https://github.com/wenju-he created https://github.com/llvm/llvm-project/pull/149775
Addresses https://github.com/llvm/llvm-project/issues/112164. minimumnum and maximumnum intrinsics were added in 5bf81e53dbea. The new built-ins can be used for implementing OpenCL math function fmax and fmin in #128506. >From 472d5bbf068e1ab2cbcbcfda66bef5fbb7c041f8 Mon Sep 17 00:00:00 2001 From: Wenju He <wenju...@intel.com> Date: Mon, 21 Jul 2025 09:49:34 +0200 Subject: [PATCH] [Clang] Add elementwise maximumnum/minimumnum builtin functions Addresses https://github.com/llvm/llvm-project/issues/112164. minimumnum and maximumnum intrinsics were added in 5bf81e53dbea. The new built-ins can be used for implementing OpenCL math function fmax and fmin in #128506. --- clang/docs/LanguageExtensions.rst | 8 + clang/docs/ReleaseNotes.rst | 1 + clang/include/clang/Basic/Builtins.td | 12 ++ clang/lib/CodeGen/CGBuiltin.cpp | 16 ++ clang/lib/Sema/SemaChecking.cpp | 2 + .../CodeGen/builtin-maximumnum-minimumnum.c | 171 ++++++++++++++++++ clang/test/Sema/builtins-elementwise-math.c | 90 +++++++++ 7 files changed, 300 insertions(+) create mode 100644 clang/test/CodeGen/builtin-maximumnum-minimumnum.c diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst index f448a9a8db172..8b83dc448d768 100644 --- a/clang/docs/LanguageExtensions.rst +++ b/clang/docs/LanguageExtensions.rst @@ -848,6 +848,14 @@ of different sizes and signs is forbidden in binary and ternary builtins. semantics, see `LangRef <http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_ for the comparison. + T __builtin_elementwise_maximumnum(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_minimumnum(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. ============================================== ====================================================================== ========================================= diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index 46a77673919d3..6a274899e3c43 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -340,6 +340,7 @@ Non-comprehensive list of changes in this release - Added `__builtin_elementwise_exp10`. - For AMDPGU targets, added `__builtin_v_cvt_off_f32_i4` that maps to the `v_cvt_off_f32_i4` instruction. - Added `__builtin_elementwise_minnum` and `__builtin_elementwise_maxnum`. +- Added `__builtin_elementwise_minnumnum` and `__builtin_elementwise_maxnumnum`. - No longer crashing on invalid Objective-C categories and extensions when dumping the AST as JSON. (#GH137320) - Clang itself now uses split stacks instead of threads for allocating more diff --git a/clang/include/clang/Basic/Builtins.td b/clang/include/clang/Basic/Builtins.td index 5ebb82180521d..c81714e9b009d 100644 --- a/clang/include/clang/Basic/Builtins.td +++ b/clang/include/clang/Basic/Builtins.td @@ -1334,6 +1334,18 @@ def ElementwiseMinimum : Builtin { let Prototype = "void(...)"; } +def ElementwiseMaximumNum : Builtin { + let Spellings = ["__builtin_elementwise_maximumnum"]; + let Attributes = [NoThrow, Const, CustomTypeChecking]; + let Prototype = "void(...)"; +} + +def ElementwiseMinimumNum : Builtin { + let Spellings = ["__builtin_elementwise_minimumnum"]; + let Attributes = [NoThrow, Const, CustomTypeChecking]; + let Prototype = "void(...)"; +} + def ElementwiseCeil : Builtin { let Spellings = ["__builtin_elementwise_ceil"]; let Attributes = [NoThrow, Const, CustomTypeChecking]; diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index 5f2eb76e7bacb..3f784fc8e798f 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -4108,6 +4108,22 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, return RValue::get(Result); } + case Builtin::BI__builtin_elementwise_maximumnum: { + Value *Op0 = EmitScalarExpr(E->getArg(0)); + Value *Op1 = EmitScalarExpr(E->getArg(1)); + Value *Result = Builder.CreateBinaryIntrinsic( + Intrinsic::maximumnum, Op0, Op1, nullptr, "elt.maximumnum"); + return RValue::get(Result); + } + + case Builtin::BI__builtin_elementwise_minimumnum: { + Value *Op0 = EmitScalarExpr(E->getArg(0)); + Value *Op1 = EmitScalarExpr(E->getArg(1)); + Value *Result = Builder.CreateBinaryIntrinsic( + Intrinsic::minimumnum, Op0, Op1, nullptr, "elt.minimumnum"); + return RValue::get(Result); + } + case Builtin::BI__builtin_reduce_max: { auto GetIntrinsicID = [this](QualType QT) { if (auto *VecTy = QT->getAs<VectorType>()) diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp index 5e523fe887318..c74b67106ad74 100644 --- a/clang/lib/Sema/SemaChecking.cpp +++ b/clang/lib/Sema/SemaChecking.cpp @@ -3013,6 +3013,8 @@ Sema::CheckBuiltinFunctionCall(FunctionDecl *FDecl, unsigned BuiltinID, case Builtin::BI__builtin_elementwise_maxnum: case Builtin::BI__builtin_elementwise_minimum: case Builtin::BI__builtin_elementwise_maximum: + case Builtin::BI__builtin_elementwise_minimumnum: + case Builtin::BI__builtin_elementwise_maximumnum: case Builtin::BI__builtin_elementwise_atan2: case Builtin::BI__builtin_elementwise_fmod: case Builtin::BI__builtin_elementwise_pow: diff --git a/clang/test/CodeGen/builtin-maximumnum-minimumnum.c b/clang/test/CodeGen/builtin-maximumnum-minimumnum.c new file mode 100644 index 0000000000000..ea9d2e7a4ed38 --- /dev/null +++ b/clang/test/CodeGen/builtin-maximumnum-minimumnum.c @@ -0,0 +1,171 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5 +// RUN: %clang_cc1 -x c++ -std=c++20 -disable-llvm-passes -O3 -triple x86_64 %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK + +typedef _Float16 half8 __attribute__((ext_vector_type(8))); +typedef __bf16 bf16x8 __attribute__((ext_vector_type(8))); +typedef float float4 __attribute__((ext_vector_type(4))); +typedef double double2 __attribute__((ext_vector_type(2))); +typedef long double ldouble2 __attribute__((ext_vector_type(2))); + +// CHECK-LABEL: define dso_local noundef <8 x half> @_Z7pfmin16Dv8_DF16_S_( +// CHECK-SAME: <8 x half> noundef [[A:%.*]], <8 x half> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x half>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x half>, align 16 +// CHECK-NEXT: store <8 x half> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2:![0-9]+]] +// CHECK-NEXT: store <8 x half> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <8 x half>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <8 x half> @llvm.minimumnum.v8f16(<8 x half> [[TMP0]], <8 x half> [[TMP1]]) +// CHECK-NEXT: ret <8 x half> [[ELT_MINIMUMNUM]] +// +half8 pfmin16(half8 a, half8 b) { + return __builtin_elementwise_minimumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <8 x bfloat> @_Z8pfmin16bDv8_DF16bS_( +// CHECK-SAME: <8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16 +// CHECK-NEXT: store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat> [[TMP0]], <8 x bfloat> [[TMP1]]) +// CHECK-NEXT: ret <8 x bfloat> [[ELT_MINIMUMNUM]] +// +bf16x8 pfmin16b(bf16x8 a, bf16x8 b) { + return __builtin_elementwise_minimumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <4 x float> @_Z7pfmin32Dv4_fS_( +// CHECK-SAME: <4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <4 x float>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <4 x float>, align 16 +// CHECK-NEXT: store <4 x float> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <4 x float> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> [[TMP0]], <4 x float> [[TMP1]]) +// CHECK-NEXT: ret <4 x float> [[ELT_MINIMUMNUM]] +// +float4 pfmin32(float4 a, float4 b) { + return __builtin_elementwise_minimumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <2 x double> @_Z7pfmin64Dv2_dS_( +// CHECK-SAME: <2 x double> noundef [[A:%.*]], <2 x double> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x double>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x double>, align 16 +// CHECK-NEXT: store <2 x double> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x double> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> [[TMP0]], <2 x double> [[TMP1]]) +// CHECK-NEXT: ret <2 x double> [[ELT_MINIMUMNUM]] +// +double2 pfmin64(double2 a, double2 b) { + return __builtin_elementwise_minimumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <2 x x86_fp80> @_Z7pfmin80Dv2_eS_( +// CHECK-SAME: ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP0:%.*]], ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP1:%.*]]) #[[ATTR2:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32 +// CHECK-NEXT: [[A:%.*]] = load <2 x x86_fp80>, ptr [[TMP0]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[B:%.*]] = load <2 x x86_fp80>, ptr [[TMP1]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x x86_fp80> [[A]], ptr [[A_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x x86_fp80> [[B]], ptr [[B_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP2:%.*]] = load <2 x x86_fp80>, ptr [[A_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP3:%.*]] = load <2 x x86_fp80>, ptr [[B_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <2 x x86_fp80> @llvm.minimumnum.v2f80(<2 x x86_fp80> [[TMP2]], <2 x x86_fp80> [[TMP3]]) +// CHECK-NEXT: ret <2 x x86_fp80> [[ELT_MINIMUMNUM]] +// +ldouble2 pfmin80(ldouble2 a, ldouble2 b) { + return __builtin_elementwise_minimumnum(a, b); +} + +// CHECK-LABEL: define dso_local noundef <8 x half> @_Z7pfmax16Dv8_DF16_S_( +// CHECK-SAME: <8 x half> noundef [[A:%.*]], <8 x half> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x half>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x half>, align 16 +// CHECK-NEXT: store <8 x half> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <8 x half> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <8 x half>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <8 x half>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MAXIMUMNUM:%.*]] = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> [[TMP0]], <8 x half> [[TMP1]]) +// CHECK-NEXT: ret <8 x half> [[ELT_MAXIMUMNUM]] +// +half8 pfmax16(half8 a, half8 b) { + return __builtin_elementwise_maximumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <8 x bfloat> @_Z8pfmax16bDv8_DF16bS_( +// CHECK-SAME: <8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16 +// CHECK-NEXT: store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MAXIMUMNUM:%.*]] = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> [[TMP0]], <8 x bfloat> [[TMP1]]) +// CHECK-NEXT: ret <8 x bfloat> [[ELT_MAXIMUMNUM]] +// +bf16x8 pfmax16b(bf16x8 a, bf16x8 b) { + return __builtin_elementwise_maximumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <4 x float> @_Z7pfmax32Dv4_fS_( +// CHECK-SAME: <4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <4 x float>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <4 x float>, align 16 +// CHECK-NEXT: store <4 x float> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <4 x float> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <4 x float>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MAXIMUMNUM:%.*]] = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> [[TMP0]], <4 x float> [[TMP1]]) +// CHECK-NEXT: ret <4 x float> [[ELT_MAXIMUMNUM]] +// +float4 pfmax32(float4 a, float4 b) { + return __builtin_elementwise_maximumnum(a, b); +} +// CHECK-LABEL: define dso_local noundef <2 x double> @_Z7pfmax64Dv2_dS_( +// CHECK-SAME: <2 x double> noundef [[A:%.*]], <2 x double> noundef [[B:%.*]]) #[[ATTR0]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x double>, align 16 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x double>, align 16 +// CHECK-NEXT: store <2 x double> [[A]], ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x double> [[B]], ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP0:%.*]] = load <2 x double>, ptr [[A_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP1:%.*]] = load <2 x double>, ptr [[B_ADDR]], align 16, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MAXIMUMNUM:%.*]] = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> [[TMP0]], <2 x double> [[TMP1]]) +// CHECK-NEXT: ret <2 x double> [[ELT_MAXIMUMNUM]] +// +double2 pfmax64(double2 a, double2 b) { + return __builtin_elementwise_maximumnum(a, b); +} + +// CHECK-LABEL: define dso_local noundef <2 x x86_fp80> @_Z7pfmax80Dv2_eS_( +// CHECK-SAME: ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP0:%.*]], ptr noundef byval(<2 x x86_fp80>) align 32 [[TMP1:%.*]]) #[[ATTR2]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[A_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32 +// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <2 x x86_fp80>, align 32 +// CHECK-NEXT: [[A:%.*]] = load <2 x x86_fp80>, ptr [[TMP0]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[B:%.*]] = load <2 x x86_fp80>, ptr [[TMP1]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x x86_fp80> [[A]], ptr [[A_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: store <2 x x86_fp80> [[B]], ptr [[B_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP2:%.*]] = load <2 x x86_fp80>, ptr [[A_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[TMP3:%.*]] = load <2 x x86_fp80>, ptr [[B_ADDR]], align 32, !tbaa [[TBAA2]] +// CHECK-NEXT: [[ELT_MINIMUMNUM:%.*]] = call <2 x x86_fp80> @llvm.minimumnum.v2f80(<2 x x86_fp80> [[TMP2]], <2 x x86_fp80> [[TMP3]]) +// CHECK-NEXT: ret <2 x x86_fp80> [[ELT_MINIMUMNUM]] +// +ldouble2 pfmax80(ldouble2 a, ldouble2 b) { + return __builtin_elementwise_minimumnum(a, b); +} + +//. +// CHECK: [[TBAA2]] = !{[[META3:![0-9]+]], [[META3]], i64 0} +// CHECK: [[META3]] = !{!"omnipotent char", [[META4:![0-9]+]], i64 0} +// CHECK: [[META4]] = !{!"Simple C++ TBAA"} +//. diff --git a/clang/test/Sema/builtins-elementwise-math.c b/clang/test/Sema/builtins-elementwise-math.c index 01057b3f8d083..8548d3be8c44a 100644 --- a/clang/test/Sema/builtins-elementwise-math.c +++ b/clang/test/Sema/builtins-elementwise-math.c @@ -386,6 +386,96 @@ void test_builtin_elementwise_minimum(int i, short s, float f, double d, float4 // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was '_Complex float')}} } +void test_builtin_elementwise_maximumnum(int i, short s, float f, double d, float4 fv, double4 dv, int3 iv, unsigned3 uv, int *p) { + i = __builtin_elementwise_maximumnum(p, d); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int *')}} + + struct Foo foo = __builtin_elementwise_maximumnum(d, d); + // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'double'}} + + i = __builtin_elementwise_maximumnum(i); + // expected-error@-1 {{too few arguments to function call, expected 2, have 1}} + + i = __builtin_elementwise_maximumnum(); + // expected-error@-1 {{too few arguments to function call, expected 2, have 0}} + + i = __builtin_elementwise_maximumnum(i, i, i); + // expected-error@-1 {{too many arguments to function call, expected 2, have 3}} + + i = __builtin_elementwise_maximumnum(fv, 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_maximumnum(uv, iv); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'unsigned3' (vector of 3 'unsigned int' values))}} + + dv = __builtin_elementwise_maximumnum(fv, dv); + // expected-error@-1 {{arguments are of different types ('float4' (vector of 4 'float' values) vs 'double4' (vector of 4 'double' values))}} + + d = __builtin_elementwise_maximumnum(f, d); + // expected-error@-1 {{arguments are of different types ('float' vs 'double')}} + + fv = __builtin_elementwise_maximumnum(fv, fv); + + i = __builtin_elementwise_maximumnum(iv, iv); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int3' (vector of 3 'int' values))}} + + i = __builtin_elementwise_maximumnum(i, i); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int')}} + + int A[10]; + A = __builtin_elementwise_maximumnum(A, A); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int *')}} + + _Complex float c1, c2; + c1 = __builtin_elementwise_maximumnum(c1, c2); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was '_Complex float')}} +} + +void test_builtin_elementwise_minimumnum(int i, short s, float f, double d, float4 fv, double4 dv, int3 iv, unsigned3 uv, int *p) { + i = __builtin_elementwise_minimumnum(p, d); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int *')}} + + struct Foo foo = __builtin_elementwise_minimumnum(d, d); + // expected-error@-1 {{initializing 'struct Foo' with an expression of incompatible type 'double'}} + + i = __builtin_elementwise_minimumnum(i); + // expected-error@-1 {{too few arguments to function call, expected 2, have 1}} + + i = __builtin_elementwise_minimumnum(); + // expected-error@-1 {{too few arguments to function call, expected 2, have 0}} + + i = __builtin_elementwise_minimumnum(i, i, i); + // expected-error@-1 {{too many arguments to function call, expected 2, have 3}} + + i = __builtin_elementwise_minimumnum(fv, 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_minimumnum(uv, iv); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'unsigned3' (vector of 3 'unsigned int' values))}} + + dv = __builtin_elementwise_minimumnum(fv, dv); + // expected-error@-1 {{arguments are of different types ('float4' (vector of 4 'float' values) vs 'double4' (vector of 4 'double' values))}} + + d = __builtin_elementwise_minimumnum(f, d); + // expected-error@-1 {{arguments are of different types ('float' vs 'double')}} + + fv = __builtin_elementwise_minimumnum(fv, fv); + + i = __builtin_elementwise_minimumnum(iv, iv); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int3' (vector of 3 'int' values))}} + + i = __builtin_elementwise_minimumnum(i, i); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int')}} + + int A[10]; + A = __builtin_elementwise_minimumnum(A, A); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (was 'int *')}} + + _Complex float c1, c2; + c1 = __builtin_elementwise_minimumnum(c1, c2); + // expected-error@-1 {{1st argument must be a scalar or vector of floating-point types (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); _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
