HotColdSplitting: invalidate the AssumptionCache on split

When a cold path is outlined, the value tracking in the assumption cache may be
invalidated due to the code motion.  We would previously trip an assertion in
subsequent passes (but required the passes to happen in a single run as the
assumption cache is shared across the passes).  Invalidating the cache ensures
that we get the correct information when needed with the legacy pass manager as
well.

llvm-svn: 372667

diff --git a/llvm/lib/Transforms/IPO/HotColdSplitting.cpp b/llvm/lib/Transforms/IPO/HotColdSplitting.cpp
index 79a5a9b..49937a7 100644 (file)
--- a/llvm/lib/Transforms/IPO/HotColdSplitting.cpp
+++ b/llvm/lib/Transforms/IPO/HotColdSplitting.cpp
@@ -659,6 +659,11 @@ bool HotColdSplitting::outlineColdRegions(Function &F, bool HasProfileSummary) {
     } while (!Region.empty());
   }
 
+  // We need to explicitly clear the assumption cache since the value tracking
+  // may now be invalid as part of the function has changed.
+  if (Changed)
+    if (AssumptionCache *AC = LookupAC(F))
+      AC->clear();
   return Changed;
 }
 

diff --git a/llvm/test/Transforms/HotColdSplit/assumption-cache-invalidation.ll b/llvm/test/Transforms/HotColdSplit/assumption-cache-invalidation.ll
new file mode 100644 (file)
index 0000000..811b507
--- /dev/null
+++ b/llvm/test/Transforms/HotColdSplit/assumption-cache-invalidation.ll
@@ -0,0 +1,38 @@
+; RUN: opt -instcombine -hotcoldsplit -instsimplify %s -o /dev/null
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64"
+
+%a = type { i64, i64 }
+%b = type { i64 }
+
+define void @f() {
+entry:
+  %0 = getelementptr inbounds %a, %a* null, i64 0, i32 1
+  br label %label
+
+label:
+  %1 = bitcast i64* %0 to %b**
+  %2 = load %b*, %b** %1, align 8
+  %3 = getelementptr inbounds %b, %b* %2, i64 undef, i32 0
+  %4 = load i64, i64* %3, align 8
+  %5 = icmp ugt i64 %4, 1
+  br i1 %5, label %if.then, label %if.else
+
+if.then:
+  unreachable
+
+if.else:
+  call void @g(i8* undef)
+  %6 = load i64, i64* undef, align 8
+  %7 = and i64 %6, -16
+  %8 = inttoptr i64 %7 to i8*
+  %9 = icmp eq i64 %4, 0
+  call void @llvm.assume(i1 %9)
+  unreachable
+}
+
+declare void @g(i8*)
+
+declare void @llvm.assume(i1)
+