Patch bug in 9a45e4b. Prevent SSA breaks when lifetime intrinsics are moved.

Author: clin111

llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp

@@ -931,6 +931,14 @@ bool MemCpyOptPass::performCallSlotOptzn(Instruction *cpyLoad,
     return false;
   }
 
+  // Code below tries to move the lifetime marker before "C". Check the
+  // correctness of this motion.
+  if (SkippedLifetimeStart && SkippedLifetimeStart->getNumOperands() == 3) {
+    auto *LiveI = cast<Instruction>(SkippedLifetimeStart->getOperand(1));
+    if (!DT->dominates(LiveI, C))
+      return false;
+  }
+
   // Check that accessing the first srcSize bytes of dest will not cause a
   // trap.  Otherwise the transform is invalid since it might cause a trap
   // to occur earlier than it otherwise would.

llvm/test/Transforms/MemCpyOpt/intel-lifetime-move.ll

@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="memcpyopt" -S %s | FileCheck %s
+
+; memcpyopt lifetime skipping, is moving the lifetime.start before the def
+; of %tm3.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+%struct.foo = type { ptr, ptr, i64, i64 }
+
+declare dso_local i32 @pluto(...)
+
+define dso_local void @wombat(ptr %meow) local_unnamed_addr {
+; CHECK-LABEL: @wombat(
+; CHECK-NEXT:  bb:
+; CHECK-NEXT:    [[TM:%.*]] = alloca [[STRUCT_FOO:%.*]], align 8
+; CHECK-NEXT:    [[TM1:%.*]] = alloca [[STRUCT_FOO]], align 8
+; CHECK-NEXT:    [[TM2:%.*]] = bitcast ptr [[TM1]] to ptr
+; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 8 dereferenceable(32) [[TM2]], ptr noundef nonnull align 8 dereferenceable(32) [[MEOW:%.*]], i64 32, i1 false)
+; CHECK-NEXT:    [[TM3:%.*]] = bitcast ptr [[TM]] to ptr
+; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 32, ptr nonnull [[TM3]])
+; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 8 [[TM3]], ptr align 8 [[MEOW]], i64 32, i1 false)
+; CHECK-NEXT:    ret void
+;
+bb:
+  %tm = alloca %struct.foo, align 8
+  %tm1 = alloca %struct.foo, align 8
+  %tm2 = bitcast ptr %tm1 to ptr
+  call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 8 dereferenceable(32) %tm2, ptr noundef nonnull align 8 dereferenceable(32) %meow, i64 32, i1 false)
+  %tm3 = bitcast ptr %tm to ptr
+  call void @llvm.lifetime.start.p0(i64 32, ptr nonnull %tm3)
+  call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 8 dereferenceable(32) %tm3, ptr noundef nonnull align 8 dereferenceable(32) %tm2, i64 32, i1 false)
+  ret void
+}
+
+; Function Attrs: nocallback nofree nosync nounwind willreturn memory(argmem: readwrite)
+declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture) #1
+
+; Function Attrs: nocallback nofree nounwind willreturn memory(argmem: readwrite)
+declare void @llvm.memcpy.p0.p0.i64(ptr noalias nocapture writeonly, ptr noalias nocapture readonly, i64, i1 immarg) #2
+
+attributes #1 = { nocallback nofree nosync nounwind willreturn memory(argmem: readwrite) }
+attributes #2 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }