[llvm] r248327 - [Unroll] Follow-up for r247769: fix a bug in UnrolledInstAnalyzer::visitLoad.

[Michael Zolotukhin via llvm-commits]

Author: mzolotukhin
Date: Tue Sep 22 16:41:29 2015
New Revision: 248327

URL: http://llvm.org/viewvc/llvm-project?rev=248327&view=rev
Log:
[Unroll] Follow-up for r247769: fix a bug in UnrolledInstAnalyzer::visitLoad.

Apart from checking that GlobalVariable is a constant, we should check
that it's not a weak constant, in which case we can't propagate its
value.

Modified:
    llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp
    llvm/trunk/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll

Modified: llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp?rev=248327&r1=248326&r2=248327&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/LoopUnrollPass.cpp Tue Sep 22 16:41:29 2015
@@ -415,7 +415,7 @@ private:
     auto *GV = dyn_cast<GlobalVariable>(AddressIt->second.Base);
     // We're only interested in loads that can be completely folded to a
     // constant.
-    if (!GV || !GV->hasInitializer() || !GV->isConstant())
+    if (!GV || !GV->hasDefinitiveInitializer() || !GV->isConstant())
       return false;
 
     ConstantDataSequential *CDS =

Modified: llvm/trunk/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll?rev=248327&r1=248326&r2=248327&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll (original)
+++ llvm/trunk/test/Transforms/LoopUnroll/full-unroll-heuristics-2.ll Tue Sep 22 16:41:29 2015
@@ -1,11 +1,13 @@
 ; RUN: opt < %s -S -loop-unroll -unroll-max-iteration-count-to-analyze=1000 -unroll-threshold=10  -unroll-percent-dynamic-cost-saved-threshold=50 -unroll-dynamic-cost-savings-discount=90 | FileCheck %s
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
+ at unknown_global = internal unnamed_addr global [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
+ at weak_constant = weak unnamed_addr constant [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
+
 ; Though @unknown_global is initialized with constant values, we can't consider
 ; it as a constant, so we shouldn't unroll the loop.
+; CHECK-LABEL: @foo
 ; CHECK: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @unknown_global, i64 0, i64 %iv
- at unknown_global = internal unnamed_addr global [9 x i32] [i32 0, i32 -1, i32 0, i32 -1, i32 5, i32 -1, i32 0, i32 -1, i32 0], align 16
-
 define i32 @foo(i32* noalias nocapture readonly %src) {
 entry:
   br label %loop
@@ -19,6 +21,32 @@ loop:
   %const_array_element = load i32, i32* %array_const_idx, align 4
   %mul = mul nsw i32 %src_element, %const_array_element
   %add = add nsw i32 %mul, %r
+  %inc = add nuw nsw i64 %iv, 1
+  %exitcond86.i = icmp eq i64 %inc, 9
+  br i1 %exitcond86.i, label %loop.end, label %loop
+
+loop.end:                                            ; preds = %loop
+  %r.lcssa = phi i32 [ %r, %loop ]
+  ret i32 %r.lcssa
+}
+
+; Similarly, we can't consider 'weak' symbols as a known constant value, so we
+; shouldn't unroll the loop.
+; CHECK-LABEL: @foo2
+; CHECK: %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @weak_constant, i64 0, i64 %iv
+define i32 @foo2(i32* noalias nocapture readonly %src) {
+entry:
+  br label %loop
+
+loop:                                                ; preds = %loop, %entry
+  %iv = phi i64 [ 0, %entry ], [ %inc, %loop ]
+  %r  = phi i32 [ 0, %entry ], [ %add, %loop ]
+  %arrayidx = getelementptr inbounds i32, i32* %src, i64 %iv
+  %src_element = load i32, i32* %arrayidx, align 4
+  %array_const_idx = getelementptr inbounds [9 x i32], [9 x i32]* @weak_constant, i64 0, i64 %iv
+  %const_array_element = load i32, i32* %array_const_idx, align 4
+  %mul = mul nsw i32 %src_element, %const_array_element
+  %add = add nsw i32 %mul, %r
   %inc = add nuw nsw i64 %iv, 1
   %exitcond86.i = icmp eq i64 %inc, 9
   br i1 %exitcond86.i, label %loop.end, label %loop