llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-llvm-ir @llvm/pr-subscribers-backend-risc-v Author: YunQiang Su (wzssyqa) <details> <summary>Changes</summary> Currently, RISC-V claims that it has VP_FMAXNUM and VP_FMINNUM, it is not correct, which should be VP_FMAXIMUMNUM and VP_FMINIMUMNUM. --- Patch is 41.70 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/181084.diff 16 Files Affected: - (modified) clang/docs/LanguageExtensions.rst (+2-10) - (modified) clang/docs/ReleaseNotes.rst (+3) - (modified) clang/lib/CodeGen/CGBuiltin.cpp (+14-18) - (modified) clang/test/CodeGen/builtins-elementwise-math.c (+2-68) - (modified) clang/test/CodeGen/strictfp-elementwise-builtins.cpp (+12-12) - (modified) clang/test/CodeGenHLSL/builtins/max-overloads.hlsl (+1-34) - (modified) clang/test/CodeGenHLSL/builtins/max.hlsl (+1-48) - (modified) clang/test/CodeGenHLSL/builtins/min-overloads.hlsl (+1-34) - (modified) clang/test/CodeGenHLSL/builtins/min.hlsl (+1-51) - (modified) clang/test/SemaHLSL/BuiltIns/vec-scalar-compat-overload-warnings.hlsl (-20) - (modified) llvm/docs/LangRef.rst (+100) - (modified) llvm/include/llvm/IR/Intrinsics.td (+10) - (modified) llvm/include/llvm/IR/VPIntrinsics.def (+14) - (modified) llvm/lib/CodeGen/ExpandVectorPredication.cpp (+2) - (modified) llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp (+2) - (modified) llvm/lib/Target/RISCV/RISCVISelLowering.cpp (+7-7) ``````````diff diff --git a/clang/docs/LanguageExtensions.rst b/clang/docs/LanguageExtensions.rst index 29328355c3e6f..745000e79027c 100644 --- a/clang/docs/LanguageExtensions.rst +++ b/clang/docs/LanguageExtensions.rst @@ -839,16 +839,8 @@ of different sizes and signs is forbidden in binary and ternary builtins. T __builtin_elementwise_copysign(T x, T y) return the magnitude of x with the sign of y. floating point types T __builtin_elementwise_fmod(T x, T y) return the floating-point remainder of (x/y) whose sign floating point types matches the sign of x. - T __builtin_elementwise_max(T x, T y) return x or y, whichever is larger integer and floating point types - For floating point types, follows semantics of maxNum - in IEEE 754-2008. See `LangRef - <http://llvm.org/docs/LangRef.html#i-fminmax-family>`_ - for the comparison. - T __builtin_elementwise_min(T x, T y) return x or y, whichever is smaller integer and floating point types - For floating point types, follows semantics of minNum - in IEEE 754-2008. See `LangRef - <http://llvm.org/docs/LangRef.html#i-fminmax-family>`_ - for the comparison. + T __builtin_elementwise_max(T x, T y) return x or y, whichever is larger integer types + T __builtin_elementwise_min(T x, T y) return x or y, whichever is smaller integer types T __builtin_elementwise_maxnum(T x, T y) return x or y, whichever is larger. Follows IEEE 754-2008 floating point types semantics (maxNum) with +0.0>-0.0. See `LangRef <http://llvm.org/docs/LangRef.html#i-fminmax-family>`_ diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst index 0dbea8efc2642..758982d6e6431 100644 --- a/clang/docs/ReleaseNotes.rst +++ b/clang/docs/ReleaseNotes.rst @@ -138,6 +138,9 @@ Non-comprehensive list of changes in this release Usable in constant expressions. Implicit conversion is supported for class/struct types with conversion operators. +- Removed float types support from ``__builtin_elementwise_max`` and + ``__builtin_elementwise_min``. + New Compiler Flags ------------------ - New option ``-fms-anonymous-structs`` / ``-fno-ms-anonymous-structs`` added diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index cf686581240a5..3daf08771c7a0 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -4066,30 +4066,26 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID, Value *Op0 = EmitScalarExpr(E->getArg(0)); Value *Op1 = EmitScalarExpr(E->getArg(1)); Value *Result; - if (Op0->getType()->isIntOrIntVectorTy()) { - QualType Ty = E->getArg(0)->getType(); - if (auto *VecTy = Ty->getAs<VectorType>()) - Ty = VecTy->getElementType(); - Result = Builder.CreateBinaryIntrinsic( - Ty->isSignedIntegerType() ? Intrinsic::smax : Intrinsic::umax, Op0, - Op1, nullptr, "elt.max"); - } else - Result = Builder.CreateMaxNum(Op0, Op1, /*FMFSource=*/nullptr, "elt.max"); + assert(Op0->getType()->isIntOrIntVectorTy()); + QualType Ty = E->getArg(0)->getType(); + if (auto *VecTy = Ty->getAs<VectorType>()) + Ty = VecTy->getElementType(); + Result = Builder.CreateBinaryIntrinsic( + Ty->isSignedIntegerType() ? Intrinsic::smax : Intrinsic::umax, Op0, Op1, + nullptr, "elt.max"); return RValue::get(Result); } case Builtin::BI__builtin_elementwise_min: { Value *Op0 = EmitScalarExpr(E->getArg(0)); Value *Op1 = EmitScalarExpr(E->getArg(1)); Value *Result; - if (Op0->getType()->isIntOrIntVectorTy()) { - QualType Ty = E->getArg(0)->getType(); - if (auto *VecTy = Ty->getAs<VectorType>()) - Ty = VecTy->getElementType(); - Result = Builder.CreateBinaryIntrinsic( - Ty->isSignedIntegerType() ? Intrinsic::smin : Intrinsic::umin, Op0, - Op1, nullptr, "elt.min"); - } else - Result = Builder.CreateMinNum(Op0, Op1, /*FMFSource=*/nullptr, "elt.min"); + assert(Op0->getType()->isIntOrIntVectorTy()); + QualType Ty = E->getArg(0)->getType(); + if (auto *VecTy = Ty->getAs<VectorType>()) + Ty = VecTy->getElementType(); + Result = Builder.CreateBinaryIntrinsic( + Ty->isSignedIntegerType() ? Intrinsic::smin : Intrinsic::umin, Op0, Op1, + nullptr, "elt.min"); return RValue::get(Result); } diff --git a/clang/test/CodeGen/builtins-elementwise-math.c b/clang/test/CodeGen/builtins-elementwise-math.c index 2df485f0155c3..a201403e8b6b1 100644 --- a/clang/test/CodeGen/builtins-elementwise-math.c +++ b/clang/test/CodeGen/builtins-elementwise-math.c @@ -339,32 +339,10 @@ void test_builtin_elementwise_minimum(float f1, float f2, double d1, double d2, 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, +void test_builtin_elementwise_max(long long int i2, si8 vi1, si8 vi2, long long int i1, 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_max( - // CHECK: [[F1:%.+]] = load float, ptr %f1.addr, align 4 - // CHECK-NEXT: [[F2:%.+]] = load float, ptr %f2.addr, align 4 - // CHECK-NEXT: call float @llvm.maxnum.f32(float [[F1]], float [[F2]]) - f1 = __builtin_elementwise_max(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.maxnum.f64(double [[D1]], double [[D2]]) - d1 = __builtin_elementwise_max(d1, d2); - - // CHECK: [[D2:%.+]] = load double, ptr %d2.addr, align 8 - // CHECK-NEXT: call double @llvm.maxnum.f64(double 2.000000e+01, double [[D2]]) - d1 = __builtin_elementwise_max(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.maxnum.v4f32(<4 x float> [[VF1]], <4 x float> [[VF2]]) - vf1 = __builtin_elementwise_max(vf1, vf2); - // CHECK: [[I1:%.+]] = load i64, ptr %i1.addr, align 8 // CHECK-NEXT: [[I2:%.+]] = load i64, ptr %i2.addr, align 8 // CHECK-NEXT: call i64 @llvm.smax.i64(i64 [[I1]], i64 [[I2]]) @@ -403,17 +381,6 @@ void test_builtin_elementwise_max(float f1, float f2, double d1, double d2, // CHECK-NEXT: call i55 @llvm.umax.i55(i55 [[LOADEDV2]], i55 [[LOADEDV3]]) bu1 = __builtin_elementwise_max(bu1, bu2); - // 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.maxnum.v4f32(<4 x float> [[CVF1]], <4 x float> [[VF2]]) - const float4 cvf1 = vf1; - vf1 = __builtin_elementwise_max(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.maxnum.v4f32(<4 x float> [[VF2]], <4 x float> [[CVF1]]) - vf1 = __builtin_elementwise_max(vf2, cvf1); - // CHECK: [[IAS1:%.+]] = load i32, ptr addrspace(1) @int_as_one, align 4 // CHECK-NEXT: [[B:%.+]] = load i32, ptr @b, align 4 // CHECK-NEXT: call i32 @llvm.smax.i32(i32 [[IAS1]], i32 [[B]]) @@ -423,32 +390,10 @@ void test_builtin_elementwise_max(float f1, float f2, double d1, double d2, i1 = __builtin_elementwise_max(1, 'a'); } -void test_builtin_elementwise_min(float f1, float f2, double d1, double d2, - float4 vf1, float4 vf2, long long int i1, - long long int i2, si8 vi1, si8 vi2, +void test_builtin_elementwise_min(long long int i2, si8 vi1, si8 vi2, long long int i1, 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_min( - // CHECK: [[F1:%.+]] = load float, ptr %f1.addr, align 4 - // CHECK-NEXT: [[F2:%.+]] = load float, ptr %f2.addr, align 4 - // CHECK-NEXT: call float @llvm.minnum.f32(float [[F1]], float [[F2]]) - f1 = __builtin_elementwise_min(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.minnum.f64(double [[D1]], double [[D2]]) - d1 = __builtin_elementwise_min(d1, d2); - - // CHECK: [[D1:%.+]] = load double, ptr %d1.addr, align 8 - // CHECK-NEXT: call double @llvm.minnum.f64(double [[D1]], double 2.000000e+00) - d1 = __builtin_elementwise_min(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.minnum.v4f32(<4 x float> [[VF1]], <4 x float> [[VF2]]) - vf1 = __builtin_elementwise_min(vf1, vf2); - // CHECK: [[I1:%.+]] = load i64, ptr %i1.addr, align 8 // CHECK-NEXT: [[I2:%.+]] = load i64, ptr %i2.addr, align 8 // CHECK-NEXT: call i64 @llvm.smin.i64(i64 [[I1]], i64 [[I2]]) @@ -494,17 +439,6 @@ void test_builtin_elementwise_min(float f1, float f2, double d1, double d2, // CHECK-NEXT: call i55 @llvm.umin.i55(i55 [[LOADEDV2]], i55 [[LOADEDV3]]) bu1 = __builtin_elementwise_min(bu1, bu2); - // 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.minnum.v4f32(<4 x float> [[CVF1]], <4 x float> [[VF2]]) - const float4 cvf1 = vf1; - vf1 = __builtin_elementwise_min(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.minnum.v4f32(<4 x float> [[VF2]], <4 x float> [[CVF1]]) - vf1 = __builtin_elementwise_min(vf2, cvf1); - // CHECK: [[IAS1:%.+]] = load i32, ptr addrspace(1) @int_as_one, align 4 // CHECK-NEXT: [[B:%.+]] = load i32, ptr @b, align 4 // CHECK-NEXT: call i32 @llvm.smin.i32(i32 [[IAS1]], i32 [[B]]) diff --git a/clang/test/CodeGen/strictfp-elementwise-builtins.cpp b/clang/test/CodeGen/strictfp-elementwise-builtins.cpp index 6453d50f044aa..7de0a396e08f9 100644 --- a/clang/test/CodeGen/strictfp-elementwise-builtins.cpp +++ b/clang/test/CodeGen/strictfp-elementwise-builtins.cpp @@ -27,24 +27,24 @@ float4 strict_elementwise_abs(float4 a) { return __builtin_elementwise_abs(a); } -// CHECK-LABEL: define dso_local noundef <4 x float> @_Z22strict_elementwise_maxDv4_fS_ -// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR0]] { +// CHECK-LABEL: define dso_local noundef <4 x float> @_Z25strict_elementwise_maxnumDv4_fS_ +// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR2]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[ELT_MAX:%.*]] = tail call <4 x float> @llvm.experimental.constrained.maxnum.v4f32(<4 x float> [[A]], <4 x float> [[B]], metadata !"fpexcept.strict") #[[ATTR4]] -// CHECK-NEXT: ret <4 x float> [[ELT_MAX]] +// CHECK-NEXT: [[ELT_MAXNUM:%.*]] = tail call <4 x float> @llvm.maxnum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]] +// CHECK-NEXT: ret <4 x float> [[ELT_MAXNUM]] // -float4 strict_elementwise_max(float4 a, float4 b) { - return __builtin_elementwise_max(a, b); +float4 strict_elementwise_maxnum(float4 a, float4 b) { + return __builtin_elementwise_maxnum(a, b); } -// CHECK-LABEL: define dso_local noundef <4 x float> @_Z22strict_elementwise_minDv4_fS_ -// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR0]] { +// CHECK-LABEL: define dso_local noundef <4 x float> @_Z25strict_elementwise_minnumDv4_fS_ +// CHECK-SAME: (<4 x float> noundef [[A:%.*]], <4 x float> noundef [[B:%.*]]) local_unnamed_addr #[[ATTR2]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[ELT_MIN:%.*]] = tail call <4 x float> @llvm.experimental.constrained.minnum.v4f32(<4 x float> [[A]], <4 x float> [[B]], metadata !"fpexcept.strict") #[[ATTR4]] -// CHECK-NEXT: ret <4 x float> [[ELT_MIN]] +// CHECK-NEXT: [[ELT_MINNUM:%.*]] = tail call <4 x float> @llvm.minnum.v4f32(<4 x float> [[A]], <4 x float> [[B]]) #[[ATTR4]] +// CHECK-NEXT: ret <4 x float> [[ELT_MINNUM]] // -float4 strict_elementwise_min(float4 a, float4 b) { - return __builtin_elementwise_min(a, b); +float4 strict_elementwise_minnum(float4 a, float4 b) { + return __builtin_elementwise_minnum(a, b); } // CHECK-LABEL: define dso_local noundef <4 x float> @_Z26strict_elementwise_maximumDv4_fS_ diff --git a/clang/test/CodeGenHLSL/builtins/max-overloads.hlsl b/clang/test/CodeGenHLSL/builtins/max-overloads.hlsl index da5cd8ff37510..6a99f2dee6c1f 100644 --- a/clang/test/CodeGenHLSL/builtins/max-overloads.hlsl +++ b/clang/test/CodeGenHLSL/builtins/max-overloads.hlsl @@ -1,7 +1,7 @@ // RUN: %clang_cc1 -std=hlsl202x -finclude-default-header -triple dxil-pc-shadermodel6.3-library %s \ // RUN: -fnative-half-type -fnative-int16-type -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,NATIVE_HALF // RUN: %clang_cc1 -std=hlsl202x -finclude-default-header -triple dxil-pc-shadermodel6.3-library %s \ -// RUN: -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,NO_HALF +// RUN: -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK #ifdef __HLSL_ENABLE_16_BIT // NATIVE_HALF-LABEL: define hidden noundef <4 x i16> {{.*}}test_max_short4_mismatch @@ -46,36 +46,3 @@ int64_t4 test_max_long4_mismatch(int64_t4 p0, int64_t p1) { return max(p0, p1); // CHECK: [[MAX:%.*]] = call noundef <4 x i64> @llvm.umax.v4i64(<4 x i64> %{{.*}}, <4 x i64> [[CONV1]]) // CHECK: ret <4 x i64> [[MAX]] uint64_t4 test_max_ulong4_mismatch(uint64_t4 p0, uint64_t p1) { return max(p0, p1); } - -// NATIVE_HALF-LABEL: define hidden noundef nofpclass(nan inf) <4 x half> {{.*}}test_max_half4_mismatch -// NATIVE_HALF: [[CONV0:%.*]] = insertelement <4 x half> poison, half %{{.*}}, i64 0 -// NATIVE_HALF: [[CONV1:%.*]] = shufflevector <4 x half> [[CONV0]], <4 x half> poison, <4 x i32> zeroinitializer -// NATIVE_HALF: [[MAX:%.*]] = call reassoc nnan ninf nsz arcp afn noundef nofpclass(nan inf) <4 x half> @llvm.maxnum.v4f16(<4 x half> %{{.*}}, <4 x half> [[CONV1]]) -// NATIVE_HALF: ret <4 x half> [[MAX]] -// NO_HALF-LABEL: define hidden noundef nofpclass(nan inf) <4 x float> {{.*}}test_max_half4_mismatch -// NO_HALF: [[CONV0:%.*]] = insertelement <4 x float> poison, float %{{.*}}, i64 0 -// NO_HALF: [[CONV1:%.*]] = shufflevector <4 x float> [[CONV0]], <4 x float> poison, <4 x i32> zeroinitializer -// NO_HALF: [[MAX:%.*]] = call reassoc nnan ninf nsz arcp afn noundef nofpclass(nan inf) <4 x float> @llvm.maxnum.v4f32(<4 x float> %{{.*}}, <4 x float> [[CONV1]]) -// NO_HALF: ret <4 x float> [[MAX]] -half4 test_max_half4_mismatch(half4 p0, half p1) { return max(p0, p1); } - -// CHECK-LABEL: define hidden noundef nofpclass(nan inf) <4 x float> {{.*}}test_max_float4_mismatch -// CHECK: [[CONV0:%.*]] = insertelement <4 x float> poison, float %{{.*}}, i64 0 -// CHECK: [[CONV1:%.*]] = shufflevector <4 x float> [[CONV0]], <4 x float> poison, <4 x i32> zeroinitializer -// CHECK: [[MAX:%.*]] = call reassoc nnan ninf nsz arcp afn noundef nofpclass(nan inf) <4 x float> @llvm.maxnum.v4f32(<4 x float> %{{.*}}, <4 x float> [[CONV1]]) -// CHECK: ret <4 x float> [[MAX]] -float4 test_max_float4_mismatch(float4 p0, float p1) { return max(p0, p1); } - -// CHECK-LABEL: define hidden noundef nofpclass(nan inf) <4 x double> {{.*}}test_max_double4_mismatch -// CHECK: [[CONV0:%.*]] = insertelement <4 x double> poison, double %{{.*}}, i64 0 -// CHECK: [[CONV1:%.*]] = shufflevector <4 x double> [[CONV0]], <4 x double> poison, <4 x i32> zeroinitializer -// CHECK: [[MAX:%.*]] = call reassoc nnan ninf nsz arcp afn noundef nofpclass(nan inf) <4 x double> @llvm.maxnum.v4f64(<4 x double> %{{.*}}, <4 x double> [[CONV1]]) -// CHECK: ret <4 x double> [[MAX]] -double4 test_max_double4_mismatch(double4 p0, double p1) { return max(p0, p1); } - -// CHECK-LABEL: define hidden noundef nofpclass(nan inf) <4 x double> {{.*}}test_max_double4_mismatch2 -// CHECK: [[CONV0:%.*]] = insertelement <4 x double> poison, double %{{.*}}, i64 0 -// CHECK: [[CONV1:%.*]] = shufflevector <4 x double> [[CONV0]], <4 x double> poison, <4 x i32> zeroinitializer -// CHECK: [[MAX:%.*]] = call reassoc nnan ninf nsz arcp afn noundef nofpclass(nan inf) <4 x double> @llvm.maxnum.v4f64(<4 x double> [[CONV1]], <4 x double> %{{.*}}) -// CHECK: ret <4 x double> [[MAX]] -double4 test_max_double4_mismatch2(double4 p0, double p1) { return max(p1, p0); } diff --git a/clang/test/CodeGenHLSL/builtins/max.hlsl b/clang/test/CodeGenHLSL/builtins/max.hlsl index 9c621e62b5336..266859710947f 100644 --- a/clang/test/CodeGenHLSL/builtins/max.hlsl +++ b/clang/test/CodeGenHLSL/builtins/max.hlsl @@ -3,7 +3,7 @@ // RUN: FileCheck %s --check-prefixes=CHECK,NATIVE_HALF // RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.3-library %s \ // RUN: -emit-llvm -disable-llvm-passes -o - | \ -// RUN: FileCheck %s --check-prefixes=CHECK,NO_HALF +// RUN: FileCheck %s --check-prefixes=CHECK #ifdef __HLSL_ENABLE_16_BIT // NATIVE_HALF-LABEL: define hidden noundef i16 @_Z14test_max_short @@ -84,50 +84,3 @@ uint64_t3 test_max_ulong3(uint64_t3 p0, uint64_t3 p1) { return max(p0, p1); } // CHECK-LABEL: define hidden noundef <4 x i64> @_Z15test_max_ulong4 // CHECK: call <4 x i64> @llvm.umax.v4i64 uint64_t4 test_max_ulong4(uint64_t4 p0, uint64_t4 p1) { return max(p0, p1); } - -// NATIVE_HALF-LABEL: define hidden noundef nofpclass(nan inf) half @_Z13test_max_half -// NATIVE_HALF: call reassoc nnan ninf nsz arcp afn half @llvm.maxnum.f16( -// NO_HALF-LABEL: define hidden noundef nofpclass(nan inf) float @_Z13test_max_half -// NO_HALF: call reassoc nnan ninf nsz arcp afn float @llvm.maxnum.f32( -half test_max_half(half p0, half p1) { return max(p0, p1); } -// NATIVE_HALF-LABEL: define hidden noundef nofpclass(nan inf) <2 x half> @_Z14test_max_half2 -// NATIVE_HALF: call reassoc nnan ninf nsz arcp afn <2 x half> @llvm.maxnum.v2f16 -// NO_HALF-LABEL: define hidden noundef nofpclass(nan inf) <2 x float> @_Z14test_max_half2 -// NO_HALF: call reassoc nnan ninf nsz arcp afn <2 x float> @llvm.maxnum.v2f32( -half2 test_max_half2(half2 p0, half2 p1) { return max(p0, p1); } -// NATIVE_HALF-LABEL: define hidden noundef nofpclass(nan inf) <3 x half> @_Z14test_max_half3 -// NATIVE_HALF: call reassoc nnan ninf nsz arcp afn <3 x half> @llvm.maxnum.v3f16 -// NO_HALF-LABEL: define hidden noundef nofpclass(nan inf) <3 x float> @_Z14test_max_half3 -// NO_HALF: call reassoc nnan ninf nsz arcp afn <3 x float> @llvm.maxnum.v3f32( -half3 test_max_half3(half3 p0, half3 p1) { return max(p0, p1); } -// NATIVE_HALF-LABEL: define hidden noundef nofpclass(nan inf) <4 x half> @_Z14test_max_half4 -// NATIVE_HALF: call reassoc nnan ninf nsz arcp afn <4 x half> @llvm.maxnum.v4f16 -// NO_HALF-LABEL: define hidden noundef nofpclass(nan inf) <4 x float> @_Z14test_max_half4 -// NO_HALF: call reassoc nnan ninf nsz arcp afn <4 x float> @llvm.maxnum.v4f32( -half4 test_max_half4(half4 p0, half4 p1) { return max(p0, p1); } - -... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/181084 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
