Index: lib/Transforms/Scalar/SROA.cpp
===================================================================
--- lib/Transforms/Scalar/SROA.cpp
+++ lib/Transforms/Scalar/SROA.cpp
@@ -3033,7 +3033,22 @@
     ConstantInt *Size =
         ConstantInt::get(cast<IntegerType>(II.getArgOperand(0)->getType()),
                          NewEndOffset - NewBeginOffset);
-    Value *Ptr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
+    // For lifetime intrinsics it's ok to cast a pointer type of a new slice
+    // to a generic i8* pointer. There is a case when using the pointer type
+    // from whole alloca leads to an assertion in PromoteMemToReg. A code
+    // looks like this. The initial alloca is
+    //
+    // alloca [10 x float]
+    //
+    // it's split into several allocas and one is just a float
+    //
+    // alloca float
+    //
+    // which is bitcast'ed to [10 x float]* type.  When PromoteMemToReg gets
+    // such bitcast it throws the assertion.
+    Type *PointerTy = IRB.getInt8PtrTy(OldPtr->getType()->getPointerAddressSpace());
+    Value *Ptr = getNewAllocaSlicePtr(IRB, PointerTy);
+
     Value *New;
     if (II.getIntrinsicID() == Intrinsic::lifetime_start)
       New = IRB.CreateLifetimeStart(Ptr, Size);
Index: test/Transforms/SROA/extra-cast-in-lifetime.ll
===================================================================
--- /dev/null
+++ test/Transforms/SROA/extra-cast-in-lifetime.ll
@@ -0,0 +1,52 @@
+; RUN: opt < %s -S -sroa | FileCheck %s
+
+@MainKernel.callA = dso_local addrspace(3) global [10 x float] undef, align 4
+
+define void @MainKernel(i32 %iNumSteps, i32 %tid) {
+; CHECK-LABEL: @MainKernel(
+; CHECK-NOT: alloca [10 x float]
+; CHECK: ret void
+
+entry:
+  %rA = alloca [10 x float], align 4
+  call void @llvm.lifetime.start.isVoid.i64.p0i8(i64 40, [10 x float]* nonnull %rA)
+ 
+  %cmp1 = icmp sgt i32 %iNumSteps, 0
+  br i1 %cmp1, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry
+  %tobool = icmp eq i32 %tid, 0
+  %conv.i = zext i32 %tid to i64
+  %0 = bitcast [10 x float]* %rA to i32*
+  %1 = load i32, i32* %0, align 4
+  %arrayidx5 = getelementptr inbounds [10 x float], [10 x float] addrspace(3)* @MainKernel.callA, i64 0, i64 %conv.i
+  %2 = bitcast float addrspace(3)* %arrayidx5 to i32 addrspace(3)*
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.inc
+  %i.02 = phi i32 [ %iNumSteps, %for.body.lr.ph ], [ %sub, %for.inc ]
+  br i1 %tobool, label %for.body.for.inc_crit_edge, label %if.then
+
+for.body.for.inc_crit_edge:                       ; preds = %for.body
+  br label %for.inc
+
+if.then:                                          ; preds = %for.body
+  store i32 %1, i32 addrspace(3)* %2, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body.for.inc_crit_edge, %if.then
+  %sub = add i32 %i.02, -1
+  %cmp = icmp sgt i32 %sub, 0
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge
+
+for.cond.for.end_crit_edge:                       ; preds = %for.inc
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
+  call void @llvm.lifetime.end.isVoid.i64.p0i8(i64 40, [10 x float]* nonnull %rA)
+
+  ret void
+}
+
+declare void @llvm.lifetime.start.isVoid.i64.p0i8(i64, [10 x float]* nocapture)
+declare void @llvm.lifetime.end.isVoid.i64.p0i8(i64, [10 x float]* nocapture)