This revision was automatically updated to reflect the committed changes.
Closed by commit rL346471: [PowerPC] [Clang] [AltiVec] The second parameter of
vec_sr function should be… (authored by wuzish, committed by ).
Herald added a subscriber: llvm-commits.
Changed prior to commit:
https://reviews.llvm.org/D54087?vs=172538&id=173263#toc
Repository:
rL LLVM
https://reviews.llvm.org/D54087
Files:
cfe/trunk/lib/Headers/altivec.h
cfe/trunk/test/CodeGen/builtins-ppc-altivec.c
cfe/trunk/test/CodeGen/builtins-ppc-p8vector.c
Index: cfe/trunk/test/CodeGen/builtins-ppc-altivec.c
===================================================================
--- cfe/trunk/test/CodeGen/builtins-ppc-altivec.c
+++ cfe/trunk/test/CodeGen/builtins-ppc-altivec.c
@@ -4256,52 +4256,76 @@
/* vec_sr */
res_vsc = vec_sr(vsc, vuc);
-// CHECK: lshr <16 x i8>
-// CHECK-LE: lshr <16 x i8>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK-LE: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vuc = vec_sr(vuc, vuc);
-// CHECK: lshr <16 x i8>
-// CHECK-LE: lshr <16 x i8>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK-LE: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vs = vec_sr(vs, vus);
-// CHECK: lshr <8 x i16>
-// CHECK-LE: lshr <8 x i16>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK-LE: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vus = vec_sr(vus, vus);
-// CHECK: lshr <8 x i16>
-// CHECK-LE: lshr <8 x i16>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK-LE: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vi = vec_sr(vi, vui);
-// CHECK: lshr <4 x i32>
-// CHECK-LE: lshr <4 x i32>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK-LE: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vui = vec_sr(vui, vui);
-// CHECK: lshr <4 x i32>
-// CHECK-LE: lshr <4 x i32>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK-LE: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vsc = vec_vsrb(vsc, vuc);
-// CHECK: shr <16 x i8>
-// CHECK-LE: shr <16 x i8>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK-LE: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vuc = vec_vsrb(vuc, vuc);
-// CHECK: shr <16 x i8>
-// CHECK-LE: shr <16 x i8>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <16 x i8> {{[0-9a-zA-Z%.]+}}, <i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8, i8 8>
+// CHECK-LE: lshr <16 x i8> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vs = vec_vsrh(vs, vus);
-// CHECK: shr <8 x i16>
-// CHECK-LE: shr <8 x i16>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK-LE: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vus = vec_vsrh(vus, vus);
-// CHECK: shr <8 x i16>
-// CHECK-LE: shr <8 x i16>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <8 x i16> {{[0-9a-zA-Z%.]+}}, <i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16, i16 16>
+// CHECK-LE: lshr <8 x i16> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vi = vec_vsrw(vi, vui);
-// CHECK: shr <4 x i32>
-// CHECK-LE: shr <4 x i32>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK-LE: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
res_vui = vec_vsrw(vui, vui);
-// CHECK: shr <4 x i32>
-// CHECK-LE: shr <4 x i32>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <4 x i32> {{[0-9a-zA-Z%.]+}}, <i32 32, i32 32, i32 32, i32 32>
+// CHECK-LE: lshr <4 x i32> {{[0-9a-zA-Z%.]+}}, [[UREM]]
/* vec_sra */
res_vsc = vec_sra(vsc, vuc);
Index: cfe/trunk/test/CodeGen/builtins-ppc-p8vector.c
===================================================================
--- cfe/trunk/test/CodeGen/builtins-ppc-p8vector.c
+++ cfe/trunk/test/CodeGen/builtins-ppc-p8vector.c
@@ -1066,13 +1066,17 @@
/* vec_sr */
res_vsll = vec_sr(vsll, vull);
-// CHECK: lshr <2 x i64>
-// CHECK-LE: lshr <2 x i64>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <2 x i64> {{[0-9a-zA-Z%.]+}}, <i64 64, i64 64>
+// CHECK: lshr <2 x i64> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <2 x i64> {{[0-9a-zA-Z%.]+}}, <i64 64, i64 64>
+// CHECK-LE: lshr <2 x i64> {{[0-9a-zA-Z%.]+}}, [[UREM]]
// CHECK-PPC: error: call to 'vec_sr' is ambiguous
res_vull = vec_sr(vull, vull);
-// CHECK: lshr <2 x i64>
-// CHECK-LE: lshr <2 x i64>
+// CHECK: [[UREM:[0-9a-zA-Z%.]+]] = urem <2 x i64> {{[0-9a-zA-Z%.]+}}, <i64 64, i64 64>
+// CHECK: lshr <2 x i64> {{[0-9a-zA-Z%.]+}}, [[UREM]]
+// CHECK-LE: [[UREM:[0-9a-zA-Z%.]+]] = urem <2 x i64> {{[0-9a-zA-Z%.]+}}, <i64 64, i64 64>
+// CHECK-LE: lshr <2 x i64> {{[0-9a-zA-Z%.]+}}, [[UREM]]
// CHECK-PPC: error: call to 'vec_sr' is ambiguous
/* vec_sra */
Index: cfe/trunk/lib/Headers/altivec.h
===================================================================
--- cfe/trunk/lib/Headers/altivec.h
+++ cfe/trunk/lib/Headers/altivec.h
@@ -9492,49 +9492,51 @@
/* vec_sr */
-static __inline__ vector signed char __ATTRS_o_ai
-vec_sr(vector signed char __a, vector unsigned char __b) {
- vector unsigned char __res = (vector unsigned char)__a >> __b;
- return (vector signed char)__res;
-}
-
+// vec_sr does modulo arithmetic on __b first, so __b is allowed to be more
+// than the length of __a.
static __inline__ vector unsigned char __ATTRS_o_ai
vec_sr(vector unsigned char __a, vector unsigned char __b) {
- return __a >> __b;
+ return __a >>
+ (__b % (vector unsigned char)(sizeof(unsigned char) * __CHAR_BIT__));
}
-static __inline__ vector signed short __ATTRS_o_ai
-vec_sr(vector signed short __a, vector unsigned short __b) {
- vector unsigned short __res = (vector unsigned short)__a >> __b;
- return (vector signed short)__res;
+static __inline__ vector signed char __ATTRS_o_ai
+vec_sr(vector signed char __a, vector unsigned char __b) {
+ return (vector signed char)vec_sr((vector unsigned char)__a, __b);
}
static __inline__ vector unsigned short __ATTRS_o_ai
vec_sr(vector unsigned short __a, vector unsigned short __b) {
- return __a >> __b;
+ return __a >>
+ (__b % (vector unsigned short)(sizeof(unsigned short) * __CHAR_BIT__));
}
-static __inline__ vector signed int __ATTRS_o_ai
-vec_sr(vector signed int __a, vector unsigned int __b) {
- vector unsigned int __res = (vector unsigned int)__a >> __b;
- return (vector signed int)__res;
+static __inline__ vector short __ATTRS_o_ai vec_sr(vector short __a,
+ vector unsigned short __b) {
+ return (vector short)vec_sr((vector unsigned short)__a, __b);
}
static __inline__ vector unsigned int __ATTRS_o_ai
vec_sr(vector unsigned int __a, vector unsigned int __b) {
- return __a >> __b;
+ return __a >>
+ (__b % (vector unsigned int)(sizeof(unsigned int) * __CHAR_BIT__));
}
-#ifdef __POWER8_VECTOR__
-static __inline__ vector signed long long __ATTRS_o_ai
-vec_sr(vector signed long long __a, vector unsigned long long __b) {
- vector unsigned long long __res = (vector unsigned long long)__a >> __b;
- return (vector signed long long)__res;
+static __inline__ vector int __ATTRS_o_ai vec_sr(vector int __a,
+ vector unsigned int __b) {
+ return (vector int)vec_sr((vector unsigned int)__a, __b);
}
+#ifdef __POWER8_VECTOR__
static __inline__ vector unsigned long long __ATTRS_o_ai
vec_sr(vector unsigned long long __a, vector unsigned long long __b) {
- return __a >> __b;
+ return __a >> (__b % (vector unsigned long long)(sizeof(unsigned long long) *
+ __CHAR_BIT__));
+}
+
+static __inline__ vector long long __ATTRS_o_ai
+vec_sr(vector long long __a, vector unsigned long long __b) {
+ return (vector long long)vec_sr((vector unsigned long long)__a, __b);
}
#endif
@@ -9544,40 +9546,40 @@
static __inline__ vector signed char __ATTRS_o_ai
vec_vsrb(vector signed char __a, vector unsigned char __b) {
- return __a >> (vector signed char)__b;
+ return vec_sr(__a, __b);
}
static __inline__ vector unsigned char __ATTRS_o_ai
vec_vsrb(vector unsigned char __a, vector unsigned char __b) {
- return __a >> __b;
+ return vec_sr(__a, __b);
}
/* vec_vsrh */
#define __builtin_altivec_vsrh vec_vsrh
static __inline__ vector short __ATTRS_o_ai
vec_vsrh(vector short __a, vector unsigned short __b) {
- return __a >> (vector short)__b;
+ return vec_sr(__a, __b);
}
static __inline__ vector unsigned short __ATTRS_o_ai
vec_vsrh(vector unsigned short __a, vector unsigned short __b) {
- return __a >> __b;
+ return vec_sr(__a, __b);
}
/* vec_vsrw */
#define __builtin_altivec_vsrw vec_vsrw
static __inline__ vector int __ATTRS_o_ai vec_vsrw(vector int __a,
vector unsigned int __b) {
- return __a >> (vector int)__b;
+ return vec_sr(__a, __b);
}
static __inline__ vector unsigned int __ATTRS_o_ai
vec_vsrw(vector unsigned int __a, vector unsigned int __b) {
- return __a >> __b;
+ return vec_sr(__a, __b);
}
/* vec_sra */
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
