+define void @testv1(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %e, <2 x double>* nocapture %d) #0 {
+entry:
+ %0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %a)
+ store <2 x double> %0, <2 x double>* %d, align 8
+ %1 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %e, <2 x double> %a)
+ %arrayidx1 = getelementptr inbounds <2 x double>* %d, i64 1
+ store <2 x double> %1, <2 x double>* %arrayidx1, align 8
+ ret void
+
+; CHECK-LABEL: @testv1
+; CHECK-DAG: xvmaddmdp 36, 35, 34
+; CHECK-DAG: xvmaddadp 34, 35, 37
+; CHECK-DAG: li [[C1:[0-9]+]], 16
+; CHECK-DAG: stxvd2x 36, 0, 3
+; CHECK-DAG: stxvd2x 34, 3, [[C1:[0-9]+]]
+; CHECK: blr
+}
+
+define void @testv2(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %e, <2 x double> %f, <2 x double>* nocapture %d) #0 {
+entry:
+ %0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %a)
+ store <2 x double> %0, <2 x double>* %d, align 8
+ %1 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %e, <2 x double> %a)
+ %arrayidx1 = getelementptr inbounds <2 x double>* %d, i64 1
+ store <2 x double> %1, <2 x double>* %arrayidx1, align 8
+ %2 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %f, <2 x double> %a)
+ %arrayidx2 = getelementptr inbounds <2 x double>* %d, i64 2
+ store <2 x double> %2, <2 x double>* %arrayidx2, align 8
+ ret void
+
+; CHECK-LABEL: @testv2
+; CHECK-DAG: xvmaddmdp 36, 35, 34
+; CHECK-DAG: xvmaddmdp 37, 35, 34
+; CHECK-DAG: li [[C1:[0-9]+]], 16
+; CHECK-DAG: li [[C2:[0-9]+]], 32
+; CHECK-DAG: xvmaddadp 34, 35, 38
+; CHECK-DAG: stxvd2x 36, 0, 3
+; CHECK-DAG: stxvd2x 37, 3, [[C1:[0-9]+]]
+; CHECK-DAG: stxvd2x 34, 3, [[C2:[0-9]+]]
+; CHECK: blr
+}
+
+define void @testv3(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %e, <2 x double> %f, <2 x double>* nocapture %d) #0 {
+entry:
+ %0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %a)
+ store <2 x double> %0, <2 x double>* %d, align 8
+ %1 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %e, <2 x double> %a)
+ %2 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %1)
+ %arrayidx1 = getelementptr inbounds <2 x double>* %d, i64 3
+ store <2 x double> %2, <2 x double>* %arrayidx1, align 8
+ %3 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %f, <2 x double> %a)
+ %arrayidx2 = getelementptr inbounds <2 x double>* %d, i64 2
+ store <2 x double> %3, <2 x double>* %arrayidx2, align 8
+ %arrayidx3 = getelementptr inbounds <2 x double>* %d, i64 1
+ store <2 x double> %1, <2 x double>* %arrayidx3, align 8
+ ret void
+
+; CHECK-LABEL: @testv3
+; CHECK-DAG: xxlor [[V1:[0-9]+]], 34, 34
+; CHECK-DAG: xvmaddmdp 37, 35, 34
+; CHECK-DAG: li [[C1:[0-9]+]], 48
+; CHECK-DAG: li [[C2:[0-9]+]], 32
+; CHECK-DAG: xvmaddadp 34, 35, 38
+; CHECK-DAG: li [[C3:[0-9]+]], 16
+
+; Note: We could convert this next FMA to M-type as well, but it would require
+; re-ordering the instructions.
+; CHECK-DAG: xvmaddadp [[V1]], 35, 36
+
+; CHECK-DAG: xvmaddmdp 35, 36, 37
+; CHECK-DAG: stxvd2x 32, 0, 3
+; CHECK-DAG: stxvd2x 35, 3, [[C1]]
+; CHECK-DAG: stxvd2x 34, 3, [[C2]]
+; CHECK-DAG: stxvd2x 37, 3, [[C3]]
+; CHECK: blr
+}
+
+define void @testv4(<2 x double> %a, <2 x double> %b, <2 x double> %c, <2 x double> %e, <2 x double> %f, <2 x double>* nocapture %d) #0 {
+entry:
+ %0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %a)
+ store <2 x double> %0, <2 x double>* %d, align 8
+ %1 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %e, <2 x double> %a)
+ %arrayidx1 = getelementptr inbounds <2 x double>* %d, i64 1
+ store <2 x double> %1, <2 x double>* %arrayidx1, align 8
+ %2 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %c, <2 x double> %1)
+ %arrayidx3 = getelementptr inbounds <2 x double>* %d, i64 3
+ store <2 x double> %2, <2 x double>* %arrayidx3, align 8
+ %3 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %b, <2 x double> %f, <2 x double> %a)
+ %arrayidx4 = getelementptr inbounds <2 x double>* %d, i64 2
+ store <2 x double> %3, <2 x double>* %arrayidx4, align 8
+ ret void
+
+; CHECK-LABEL: @testv4
+; CHECK-DAG: xxlor [[V1:[0-9]+]], 34, 34
+; CHECK-DAG: xvmaddmdp 37, 35, 34
+; CHECK-DAG: li [[C1:[0-9]+]], 16
+; CHECK-DAG: li [[C2:[0-9]+]], 32
+; CHECK-DAG: xvmaddadp 34, 35, 38
+
+; Note: We could convert this next FMA to M-type as well, but it would require
+; re-ordering the instructions.
+; CHECK-DAG: xvmaddadp [[V1]], 35, 36
+
+; CHECK-DAG: stxvd2x 32, 0, 3
+; CHECK-DAG: stxvd2x 37, 3, [[C1]]
+; CHECK-DAG: li [[C3:[0-9]+]], 48
+; CHECK-DAG: xvmaddadp 37, 35, 36
+; CHECK-DAG: stxvd2x 37, 3, [[C3]]
+; CHECK-DAG: stxvd2x 34, 3, [[C2]]
+; CHECK: blr
+}
+
+declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>) #0
+