader()->getParent()->hasOptSize();
   unsigned NumInlineCandidates;
   bool NotDuplicatable;
   bool Convergent;
@@ -1000,8 +1002,11 @@ static LoopUnrollResult tryToUnrollLoop(
       L, SE, TTI, BFI, PSI, OptLevel, ProvidedThreshold, ProvidedCount,
       ProvidedAllowPartial, ProvidedRuntime, ProvidedUpperBound,
       ProvidedAllowPeeling);
-  // Exit early if unrolling is disabled.
-  if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0))
+
+  // Exit early if unrolling is disabled. For OptForSize, we pick the loop size
+  // as threshold later on.
+  if (UP.Threshold == 0 && (!UP.Partial || UP.PartialThreshold == 0) &&
+      !OptForSize)
     return LoopUnrollResult::Unmodified;
 
   SmallPtrSet<const Value *, 32> EphValues;
@@ -1016,6 +1021,12 @@ static LoopUnrollResult tryToUnrollLoop(
                       << " instructions.\n");
     return LoopUnrollResult::Unmodified;
   }
+
+  // When optimizing for size, use LoopSize as threshold, to (fully) unroll
+  // loops, if it does not increase code size.
+  if (OptForSize)
+    UP.Threshold = std::max(UP.Threshold, LoopSize);
+
   if (NumInlineCandidates != 0) {
     LLVM_DEBUG(dbgs() << "  Not unrolling loop with inlinable calls.\n");
     return LoopUnrollResult::Unmodified;

diff --git a/test/Transforms/LoopUnroll/AArch64/unroll-optsize.ll b/test/Transforms/LoopUnroll/AArch64/unroll-optsize.ll
new file mode 100644 (file)
index 0000000..c0bf00b
--- /dev/null
+++ b/test/Transforms/LoopUnroll/AArch64/unroll-optsize.ll
@@ -0,0 +1,171 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -loop-unroll -mtriple=arm64-apple-iphoneos -S %s | FileCheck %s
+
+; Check we unroll even with optsize, if the result is smaller, either because
+; we have single iteration loops or bodies with constant folding opportunities
+; after fully unrolling.
+
+declare i32 @get()
+
+define void @fully_unrolled_single_iteration(i32* %src) #0 {
+; CHECK-LABEL: @fully_unrolled_single_iteration(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARR:%.*]] = alloca [4 x i32], align 4
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[V:%.*]] = load i32, i32* [[SRC:%.*]]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
+; CHECK-NEXT:    store i32 [[V]], i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
+; CHECK-NEXT:    call void @use(i32* nonnull [[PTR]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %arr = alloca [4 x i32], align 4
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %src.idx = getelementptr inbounds i32, i32* %src, i64 %indvars.iv
+  %v = load i32, i32* %src.idx
+  %arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
+  store i32 %v, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  %ptr = bitcast [4 x i32]* %arr to i32*
+  call void @use(i32* nonnull %ptr) #4
+  ret void
+}
+
+
+define void @fully_unrolled_smaller() #0 {
+; CHECK-LABEL: @fully_unrolled_smaller(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARR:%.*]] = alloca [4 x i32], align 4
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
+; CHECK-NEXT:    store i32 16, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_1:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 1
+; CHECK-NEXT:    store i32 4104, i32* [[ARRAYIDX_1]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_2:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 2
+; CHECK-NEXT:    store i32 1048592, i32* [[ARRAYIDX_2]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_3:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 3
+; CHECK-NEXT:    store i32 268435480, i32* [[ARRAYIDX_3]], align 4
+; CHECK-NEXT:    [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
+; CHECK-NEXT:    call void @use(i32* nonnull [[PTR]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %arr = alloca [4 x i32], align 4
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %indvars.iv.tr = trunc i64 %indvars.iv to i32
+  %shl.0 = shl i32 %indvars.iv.tr, 3
+  %shl.1 = shl i32 16, %shl.0
+  %or = or i32 %shl.1, %shl.0
+  %arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
+  store i32 %or, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv, 3
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  %ptr = bitcast [4 x i32]* %arr to i32*
+  call void @use(i32* nonnull %ptr) #4
+  ret void
+}
+
+define void @fully_unrolled_smaller_Oz() #1 {
+; CHECK-LABEL: @fully_unrolled_smaller_Oz(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARR:%.*]] = alloca [4 x i32], align 4
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 0
+; CHECK-NEXT:    store i32 16, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_1:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 1
+; CHECK-NEXT:    store i32 4104, i32* [[ARRAYIDX_1]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_2:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 2
+; CHECK-NEXT:    store i32 1048592, i32* [[ARRAYIDX_2]], align 4
+; CHECK-NEXT:    [[ARRAYIDX_3:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 3
+; CHECK-NEXT:    store i32 268435480, i32* [[ARRAYIDX_3]], align 4
+; CHECK-NEXT:    [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
+; CHECK-NEXT:    call void @use(i32* nonnull [[PTR]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %arr = alloca [4 x i32], align 4
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %indvars.iv.tr = trunc i64 %indvars.iv to i32
+  %shl.0 = shl i32 %indvars.iv.tr, 3
+  %shl.1 = shl i32 16, %shl.0
+  %or = or i32 %shl.1, %shl.0
+  %arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
+  store i32 %or, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv, 3
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  %ptr = bitcast [4 x i32]* %arr to i32*
+  call void @use(i32* nonnull %ptr) #4
+  ret void
+}
+
+
+define void @fully_unrolled_bigger() #0 {
+; CHECK-LABEL: @fully_unrolled_bigger(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ARR:%.*]] = alloca [4 x i32], align 4
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[INDVARS_IV_TR:%.*]] = trunc i64 [[INDVARS_IV]] to i32
+; CHECK-NEXT:    [[SHL_0:%.*]] = shl i32 [[INDVARS_IV_TR]], 3
+; CHECK-NEXT:    [[SHL_1:%.*]] = shl i32 16, [[SHL_0]]
+; CHECK-NEXT:    [[OR:%.*]] = or i32 [[SHL_1]], [[SHL_0]]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [4 x i32], [4 x i32]* [[ARR]], i64 0, i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store i32 [[OR]], i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV]], 6
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    [[PTR:%.*]] = bitcast [4 x i32]* [[ARR]] to i32*
+; CHECK-NEXT:    call void @use(i32* nonnull [[PTR]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %arr = alloca [4 x i32], align 4
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+  %indvars.iv.tr = trunc i64 %indvars.iv to i32
+  %shl.0 = shl i32 %indvars.iv.tr, 3
+  %shl.1 = shl i32 16, %shl.0
+  %or = or i32 %shl.1, %shl.0
+  %arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %arr, i64 0, i64 %indvars.iv
+  store i32 %or, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv, 6
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.cond
+  %ptr = bitcast [4 x i32]* %arr to i32*
+  call void @use(i32* nonnull %ptr) #4
+  ret void
+}
+
+declare void @use(i32*)
+
+attributes #0 = { optsize }
+attributes #1 = { minsize optsize }