[PowerPC] Implement vector float and vector double version for vec_orc builtin

[Conanap]

Summary

The builtin for vec_orc has support for the following two signatures,
but currently the compiler marks it ambiguous:
vector float vec_orc(vector float, vector float)
vector double vec_orc(vector double, vector double)

This patch implements these two builtins.

[nemanjai]

LGTM. Please run clang-format on the patch (only the modified lines).

clang/lib/Headers/altivec.h

7164

nit: line too long?

clang/lib/Headers/altivec.h

  return (vector float)(__a | ~(vector unsigned int)__b);
 }
 
 static __inline__ vector float __ATTRS_o_ai
 vec_orc(vector float __a, vector bool int __b) {
   return (vector float)((vector unsigned int)__a | ~__b);
 }
 
+static __inline__ vector float __ATTRS_o_ai
+vec_orc(vector float __a, vector float __b) {
+  return (vector float) ((vector unsigned int)__a | ~(vector unsigned int)__b);
+}
+
 static __inline__ vector signed long long __ATTRS_o_ai
 vec_orc(vector signed long long __a, vector signed long long __b) {
   return __a | ~__b;
 }
 
 static __inline__ vector signed long long __ATTRS_o_ai
 vec_orc(vector signed long long __a, vector bool long long __b) {
   return __a | ~__b;

 vec_orc(vector double __a, vector bool long long __b) {
   return (vector double)((vector unsigned long long)__a | ~__b);
 }
 
 static __inline__ vector double __ATTRS_o_ai
 vec_orc(vector bool long long __a, vector double __b) {
   return (vector double)(__a | ~(vector unsigned long long)__b);
 }
+
+static __inline__ vector double __ATTRS_o_ai
+vec_orc(vector double __a, vector double __b) {
+  return (vector double)((vector bool long long)__a | ~(vector unsigned long long)__b);
+}
 #endif
 
 /* vec_vor */
 
 static __inline__ vector signed char __ATTRS_o_ai
 vec_vor(vector signed char __a, vector signed char __b) {
   return __a | __b;
 }

clang/test/CodeGen/builtins-ppc-p8vector.c

 vector signed long long vsll = { 1, 2 };
 vector unsigned long long vull = { 1, 2 };
 vector bool long long vbll = { 1, 0 };
 
 vector signed __int128 vsx = { 1 };
 vector unsigned __int128 vux = { 1 };
 
 vector float vfa = { 1.e-4f, -132.23f, -22.1, 32.00f };
+vector float vfb = { 1.e-4f, -132.23f, -22.1, 32.00f };
 vector double vda = { 1.e-11, -132.23e10 };
+vector double vdb = { 1.e-11, -132.23e10 };
 
 int res_i;
 double res_d;
 signed long long res_sll;
 unsigned long long res_ull;
 
 vector signed char res_vsc;
 vector unsigned char res_vuc;

 // CHECK-LE: or <4 x i32> {{%.+}}, [[T1]]
 
   res_vf = vec_orc(vfa, vbi);
 // CHECK: [[T1:%.+]] = xor <4 x i32> {{%.+}}, <i32 -1, i32 -1, i32 -1, i32 -1>
 // CHECK: or <4 x i32> {{%.+}}, [[T1]]
 // CHECK-LE: [[T1:%.+]] = xor <4 x i32> {{%.+}}, <i32 -1, i32 -1, i32 -1, i32 -1>
 // CHECK-LE: or <4 x i32> {{%.+}}, [[T1]]
 
+  res_vf = vec_orc(vfa, vfb);
+// CHECK: [[T1:%.+]] = xor <4 x i32> {{%.+}}, <i32 -1, i32 -1, i32 -1, i32 -1>
+// CHECK: or <4 x i32> {{%.+}}, [[T1]]
+// CHECK-LE: [[T1:%.+]] = xor <4 x i32> {{%.+}}, <i32 -1, i32 -1, i32 -1, i32 -1>
+// CHECK-LE: or <4 x i32> {{%.+}}, [[T1]]
+
   res_vsll = vec_orc(vsll, vsll);
 // CHECK: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
 // CHECK: or <2 x i64> {{%.+}}, [[T1]]
 // CHECK-LE: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
 // CHECK-LE: or <2 x i64> {{%.+}}, [[T1]]
 
   res_vsll = vec_orc(vsll, vbll);
 // CHECK: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>

 // CHECK-LE: or <2 x i64> {{%.+}}, [[T1]]
 
   res_vd = vec_orc(vda, vbll);
 // CHECK: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
 // CHECK: or <2 x i64> {{%.+}}, [[T1]]
 // CHECK-LE: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
 // CHECK-LE: or <2 x i64> {{%.+}}, [[T1]]
 
+  res_vd = vec_orc(vda, vdb);
+// CHECK: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
+// CHECK: or <2 x i64> {{%.+}}, [[T1]]
+// CHECK-LE: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
+// CHECK-LE: or <2 x i64> {{%.+}}, [[T1]]
+
   /* vec_sub */
   res_vsll = vec_sub(vsll, vsll);
 // CHECK: sub <2 x i64>
 // CHECK-LE: sub <2 x i64>
 
   res_vull = vec_sub(vull, vull);
 // CHECK: sub <2 x i64>
 // CHECK-LE: sub <2 x i64>