[PowerPC][Power10] Implement low-order Vector Modulus Builtins, and add Vector Multiply/Divide/Modulus Builtins Tests

[amyk]

Summary

In Power10, there are new instructions for the following:

1. mul of two v2i64
2. div of two v4i32 and of two v2i64
3. mod of two v4i32 and of two v2i64

This patch aims to add the following function prototypes to account for vec_mod (since 1) and 2) have already
been previously implemented in altivec.h as vec_mul and vec_div respectively. In Power10, these
functions will use the instructions introduced in D82510.

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

Depends on D82584.

[amyk]

Rebased patch.

[bsaleil]

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

38

Are the tests for vec_mul with v4i32 missing ?

[amyk]

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

38

I should probably reword the description. So for Power10, we actually have new instructions for:

• mul with v2i64
• div with v4i32 and v2i64
• mod with v4i32 and v2i64

Which is why I have only added vec_mul for v4i32 here. All of those functions exist in altivec.h already except for vec_mod, which I have added.

[bsaleil]

Thanks for the explanation. LGTM.

clang/lib/Headers/altivec.h

 
 /* vec_cnttzm */
 
 static __inline__ vector unsigned long long __ATTRS_o_ai
 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))
 
 /* vec_srdbi */
 
 #define vec_srdb(__a, __b, __c) __builtin_altivec_vsrdbi(__a, __b, (__c & 0x7))
 

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

 vector unsigned __int128 vui128a, vui128b, vui128c;
 vector float vfa, vfb;
 vector double vda, vdb;
 unsigned int uia, uib;
 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>
   return vec_pdep(vulla, vullb);
 }
 
 vector unsigned long long test_vpextd(void) {
   // CHECK: @llvm.ppc.altivec.vpextd(<2 x i64>