[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

27

Are the tests for vec_mul with v4i32 missing ?

[amyk]

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

27

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

 /*===---- altivec.h - Standard header for type generic math ---------------===*\
  *
  * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
  * See https://llvm.org/LICENSE.txt for license information.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  *
 \*===----------------------------------------------------------------------===*/
 
 #ifndef __ALTIVEC_H
 #define __ALTIVEC_H
 
 #ifndef __ALTIVEC__
 #error "AltiVec support not enabled"
 #endif
 
 /* Constants for mapping CR6 bits to predicate result. */
 
 #define __CR6_EQ 0
 #define __CR6_EQ_REV 1
 #define __CR6_LT 2
 #define __CR6_LT_REV 3
#define __VEC_CLASS_FP_NOT_NORMAL (__VEC_CLASS_FP_NAN        | \
                                    __VEC_CLASS_FP_INFINITY)
 
 #define __ATTRS_o_ai __attribute__((__overloadable__, __always_inline__))
 
 #ifdef __POWER9_VECTOR__
 #include <stddef.h>
 #endif
 
 static __inline__ vector signed char __ATTRS_o_ai vec_perm(
     vector signed char __a, vector signed char __b, vector unsigned char __c);
 
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_perm(vector unsigned char __a, vector unsigned char __b,
          vector unsigned char __c);
 
 static __inline__ vector bool char __ATTRS_o_ai
 vec_perm(vector bool char __a, vector bool char __b, vector unsigned char __c);
 
 static __inline__ vector short __ATTRS_o_ai vec_perm(vector signed short __a,
                                                      vector signed short __b,
                                                      vector unsigned char __c);
 
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_perm(vector unsigned short __a, vector unsigned short __b,
          vector unsigned char __c);
 
 static __inline__ vector bool short __ATTRS_o_ai vec_perm(
     vector bool short __a, vector bool short __b, vector unsigned char __c);
 
 static __inline__ vector pixel __ATTRS_o_ai vec_perm(vector pixel __a,
                                                      vector pixel __b,
                                                      vector unsigned char __c);

 
 /* 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;
+}
+
 #endif /* __POWER10_VECTOR__ */
 
 #undef __ATTRS_o_ai
 
 #endif /* __ALTIVEC_H */

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

 // REQUIRES: powerpc-registered-target
 // RUN: %clang_cc1 -target-feature +vsx -target-feature +altivec \
 // RUN:   -target-cpu pwr10 -triple powerpc64le-unknown-unknown -emit-llvm %s \
 // RUN:   -o - | FileCheck %s
 
 #include <altivec.h>
 
 vector signed char vsca;
 vector unsigned char vuca;
 vector unsigned short vusa;
-vector unsigned int vuia;
+vector signed int vsia, vsib;
+vector unsigned int vuia, vuib;
+vector signed long long vslla, vsllb;
 vector unsigned long long vulla, vullb;
 unsigned int uia;
 
+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>