From 9455c1d2b1fc7cd551ff80f004e14cf9ffd4c371 Mon Sep 17 00:00:00 2001
From: Adam Nemet <anemet@apple.com>
Date: Fri, 5 Feb 2016 01:14:05 +0000
Subject: [PATCH] [LoopLoadElim] Don't allow versioning when optForSize

This was requested in the review of D16300.

llvm-svn: 259861
---
 llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp | 11 +++-
 llvm/test/Transforms/LoopLoadElim/opt-size.ll      | 76 ++++++++++++++++++++++
 2 files changed, 85 insertions(+), 2 deletions(-)
 create mode 100644 llvm/test/Transforms/LoopLoadElim/opt-size.ll

diff --git a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
index 1064d08..db96bea 100644
--- a/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopLoadElimination.cpp
@@ -465,9 +465,16 @@ public:
       return false;
     }
 
-    // Point of no-return, start the transformation.  First, version the loop if
-    // necessary.
     if (!Checks.empty() || !LAI.PSE.getUnionPredicate().isAlwaysTrue()) {
+      if (L->getHeader()->getParent()->optForSize()) {
+        DEBUG(dbgs() << "Versioning is needed but not allowed when optimizing "
+                        "for size.\n");
+        return false;
+      }
+
+      // Point of no-return, start the transformation.  First, version the loop
+      // if necessary.
+
       LoopVersioning LV(LAI, L, LI, DT, PSE.getSE(), false);
       LV.setAliasChecks(std::move(Checks));
       LV.setSCEVChecks(LAI.PSE.getUnionPredicate());
diff --git a/llvm/test/Transforms/LoopLoadElim/opt-size.ll b/llvm/test/Transforms/LoopLoadElim/opt-size.ll
new file mode 100644
index 0000000..a6322d8
--- /dev/null
+++ b/llvm/test/Transforms/LoopLoadElim/opt-size.ll
@@ -0,0 +1,76 @@
+; RUN: opt -basicaa -loop-load-elim -S < %s | FileCheck %s
+
+; When optimizing for size don't eliminate in this loop because the loop would
+; have to be versioned first because A and C may alias.
+;
+;   for (unsigned i = 0; i < 100; i++) {
+;     A[i+1] = B[i] + 2;
+;     C[i] = A[i] * 2;
+;   }
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; CHECK-LABEL: @f(
+define void @f(i32* %A, i32* %B, i32* %C, i64 %N) optsize {
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+  %Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next
+  %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
+  %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
+  %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+
+  %b = load i32, i32* %Bidx, align 4
+  %a_p1 = add i32 %b, 2
+  store i32 %a_p1, i32* %Aidx_next, align 4
+
+  %a = load i32, i32* %Aidx, align 4
+; CHECK: %c = mul i32 %a, 2
+  %c = mul i32 %a, 2
+  store i32 %c, i32* %Cidx, align 4
+
+  %exitcond = icmp eq i64 %indvars.iv.next, %N
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
+
+; Same loop but with noalias on %A and %C.  In this case load-eliminate even
+; with -Os.
+
+; CHECK-LABEL: @g(
+define void @g(i32* noalias %A, i32* %B, i32* noalias %C, i64 %N) optsize {
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+
+  %Aidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next
+  %Bidx = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
+  %Cidx = getelementptr inbounds i32, i32* %C, i64 %indvars.iv
+  %Aidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
+
+  %b = load i32, i32* %Bidx, align 4
+  %a_p1 = add i32 %b, 2
+  store i32 %a_p1, i32* %Aidx_next, align 4
+
+  %a = load i32, i32* %Aidx, align 4
+; CHECK: %c = mul i32 %store_forwarded, 2
+  %c = mul i32 %a, 2
+  store i32 %c, i32* %Cidx, align 4
+
+  %exitcond = icmp eq i64 %indvars.iv.next, %N
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}
-- 
2.7.4