From 1ff93618e58df210def48d26878c20a1b414d900 Mon Sep 17 00:00:00 2001
From: Nemanja Ivanovic <nemanja.i.ibm@gmail.com>
Date: Mon, 1 Mar 2021 21:38:41 -0600
Subject: [PATCH] [PowerPC] Add missing overloads of vec_promote to altivec.h

The VSX-only overloads (for 8-byte element vectors) are missing.
Add the missing overloads and convert element numbering to
modulo arithmetic to match GCC and XLC.
---
 clang/lib/Headers/altivec.h           | 36 +++++++++++++++++++++------
 clang/test/CodeGen/builtins-ppc-vsx.c | 19 ++++++++++++++
 2 files changed, 48 insertions(+), 7 deletions(-)

diff --git a/clang/lib/Headers/altivec.h b/clang/lib/Headers/altivec.h
index 402f3b389496..935eac3c8672 100644
--- a/clang/lib/Headers/altivec.h
+++ b/clang/lib/Headers/altivec.h
@@ -14024,49 +14024,71 @@ static __inline__ void __ATTRS_o_ai vec_stvrxl(vector float __a, int __b,
 static __inline__ vector signed char __ATTRS_o_ai vec_promote(signed char __a,
                                                               int __b) {
   vector signed char __res = (vector signed char)(0);
-  __res[__b] = __a;
+  __res[__b & 0x7] = __a;
   return __res;
 }
 
 static __inline__ vector unsigned char __ATTRS_o_ai
 vec_promote(unsigned char __a, int __b) {
   vector unsigned char __res = (vector unsigned char)(0);
-  __res[__b] = __a;
+  __res[__b & 0x7] = __a;
   return __res;
 }
 
 static __inline__ vector short __ATTRS_o_ai vec_promote(short __a, int __b) {
   vector short __res = (vector short)(0);
-  __res[__b] = __a;
+  __res[__b & 0x7] = __a;
   return __res;
 }
 
 static __inline__ vector unsigned short __ATTRS_o_ai
 vec_promote(unsigned short __a, int __b) {
   vector unsigned short __res = (vector unsigned short)(0);
-  __res[__b] = __a;
+  __res[__b & 0x7] = __a;
   return __res;
 }
 
 static __inline__ vector int __ATTRS_o_ai vec_promote(int __a, int __b) {
   vector int __res = (vector int)(0);
-  __res[__b] = __a;
+  __res[__b & 0x3] = __a;
   return __res;
 }
 
 static __inline__ vector unsigned int __ATTRS_o_ai vec_promote(unsigned int __a,
                                                                int __b) {
   vector unsigned int __res = (vector unsigned int)(0);
-  __res[__b] = __a;
+  __res[__b & 0x3] = __a;
   return __res;
 }
 
 static __inline__ vector float __ATTRS_o_ai vec_promote(float __a, int __b) {
   vector float __res = (vector float)(0);
-  __res[__b] = __a;
+  __res[__b & 0x3] = __a;
   return __res;
 }
 
+#ifdef __VSX__
+static __inline__ vector double __ATTRS_o_ai vec_promote(double __a, int __b) {
+  vector double __res = (vector double)(0);
+  __res[__b & 0x1] = __a;
+  return __res;
+}
+
+static __inline__ vector signed long long __ATTRS_o_ai
+vec_promote(signed long long __a, int __b) {
+  vector signed long long __res = (vector signed long long)(0);
+  __res[__b & 0x1] = __a;
+  return __res;
+}
+
+static __inline__ vector unsigned long long __ATTRS_o_ai
+vec_promote(unsigned long long __a, int __b) {
+  vector unsigned long long __res = (vector unsigned long long)(0);
+  __res[__b & 0x1] = __a;
+  return __res;
+}
+#endif
+
 /* vec_splats */
 
 static __inline__ vector signed char __ATTRS_o_ai vec_splats(signed char __a) {
diff --git a/clang/test/CodeGen/builtins-ppc-vsx.c b/clang/test/CodeGen/builtins-ppc-vsx.c
index bd0e66e69800..53370cb3949e 100644
--- a/clang/test/CodeGen/builtins-ppc-vsx.c
+++ b/clang/test/CodeGen/builtins-ppc-vsx.c
@@ -22,6 +22,7 @@ vector signed long long vsll = { 255LL, -937LL };
 vector unsigned long long vull = { 1447LL, 2894LL };
 double d = 23.4;
 signed long long sll = 618LL;
+unsigned long long ull = 618ULL;
 float af[4] = {23.4f, 56.7f, 89.0f, 12.3f};
 double ad[2] = {23.4, 56.7};
 signed char asc[16] = { -8,  9, -10, 11, -12, 13, -14, 15,
@@ -1851,6 +1852,24 @@ res_vsc = vec_xxsldwi(vsc, vsc, 0);
 res_vuc = vec_xxsldwi(vuc, vuc, 1);
 // CHECK: shufflevector <4 x i32> %{{[0-9]+}}, <4 x i32> %{{[0-9]+}}, <4 x i32> <i32 1, i32 2, i32 3, i32 4>
 // CHECK-LE: shufflevector <4 x i32> %{{[0-9]+}}, <4 x i32> %{{[0-9]+}}, <4 x i32> <i32 7, i32 0, i32 1, i32 2>
+
+res_vd = vec_promote(d, 0);
+// CHECK: store <2 x double> zeroinitializer
+// CHECK: insertelement <2 x double>
+// CHECK-LE: store <2 x double> zeroinitializer
+// CHECK-LE: insertelement <2 x double>
+
+res_vsll = vec_promote(sll, 0);
+// CHECK: store <2 x i64> zeroinitializer
+// CHECK: insertelement <2 x i64>
+// CHECK-LE: store <2 x i64> zeroinitializer
+// CHECK-LE: insertelement <2 x i64>
+
+res_vull = vec_promote(ull, 0);
+// CHECK: store <2 x i64> zeroinitializer
+// CHECK: insertelement <2 x i64>
+// CHECK-LE: store <2 x i64> zeroinitializer
+// CHECK-LE: insertelement <2 x i64>
 }
 
 // The return type of the call expression may be different from the return type of the shufflevector.