[PowerPC] Implement low-order Vector Modulus Builtins, and add Vector Multiply/Divide/Modulus Builtins Tests

Power10 introduces new instructions for vector multiply, divide and modulus.
These instructions can be exploited by the builtin functions: vec_mul, vec_div,
and vec_mod, respectively.

This patch aims adds the function prototype, vec_mod, as vec_mul and vec_div
been previously implemented in altivec.h.

This patch also adds the following front end tests:
vec_mul for v2i64
vec_div for v4i32 and v2i64
vec_mod for v4i32 and v2i64

Differential Revision: https://reviews.llvm.org/D82576

clang/lib/Headers/altivec.h

@@ -16933,6 +16933,28 @@ vec_cnttzm(vector unsigned long long __a, vector unsigned long long __b) {
   return __builtin_altivec_vctzdm(__a, __b);
 }
 
+/* vec_mod */
+
+static __inline__ vector signed int __ATTRS_o_ai
+vec_mod(vector signed int __a, vector signed int __b) {
+  return __a % __b;
+}
+
+static __inline__ vector unsigned int __ATTRS_o_ai
+vec_mod(vector unsigned int __a, vector unsigned int __b) {
+  return __a % __b;
+}
+
+static __inline__ vector signed long long __ATTRS_o_ai
+vec_mod(vector signed long long __a, vector signed long long __b) {
+  return __a % __b;
+}
+
+static __inline__ vector unsigned long long __ATTRS_o_ai
+vec_mod(vector unsigned long long __a, vector unsigned long long __b) {
+  return __a % __b;
+}
+
 /* vec_sldbi */
 
 #define vec_sldb(__a, __b, __c) __builtin_altivec_vsldbi(__a, __b, (__c & 0x7))

clang/test/CodeGen/builtins-ppc-p10vector.c

@@ -25,6 +25,66 @@ unsigned char uca;
 unsigned short usa;
 unsigned long long ulla;
 
+vector signed long long test_vec_mul_sll(void) {
+  // CHECK: mul <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_mul(vslla, vsllb);
+}
+
+vector unsigned long long test_vec_mul_ull(void) {
+  // CHECK: mul <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_mul(vulla, vullb);
+}
+
+vector signed int test_vec_div_si(void) {
+  // CHECK: sdiv <4 x i32>
+  // CHECK-NEXT: ret <4 x i32>
+  return vec_div(vsia, vsib);
+}
+
+vector unsigned int test_vec_div_ui(void) {
+  // CHECK: udiv <4 x i32>
+  // CHECK-NEXT: ret <4 x i32>
+  return vec_div(vuia, vuib);
+}
+
+vector signed long long test_vec_div_sll(void) {
+  // CHECK: sdiv <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_div(vslla, vsllb);
+}
+
+vector unsigned long long test_vec_div_ull(void) {
+  // CHECK: udiv <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_div(vulla, vullb);
+}
+
+vector signed int test_vec_mod_si(void) {
+  // CHECK: srem <4 x i32>
+  // CHECK-NEXT: ret <4 x i32>
+  return vec_mod(vsia, vsib);
+}
+
+vector unsigned int test_vec_mod_ui(void) {
+  // CHECK: urem <4 x i32>
+  // CHECK-NEXT: ret <4 x i32>
+  return vec_mod(vuia, vuib);
+}
+
+vector signed long long test_vec_mod_sll(void) {
+  // CHECK: srem <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_mod(vslla, vsllb);
+}
+
+vector unsigned long long test_vec_mod_ull(void) {
+  // CHECK: urem <2 x i64>
+  // CHECK-NEXT: ret <2 x i64>
+  return vec_mod(vulla, vullb);
+}
+
 vector unsigned long long test_vpdepd(void) {
   // CHECK: @llvm.ppc.altivec.vpdepd(<2 x i64>
   // CHECK-NEXT: ret <2 x i64>