[Clang] Add elementwise abs builtin.

fhahn · fhahn · commit 2823377dec7b · 2021-11-03T09:30:33.000+01:00
This patch implements __builtin_elementwise_abs as specified in D111529. Reviewed By: aaron.ballman, scanon Differential Revision: https://reviews.llvm.org/D111986 (cherry-picked from 01870d5)
diff --git a/clang/include/clang/Basic/Builtins.def b/clang/include/clang/Basic/Builtins.def
@@ -645,6 +645,7 @@ BUILTIN(__builtin_alloca, "v*z"   , "Fn")
 BUILTIN(__builtin_alloca_with_align, "v*zIz", "Fn")
 BUILTIN(__builtin_call_with_static_chain, "v.", "nt")
 
+BUILTIN(__builtin_elementwise_abs, "v.", "nct")
 BUILTIN(__builtin_elementwise_max, "v.", "nct")
 BUILTIN(__builtin_elementwise_min, "v.", "nct")
 
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -11355,7 +11355,8 @@ def err_builtin_launder_invalid_arg : Error<
 def err_builtin_invalid_arg_type: Error <
   "%ordinal0 argument must be a "
   "%select{vector, integer or floating point type|matrix|"
-   "pointer to a valid matrix element type}1 (was %2)">;
+   "pointer to a valid matrix element type|"
+   "signed integer or floating point type}1 (was %2)">;
 
 def err_builtin_matrix_disabled: Error<
   "matrix types extension is disabled. Pass -fenable-matrix to enable it">;
diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h
@@ -12679,6 +12679,7 @@ class Sema final {
   bool CheckPPCMMAType(QualType Type, SourceLocation TypeLoc);
 
   bool SemaBuiltinElementwiseMath(CallExpr *TheCall);
+  bool SemaBuiltinElementwiseMathOneArg(CallExpr *TheCall);
 
   // Matrix builtin handling.
   ExprResult SemaBuiltinMatrixTranspose(CallExpr *TheCall,
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -3101,6 +3101,17 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     return RValue::get(V);
   }
 
+  case Builtin::BI__builtin_elementwise_abs: {
+    Value *Op0 = EmitScalarExpr(E->getArg(0));
+    Value *Result;
+    if (Op0->getType()->isIntOrIntVectorTy())
+      Result = Builder.CreateBinaryIntrinsic(
+          llvm::Intrinsic::abs, Op0, Builder.getFalse(), nullptr, "elt.abs");
+    else
+      Result = Builder.CreateUnaryIntrinsic(llvm::Intrinsic::fabs, Op0, nullptr,
+                                            "elt.abs");
+    return RValue::get(Result);
+  }
   case Builtin::BI__builtin_elementwise_max: {
     Value *Op0 = EmitScalarExpr(E->getArg(0));
     Value *Op1 = EmitScalarExpr(E->getArg(1));
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
@@ -2288,6 +2288,10 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID,
     break;
   }
 
+  case Builtin::BI__builtin_elementwise_abs:
+    if (SemaBuiltinElementwiseMathOneArg(TheCall))
+      return ExprError();
+    break;
   case Builtin::BI__builtin_elementwise_min:
   case Builtin::BI__builtin_elementwise_max:
     if (SemaBuiltinElementwiseMath(TheCall))
@@ -16755,6 +16759,31 @@ static bool checkMathBuiltinElementType(Sema &S, SourceLocation Loc,
   return false;
 }
 
+bool Sema::SemaBuiltinElementwiseMathOneArg(CallExpr *TheCall) {
+  if (checkArgCount(*this, TheCall, 1))
+    return true;
+
+  ExprResult A = UsualUnaryConversions(TheCall->getArg(0));
+  SourceLocation ArgLoc = TheCall->getArg(0)->getBeginLoc();
+  if (A.isInvalid())
+    return true;
+
+  TheCall->setArg(0, A.get());
+  QualType TyA = A.get()->getType();
+  if (checkMathBuiltinElementType(*this, ArgLoc, TyA))
+    return true;
+
+  QualType EltTy = TyA;
+  if (auto *VecTy = EltTy->getAs<VectorType>())
+    EltTy = VecTy->getElementType();
+  if (EltTy->isUnsignedIntegerType())
+    return Diag(ArgLoc, diag::err_builtin_invalid_arg_type)
+           << 1 << /*signed integer or float ty*/ 3 << TyA;
+
+  TheCall->setType(TyA);
+  return false;
+}
+
 bool Sema::SemaBuiltinElementwiseMath(CallExpr *TheCall) {
   if (checkArgCount(*this, TheCall, 2))
     return true;
diff --git a/clang/test/CodeGen/builtins-elementwise-math.c b/clang/test/CodeGen/builtins-elementwise-math.c
@@ -8,12 +8,54 @@ __attribute__((address_space(1))) int int_as_one;
 typedef int bar;
 bar b;
 
+void test_builtin_elementwise_abs(float f1, float f2, double d1, double d2,
+                                  float4 vf1, float4 vf2, si8 vi1, si8 vi2,
+                                  long long int i1, long long int i2, short si) {
+  // CHECK-LABEL: define void @test_builtin_elementwise_abs(
+  // CHECK:      [[F1:%.+]] = load float, float* %f1.addr, align 4
+  // CHECK-NEXT:  call float @llvm.fabs.f32(float [[F1]])
+  f2 = __builtin_elementwise_abs(f1);
+
+  // CHECK:      [[D1:%.+]] = load double, double* %d1.addr, align 8
+  // CHECK-NEXT: call double @llvm.fabs.f64(double [[D1]])
+  d2 = __builtin_elementwise_abs(d1);
+
+  // CHECK:      [[VF1:%.+]] = load <4 x float>, <4 x float>* %vf1.addr, align 16
+  // CHECK-NEXT: call <4 x float> @llvm.fabs.v4f32(<4 x float> [[VF1]])
+  vf2 = __builtin_elementwise_abs(vf1);
+
+  // CHECK:      [[I1:%.+]] = load i64, i64* %i1.addr, align 8
+  // CHECK-NEXT: call i64 @llvm.abs.i64(i64 [[I1]], i1 false)
+  i2 = __builtin_elementwise_abs(i1);
+
+  // CHECK:      [[VI1:%.+]] = load <8 x i16>, <8 x i16>* %vi1.addr, align 16
+  // CHECK-NEXT: call <8 x i16> @llvm.abs.v8i16(<8 x i16> [[VI1]], i1 false)
+  vi2 = __builtin_elementwise_abs(vi1);
+
+  // CHECK:      [[CVI2:%.+]] = load <8 x i16>, <8 x i16>* %cvi2, align 16
+  // CHECK-NEXT: call <8 x i16> @llvm.abs.v8i16(<8 x i16> [[CVI2]], i1 false)
+  const si8 cvi2 = vi2;
+  vi2 = __builtin_elementwise_abs(cvi2);
+
+  // CHECK:      [[IA1:%.+]] = load i32, i32 addrspace(1)* @int_as_one, align 4
+  // CHECK-NEXT: call i32 @llvm.abs.i32(i32 [[IA1]], i1 false)
+  b = __builtin_elementwise_abs(int_as_one);
+
+  // CHECK:   call i32 @llvm.abs.i32(i32 -10, i1 false)
+  b = __builtin_elementwise_abs(-10);
+
+  // CHECK:      [[SI:%.+]] = load i16, i16* %si.addr, align 2
+  // CHECK-NEXT: [[SI_EXT:%.+]] = sext i16 [[SI]] to i32
+  // CHECK-NEXT: [[RES:%.+]] = call i32 @llvm.abs.i32(i32 [[SI_EXT]], i1 false)
+  // CHECK-NEXT: = trunc i32 [[RES]] to i16
+  si = __builtin_elementwise_abs(si);
+}
+
 void test_builtin_elementwise_max(float f1, float f2, double d1, double d2,
                                   float4 vf1, float4 vf2, long long int i1,
                                   long long int i2, si8 vi1, si8 vi2,
                                   unsigned u1, unsigned u2, u4 vu1, u4 vu2) {
   // CHECK-LABEL: define void @test_builtin_elementwise_max(
-
   // CHECK:      [[F1:%.+]] = load float, float* %f1.addr, align 4
   // CHECK-NEXT: [[F2:%.+]] = load float, float* %f2.addr, align 4
   // CHECK-NEXT:  call float @llvm.maxnum.f32(float %0, float %1)
diff --git a/clang/test/Sema/builtins-elementwise-math.c b/clang/test/Sema/builtins-elementwise-math.c
@@ -2,6 +2,7 @@
 
 typedef float float4 __attribute__((ext_vector_type(4)));
 typedef int int3 __attribute__((ext_vector_type(3)));
+typedef unsigned unsigned4 __attribute__((ext_vector_type(4)));
 
 struct Foo {
   char *p;
@@ -11,6 +12,26 @@ __attribute__((address_space(1))) int int_as_one;
 typedef int bar;
 bar b;
 
+void test_builtin_elementwise_abs(int i, double d, float4 v, int3 iv, unsigned u, unsigned4 uv) {
+  struct Foo s = __builtin_elementwise_abs(i);
+  // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'int'}}
+
+  i = __builtin_elementwise_abs();
+  // expected-error@-1 {{too few arguments to function call, expected 1, have 0}}
+
+  i = __builtin_elementwise_abs(i, i);
+  // expected-error@-1 {{too many arguments to function call, expected 1, have 2}}
+
+  i = __builtin_elementwise_abs(v);
+  // expected-error@-1 {{assigning to 'int' from incompatible type 'float4' (vector of 4 'float' values)}}
+
+  u = __builtin_elementwise_abs(u);
+  // expected-error@-1 {{1st argument must be a signed integer or floating point type (was 'unsigned int')}}
+
+  uv = __builtin_elementwise_abs(uv);
+  // expected-error@-1 {{1st argument must be a signed integer or floating point type (was 'unsigned4' (vector of 4 'unsigned int' values))}}
+}
+
 void test_builtin_elementwise_max(int i, short s, double d, float4 v, int3 iv, int *p) {
   i = __builtin_elementwise_max(p, d);
   // expected-error@-1 {{arguments are of different types ('int *' vs 'double')}}
diff --git a/clang/test/SemaCXX/builtins-elementwise-math.cpp b/clang/test/SemaCXX/builtins-elementwise-math.cpp
@@ -14,6 +14,13 @@ template <class T> struct is_const<const T> : true_type {};
 
 // expected-no-diagnostics
 
+void test_builtin_elementwise_abs() {
+  const int a = 2;
+  int b = 1;
+  static_assert(!is_const<decltype(__builtin_elementwise_abs(a))>::value);
+  static_assert(!is_const<decltype(__builtin_elementwise_abs(b))>::value);
+}
+
 void test_builtin_elementwise_max() {
   const int a = 2;
   int b = 1;
