[PPC] add float and double overloads for vec_orc and vec_nand in altivec.h

This patch corresponds to review https://reviews.llvm.org/D25950.
Committing on behalf of Sean Fertile.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@285439 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Headers/altivec.h b/lib/Headers/altivec.h
index a4b5f9cf67c697a90fa8eb49cb0113143972a8db..10714256ff7672b37ff822830e75047716df06f2 100644 (file)
--- a/lib/Headers/altivec.h
+++ b/lib/Headers/altivec.h
@@ -5356,6 +5356,12 @@ static __inline__ vector bool int __ATTRS_o_ai vec_nand(vector bool int __a,
   return ~(__a & __b);
 }
 
+static __inline__ vector float __ATTRS_o_ai
+vec_nand(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_nand(vector signed long long __a, vector signed long long __b) {
   return ~(__a & __b);
@@ -5391,6 +5397,12 @@ vec_nand(vector bool long long __a, vector bool long long __b) {
   return ~(__a & __b);
 }
 
+static __inline__ vector double __ATTRS_o_ai
+vec_nand(vector double __a, vector double __b) {
+  return (vector double)(~((vector unsigned long long)__a &
+                           (vector unsigned long long)__b));
+}
+
 #endif
 
 /* vec_nmadd */
@@ -5862,6 +5874,16 @@ static __inline__ vector bool int __ATTRS_o_ai vec_orc(vector bool int __a,
   return __a | ~__b;
 }
 
+static __inline__ vector float __ATTRS_o_ai
+vec_orc(vector bool int __a, vector float __b) {
+ 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 signed long long __ATTRS_o_ai
 vec_orc(vector signed long long __a, vector signed long long __b) {
   return __a | ~__b;
@@ -5896,6 +5918,16 @@ static __inline__ vector bool long long __ATTRS_o_ai
 vec_orc(vector bool long long __a, vector bool long long __b) {
   return __a | ~__b;
 }
+
+static __inline__ vector double __ATTRS_o_ai
+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);
+}
 #endif
 
 /* vec_vor */

diff --git a/test/CodeGen/builtins-ppc-p8vector.c b/test/CodeGen/builtins-ppc-p8vector.c
index 096e3e1bb6b54c0835075ac249c44b7e85e302ab..5edb9481dde0bb7e627ce0641f3ed14b0732a01d 100644 (file)
--- a/test/CodeGen/builtins-ppc-p8vector.c
+++ b/test/CodeGen/builtins-ppc-p8vector.c
@@ -1264,6 +1264,12 @@ void test1() {
 // CHECK: [[T1:%.+]] = and <4 x i32>
 // CHECK: xor <4 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1>
 // CHECK-LE: [[T1:%.+]] = and <4 x i32>
+// CHECK-LE: xor <4 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1>
+
+  res_vf = vec_nand(vfa, vfa);
+// CHECK: [[T1:%.+]] = and <4 x i32>
+// CHECK: xor <4 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1>
+// CHECK-LE: [[T1:%.+]] = and <4 x i32>
 // CHECK-LE: xor <4 x i32> [[T1]], <i32 -1, i32 -1, i32 -1, i32 -1>
 
   res_vsll = vec_nand(vsll, vsll);
@@ -1282,6 +1288,12 @@ void test1() {
 // CHECK: [[T1:%.+]] = and <2 x i64>
 // CHECK: xor <2 x i64> [[T1]], <i64 -1, i64 -1>
 // CHECK-LE: [[T1:%.+]] = and <2 x i64>
+// CHECK-LE: xor <2 x i64> [[T1]], <i64 -1, i64 -1>
+
+  res_vd = vec_nand(vda, vda);
+// CHECK: [[T1:%.+]] = and <2 x i64>
+// CHECK: xor <2 x i64> [[T1]], <i64 -1, i64 -1>
+// CHECK-LE: [[T1:%.+]] = and <2 x i64>
 // CHECK-LE: xor <2 x i64> [[T1]], <i64 -1, i64 -1>
 
   /* vec_orc */
@@ -1410,6 +1422,18 @@ void test1() {
 // 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(vbi, vfa);
+// 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, 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_vsll = vec_orc(vsll, vsll);
@@ -1452,6 +1476,18 @@ void test1() {
 // 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(vbll, vda);
+// 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, 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]]
 
   /* vec_sub */