[PowerPC] Implement Vector Splat Immediate Builtins in Clang

Implements builtins for the following prototypes:
  vector signed int vec_splati (const signed int);
  vector float vec_splati (const float);
  vector double vec_splatid (const float);
  vector signed int vec_splati_ins (vector signed int, const unsigned int,
                                    const signed int);
  vector unsigned int vec_splati_ins (vector unsigned int, const unsigned int,
                                      const unsigned int);
  vector float vec_splati_ins (vector float, const unsigned int, const float);

Differential Revision: https://reviews.llvm.org/D82520

diff --git a/clang/lib/Headers/altivec.h b/clang/lib/Headers/altivec.h
index a63f2ee..9a40092 100644 (file)
--- a/clang/lib/Headers/altivec.h
+++ b/clang/lib/Headers/altivec.h
@@ -17094,6 +17094,58 @@ vec_blendv(vector double __a, vector double __b,
            vector unsigned long long __c) {
   return __builtin_vsx_xxblendvd(__a, __b, __c);
 }
+
+/* vec_splati */
+
+#define vec_splati(__a)                                                        \
+  _Generic((__a), signed int                                                   \
+           : ((vector signed int)__a), unsigned int                            \
+           : ((vector unsigned int)__a), float                                 \
+           : ((vector float)__a))
+
+/* vec_spatid */
+
+static __inline__ vector double __ATTRS_o_ai vec_splatid(const float __a) {
+  return ((vector double)((double)__a));
+}
+
+/* vec_splati_ins */
+
+static __inline__ vector signed int __ATTRS_o_ai vec_splati_ins(
+    vector signed int __a, const unsigned int __b, const signed int __c) {
+#ifdef __LITTLE_ENDIAN__
+  __a[1 - __b] = __c;
+  __a[3 - __b] = __c;
+#else
+  __a[__b] = __c;
+  __a[2 + __b] = __c;
+#endif
+  return __a;
+}
+
+static __inline__ vector unsigned int __ATTRS_o_ai vec_splati_ins(
+    vector unsigned int __a, const unsigned int __b, const unsigned int __c) {
+#ifdef __LITTLE_ENDIAN__
+  __a[1 - __b] = __c;
+  __a[3 - __b] = __c;
+#else
+  __a[__b] = __c;
+  __a[2 + __b] = __c;
+#endif
+  return __a;
+}
+
+static __inline__ vector float __ATTRS_o_ai
+vec_splati_ins(vector float __a, const unsigned int __b, const float __c) {
+#ifdef __LITTLE_ENDIAN__
+  __a[1 - __b] = __c;
+  __a[3 - __b] = __c;
+#else
+  __a[__b] = __c;
+  __a[2 + __b] = __c;
+#endif
+  return __a;
+}
 #endif /* __VSX__ */
 #endif /* __POWER10_VECTOR__ */
 

diff --git a/clang/test/CodeGen/builtins-ppc-p10vector.c b/clang/test/CodeGen/builtins-ppc-p10vector.c
index b0602dd..22b4e7a 100644 (file)
--- a/clang/test/CodeGen/builtins-ppc-p10vector.c
+++ b/clang/test/CodeGen/builtins-ppc-p10vector.c
@@ -512,3 +512,72 @@ vector unsigned int test_vec_inserth_uiv(void) {
   // CHECK-LE-NEXT: ret <4 x i32>
   return vec_inserth(vuia, vuib, uia);
 }
+
+vector signed int test_vec_vec_splati_si(void) {
+  // CHECK-BE: ret <4 x i32> <i32 -17, i32 -17, i32 -17, i32 -17>
+  // CHECK: ret <4 x i32> <i32 -17, i32 -17, i32 -17, i32 -17>
+  return vec_splati(-17);
+}
+
+vector unsigned int test_vec_vec_splati_ui(void) {
+  // CHECK-BE: ret <4 x i32> <i32 16, i32 16, i32 16, i32 16>
+  // CHECK: ret <4 x i32> <i32 16, i32 16, i32 16, i32 16>
+  return vec_splati(16U);
+}
+
+vector float test_vec_vec_splati_f(void) {
+  // CHECK-BE: ret <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
+  // CHECK: ret <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
+  return vec_splati(1.0f);
+}
+
+vector double test_vec_vec_splatid(void) {
+  // CHECK-BE: [[T1:%.+]] = fpext float %{{.+}} to double
+  // CHECK-BE-NEXT: [[T2:%.+]] = insertelement <2 x double> undef, double [[T1:%.+]], i32 0
+  // CHECK-BE-NEXT: [[T3:%.+]] = shufflevector <2 x double> [[T2:%.+]], <2 x double> undef, <2 x i32> zeroinitialize
+  // CHECK-BE-NEXT: ret <2 x double> [[T3:%.+]]
+  // CHECK: [[T1:%.+]] = fpext float %{{.+}} to double
+  // CHECK-NEXT: [[T2:%.+]] = insertelement <2 x double> undef, double [[T1:%.+]], i32 0
+  // CHECK-NEXT: [[T3:%.+]] = shufflevector <2 x double> [[T2:%.+]], <2 x double> undef, <2 x i32> zeroinitialize
+  // CHECK-NEXT: ret <2 x double> [[T3:%.+]]
+  return vec_splatid(1.0);
+}
+
+vector signed int test_vec_vec_splati_ins_si(void) {
+  // CHECK-BE: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 %{{.+}}
+  // CHECK-BE:  [[T1:%.+]] = add i32 2, %{{.+}}
+  // CHECK-BE: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T1]]
+  // CHECK-BE: ret <4 x i32>
+  // CHECK:  [[T1:%.+]] = sub i32 1, %{{.+}}
+  // CHECK: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T1]]
+  // CHECK:  [[T2:%.+]] = sub i32 3, %{{.+}}
+  // CHECK: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T2]]
+  // CHECK: ret <4 x i32>
+  return vec_splati_ins(vsia, 0, -17);
+}
+
+vector unsigned int test_vec_vec_splati_ins_ui(void) {
+  // CHECK-BE: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 %{{.+}}
+  // CHECK-BE:  [[T1:%.+]] = add i32 2, %{{.+}}
+  // CHECK-BE: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T1]]
+  // CHECK-BE: ret <4 x i32>
+  // CHECK:  [[T1:%.+]] = sub i32 1, %{{.+}}
+  // CHECK: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T1]]
+  // CHECK:  [[T2:%.+]] = sub i32 3, %{{.+}}
+  // CHECK: insertelement <4 x i32> %{{.+}}, i32 %{{.+}}, i32 [[T2]]
+  // CHECK: ret <4 x i32>
+  return vec_splati_ins(vuia, 1, 16U);
+}
+
+vector float test_vec_vec_splati_ins_f(void) {
+  // CHECK-BE: insertelement <4 x float> %{{.+}}, float %{{.+}}, i32 %{{.+}}
+  // CHECK-BE:  [[T1:%.+]] = add i32 2, %{{.+}}
+  // CHECK-BE: insertelement <4 x float> %{{.+}}, float %{{.+}}, i32 [[T1]]
+  // CHECK-BE: ret <4 x float>
+  // CHECK:  [[T1:%.+]] = sub i32 1, %{{.+}}
+  // CHECK: insertelement <4 x float> %{{.+}}, float %{{.+}}, i32 [[T1]]
+  // CHECK:  [[T2:%.+]] = sub i32 3, %{{.+}}
+  // CHECK: insertelement <4 x float> %{{.+}}, float %{{.+}}, i32 [[T2]]
+  // CHECK: ret <4 x float>
+  return vec_splati_ins(vfa, 0, 1.0f);
+}

diff --git a/llvm/test/CodeGen/PowerPC/p10-splatImm.ll b/llvm/test/CodeGen/PowerPC/p10-splatImm.ll
index b468f6d..8bb83c2 100644 (file)
--- a/llvm/test/CodeGen/PowerPC/p10-splatImm.ll
+++ b/llvm/test/CodeGen/PowerPC/p10-splatImm.ll
@@ -286,3 +286,21 @@ define dso_local double @testDoubleZeroScalar() local_unnamed_addr {
 entry:
   ret double 0.000000e+00
 }
+
+define dso_local <4 x i32> @vec_splati() local_unnamed_addr {
+; CHECK-LABEL: vec_splati:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xxspltiw vs34, -17
+; CHECK-NEXT:    blr
+entry:
+  ret <4 x i32> <i32 -17, i32 -17, i32 -17, i32 -17>
+}
+
+define dso_local <2 x double> @vec_splatid() local_unnamed_addr {
+; CHECK-LABEL: vec_splatid:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xxspltidp vs34, 1065353216
+; CHECK-NEXT:    blr
+entry:
+  ret <2 x double> <double 1.000000e+00, double 1.000000e+00>
+}