+
+; This case could easily end up inf-looping in the DAG combiner due to an
+; low alignment load of the vector which prevents us from reliably forming a
+; narrow load.
+; FIXME: It would be nice to detect whether the target has fast and legal
+; unaligned loads and use them here.
+define void @t3() {
+; CHECK-LABEL: t3:
+;
+; This movs the entire vector, shuffling the high double down. If we fixed the
+; FIXME above it would just move the high double directly.
+; CHECK: movupd
+; CHECK: shufpd
+; CHECK: movlpd
+
+bb:
+ %tmp13 = load <2 x double>* undef, align 1
+ %.sroa.3.24.vec.extract = extractelement <2 x double> %tmp13, i32 1
+ store double %.sroa.3.24.vec.extract, double* undef, align 8
+ unreachable
+}
+
+; Case where a load is unary shuffled, then bitcast (to a type with the same
+; number of elements) before extractelement.
+; This is testing for an assertion - the extraction was assuming that the undef
+; second shuffle operand was a post-bitcast type instead of a pre-bitcast type.
+define i64 @t4(<2 x double>* %a) {
+; CHECK-LABEL: t4:
+; CHECK: mov
+; CHECK: ret
+ %b = load <2 x double>* %a, align 16
+ %c = shufflevector <2 x double> %b, <2 x double> %b, <2 x i32> <i32 1, i32 0>
+ %d = bitcast <2 x double> %c to <2 x i64>
+ %e = extractelement <2 x i64> %d, i32 1
+ ret i64 %e
+}
+