[ConstantFold] Handle vectors in ConstantFoldLoadThroughBitcast()

There seems to be an impedance mismatch between what the type
system considers an aggregate (structs and arrays) and what
constants consider an aggregate (structs, arrays and vectors).

Rather than adjusting the type check, simply drop it entirely,
as getAggregateElement() is well-defined for non-aggregates: It
simply returns null in that case.

Author: nikic

llvm/lib/Analysis/ConstantFolding.cpp

@@ -387,11 +387,6 @@ Constant *llvm::ConstantFoldLoadThroughBitcast(Constant *C, Type *DestTy,
         return ConstantExpr::getCast(Cast, C, DestTy);
     }
 
-    // If this isn't an aggregate type, there is nothing we can do to drill down
-    // and find a bitcastable constant.
-    if (!SrcTy->isAggregateType())
-      return nullptr;
-
     // We're simulating a load through a pointer that was bitcast to point to
     // a different type, so we can try to walk down through the initial
     // elements of an aggregate to see if some part of the aggregate is

llvm/test/Transforms/GVN/non-integral-pointers-inseltpoison.ll

@@ -213,14 +213,12 @@ entry:
   ret i64 addrspace(4)* %ref
 }
 
-; TODO: missed optimization
 define i8 addrspace(4)* @forward_memcopy(i8 addrspace(4)* addrspace(4)* %loc) {
 ; CHECK-LABEL: @forward_memcopy(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[LOC_BC:%.*]] = bitcast i8 addrspace(4)* addrspace(4)* [[LOC:%.*]] to i8 addrspace(4)*
 ; CHECK-NEXT:    call void @llvm.memcpy.p4i8.p0i8.i64(i8 addrspace(4)* align 4 [[LOC_BC]], i8* bitcast (<4 x i64 addrspace(4)*>* @NonZeroConstant2 to i8*), i64 8, i1 false)
-; CHECK-NEXT:    [[REF:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* [[LOC]], align 8
-; CHECK-NEXT:    ret i8 addrspace(4)* [[REF]]
+; CHECK-NEXT:    ret i8 addrspace(4)* bitcast (i64 addrspace(4)* getelementptr (i64, i64 addrspace(4)* null, i32 3) to i8 addrspace(4)*)
 ;
 entry:
   %loc.bc = bitcast i8 addrspace(4)* addrspace(4)* %loc to i8 addrspace(4)*

llvm/test/Transforms/GVN/non-integral-pointers.ll

@@ -213,14 +213,12 @@ entry:
   ret i64 addrspace(4)* %ref
 }
 
-; TODO: missed optimization
 define i8 addrspace(4)* @forward_memcopy(i8 addrspace(4)* addrspace(4)* %loc) {
 ; CHECK-LABEL: @forward_memcopy(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[LOC_BC:%.*]] = bitcast i8 addrspace(4)* addrspace(4)* [[LOC:%.*]] to i8 addrspace(4)*
 ; CHECK-NEXT:    call void @llvm.memcpy.p4i8.p0i8.i64(i8 addrspace(4)* align 4 [[LOC_BC]], i8* bitcast (<4 x i64 addrspace(4)*>* @NonZeroConstant2 to i8*), i64 8, i1 false)
-; CHECK-NEXT:    [[REF:%.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* [[LOC]], align 8
-; CHECK-NEXT:    ret i8 addrspace(4)* [[REF]]
+; CHECK-NEXT:    ret i8 addrspace(4)* bitcast (i64 addrspace(4)* getelementptr (i64, i64 addrspace(4)* null, i32 3) to i8 addrspace(4)*)
 ;
 entry:
   %loc.bc = bitcast i8 addrspace(4)* addrspace(4)* %loc to i8 addrspace(4)*