https://github.com/francisvm updated
https://github.com/llvm/llvm-project/pull/110198
>From 8b53cbbcb3f9ea11b091407ec4ecfa59d1f748a3 Mon Sep 17 00:00:00 2001
From: Francis Visoiu Mistrih <franci...@apple.com>
Date: Thu, 26 Sep 2024 18:05:09 -0700
Subject: [PATCH] [Clang] Add __builtin_elementwise|reduce_max|minimum
We have the LLVM intrinsics, and we're missing the clang builtins to be
used directly in code that needs to make the distinction in NaN semantics.
---
clang/docs/LanguageExtensions.rst | 158 ++++++++++--------
clang/include/clang/Basic/Builtins.td | 24 +++
.../clang/Basic/DiagnosticSemaKinds.td | 3 +-
clang/include/clang/Sema/Sema.h | 6 +-
clang/lib/CodeGen/CGBuiltin.cpp | 39 +++++
clang/lib/Sema/SemaChecking.cpp | 49 ++++--
.../test/CodeGen/builtins-elementwise-math.c | 76 +++++++++
clang/test/CodeGen/builtins-reduction-math.c | 24 +++
.../CodeGen/strictfp-elementwise-bulitins.cpp | 20 +++
clang/test/Sema/builtins-elementwise-math.c | 82 +++++++++
clang/test/Sema/builtins-reduction-math.c | 28 ++++
.../SemaCXX/builtins-elementwise-math.cpp | 16 ++
12 files changed, 438 insertions(+), 87 deletions(-)
diff --git a/clang/docs/LanguageExtensions.rst
b/clang/docs/LanguageExtensions.rst
index 0c6b9b1b8f9ce4..9eefbfecbce514 100644
--- a/clang/docs/LanguageExtensions.rst
+++ b/clang/docs/LanguageExtensions.rst
@@ -647,66 +647,74 @@ elementwise to the input.
Unless specified otherwise operation(±0) = ±0 and operation(±infinity) =
±infinity
-===========================================
================================================================
=========================================
- Name Operation
Supported element types
-===========================================
================================================================
=========================================
- T __builtin_elementwise_abs(T x) return the absolute value of a
number x; the absolute value of signed integer and floating point types
- the most negative integer remains
the most negative integer
- T __builtin_elementwise_fma(T x, T y, T z) fused multiply add, (x * y) + z.
floating point types
- T __builtin_elementwise_ceil(T x) return the smallest integral
value greater than or equal to x floating point types
- T __builtin_elementwise_sin(T x) return the sine of x interpreted
as an angle in radians floating point types
- T __builtin_elementwise_cos(T x) return the cosine of x
interpreted as an angle in radians floating point types
- T __builtin_elementwise_tan(T x) return the tangent of x
interpreted as an angle in radians floating point types
- T __builtin_elementwise_asin(T x) return the arcsine of x
interpreted as an angle in radians floating point types
- T __builtin_elementwise_acos(T x) return the arccosine of x
interpreted as an angle in radians floating point types
- T __builtin_elementwise_atan(T x) return the arctangent of x
interpreted as an angle in radians floating point types
- T __builtin_elementwise_sinh(T x) return the hyperbolic sine of
angle x in radians floating point types
- T __builtin_elementwise_cosh(T x) return the hyperbolic cosine of
angle x in radians floating point types
- T __builtin_elementwise_tanh(T x) return the hyperbolic tangent of
angle x in radians floating point types
- T __builtin_elementwise_floor(T x) return the largest integral value
less than or equal to x floating point types
- T __builtin_elementwise_log(T x) return the natural logarithm of x
floating point types
- T __builtin_elementwise_log2(T x) return the base 2 logarithm of x
floating point types
- T __builtin_elementwise_log10(T x) return the base 10 logarithm of x
floating point types
- T __builtin_elementwise_popcount(T x) return the number of 1 bits in x
integer types
- T __builtin_elementwise_pow(T x, T y) return x raised to the power of y
floating point types
- T __builtin_elementwise_bitreverse(T x) return the integer represented
after reversing the bits of x integer types
- T __builtin_elementwise_exp(T x) returns the base-e exponential,
e^x, of the specified value floating point types
- T __builtin_elementwise_exp2(T x) returns the base-2 exponential,
2^x, of the specified value floating point types
-
- T __builtin_elementwise_sqrt(T x) return the square root of a
floating-point number floating point types
- T __builtin_elementwise_roundeven(T x) round x to the nearest integer
value in floating point format, floating point types
- rounding halfway cases to even
(that is, to the nearest value
- that is an even integer),
regardless of the current rounding
- direction.
- T __builtin_elementwise_round(T x) round x to the nearest integer
value in floating point format, floating point types
- rounding halfway cases away from
zero, regardless of the
- current rounding direction. May
raise floating-point
- exceptions.
- T __builtin_elementwise_trunc(T x) return the integral value nearest
to but no larger in floating point types
- magnitude than x
-
- T __builtin_elementwise_nearbyint(T x) round x to the nearest integer
value in floating point format, floating point types
- rounding according to the current
rounding direction.
- May not raise the inexact
floating-point exception. This is
- treated the same as
``__builtin_elementwise_rint`` unless
- :ref:`FENV_ACCESS is enabled
<floating-point-environment>`.
-
- T __builtin_elementwise_rint(T x) round x to the nearest integer
value in floating point format, floating point types
- rounding according to the current
rounding
- direction. May raise
floating-point exceptions. This is treated
- the same as
``__builtin_elementwise_nearbyint`` unless
- :ref:`FENV_ACCESS is enabled
<floating-point-environment>`.
-
- T __builtin_elementwise_canonicalize(T x) return the platform specific
canonical encoding floating point types
- of a floating-point number
- T __builtin_elementwise_copysign(T x, T y) return the magnitude of x with
the sign of y. floating point types
- T __builtin_elementwise_max(T x, T y) return x or y, whichever is
larger integer and floating point types
- T __builtin_elementwise_min(T x, T y) return x or y, whichever is
smaller integer and floating point types
- T __builtin_elementwise_add_sat(T x, T y) return the sum of x and y,
clamped to the range of integer types
- representable values for the
signed/unsigned integer type.
- T __builtin_elementwise_sub_sat(T x, T y) return the difference of x and y,
clamped to the range of integer types
- representable values for the
signed/unsigned integer type.
-===========================================
================================================================
=========================================
+==============================================
======================================================================
=========================================
+ Name Operation
Supported element types
+==============================================
======================================================================
=========================================
+ T __builtin_elementwise_abs(T x) return the absolute value of a
number x; the absolute value of signed integer and floating point types
+ the most negative integer
remains the most negative integer
+ T __builtin_elementwise_fma(T x, T y, T z) fused multiply add, (x * y) +
z. floating point types
+ T __builtin_elementwise_ceil(T x) return the smallest integral
value greater than or equal to x floating point types
+ T __builtin_elementwise_sin(T x) return the sine of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_cos(T x) return the cosine of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_tan(T x) return the tangent of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_asin(T x) return the arcsine of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_acos(T x) return the arccosine of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_atan(T x) return the arctangent of x
interpreted as an angle in radians floating point types
+ T __builtin_elementwise_sinh(T x) return the hyperbolic sine of
angle x in radians floating point types
+ T __builtin_elementwise_cosh(T x) return the hyperbolic cosine
of angle x in radians floating point types
+ T __builtin_elementwise_tanh(T x) return the hyperbolic tangent
of angle x in radians floating point types
+ T __builtin_elementwise_floor(T x) return the largest integral
value less than or equal to x floating point types
+ T __builtin_elementwise_log(T x) return the natural logarithm
of x floating point types
+ T __builtin_elementwise_log2(T x) return the base 2 logarithm of
x floating point types
+ T __builtin_elementwise_log10(T x) return the base 10 logarithm
of x floating point types
+ T __builtin_elementwise_popcount(T x) return the number of 1 bits in
x integer types
+ T __builtin_elementwise_pow(T x, T y) return x raised to the power
of y floating point types
+ T __builtin_elementwise_bitreverse(T x) return the integer represented
after reversing the bits of x integer types
+ T __builtin_elementwise_exp(T x) returns the base-e
exponential, e^x, of the specified value floating point types
+ T __builtin_elementwise_exp2(T x) returns the base-2
exponential, 2^x, of the specified value floating point types
+
+ T __builtin_elementwise_sqrt(T x) return the square root of a
floating-point number floating point types
+ T __builtin_elementwise_roundeven(T x) round x to the nearest integer
value in floating point format, floating point types
+ rounding halfway cases to even
(that is, to the nearest value
+ that is an even integer),
regardless of the current rounding
+ direction.
+ T __builtin_elementwise_round(T x) round x to the nearest
integer value in floating point format, floating point types
+ rounding halfway cases away
from zero, regardless of the
+ current rounding direction.
May raise floating-point
+ exceptions.
+ T __builtin_elementwise_trunc(T x) return the integral value
nearest to but no larger in floating point types
+ magnitude than x
+
+ T __builtin_elementwise_nearbyint(T x) round x to the nearest
integer value in floating point format, floating point types
+ rounding according to the
current rounding direction.
+ May not raise the inexact
floating-point exception. This is
+ treated the same as
``__builtin_elementwise_rint`` unless
+ :ref:`FENV_ACCESS is enabled
<floating-point-environment>`.
+
+ T __builtin_elementwise_rint(T x) round x to the nearest
integer value in floating point format, floating point types
+ rounding according to the
current rounding
+ direction. May raise
floating-point exceptions. This is treated
+ the same as
``__builtin_elementwise_nearbyint`` unless
+ :ref:`FENV_ACCESS is enabled
<floating-point-environment>`.
+
+ T __builtin_elementwise_canonicalize(T x) return the platform specific
canonical encoding floating point types
+ of a floating-point number
+ T __builtin_elementwise_copysign(T x, T y) return the magnitude of x with
the sign of y. floating point types
+ T __builtin_elementwise_max(T x, T y) return x or y, whichever is
larger integer and floating point types
+ T __builtin_elementwise_min(T x, T y) return x or y, whichever is
smaller integer and floating point types
+ T __builtin_elementwise_add_sat(T x, T y) return the sum of x and y,
clamped to the range of integer types
+ representable values for the
signed/unsigned integer type.
+ T __builtin_elementwise_sub_sat(T x, T y) return the difference of x and
y, clamped to the range of integer types
+ representable values for the
signed/unsigned integer type.
+ T __builtin_elementwise_maximum(T x, T y) return x or y, whichever is
larger. Follows IEEE 754-2019 floating point types
+ semantics, see `LangRef
+
<http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+ for the comparison.
+ T __builtin_elementwise_minimum(T x, T y) return x or y, whichever is
smaller. Follows IEEE 754-2019 floating point types
+ semantics, see `LangRef
+
<http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+ for the comparison.
+==============================================
======================================================================
=========================================
*Reduction Builtins*
@@ -731,21 +739,29 @@ Example:
Let ``VT`` be a vector type and ``ET`` the element type of ``VT``.
-=======================================
================================================================
==================================
- Name Operation
Supported element types
-=======================================
================================================================
==================================
- ET __builtin_reduce_max(VT a) return x or y, whichever is larger;
If exactly one argument is integer and floating point types
+=======================================
======================================================================
==================================
+ Name Operation
Supported element types
+=======================================
======================================================================
==================================
+ ET __builtin_reduce_max(VT a) return x or y, whichever is larger;
If exactly one argument is integer and floating point types
a NaN, return the other argument. If
both arguments are NaNs,
fmax() return a NaN.
- ET __builtin_reduce_min(VT a) return x or y, whichever is smaller;
If exactly one argument integer and floating point types
+ ET __builtin_reduce_min(VT a) return x or y, whichever is smaller;
If exactly one argument integer and floating point types
is a NaN, return the other argument.
If both arguments are
NaNs, fmax() return a NaN.
- ET __builtin_reduce_add(VT a) \+
integer types
- ET __builtin_reduce_mul(VT a) \*
integer types
- ET __builtin_reduce_and(VT a) &
integer types
- ET __builtin_reduce_or(VT a) \|
integer types
- ET __builtin_reduce_xor(VT a) ^
integer types
-=======================================
================================================================
==================================
+ ET __builtin_reduce_add(VT a) \+
integer types
+ ET __builtin_reduce_mul(VT a) \*
integer types
+ ET __builtin_reduce_and(VT a) &
integer types
+ ET __builtin_reduce_or(VT a) \|
integer types
+ ET __builtin_reduce_xor(VT a) ^
integer types
+ ET __builtin_reduce_maximum(VT a) return the largest element of the
vector. Follows IEEE 754-2019 floating point types
+ semantics, see `LangRef
+
<http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+ for the comparison.
+ ET __builtin_reduce_minimum(VT a) return the smallest element of the
vector. Follows IEEE 754-2019 floating point types
+ semantics, see `LangRef
+
<http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+ for the comparison.
+=======================================
======================================================================
==================================
Matrix Types
============
diff --git a/clang/include/clang/Basic/Builtins.td
b/clang/include/clang/Basic/Builtins.td
index 33791270800c9d..d26f5b9a6c8bdc 100644
--- a/clang/include/clang/Basic/Builtins.td
+++ b/clang/include/clang/Basic/Builtins.td
@@ -1268,6 +1268,18 @@ def ElementwiseMin : Builtin {
let Prototype = "void(...)";
}
+def ElementwiseMaximum : Builtin {
+ let Spellings = ["__builtin_elementwise_maximum"];
+ let Attributes = [NoThrow, Const, CustomTypeChecking];
+ let Prototype = "void(...)";
+}
+
+def ElementwiseMinimum : Builtin {
+ let Spellings = ["__builtin_elementwise_minimum"];
+ let Attributes = [NoThrow, Const, CustomTypeChecking];
+ let Prototype = "void(...)";
+}
+
def ElementwiseCeil : Builtin {
let Spellings = ["__builtin_elementwise_ceil"];
let Attributes = [NoThrow, Const, CustomTypeChecking];
@@ -1436,6 +1448,18 @@ def ReduceMin : Builtin {
let Prototype = "void(...)";
}
+def ReduceMaximum : Builtin {
+ let Spellings = ["__builtin_reduce_maximum"];
+ let Attributes = [NoThrow, Const, CustomTypeChecking];
+ let Prototype = "void(...)";
+}
+
+def ReduceMinimum : Builtin {
+ let Spellings = ["__builtin_reduce_minimum"];
+ let Attributes = [NoThrow, Const, CustomTypeChecking];
+ let Prototype = "void(...)";
+}
+
def ReduceXor : Builtin {
let Spellings = ["__builtin_reduce_xor"];
let Attributes = [NoThrow, Const, CustomTypeChecking];
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td
b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index f3d5d4c56606cc..4f598f7517cf23 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -12216,7 +12216,8 @@ def err_builtin_invalid_arg_type: Error <
"a floating point type|"
"a vector of integers|"
"an unsigned integer|"
- "an 'int'}1 (was %2)">;
+ "an 'int'|"
+ "a vector of floating points}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
index e1c3a99cfa167e..2549be38beb2b6 100644
--- a/clang/include/clang/Sema/Sema.h
+++ b/clang/include/clang/Sema/Sema.h
@@ -2381,7 +2381,8 @@ class Sema final : public SemaBase {
bool CheckFunctionCall(FunctionDecl *FDecl, CallExpr *TheCall,
const FunctionProtoType *Proto);
- bool BuiltinVectorMath(CallExpr *TheCall, QualType &Res);
+ /// \param FPOnly restricts the arguments to floating-point types.
+ bool BuiltinVectorMath(CallExpr *TheCall, QualType &Res, bool FPOnly =
false);
bool BuiltinVectorToScalarMath(CallExpr *TheCall);
/// Handles the checks for format strings, non-POD arguments to vararg
@@ -2573,7 +2574,8 @@ class Sema final : public SemaBase {
ExprResult AtomicOpsOverloaded(ExprResult TheCallResult,
AtomicExpr::AtomicOp Op);
- bool BuiltinElementwiseMath(CallExpr *TheCall);
+ /// \param FPOnly restricts the arguments to floating-point types.
+ bool BuiltinElementwiseMath(CallExpr *TheCall, bool FPOnly = false);
bool PrepareBuiltinReduceMathOneArgCall(CallExpr *TheCall);
bool BuiltinNonDeterministicValue(CallExpr *TheCall);
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 9033cd1ccd781d..cbc51ebbe97747 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -3960,6 +3960,22 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl
GD, unsigned BuiltinID,
return RValue::get(Result);
}
+ case Builtin::BI__builtin_elementwise_maximum: {
+ Value *Op0 = EmitScalarExpr(E->getArg(0));
+ Value *Op1 = EmitScalarExpr(E->getArg(1));
+ Value *Result = Builder.CreateBinaryIntrinsic(llvm::Intrinsic::maximum,
Op0,
+ Op1, nullptr, "elt.maximum");
+ return RValue::get(Result);
+ }
+
+ case Builtin::BI__builtin_elementwise_minimum: {
+ Value *Op0 = EmitScalarExpr(E->getArg(0));
+ Value *Op1 = EmitScalarExpr(E->getArg(1));
+ Value *Result = Builder.CreateBinaryIntrinsic(llvm::Intrinsic::minimum,
Op0,
+ Op1, nullptr, "elt.minimum");
+ return RValue::get(Result);
+ }
+
case Builtin::BI__builtin_reduce_max: {
auto GetIntrinsicID = [this](QualType QT) {
if (auto *VecTy = QT->getAs<VectorType>())
@@ -4013,6 +4029,29 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl
GD, unsigned BuiltinID,
return RValue::get(emitBuiltinWithOneOverloadedType<1>(
*this, E, llvm::Intrinsic::vector_reduce_and, "rdx.and"));
+ case Builtin::BI__builtin_reduce_maximum: {
+ auto GetIntrinsicID = [](QualType QT) {
+ if (auto *VecTy = QT->getAs<VectorType>())
+ QT = VecTy->getElementType();
+ assert(QT->isFloatingType() && "must have a float here");
+ return llvm::Intrinsic::vector_reduce_fmaximum;
+ };
+ return RValue::get(emitBuiltinWithOneOverloadedType<1>(
+ *this, E, GetIntrinsicID(E->getArg(0)->getType()), "rdx.maximum"));
+ }
+
+ case Builtin::BI__builtin_reduce_minimum: {
+ auto GetIntrinsicID = [](QualType QT) {
+ if (auto *VecTy = QT->getAs<VectorType>())
+ QT = VecTy->getElementType();
+ assert(QT->isFloatingType() && "must have a float here");
+ return llvm::Intrinsic::vector_reduce_fminimum;
+ };
+
+ return RValue::get(emitBuiltinWithOneOverloadedType<1>(
+ *this, E, GetIntrinsicID(E->getArg(0)->getType()), "rdx.minimum"));
+ }
+
case Builtin::BI__builtin_matrix_transpose: {
auto *MatrixTy = E->getArg(0)->getType()->castAs<ConstantMatrixType>();
Value *MatValue = EmitScalarExpr(E->getArg(0));
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index af1dc21594da8a..2b033f3f7fb367 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -2755,15 +2755,10 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl,
unsigned BuiltinID,
// These builtins restrict the element type to floating point
// types only, and take in two arguments.
+ case Builtin::BI__builtin_elementwise_minimum:
+ case Builtin::BI__builtin_elementwise_maximum:
case Builtin::BI__builtin_elementwise_pow: {
- if (BuiltinElementwiseMath(TheCall))
- return ExprError();
-
- QualType ArgTy = TheCall->getArg(0)->getType();
- if (checkFPMathBuiltinElementType(*this, TheCall->getArg(0)->getBeginLoc(),
- ArgTy, 1) ||
- checkFPMathBuiltinElementType(*this, TheCall->getArg(1)->getBeginLoc(),
- ArgTy, 2))
+ if (BuiltinElementwiseMath(TheCall, /*FPOnly=*/true))
return ExprError();
break;
}
@@ -2867,6 +2862,29 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl,
unsigned BuiltinID,
TheCall->setType(ElTy);
break;
}
+ case Builtin::BI__builtin_reduce_maximum:
+ case Builtin::BI__builtin_reduce_minimum: {
+ if (PrepareBuiltinReduceMathOneArgCall(TheCall))
+ return ExprError();
+
+ const Expr *Arg = TheCall->getArg(0);
+ const auto *TyA = Arg->getType()->getAs<VectorType>();
+
+ QualType ElTy;
+ if (TyA)
+ ElTy = TyA->getElementType();
+ else if (Arg->getType()->isSizelessVectorType())
+ ElTy = Arg->getType()->getSizelessVectorEltType(Context);
+
+ if (ElTy.isNull() || !ElTy->isFloatingType()) {
+ Diag(Arg->getBeginLoc(), diag::err_builtin_invalid_arg_type)
+ << 1 << /* vector of floating points */ 9 << Arg->getType();
+ return ExprError();
+ }
+
+ TheCall->setType(ElTy);
+ break;
+ }
// These builtins support vectors of integers only.
// TODO: ADD/MUL should support floating-point types.
@@ -14377,9 +14395,9 @@ bool
Sema::PrepareBuiltinElementwiseMathOneArgCall(CallExpr *TheCall) {
return false;
}
-bool Sema::BuiltinElementwiseMath(CallExpr *TheCall) {
+bool Sema::BuiltinElementwiseMath(CallExpr *TheCall, bool FPOnly) {
QualType Res;
- if (BuiltinVectorMath(TheCall, Res))
+ if (BuiltinVectorMath(TheCall, Res, FPOnly))
return true;
TheCall->setType(Res);
return false;
@@ -14398,7 +14416,7 @@ bool Sema::BuiltinVectorToScalarMath(CallExpr *TheCall)
{
return false;
}
-bool Sema::BuiltinVectorMath(CallExpr *TheCall, QualType &Res) {
+bool Sema::BuiltinVectorMath(CallExpr *TheCall, QualType &Res, bool FPOnly) {
if (checkArgCount(TheCall, 2))
return true;
@@ -14418,8 +14436,13 @@ bool Sema::BuiltinVectorMath(CallExpr *TheCall,
QualType &Res) {
diag::err_typecheck_call_different_arg_types)
<< TyA << TyB;
- if (checkMathBuiltinElementType(*this, A.get()->getBeginLoc(), TyA, 1))
- return true;
+ if (FPOnly) {
+ if (checkFPMathBuiltinElementType(*this, A.get()->getBeginLoc(), TyA, 1))
+ return true;
+ } else {
+ if (checkMathBuiltinElementType(*this, A.get()->getBeginLoc(), TyA, 1))
+ return true;
+ }
TheCall->setArg(0, A.get());
TheCall->setArg(1, B.get());
diff --git a/clang/test/CodeGen/builtins-elementwise-math.c
b/clang/test/CodeGen/builtins-elementwise-math.c
index 7e094a52653ef0..4a02b2f6467c34 100644
--- a/clang/test/CodeGen/builtins-elementwise-math.c
+++ b/clang/test/CodeGen/builtins-elementwise-math.c
@@ -169,6 +169,82 @@ void test_builtin_elementwise_sub_sat(float f1, float f2,
double d1, double d2,
i1 = __builtin_elementwise_sub_sat(1, 'a');
}
+void test_builtin_elementwise_maximum(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,
+ _BitInt(31) bi1, _BitInt(31) bi2,
+ unsigned _BitInt(55) bu1, unsigned
_BitInt(55) bu2) {
+ // CHECK-LABEL: define void @test_builtin_elementwise_maximum(
+ // CHECK: [[F1:%.+]] = load float, ptr %f1.addr, align 4
+ // CHECK-NEXT: [[F2:%.+]] = load float, ptr %f2.addr, align 4
+ // CHECK-NEXT: call float @llvm.maximum.f32(float [[F1]], float [[F2]])
+ f1 = __builtin_elementwise_maximum(f1, f2);
+
+ // CHECK: [[D1:%.+]] = load double, ptr %d1.addr, align 8
+ // CHECK-NEXT: [[D2:%.+]] = load double, ptr %d2.addr, align 8
+ // CHECK-NEXT: call double @llvm.maximum.f64(double [[D1]], double [[D2]])
+ d1 = __builtin_elementwise_maximum(d1, d2);
+
+ // CHECK: [[D2:%.+]] = load double, ptr %d2.addr, align 8
+ // CHECK-NEXT: call double @llvm.maximum.f64(double 2.000000e+01, double
[[D2]])
+ d1 = __builtin_elementwise_maximum(20.0, d2);
+
+ // CHECK: [[VF1:%.+]] = load <4 x float>, ptr %vf1.addr, align 16
+ // CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.maximum.v4f32(<4 x float> [[VF1]], <4
x float> [[VF2]])
+ vf1 = __builtin_elementwise_maximum(vf1, vf2);
+
+ // CHECK: [[CVF1:%.+]] = load <4 x float>, ptr %cvf1, align 16
+ // CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.maximum.v4f32(<4 x float> [[CVF1]], <4
x float> [[VF2]])
+ const float4 cvf1 = vf1;
+ vf1 = __builtin_elementwise_maximum(cvf1, vf2);
+
+ // CHECK: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: [[CVF1:%.+]] = load <4 x float>, ptr %cvf1, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.maximum.v4f32(<4 x float> [[VF2]], <4
x float> [[CVF1]])
+ vf1 = __builtin_elementwise_maximum(vf2, cvf1);
+}
+
+void test_builtin_elementwise_minimum(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,
+ _BitInt(31) bi1, _BitInt(31) bi2,
+ unsigned _BitInt(55) bu1, unsigned
_BitInt(55) bu2) {
+ // CHECK-LABEL: define void @test_builtin_elementwise_minimum(
+ // CHECK: [[F1:%.+]] = load float, ptr %f1.addr, align 4
+ // CHECK-NEXT: [[F2:%.+]] = load float, ptr %f2.addr, align 4
+ // CHECK-NEXT: call float @llvm.minimum.f32(float [[F1]], float [[F2]])
+ f1 = __builtin_elementwise_minimum(f1, f2);
+
+ // CHECK: [[D1:%.+]] = load double, ptr %d1.addr, align 8
+ // CHECK-NEXT: [[D2:%.+]] = load double, ptr %d2.addr, align 8
+ // CHECK-NEXT: call double @llvm.minimum.f64(double [[D1]], double [[D2]])
+ d1 = __builtin_elementwise_minimum(d1, d2);
+
+ // CHECK: [[D1:%.+]] = load double, ptr %d1.addr, align 8
+ // CHECK-NEXT: call double @llvm.minimum.f64(double [[D1]], double
2.000000e+00)
+ d1 = __builtin_elementwise_minimum(d1, 2.0);
+
+ // CHECK: [[VF1:%.+]] = load <4 x float>, ptr %vf1.addr, align 16
+ // CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.minimum.v4f32(<4 x float> [[VF1]], <4
x float> [[VF2]])
+ vf1 = __builtin_elementwise_minimum(vf1, vf2);
+
+ // CHECK: [[CVF1:%.+]] = load <4 x float>, ptr %cvf1, align 16
+ // CHECK-NEXT: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.minimum.v4f32(<4 x float> [[CVF1]], <4
x float> [[VF2]])
+ const float4 cvf1 = vf1;
+ vf1 = __builtin_elementwise_minimum(cvf1, vf2);
+
+ // CHECK: [[VF2:%.+]] = load <4 x float>, ptr %vf2.addr, align 16
+ // CHECK-NEXT: [[CVF1:%.+]] = load <4 x float>, ptr %cvf1, align 16
+ // CHECK-NEXT: call <4 x float> @llvm.minimum.v4f32(<4 x float> [[VF2]], <4
x float> [[CVF1]])
+ vf1 = __builtin_elementwise_minimum(vf2, cvf1);
+}
+
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,
diff --git a/clang/test/CodeGen/builtins-reduction-math.c
b/clang/test/CodeGen/builtins-reduction-math.c
index acafe9222d59fd..e12fd729c84c0b 100644
--- a/clang/test/CodeGen/builtins-reduction-math.c
+++ b/clang/test/CodeGen/builtins-reduction-math.c
@@ -138,6 +138,30 @@ void test_builtin_reduce_and(si8 vi1, u4 vu1) {
unsigned r3 = __builtin_reduce_and(vu1);
}
+void test_builtin_reduce_maximum(float4 vf1) {
+ // CHECK-LABEL: define void @test_builtin_reduce_maximum(
+ // CHECK: [[VF1:%.+]] = load <4 x float>, ptr %vf1.addr, align 16
+ // CHECK-NEXT: call float @llvm.vector.reduce.fmaximum.v4f32(<4 x float>
[[VF1]])
+ float r1 = __builtin_reduce_maximum(vf1);
+
+ // CHECK: [[VF1_AS1:%.+]] = load <4 x float>, ptr addrspace(1)
@vf1_as_one, align 16
+ // CHECK-NEXT: [[RDX1:%.+]] = call float
@llvm.vector.reduce.fmaximum.v4f32(<4 x float> [[VF1_AS1]])
+ // CHECK-NEXT: fpext float [[RDX1]] to double
+ const double r4 = __builtin_reduce_maximum(vf1_as_one);
+}
+
+void test_builtin_reduce_minimum(float4 vf1) {
+ // CHECK-LABEL: define void @test_builtin_reduce_minimum(
+ // CHECK: [[VF1:%.+]] = load <4 x float>, ptr %vf1.addr, align 16
+ // CHECK-NEXT: call float @llvm.vector.reduce.fminimum.v4f32(<4 x float>
[[VF1]])
+ float r1 = __builtin_reduce_minimum(vf1);
+
+ // CHECK: [[VF1_AS1:%.+]] = load <4 x float>, ptr addrspace(1)
@vf1_as_one, align 16
+ // CHECK-NEXT: [[RDX1:%.+]] = call float
@llvm.vector.reduce.fminimum.v4f32(<4 x float> [[VF1_AS1]])
+ // CHECK-NEXT: fpext float [[RDX1]] to double
+ const double r4 = __builtin_reduce_minimum(vf1_as_one);
+}
+
#if defined(__ARM_FEATURE_SVE)
#include <arm_sve.h>
diff --git a/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
b/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
index 55ba17a1955800..dc5674ddab233c 100644
--- a/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
+++ b/clang/test/CodeGen/strictfp-elementwise-bulitins.cpp
@@ -47,6 +47,26 @@ float4 strict_elementwise_min(float4 a, float4 b) {
return __builtin_elementwise_min(a, b);
}
+// CHECK-LABEL: define dso_local noundef <4 x float>
@_Z26strict_elementwise_maximumDv4_fS_
+// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]])
local_unnamed_addr #[[ATTR2]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[ELT_MAXIMUM:%.*]] = tail call <4 x float>
@llvm.maximum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]]
+// CHECK-NEXT: ret <4 x float> [[ELT_MAXIMUM]]
+//
+float4 strict_elementwise_maximum(float4 a, float4 b) {
+ return __builtin_elementwise_maximum(a, b);
+}
+
+// CHECK-LABEL: define dso_local noundef <4 x float>
@_Z26strict_elementwise_minimumDv4_fS_
+// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]])
local_unnamed_addr #[[ATTR2]] {
+// CHECK-NEXT: entry:
+// CHECK-NEXT: [[ELT_MINIMUM:%.*]] = tail call <4 x float>
@llvm.minimum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]]
+// CHECK-NEXT: ret <4 x float> [[ELT_MINIMUM]]
+//
+float4 strict_elementwise_minimum(float4 a, float4 b) {
+ return __builtin_elementwise_minimum(a, b);
+}
+
// CHECK-LABEL: define dso_local noundef <4 x float>
@_Z23strict_elementwise_ceilDv4_f
// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) local_unnamed_addr #[[ATTR2]] {
// CHECK-NEXT: entry:
diff --git a/clang/test/Sema/builtins-elementwise-math.c
b/clang/test/Sema/builtins-elementwise-math.c
index 1727be1d6286d5..6eef5874391916 100644
--- a/clang/test/Sema/builtins-elementwise-math.c
+++ b/clang/test/Sema/builtins-elementwise-math.c
@@ -273,6 +273,88 @@ void test_builtin_elementwise_min(int i, short s, double
d, float4 v, int3 iv, u
// expected-error@-1 {{1st argument must be a vector, integer or floating
point type (was '_Complex float')}}
}
+void test_builtin_elementwise_maximum(int i, short s, float f, double d,
float4 v, int3 iv, unsigned3 uv, int *p) {
+ i = __builtin_elementwise_maximum(p, d);
+ // expected-error@-1 {{arguments are of different types ('int *' vs
'double')}}
+
+ struct Foo foo = __builtin_elementwise_maximum(d, d);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of
incompatible type 'double'}}
+
+ i = __builtin_elementwise_maximum(i);
+ // expected-error@-1 {{too few arguments to function call, expected 2, have
1}}
+
+ i = __builtin_elementwise_maximum();
+ // expected-error@-1 {{too few arguments to function call, expected 2, have
0}}
+
+ i = __builtin_elementwise_maximum(i, i, i);
+ // expected-error@-1 {{too many arguments to function call, expected 2, have
3}}
+
+ i = __builtin_elementwise_maximum(v, iv);
+ // expected-error@-1 {{arguments are of different types ('float4' (vector of
4 'float' values) vs 'int3' (vector of 3 'int' values))}}
+
+ i = __builtin_elementwise_maximum(uv, iv);
+ // expected-error@-1 {{arguments are of different types ('unsigned3' (vector
of 3 'unsigned int' values) vs 'int3' (vector of 3 'int' values))}}
+
+ d = __builtin_elementwise_maximum(f, d);
+
+ v = __builtin_elementwise_maximum(v, v);
+
+ i = __builtin_elementwise_maximum(iv, iv);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'int3' (vector of 3 'int' values))}}
+
+ i = __builtin_elementwise_maximum(i, i);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'int')}}
+
+ int A[10];
+ A = __builtin_elementwise_maximum(A, A);
+ // expected-error@-1 {{1st argument must be a floating point type (was 'int
*')}}
+
+ _Complex float c1, c2;
+ c1 = __builtin_elementwise_maximum(c1, c2);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'_Complex float')}}
+}
+
+void test_builtin_elementwise_minimum(int i, short s, float f, double d,
float4 v, int3 iv, unsigned3 uv, int *p) {
+ i = __builtin_elementwise_minimum(p, d);
+ // expected-error@-1 {{arguments are of different types ('int *' vs
'double')}}
+
+ struct Foo foo = __builtin_elementwise_minimum(d, d);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of
incompatible type 'double'}}
+
+ i = __builtin_elementwise_minimum(i);
+ // expected-error@-1 {{too few arguments to function call, expected 2, have
1}}
+
+ i = __builtin_elementwise_minimum();
+ // expected-error@-1 {{too few arguments to function call, expected 2, have
0}}
+
+ i = __builtin_elementwise_minimum(i, i, i);
+ // expected-error@-1 {{too many arguments to function call, expected 2, have
3}}
+
+ i = __builtin_elementwise_minimum(v, iv);
+ // expected-error@-1 {{arguments are of different types ('float4' (vector of
4 'float' values) vs 'int3' (vector of 3 'int' values))}}
+
+ i = __builtin_elementwise_minimum(uv, iv);
+ // expected-error@-1 {{arguments are of different types ('unsigned3' (vector
of 3 'unsigned int' values) vs 'int3' (vector of 3 'int' values))}}
+
+ d = __builtin_elementwise_minimum(f, d);
+
+ v = __builtin_elementwise_minimum(v, v);
+
+ i = __builtin_elementwise_minimum(iv, iv);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'int3' (vector of 3 'int' values))}}
+
+ i = __builtin_elementwise_minimum(i, i);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'int')}}
+
+ int A[10];
+ A = __builtin_elementwise_minimum(A, A);
+ // expected-error@-1 {{1st argument must be a floating point type (was 'int
*')}}
+
+ _Complex float c1, c2;
+ c1 = __builtin_elementwise_minimum(c1, c2);
+ // expected-error@-1 {{1st argument must be a floating point type (was
'_Complex float')}}
+}
+
void test_builtin_elementwise_bitreverse(int i, float f, double d, float4 v,
int3 iv, unsigned u, unsigned4 uv) {
struct Foo s = __builtin_elementwise_bitreverse(i);
diff --git a/clang/test/Sema/builtins-reduction-math.c
b/clang/test/Sema/builtins-reduction-math.c
index 9d5eed75eb8141..9b0d91bfd6e3d2 100644
--- a/clang/test/Sema/builtins-reduction-math.c
+++ b/clang/test/Sema/builtins-reduction-math.c
@@ -120,3 +120,31 @@ void test_builtin_reduce_and(int i, float4 v, int3 iv) {
i = __builtin_reduce_and(v);
// expected-error@-1 {{1st argument must be a vector of integers (was
'float4' (vector of 4 'float' values))}}
}
+
+void test_builtin_reduce_maximum(int i, float4 v, int3 iv) {
+ struct Foo s = __builtin_reduce_maximum(v);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of
incompatible type 'float'}}
+
+ i = __builtin_reduce_maximum(v, v);
+ // expected-error@-1 {{too many arguments to function call, expected 1, have
2}}
+
+ i = __builtin_reduce_maximum();
+ // expected-error@-1 {{too few arguments to function call, expected 1, have
0}}
+
+ i = __builtin_reduce_maximum(i);
+ // expected-error@-1 {{1st argument must be a vector of floating points (was
'int')}}
+}
+
+void test_builtin_reduce_minimum(int i, float4 v, int3 iv) {
+ struct Foo s = __builtin_reduce_minimum(v);
+ // expected-error@-1 {{initializing 'struct Foo' with an expression of
incompatible type 'float'}}
+
+ i = __builtin_reduce_minimum(v, v);
+ // expected-error@-1 {{too many arguments to function call, expected 1, have
2}}
+
+ i = __builtin_reduce_minimum();
+ // expected-error@-1 {{too few arguments to function call, expected 1, have
0}}
+
+ i = __builtin_reduce_minimum(i);
+ // expected-error@-1 {{1st argument must be a vector of floating points (was
'int')}}
+}
diff --git a/clang/test/SemaCXX/builtins-elementwise-math.cpp
b/clang/test/SemaCXX/builtins-elementwise-math.cpp
index c3d8bc593c0bbc..c83ef3bedb0e81 100644
--- a/clang/test/SemaCXX/builtins-elementwise-math.cpp
+++ b/clang/test/SemaCXX/builtins-elementwise-math.cpp
@@ -76,6 +76,22 @@ void test_builtin_elementwise_min_fp() {
static_assert(!is_const<decltype(__builtin_elementwise_min(a, a))>::value);
}
+void test_builtin_elementwise_maximum() {
+ const float a = 2.0f;
+ float b = 1.0f;
+ static_assert(!is_const<decltype(__builtin_elementwise_maximum(a,
b))>::value);
+ static_assert(!is_const<decltype(__builtin_elementwise_maximum(b,
a))>::value);
+ static_assert(!is_const<decltype(__builtin_elementwise_maximum(a,
a))>::value);
+}
+
+void test_builtin_elementwise_minimum() {
+ const float a = 2.0f;
+ float b = 1.0f;
+ static_assert(!is_const<decltype(__builtin_elementwise_minimum(a,
b))>::value);
+ static_assert(!is_const<decltype(__builtin_elementwise_minimum(b,
a))>::value);
+ static_assert(!is_const<decltype(__builtin_elementwise_minimum(a,
a))>::value);
+}
+
void test_builtin_elementwise_ceil() {
const float a = 42.0;
float b = 42.3;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
