SjoerdMeijer created this revision.
SjoerdMeijer added reviewers: olista01, t.p.northover, rjmccall, aschwaighofer.
Herald added subscribers: kristof.beyls, javed.absar, aemerson.
Pass and return _Float16 as if it were an int or float for ARM, but with the
top 16 bits unspecified, similarly like we already do for __fp16.
We will implement proper half-precision function argument lowering in the ARM
backend
soon, but want to use this workaround in the mean time.
https://reviews.llvm.org/D42318
Files:
include/clang/AST/Type.h
lib/CodeGen/TargetInfo.cpp
test/CodeGen/arm-float16-arguments.c
Index: test/CodeGen/arm-float16-arguments.c
===================================================================
--- /dev/null
+++ test/CodeGen/arm-float16-arguments.c
@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi
soft -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s
--check-prefix=CHECK --check-prefix=SOFT
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi
hard -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s
--check-prefix=CHECK --check-prefix=HARD
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi
soft -fnative-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s
--check-prefix=NATIVE
+
+_Float16 g;
+
+void t1(_Float16 a) { g = a; }
+// SOFT: define void @t1(i32 [[PARAM:%.*]])
+// SOFT: [[TRUNC:%.*]] = trunc i32 [[PARAM]] to i16
+// HARD: define arm_aapcs_vfpcc void @t1(float [[PARAM:%.*]])
+// HARD: [[BITCAST:%.*]] = bitcast float [[PARAM]] to i32
+// HARD: [[TRUNC:%.*]] = trunc i32 [[BITCAST]] to i16
+// CHECK: store i16 [[TRUNC]], i16* bitcast (half* @g to i16*)
+// NATIVE: define void @t1(half [[PARAM:%.*]])
+// NATIVE: store half [[PARAM]], half* @g
+
+_Float16 t2() { return g; }
+// SOFT: define i32 @t2()
+// HARD: define arm_aapcs_vfpcc float @t2()
+// NATIVE: define half @t2()
+// CHECK: [[LOAD:%.*]] = load i16, i16* bitcast (half* @g to i16*)
+// CHECK: [[ZEXT:%.*]] = zext i16 [[LOAD]] to i32
+// SOFT: ret i32 [[ZEXT]]
+// HARD: [[BITCAST:%.*]] = bitcast i32 [[ZEXT]] to float
+// HARD: ret float [[BITCAST]]
+// NATIVE: [[LOAD:%.*]] = load half, half* @g
+// NATIVE: ret half [[LOAD]]
Index: lib/CodeGen/TargetInfo.cpp
===================================================================
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -5721,10 +5721,11 @@
return getNaturalAlignIndirect(Ty, /*ByVal=*/false);
}
- // __fp16 gets passed as if it were an int or float, but with the top 16 bits
- // unspecified. This is not done for OpenCL as it handles the half type
- // natively, and does not need to interwork with AAPCS code.
- if (Ty->isHalfType() &&
!getContext().getLangOpts().NativeHalfArgsAndReturns) {
+ // _Float16 and __fp16 get passed as if it were an int or float, but with
+ // the top 16 bits unspecified. This is not done for OpenCL as it handles the
+ // half type natively, and does not need to interwork with AAPCS code.
+ if ((Ty->isFloat16Type() || Ty->isHalfType()) &&
+ !getContext().getLangOpts().NativeHalfArgsAndReturns) {
llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
llvm::Type::getFloatTy(getVMContext()) :
llvm::Type::getInt32Ty(getVMContext());
@@ -5919,10 +5920,11 @@
return getNaturalAlignIndirect(RetTy);
}
- // __fp16 gets returned as if it were an int or float, but with the top 16
- // bits unspecified. This is not done for OpenCL as it handles the half type
- // natively, and does not need to interwork with AAPCS code.
- if (RetTy->isHalfType() &&
!getContext().getLangOpts().NativeHalfArgsAndReturns) {
+ // _Float16 and __fp16 get returned as if it were an int or float, but with
+ // the top 16 bits unspecified. This is not done for OpenCL as it handles the
+ // half type natively, and does not need to interwork with AAPCS code.
+ if ((RetTy->isFloat16Type() || RetTy->isHalfType()) &&
+ !getContext().getLangOpts().NativeHalfArgsAndReturns) {
llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
llvm::Type::getFloatTy(getVMContext()) :
llvm::Type::getInt32Ty(getVMContext());
Index: include/clang/AST/Type.h
===================================================================
--- include/clang/AST/Type.h
+++ include/clang/AST/Type.h
@@ -1728,6 +1728,7 @@
bool isAnyComplexType() const; // C99 6.2.5p11 (complex) + Complex Int.
bool isFloatingType() const; // C99 6.2.5p11 (real floating + complex)
bool isHalfType() const; // OpenCL 6.1.1.1, NEON (IEEE 754-2008 half)
+ bool isFloat16Type() const; // C11 extension ISO/IEC TS 18661
bool isRealType() const; // C99 6.2.5p17 (real floating + integer)
bool isArithmeticType() const; // C99 6.2.5p18 (integer + floating)
bool isVoidType() const; // C99 6.2.5p19
@@ -6179,6 +6180,12 @@
return false;
}
+inline bool Type::isFloat16Type() const {
+ if (const BuiltinType *BT = dyn_cast<BuiltinType>(CanonicalType))
+ return BT->getKind() == BuiltinType::Float16;
+ return false;
+}
+
inline bool Type::isNullPtrType() const {
if (const BuiltinType *BT = getAs<BuiltinType>())
return BT->getKind() == BuiltinType::NullPtr;
Index: test/CodeGen/arm-float16-arguments.c
===================================================================
--- /dev/null
+++ test/CodeGen/arm-float16-arguments.c
@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=CHECK --check-prefix=SOFT
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi hard -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=CHECK --check-prefix=HARD
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fnative-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=NATIVE
+
+_Float16 g;
+
+void t1(_Float16 a) { g = a; }
+// SOFT: define void @t1(i32 [[PARAM:%.*]])
+// SOFT: [[TRUNC:%.*]] = trunc i32 [[PARAM]] to i16
+// HARD: define arm_aapcs_vfpcc void @t1(float [[PARAM:%.*]])
+// HARD: [[BITCAST:%.*]] = bitcast float [[PARAM]] to i32
+// HARD: [[TRUNC:%.*]] = trunc i32 [[BITCAST]] to i16
+// CHECK: store i16 [[TRUNC]], i16* bitcast (half* @g to i16*)
+// NATIVE: define void @t1(half [[PARAM:%.*]])
+// NATIVE: store half [[PARAM]], half* @g
+
+_Float16 t2() { return g; }
+// SOFT: define i32 @t2()
+// HARD: define arm_aapcs_vfpcc float @t2()
+// NATIVE: define half @t2()
+// CHECK: [[LOAD:%.*]] = load i16, i16* bitcast (half* @g to i16*)
+// CHECK: [[ZEXT:%.*]] = zext i16 [[LOAD]] to i32
+// SOFT: ret i32 [[ZEXT]]
+// HARD: [[BITCAST:%.*]] = bitcast i32 [[ZEXT]] to float
+// HARD: ret float [[BITCAST]]
+// NATIVE: [[LOAD:%.*]] = load half, half* @g
+// NATIVE: ret half [[LOAD]]
Index: lib/CodeGen/TargetInfo.cpp
===================================================================
--- lib/CodeGen/TargetInfo.cpp
+++ lib/CodeGen/TargetInfo.cpp
@@ -5721,10 +5721,11 @@
return getNaturalAlignIndirect(Ty, /*ByVal=*/false);
}
- // __fp16 gets passed as if it were an int or float, but with the top 16 bits
- // unspecified. This is not done for OpenCL as it handles the half type
- // natively, and does not need to interwork with AAPCS code.
- if (Ty->isHalfType() && !getContext().getLangOpts().NativeHalfArgsAndReturns) {
+ // _Float16 and __fp16 get passed as if it were an int or float, but with
+ // the top 16 bits unspecified. This is not done for OpenCL as it handles the
+ // half type natively, and does not need to interwork with AAPCS code.
+ if ((Ty->isFloat16Type() || Ty->isHalfType()) &&
+ !getContext().getLangOpts().NativeHalfArgsAndReturns) {
llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
llvm::Type::getFloatTy(getVMContext()) :
llvm::Type::getInt32Ty(getVMContext());
@@ -5919,10 +5920,11 @@
return getNaturalAlignIndirect(RetTy);
}
- // __fp16 gets returned as if it were an int or float, but with the top 16
- // bits unspecified. This is not done for OpenCL as it handles the half type
- // natively, and does not need to interwork with AAPCS code.
- if (RetTy->isHalfType() && !getContext().getLangOpts().NativeHalfArgsAndReturns) {
+ // _Float16 and __fp16 get returned as if it were an int or float, but with
+ // the top 16 bits unspecified. This is not done for OpenCL as it handles the
+ // half type natively, and does not need to interwork with AAPCS code.
+ if ((RetTy->isFloat16Type() || RetTy->isHalfType()) &&
+ !getContext().getLangOpts().NativeHalfArgsAndReturns) {
llvm::Type *ResType = IsEffectivelyAAPCS_VFP ?
llvm::Type::getFloatTy(getVMContext()) :
llvm::Type::getInt32Ty(getVMContext());
Index: include/clang/AST/Type.h
===================================================================
--- include/clang/AST/Type.h
+++ include/clang/AST/Type.h
@@ -1728,6 +1728,7 @@
bool isAnyComplexType() const; // C99 6.2.5p11 (complex) + Complex Int.
bool isFloatingType() const; // C99 6.2.5p11 (real floating + complex)
bool isHalfType() const; // OpenCL 6.1.1.1, NEON (IEEE 754-2008 half)
+ bool isFloat16Type() const; // C11 extension ISO/IEC TS 18661
bool isRealType() const; // C99 6.2.5p17 (real floating + integer)
bool isArithmeticType() const; // C99 6.2.5p18 (integer + floating)
bool isVoidType() const; // C99 6.2.5p19
@@ -6179,6 +6180,12 @@
return false;
}
+inline bool Type::isFloat16Type() const {
+ if (const BuiltinType *BT = dyn_cast<BuiltinType>(CanonicalType))
+ return BT->getKind() == BuiltinType::Float16;
+ return false;
+}
+
inline bool Type::isNullPtrType() const {
if (const BuiltinType *BT = getAs<BuiltinType>())
return BT->getKind() == BuiltinType::NullPtr;
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
