[Matrix] Fix test on SystemZ

[kuhar]

Summary

As reported by @uweigand in https://reviews.llvm.org/D158883:

The newly added test cases in ffp-model.c fail on SystemZ, making CI red:
https://lab.llvm.org/buildbot/#/builders/94/builds/16280

The root cause seems to be that by default, the SystemZ back-end targets
a machine without SIMD support, and therefore vector return types are
passed via implicit reference according to the ABI

this uses manual stores instead of vector returns.

[kuhar]

Gah, disregard

clang/test/CodeGen/ffp-model.c

float mymuladd(float x, float y, float z) {
   // CHECK-FAST1: load float, ptr
   // CHECK-FAST1: fmul fast float {{.*}}, {{.*}}
   // CHECK-FAST1: load float, ptr {{.*}}
   // CHECK-FAST1: fadd fast float {{.*}}, {{.*}}
 }
 
 typedef float __attribute__((ext_vector_type(2))) v2f;
 
-v2f my_vec_muladd(v2f x, float y, v2f z) {
-  // CHECK: define{{.*}} @my_vec_muladd
-  return x * y + z;
+void my_vec_muladd(v2f x, float y, v2f z, v2f *res) {
+  // CHECK: define{{.*}}@my_vec_muladd
+  *res = x * y + z;
 
   // CHECK-FAST: fmul fast <2 x float>
   // CHECK-FAST: load <2 x float>, ptr
   // CHECK-FAST: fadd fast <2 x float>
 
   // CHECK-PRECISE: load <2 x float>, ptr
   // CHECK-PRECISE: load float, ptr
   // CHECK-PRECISE: load <2 x float>, ptr
void my_vec_muladd(v2f x, float y, v2f z, v2f *res) {
   // CHECK-FAST1: load float, ptr
   // CHECK-FAST1: fmul fast <2 x float> {{.*}}, {{.*}}
   // CHECK-FAST1: load <2 x float>, ptr {{.*}}
   // CHECK-FAST1: fadd fast <2 x float> {{.*}}, {{.*}}
 }
 
 typedef float __attribute__((matrix_type(2, 1))) m21f;
 
-m21f my_m21_muladd(m21f x, float y, m21f z) {
-  // CHECK: define{{.*}} <2 x float> @my_m21_muladd
-  return x * y + z;
+void my_m21_muladd(m21f x, float y, m21f z, m21f *res) {
+  // CHECK: define{{.*}}@my_m21_muladd
+  *res = x * y + z;
 
   // CHECK-FAST: fmul fast <2 x float>
   // CHECK-FAST: load <2 x float>, ptr
   // CHECK-FAST: fadd fast <2 x float>
 
   // CHECK-PRECISE: load <2 x float>, ptr
   // CHECK-PRECISE: load float, ptr
   // CHECK-PRECISE: load <2 x float>, ptr
void my_m21_muladd(m21f x, float y, m21f z, m21f *res) {
   // CHECK-FAST1: load float, ptr
   // CHECK-FAST1: fmul fast <2 x float> {{.*}}, {{.*}}
   // CHECK-FAST1: load <2 x float>, ptr {{.*}}
   // CHECK-FAST1: fadd fast <2 x float> {{.*}}, {{.*}}
 }
 
 typedef float __attribute__((matrix_type(2, 2))) m22f;
 
-m22f my_m22_muladd(m22f x, float y, m22f z) {
-  // CHECK: define{{.*}} <4 x float> @my_m22_muladd
-  return x * y + z;
+void my_m22_muladd(m22f x, float y, m22f z, m22f *res) {
+  // CHECK: define{{.*}}@my_m22_muladd
+  *res = x * y + z;
 
   // CHECK-FAST: fmul fast <4 x float>
   // CHECK-FAST: load <4 x float>, ptr
   // CHECK-FAST: fadd fast <4 x float>
 
   // CHECK-PRECISE: load <4 x float>, ptr
   // CHECK-PRECISE: load float, ptr
   // CHECK-PRECISE: load <4 x float>, ptr