From: Nemanja Ivanovic <nemanja.i.ibm@gmail.com>
Date: Fri, 28 Oct 2016 20:04:53 +0000 (+0000)
Subject: [PPC] add float and double overloads for vec_orc and vec_nand in altivec.h
X-Git-Tag: llvmorg-4.0.0-rc1~6000
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=931bc548e6b6f643370a32306d9d897d19884c37;p=platform%2Fupstream%2Fllvm.git

[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.

llvm-svn: 285439
---

diff --git a/clang/lib/Headers/altivec.h b/clang/lib/Headers/altivec.h
index a4b5f9c..1071425 100644
--- a/clang/lib/Headers/altivec.h
+++ b/clang/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/clang/test/CodeGen/builtins-ppc-p8vector.c b/clang/test/CodeGen/builtins-ppc-p8vector.c
index 096e3e1..5edb948 100644
--- a/clang/test/CodeGen/builtins-ppc-p8vector.c
+++ b/clang/test/CodeGen/builtins-ppc-p8vector.c
@@ -1266,6 +1266,12 @@ void test1() {
 // 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);
 // CHECK: [[T1:%.+]] = and <2 x i64>
 // CHECK: xor <2 x i64> [[T1]], <i64 -1, i64 -1>
@@ -1284,6 +1290,12 @@ void test1() {
 // 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 */
   res_vsc = vec_orc(vsc, vsc);
 // CHECK: [[T1:%.+]] = xor <16 x i8> {{%.+}}, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
@@ -1412,6 +1424,18 @@ void test1() {
 // 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);
 // CHECK: [[T1:%.+]] = xor <2 x i64> {{%.+}}, <i64 -1, i64 -1>
 // CHECK: or <2 x i64> {{%.+}}, [[T1]]
@@ -1454,6 +1478,18 @@ void test1() {
 // 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 */
   res_vsll = vec_sub(vsll, vsll);
 // CHECK: sub <2 x i64>