diff options
Diffstat (limited to 'clang/test')
27 files changed, 775 insertions, 182 deletions
diff --git a/clang/test/AST/ByteCode/builtin-functions.cpp b/clang/test/AST/ByteCode/builtin-functions.cpp index e9093b2..a90f636 100644 --- a/clang/test/AST/ByteCode/builtin-functions.cpp +++ b/clang/test/AST/ByteCode/builtin-functions.cpp @@ -1856,7 +1856,8 @@ namespace InitParam { #endif -namespace SAddOverflowInt { +namespace NonBlockPointerStore { int a; void foo(void) { a *= __builtin_sadd_overflow(1, 2, 0); } + void foo2(void) { a *= __builtin_addc(1, 2, 0, 0); } } diff --git a/clang/test/AST/ByteCode/cxx20.cpp b/clang/test/AST/ByteCode/cxx20.cpp index 1888998..cb788fa 100644 --- a/clang/test/AST/ByteCode/cxx20.cpp +++ b/clang/test/AST/ByteCode/cxx20.cpp @@ -1183,3 +1183,21 @@ namespace VirtualFunctionCallThroughArrayElem { static_assert(a[2][3].foo()); // both-error {{not an integral constant expression}} \ // both-note {{virtual function called on object 'a[2][3]' whose dynamic type is not constant}} } + +namespace NonPureVirtualCall { + struct A { + constexpr virtual void call(int) = 0; + constexpr void call2() { call(0); } + }; + + struct B : A { + constexpr void call(int) override {} + }; + + consteval void check() { + B b; + b.call2(); + } + + int main() { check(); } +} diff --git a/clang/test/CIR/CodeGen/try-catch.cpp b/clang/test/CIR/CodeGen/try-catch.cpp index 1e4d2a6..27e3d8e 100644 --- a/clang/test/CIR/CodeGen/try-catch.cpp +++ b/clang/test/CIR/CodeGen/try-catch.cpp @@ -164,3 +164,33 @@ void try_catch_with_alloca() { // OGCG: %[[TMP_B:.*]] = load i32, ptr %[[B_ADDR]], align 4 // OGCG: %[[RESULT:.*]] = add nsw i32 %[[TMP_A]], %[[TMP_B]] // OGCG: store i32 %[[RESULT]], ptr %[[C_ADDR]], align 4 + +void function_with_noexcept() noexcept; + +void calling_noexcept_function_inside_try_block() { + try { + function_with_noexcept(); + } catch (...) { + } +} + +// CIR: cir.scope { +// CIR: cir.try { +// CIR: cir.call @_Z22function_with_noexceptv() nothrow : () -> () +// CIR: cir.yield +// CIR: } +// CIR: } + +// LLVM: br label %[[LABEL_1:.*]] +// LLVM: [[LABEL_1]]: +// LLVM: br label %[[LABEL_2:.*]] +// LLVM: [[LABEL_2]]: +// LLVM: call void @_Z22function_with_noexceptv() +// LLVM: br label %[[LABEL_3:.*]] +// LLVM: [[LABEL_3]]: +// LLVM: br label %[[LABEL_4:.*]] +// LLVM: [[LABEL_4]]: +// LLVM: ret void + +// OGCG: call void @_Z22function_with_noexceptv() +// OGCG: ret void diff --git a/clang/test/CodeGen/AArch64/ext-vector-coercion.c b/clang/test/CodeGen/AArch64/ext-vector-coercion.c new file mode 100644 index 0000000..354980a --- /dev/null +++ b/clang/test/CodeGen/AArch64/ext-vector-coercion.c @@ -0,0 +1,42 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6 +// RUN: %clang_cc1 -fenable-matrix -triple arm64-apple-macosx %s -emit-llvm -disable-llvm-passes -o - | FileCheck %s + +typedef float float3 __attribute__((ext_vector_type(3))); +struct Vec3 { + union { + struct { + float x; + float y; + float z; + }; + float vec __attribute__((ext_vector_type(3))); + }; +}; + +// CHECK-LABEL: define i128 @add( +// CHECK-SAME: i128 [[A_COERCE:%.*]]) #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: [[ENTRY:.*:]] +// CHECK-NEXT: [[RETVAL:%.*]] = alloca [[STRUCT_VEC3:%.*]], align 16 +// CHECK-NEXT: [[A:%.*]] = alloca [[STRUCT_VEC3]], align 16 +// CHECK-NEXT: [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0 +// CHECK-NEXT: store i128 [[A_COERCE]], ptr [[COERCE_DIVE]], align 16 +// CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0 +// CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x float>, ptr [[TMP0]], align 16 +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <4 x float> [[LOADVECN]], <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2> +// CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0 +// CHECK-NEXT: [[LOADVECN1:%.*]] = load <4 x float>, ptr [[TMP1]], align 16 +// CHECK-NEXT: [[EXTRACTVEC2:%.*]] = shufflevector <4 x float> [[LOADVECN1]], <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2> +// CHECK-NEXT: [[ADD:%.*]] = fadd <3 x float> [[EXTRACTVEC]], [[EXTRACTVEC2]] +// CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[RETVAL]], i32 0, i32 0 +// CHECK-NEXT: [[EXTRACTVEC3:%.*]] = shufflevector <3 x float> [[ADD]], <3 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> +// CHECK-NEXT: store <4 x float> [[EXTRACTVEC3]], ptr [[TMP2]], align 16 +// CHECK-NEXT: [[COERCE_DIVE4:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[RETVAL]], i32 0, i32 0 +// CHECK-NEXT: [[TMP3:%.*]] = load i128, ptr [[COERCE_DIVE4]], align 16 +// CHECK-NEXT: ret i128 [[TMP3]] +// +struct Vec3 add(struct Vec3 a) { + struct Vec3 res; + res.vec = a.vec + a.vec; + return res; +} + diff --git a/clang/test/CodeGen/AArch64/neon-across.c b/clang/test/CodeGen/AArch64/neon-across.c index d365975..aae5097 100644 --- a/clang/test/CodeGen/AArch64/neon-across.c +++ b/clang/test/CodeGen/AArch64/neon-across.c @@ -49,7 +49,7 @@ uint32_t test_vaddlv_u16(uint16x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_s8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1:[0-9]+]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v16i8(<16 x i8> [[A]]) // CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16 @@ -60,7 +60,7 @@ int16_t test_vaddlvq_s8(int8x16_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_s16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v8i16(<8 x i16> [[A]]) // CHECK-NEXT: ret i32 [[VADDLV_I]] @@ -70,7 +70,7 @@ int32_t test_vaddlvq_s16(int16x8_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_s32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLVQ_S32_I:%.*]] = call i64 @llvm.aarch64.neon.saddlv.i64.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i64 [[VADDLVQ_S32_I]] @@ -80,7 +80,7 @@ int64_t test_vaddlvq_s32(int32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_u8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v16i8(<16 x i8> [[A]]) // CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16 @@ -91,7 +91,7 @@ uint16_t test_vaddlvq_u8(uint8x16_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_u16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v8i16(<8 x i16> [[A]]) // CHECK-NEXT: ret i32 [[VADDLV_I]] @@ -101,7 +101,7 @@ uint32_t test_vaddlvq_u16(uint16x8_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddlvq_u32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VADDLVQ_U32_I:%.*]] = call i64 @llvm.aarch64.neon.uaddlv.i64.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i64 [[VADDLVQ_U32_I]] @@ -113,9 +113,8 @@ uint64_t test_vaddlvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXV_S8_I:%.*]] = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXV_S8_I]] // int8_t test_vmaxv_s8(int8x8_t a) { return vmaxv_s8(a); @@ -124,9 +123,8 @@ int8_t test_vmaxv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXV_S16_I:%.*]] = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXV_S16_I]] // int16_t test_vmaxv_s16(int16x4_t a) { return vmaxv_s16(a); @@ -135,9 +133,8 @@ int16_t test_vmaxv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXV_U8_I:%.*]] = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXV_U8_I]] // uint8_t test_vmaxv_u8(uint8x8_t a) { return vmaxv_u8(a); @@ -146,40 +143,37 @@ uint8_t test_vmaxv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vmaxv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXV_U16_I:%.*]] = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXV_U16_I]] // uint16_t test_vmaxv_u16(uint16x4_t a) { return vmaxv_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXVQ_S8_I]] // int8_t test_vmaxvq_s8(int8x16_t a) { return vmaxvq_s8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXVQ_S16_I]] // int16_t test_vmaxvq_s16(int16x8_t a) { return vmaxvq_s16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_s32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMAXVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXVQ_S32_I]] // int32_t test_vmaxvq_s32(int32x4_t a) { @@ -187,31 +181,29 @@ int32_t test_vmaxvq_s32(int32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMAXVQ_U8_I]] // uint8_t test_vmaxvq_u8(uint8x16_t a) { return vmaxvq_u8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMAXVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMAXVQ_U16_I]] // uint16_t test_vmaxvq_u16(uint16x8_t a) { return vmaxvq_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_u32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMAXVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMAXVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXVQ_U32_I]] // uint32_t test_vmaxvq_u32(uint32x4_t a) { @@ -221,9 +213,8 @@ uint32_t test_vmaxvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINV_S8_I:%.*]] = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINV_S8_I]] // int8_t test_vminv_s8(int8x8_t a) { return vminv_s8(a); @@ -232,9 +223,8 @@ int8_t test_vminv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINV_S16_I:%.*]] = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINV_S16_I]] // int16_t test_vminv_s16(int16x4_t a) { return vminv_s16(a); @@ -243,9 +233,8 @@ int16_t test_vminv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINV_U8_I:%.*]] = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINV_U8_I]] // uint8_t test_vminv_u8(uint8x8_t a) { return vminv_u8(a); @@ -254,40 +243,37 @@ uint8_t test_vminv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vminv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINV_U16_I:%.*]] = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINV_U16_I]] // uint16_t test_vminv_u16(uint16x4_t a) { return vminv_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINVQ_S8_I]] // int8_t test_vminvq_s8(int8x16_t a) { return vminvq_s8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINVQ_S16_I]] // int16_t test_vminvq_s16(int16x8_t a) { return vminvq_s16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_s32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMINVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINVQ_S32_I]] // int32_t test_vminvq_s32(int32x4_t a) { @@ -295,31 +281,29 @@ int32_t test_vminvq_s32(int32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VMINVQ_U8_I]] // uint8_t test_vminvq_u8(uint8x16_t a) { return vminvq_u8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VMINVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VMINVQ_U16_I]] // uint16_t test_vminvq_u16(uint16x8_t a) { return vminvq_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_u32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VMINVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VMINVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINVQ_U32_I]] // uint32_t test_vminvq_u32(uint32x4_t a) { @@ -329,9 +313,8 @@ uint32_t test_vminvq_u32(uint32x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_s8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDV_S8_I:%.*]] = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDV_S8_I]] // int8_t test_vaddv_s8(int8x8_t a) { return vaddv_s8(a); @@ -340,9 +323,8 @@ int8_t test_vaddv_s8(int8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_s16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDV_S16_I:%.*]] = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDV_S16_I]] // int16_t test_vaddv_s16(int16x4_t a) { return vaddv_s16(a); @@ -351,9 +333,8 @@ int16_t test_vaddv_s16(int16x4_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_u8 // CHECK-SAME: (<8 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i8(<8 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDV_U8_I:%.*]] = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDV_U8_I]] // uint8_t test_vaddv_u8(uint8x8_t a) { return vaddv_u8(a); @@ -362,40 +343,37 @@ uint8_t test_vaddv_u8(uint8x8_t a) { // CHECK-LABEL: define {{[^@]+}}@test_vaddv_u16 // CHECK-SAME: (<4 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i16(<4 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDV_U16_I:%.*]] = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDV_U16_I]] // uint16_t test_vaddv_u16(uint16x4_t a) { return vaddv_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_S8_I:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDVQ_S8_I]] // int8_t test_vaddvq_s8(int8x16_t a) { return vaddvq_s8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_S16_I:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDVQ_S16_I]] // int16_t test_vaddvq_s16(int16x8_t a) { return vaddvq_s16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_s32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VADDVQ_S32_I:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDVQ_S32_I]] // int32_t test_vaddvq_s32(int32x4_t a) { @@ -403,31 +381,29 @@ int32_t test_vaddvq_s32(int32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u8 -// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<16 x i8> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v16i8(<16 x i8> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8 -// CHECK-NEXT: ret i8 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_U8_I:%.*]] = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> [[A]]) +// CHECK-NEXT: ret i8 [[VADDVQ_U8_I]] // uint8_t test_vaddvq_u8(uint8x16_t a) { return vaddvq_u8(a); } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u16 -// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<8 x i16> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i16(<8 x i16> [[A]]) -// CHECK-NEXT: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i16 -// CHECK-NEXT: ret i16 [[TMP0]] +// CHECK-NEXT: [[VADDVQ_U16_I:%.*]] = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> [[A]]) +// CHECK-NEXT: ret i16 [[VADDVQ_U16_I]] // uint16_t test_vaddvq_u16(uint16x8_t a) { return vaddvq_u16(a); } // CHECK-LABEL: define {{[^@]+}}@test_vaddvq_u32 -// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: -// CHECK-NEXT: [[VADDVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i32(<4 x i32> [[A]]) +// CHECK-NEXT: [[VADDVQ_U32_I:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDVQ_U32_I]] // uint32_t test_vaddvq_u32(uint32x4_t a) { @@ -435,7 +411,7 @@ uint32_t test_vaddvq_u32(uint32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vmaxvq_f32 -// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VMAXVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fmaxv.f32.v4f32(<4 x float> [[A]]) // CHECK-NEXT: ret float [[VMAXVQ_F32_I]] @@ -445,7 +421,7 @@ float32_t test_vmaxvq_f32(float32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vminvq_f32 -// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VMINVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fminv.f32.v4f32(<4 x float> [[A]]) // CHECK-NEXT: ret float [[VMINVQ_F32_I]] @@ -455,7 +431,7 @@ float32_t test_vminvq_f32(float32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vmaxnmvq_f32 -// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VMAXNMVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fmaxnmv.f32.v4f32(<4 x float> [[A]]) // CHECK-NEXT: ret float [[VMAXNMVQ_F32_I]] @@ -465,7 +441,7 @@ float32_t test_vmaxnmvq_f32(float32x4_t a) { } // CHECK-LABEL: define {{[^@]+}}@test_vminnmvq_f32 -// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR1]] { +// CHECK-SAME: (<4 x float> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: entry: // CHECK-NEXT: [[VMINNMVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fminnmv.f32.v4f32(<4 x float> [[A]]) // CHECK-NEXT: ret float [[VMINNMVQ_F32_I]] diff --git a/clang/test/CodeGen/AArch64/neon-intrinsics.c b/clang/test/CodeGen/AArch64/neon-intrinsics.c index 035e1ca..1c628bb 100644 --- a/clang/test/CodeGen/AArch64/neon-intrinsics.c +++ b/clang/test/CodeGen/AArch64/neon-intrinsics.c @@ -12643,7 +12643,7 @@ uint64_t test_vqrshld_u64(uint64_t a, int64_t b) { // CHECK-LABEL: define dso_local i64 @test_vpaddd_s64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VPADDD_S64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VPADDD_S64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VPADDD_S64_I]] // int64_t test_vpaddd_s64(int64x2_t a) { @@ -23227,7 +23227,7 @@ uint64x2_t test_vpaddq_u64(uint64x2_t a, uint64x2_t b) { // CHECK-LABEL: define dso_local i64 @test_vpaddd_u64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VPADDD_U64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VPADDD_U64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VPADDD_U64_I]] // uint64_t test_vpaddd_u64(uint64x2_t a) { @@ -23237,7 +23237,7 @@ uint64_t test_vpaddd_u64(uint64x2_t a) { // CHECK-LABEL: define dso_local i64 @test_vaddvq_s64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDVQ_S64_I:%.*]] = call i64 @llvm.aarch64.neon.saddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VADDVQ_S64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VADDVQ_S64_I]] // int64_t test_vaddvq_s64(int64x2_t a) { @@ -23247,7 +23247,7 @@ int64_t test_vaddvq_s64(int64x2_t a) { // CHECK-LABEL: define dso_local i64 @test_vaddvq_u64( // CHECK-SAME: <2 x i64> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDVQ_U64_I:%.*]] = call i64 @llvm.aarch64.neon.uaddv.i64.v2i64(<2 x i64> [[A]]) +// CHECK-NEXT: [[VADDVQ_U64_I:%.*]] = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> [[A]]) // CHECK-NEXT: ret i64 [[VADDVQ_U64_I]] // uint64_t test_vaddvq_u64(uint64x2_t a) { @@ -23878,7 +23878,7 @@ float64x1_t test_vrsqrts_f64(float64x1_t a, float64x1_t b) { // CHECK-LABEL: define dso_local i32 @test_vminv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMINV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMINV_S32_I:%.*]] = call i32 @llvm.vector.reduce.smin.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINV_S32_I]] // int32_t test_vminv_s32(int32x2_t a) { @@ -23888,7 +23888,7 @@ int32_t test_vminv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vminv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMINV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMINV_U32_I:%.*]] = call i32 @llvm.vector.reduce.umin.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMINV_U32_I]] // uint32_t test_vminv_u32(uint32x2_t a) { @@ -23898,7 +23898,7 @@ uint32_t test_vminv_u32(uint32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vmaxv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMAXV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMAXV_S32_I:%.*]] = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXV_S32_I]] // int32_t test_vmaxv_s32(int32x2_t a) { @@ -23908,7 +23908,7 @@ int32_t test_vmaxv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vmaxv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VMAXV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VMAXV_U32_I:%.*]] = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VMAXV_U32_I]] // uint32_t test_vmaxv_u32(uint32x2_t a) { @@ -23918,7 +23918,7 @@ uint32_t test_vmaxv_u32(uint32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vaddv_s32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDV_S32_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VADDV_S32_I:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDV_S32_I]] // int32_t test_vaddv_s32(int32x2_t a) { @@ -23928,7 +23928,7 @@ int32_t test_vaddv_s32(int32x2_t a) { // CHECK-LABEL: define dso_local i32 @test_vaddv_u32( // CHECK-SAME: <2 x i32> noundef [[A:%.*]]) #[[ATTR0]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[VADDV_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v2i32(<2 x i32> [[A]]) +// CHECK-NEXT: [[VADDV_U32_I:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[A]]) // CHECK-NEXT: ret i32 [[VADDV_U32_I]] // uint32_t test_vaddv_u32(uint32x2_t a) { diff --git a/clang/test/CodeGen/X86/avx512vlbw-builtins.c b/clang/test/CodeGen/X86/avx512vlbw-builtins.c index 116d86f..febef46 100644 --- a/clang/test/CodeGen/X86/avx512vlbw-builtins.c +++ b/clang/test/CodeGen/X86/avx512vlbw-builtins.c @@ -645,6 +645,21 @@ __mmask16 test_mm_cmp_epi8_mask(__m128i __a, __m128i __b) { return (__mmask16)_mm_cmp_epi8_mask(__a, __b, 0); } +TEST_CONSTEXPR(_mm_cmpeq_epi8_mask( + ((__m128i)(__v16qi){5, 3, 7, 2, 9, 3, 7, 1, 5, 4, 8, 2, 9, 6, 7, 5}), + ((__m128i)(__v16qi){5, 2, 7, 3, 9, 4, 6, 1, 5, 3, 8, 1, 9, 5, 7, 5}) +) == (__mmask16)0xd595); + +TEST_CONSTEXPR(_mm_cmplt_epi8_mask( + ((__m128i)(__v16qi){1, 5, 3, 7, 2, 8, 4, 6, 9, 5, 3, 11, 2, 6, 15, 8}), + ((__m128i)(__v16qi){2, 4, 6, 8, 3, 5, 7, 9, 4, 6, 8, 10, 5, 7, 9, 11}) +) == (__mmask16)0xb6dd); + +TEST_CONSTEXPR(_mm_cmple_epi8_mask( + ((__m128i)(__v16qi){1, 3, 5, 7, 2, 6, 6, 8, 1, 3, 9, 7, 2, 4, 6, 10}), + ((__m128i)(__v16qi){2, 3, 4, 7, 3, 4, 5, 8, 2, 3, 4, 7, 3, 4, 5, 8}) +) == (__mmask16)0x3b9b); + __mmask16 test_mm_mask_cmp_epi8_mask(__mmask16 __u, __m128i __a, __m128i __b) { // CHECK-LABEL: test_mm_mask_cmp_epi8_mask // CHECK: icmp eq <16 x i8> %{{.*}}, %{{.*}} @@ -2894,6 +2909,12 @@ __mmask16 test_mm_test_epi8_mask(__m128i __A, __m128i __B) { return _mm_test_epi8_mask(__A, __B); } +TEST_CONSTEXPR(_mm_test_epi8_mask( + (__m128i)(__v16qi){1, 2, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, + (__m128i)(__v16qi){1, 2, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16} +) +== (__mmask16)0xfffb); + __mmask16 test_mm_mask_test_epi8_mask(__mmask16 __U, __m128i __A, __m128i __B) { // CHECK-LABEL: test_mm_mask_test_epi8_mask // CHECK: and <2 x i64> %{{.*}}, %{{.*}} @@ -2901,6 +2922,12 @@ __mmask16 test_mm_mask_test_epi8_mask(__mmask16 __U, __m128i __A, __m128i __B) { // CHECK: and <16 x i1> %{{.*}}, %{{.*}} return _mm_mask_test_epi8_mask(__U, __A, __B); } +TEST_CONSTEXPR(_mm_mask_test_epi8_mask( + 0xFFFF, + (__m128i)(__v16qi){1, 2, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, + (__m128i)(__v16qi){1, 2, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16} +) +== (__mmask16)0xfffb); __mmask32 test_mm256_test_epi8_mask(__m256i __A, __m256i __B) { // CHECK-LABEL: test_mm256_test_epi8_mask @@ -2908,6 +2935,11 @@ __mmask32 test_mm256_test_epi8_mask(__m256i __A, __m256i __B) { // CHECK: icmp ne <32 x i8> %{{.*}}, %{{.*}} return _mm256_test_epi8_mask(__A, __B); } +TEST_CONSTEXPR(_mm256_test_epi8_mask( + (__m256i)(__v32qi){1, 2, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 1, 2, 2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}, + (__m256i)(__v32qi){1, 2, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 1, 2, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16} +) +== (__mmask32)0xfffbfffb); __mmask32 test_mm256_mask_test_epi8_mask(__mmask32 __U, __m256i __A, __m256i __B) { // CHECK-LABEL: test_mm256_mask_test_epi8_mask @@ -2954,6 +2986,12 @@ __mmask16 test_mm_testn_epi8_mask(__m128i __A, __m128i __B) { return _mm_testn_epi8_mask(__A, __B); } +TEST_CONSTEXPR(_mm_testn_epi8_mask( + (__m128i)(__v16qi){1, 2, 77, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 1, 16, 16}, + (__m128i)(__v16qi){2, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 15} +) +== (__mmask16)0xe001); + __mmask16 test_mm_mask_testn_epi8_mask(__mmask16 __U, __m128i __A, __m128i __B) { // CHECK-LABEL: test_mm_mask_testn_epi8_mask // CHECK: and <2 x i64> %{{.*}}, %{{.*}} diff --git a/clang/test/CodeGen/lto-newpm-pipeline.c b/clang/test/CodeGen/lto-newpm-pipeline.c index ea9784a..dceaaf1 100644 --- a/clang/test/CodeGen/lto-newpm-pipeline.c +++ b/clang/test/CodeGen/lto-newpm-pipeline.c @@ -32,10 +32,12 @@ // CHECK-FULL-O0-NEXT: Running pass: AlwaysInlinerPass // CHECK-FULL-O0-NEXT: Running analysis: ProfileSummaryAnalysis // CHECK-FULL-O0-NEXT: Running pass: CoroConditionalWrapper +// CHECK-FULL-O0-NEXT: Running pass: AllocTokenPass +// CHECK-FULL-O0-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis +// CHECK-FULL-O0-NEXT: Running analysis: TargetLibraryAnalysis // CHECK-FULL-O0-NEXT: Running pass: CanonicalizeAliasesPass // CHECK-FULL-O0-NEXT: Running pass: NameAnonGlobalPass // CHECK-FULL-O0-NEXT: Running pass: AnnotationRemarksPass -// CHECK-FULL-O0-NEXT: Running analysis: TargetLibraryAnalysis // CHECK-FULL-O0-NEXT: Running pass: VerifierPass // CHECK-FULL-O0-NEXT: Running pass: BitcodeWriterPass @@ -46,10 +48,12 @@ // CHECK-THIN-O0-NEXT: Running pass: AlwaysInlinerPass // CHECK-THIN-O0-NEXT: Running analysis: ProfileSummaryAnalysis // CHECK-THIN-O0-NEXT: Running pass: CoroConditionalWrapper +// CHECK-THIN-O0-NEXT: Running pass: AllocTokenPass +// CHECK-THIN-O0-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis +// CHECK-THIN-O0-NEXT: Running analysis: TargetLibraryAnalysis // CHECK-THIN-O0-NEXT: Running pass: CanonicalizeAliasesPass // CHECK-THIN-O0-NEXT: Running pass: NameAnonGlobalPass // CHECK-THIN-O0-NEXT: Running pass: AnnotationRemarksPass -// CHECK-THIN-O0-NEXT: Running analysis: TargetLibraryAnalysis // CHECK-THIN-O0-NEXT: Running pass: VerifierPass // CHECK-THIN-O0-NEXT: Running pass: ThinLTOBitcodeWriterPass diff --git a/clang/test/CodeGenCXX/alloc-token-builtin.cpp b/clang/test/CodeGenCXX/alloc-token-builtin.cpp new file mode 100644 index 0000000..adadf7b --- /dev/null +++ b/clang/test/CodeGenCXX/alloc-token-builtin.cpp @@ -0,0 +1,97 @@ +// To test IR generation of the builtin without evaluating the LLVM intrinsic, +// we set the mode to a stateful mode, which prohibits constant evaluation. +// RUN: %clang_cc1 -triple x86_64-linux-gnu -Werror -std=c++20 -emit-llvm -falloc-token-mode=random -disable-llvm-passes %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-CODEGEN +// RUN: %clang_cc1 -triple x86_64-linux-gnu -Werror -std=c++20 -emit-llvm -falloc-token-max=2 %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-LOWER + +extern "C" void *my_malloc(unsigned long, unsigned long); + +struct NoPtr { + int x; + long y; +}; + +struct WithPtr { + int a; + char *buf; +}; + +int unevaluated_fn(); + +// CHECK-LABEL: @_Z16test_builtin_intv( +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_INT:[0-9]+]]) +// CHECK-LOWER: ret i64 0 +unsigned long test_builtin_int() { + return __builtin_infer_alloc_token(sizeof(1)); +} + +// CHECK-LABEL: @_Z16test_builtin_ptrv( +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_PTR:[0-9]+]]) +// CHECK-LOWER: ret i64 1 +unsigned long test_builtin_ptr() { + return __builtin_infer_alloc_token(sizeof(int *)); +} + +// CHECK-LABEL: @_Z25test_builtin_struct_noptrv( +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_NOPTR:[0-9]+]]) +// CHECK-LOWER: ret i64 0 +unsigned long test_builtin_struct_noptr() { + return __builtin_infer_alloc_token(sizeof(NoPtr)); +} + +// CHECK-LABEL: @_Z25test_builtin_struct_w_ptrv( +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_WITHPTR:[0-9]+]]) +// CHECK-LOWER: ret i64 1 +unsigned long test_builtin_struct_w_ptr() { + return __builtin_infer_alloc_token(sizeof(WithPtr), 123); +} + +// CHECK-LABEL: @_Z24test_builtin_unevaluatedv( +// CHECK-NOT: call{{.*}}unevaluated_fn +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_INT:[0-9]+]]) +// CHECK-LOWER: ret i64 0 +unsigned long test_builtin_unevaluated() { + return __builtin_infer_alloc_token(sizeof(int) * unevaluated_fn()); +} + +// CHECK-LABEL: @_Z36test_builtin_unsequenced_unevaluatedi( +// CHECK: add nsw +// CHECK-NOT: add nsw +// CHECK-CODEGEN: %[[REG:[0-9]+]] = call i64 @llvm.alloc.token.id.i64(metadata ![[META_UNKNOWN:[0-9]+]]) +// CHECK-CODEGEN: call{{.*}}@my_malloc({{.*}}, i64 noundef %[[REG]]) +// CHECK-LOWER: call{{.*}}@my_malloc({{.*}}, i64 noundef 0) +void test_builtin_unsequenced_unevaluated(int x) { + my_malloc(++x, __builtin_infer_alloc_token(++x)); +} + +// CHECK-LABEL: @_Z20test_builtin_unknownv( +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_UNKNOWN:[0-9]+]]) +// CHECK-LOWER: ret i64 0 +unsigned long test_builtin_unknown() { + return __builtin_infer_alloc_token(4096); +} + +// Test template instantiation. +template <typename T> +constexpr unsigned long get_token() { + return __builtin_infer_alloc_token(sizeof(T)); +} + +// CHECK-LABEL: @_Z13get_token_intv() +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_INT]]) +// CHECK-LOWER: ret i64 0 +unsigned long get_token_int() { + return get_token<int>(); +} + +// CHECK-LABEL: @_Z13get_token_ptrv() +// CHECK-CODEGEN: call i64 @llvm.alloc.token.id.i64(metadata ![[META_PTR]]) +// CHECK-LOWER: ret i64 1 +unsigned long get_token_ptr() { + return get_token<int *>(); +} + +// CHECK-CODEGEN: ![[META_INT]] = !{!"int", i1 false} +// CHECK-CODEGEN: ![[META_PTR]] = !{!"int *", i1 true} +// CHECK-CODEGEN: ![[META_NOPTR]] = !{!"NoPtr", i1 false} +// CHECK-CODEGEN: ![[META_WITHPTR]] = !{!"WithPtr", i1 true} +// CHECK-CODEGEN: ![[META_UNKNOWN]] = !{} diff --git a/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp b/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp index 2e7531b..4be1cb3 100644 --- a/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp +++ b/clang/test/CodeGenCXX/matrix-vector-bit-int.cpp @@ -19,7 +19,7 @@ using i4x3x3 = _BitInt(4) __attribute__((matrix_type(3, 3))); // CHECK-NEXT: store i32 [[A_COERCE]], ptr [[A]], align 4 // CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x i8>, ptr [[A]], align 4 // CHECK-NEXT: [[A1:%.*]] = shufflevector <4 x i8> [[LOADVECN]], <4 x i8> poison, <3 x i32> <i32 0, i32 1, i32 2> -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i8> [[A1]], <3 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i8> [[A1]], <3 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i8> [[EXTRACTVEC]], ptr [[A_ADDR]], align 4 // CHECK-NEXT: [[LOADVECN2:%.*]] = load <4 x i8>, ptr [[A_ADDR]], align 4 // CHECK-NEXT: [[EXTRACTVEC3:%.*]] = shufflevector <4 x i8> [[LOADVECN2]], <4 x i8> poison, <3 x i32> <i32 0, i32 1, i32 2> @@ -38,7 +38,7 @@ i8x3 v1(i8x3 a) { // CHECK-SAME: <3 x i32> noundef [[A:%.*]]) #[[ATTR1:[0-9]+]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[A_ADDR:%.*]] = alloca <3 x i32>, align 16 -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i32> [[A]], <3 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i32> [[A]], <3 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i32> [[EXTRACTVEC]], ptr [[A_ADDR]], align 16 // CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x i32>, ptr [[A_ADDR]], align 16 // CHECK-NEXT: [[EXTRACTVEC1:%.*]] = shufflevector <4 x i32> [[LOADVECN]], <4 x i32> poison, <3 x i32> <i32 0, i32 1, i32 2> @@ -57,7 +57,7 @@ i32x3 v2(i32x3 a) { // CHECK-NEXT: [[A_ADDR:%.*]] = alloca <3 x i512>, align 256 // CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x i512>, ptr [[TMP0]], align 256 // CHECK-NEXT: [[A:%.*]] = shufflevector <4 x i512> [[LOADVECN]], <4 x i512> poison, <3 x i32> <i32 0, i32 1, i32 2> -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i512> [[A]], <3 x i512> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i512> [[A]], <3 x i512> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i512> [[EXTRACTVEC]], ptr [[A_ADDR]], align 256 // CHECK-NEXT: [[LOADVECN1:%.*]] = load <4 x i512>, ptr [[A_ADDR]], align 256 // CHECK-NEXT: [[EXTRACTVEC2:%.*]] = shufflevector <4 x i512> [[LOADVECN1]], <4 x i512> poison, <3 x i32> <i32 0, i32 1, i32 2> @@ -80,7 +80,7 @@ i512x3 v3(i512x3 a) { // CHECK-NEXT: store i32 [[A_COERCE]], ptr [[A]], align 4 // CHECK-NEXT: [[LOADVECN:%.*]] = load <4 x i4>, ptr [[A]], align 4 // CHECK-NEXT: [[A1:%.*]] = shufflevector <4 x i4> [[LOADVECN]], <4 x i4> poison, <3 x i32> <i32 0, i32 1, i32 2> -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i4> [[A1]], <3 x i4> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i4> [[A1]], <3 x i4> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i4> [[EXTRACTVEC]], ptr [[A_ADDR]], align 4 // CHECK-NEXT: [[LOADVECN2:%.*]] = load <4 x i4>, ptr [[A_ADDR]], align 4 // CHECK-NEXT: [[EXTRACTVEC3:%.*]] = shufflevector <4 x i4> [[LOADVECN2]], <4 x i4> poison, <3 x i32> <i32 0, i32 1, i32 2> diff --git a/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl b/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl new file mode 100644 index 0000000..1194f84 --- /dev/null +++ b/clang/test/CodeGenHLSL/builtins/WaveActiveMin.hlsl @@ -0,0 +1,46 @@ +// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \ +// RUN: dxil-pc-shadermodel6.3-compute %s -emit-llvm -disable-llvm-passes -o - | \ +// RUN: FileCheck %s --check-prefixes=CHECK,CHECK-DXIL +// RUN: %clang_cc1 -std=hlsl2021 -finclude-default-header -triple \ +// RUN: spirv-pc-vulkan-compute %s -emit-llvm -disable-llvm-passes -o - | \ +// RUN: FileCheck %s --check-prefixes=CHECK,CHECK-SPIRV + +// Test basic lowering to runtime function call. + +// CHECK-LABEL: test_int +int test_int(int expr) { + // CHECK-SPIRV: %[[RET:.*]] = call spir_func [[TY:.*]] @llvm.spv.wave.reduce.min.i32([[TY]] %[[#]]) + // CHECK-DXIL: %[[RET:.*]] = call [[TY:.*]] @llvm.dx.wave.reduce.min.i32([[TY]] %[[#]]) + // CHECK: ret [[TY]] %[[RET]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY]] @llvm.dx.wave.reduce.min.i32([[TY]]) #[[#attr:]] +// CHECK-SPIRV: declare [[TY]] @llvm.spv.wave.reduce.min.i32([[TY]]) #[[#attr:]] + +// CHECK-LABEL: test_uint64_t +uint64_t test_uint64_t(uint64_t expr) { + // CHECK-SPIRV: %[[RET:.*]] = call spir_func [[TY:.*]] @llvm.spv.wave.reduce.umin.i64([[TY]] %[[#]]) + // CHECK-DXIL: %[[RET:.*]] = call [[TY:.*]] @llvm.dx.wave.reduce.umin.i64([[TY]] %[[#]]) + // CHECK: ret [[TY]] %[[RET]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY]] @llvm.dx.wave.reduce.umin.i64([[TY]]) #[[#attr:]] +// CHECK-SPIRV: declare [[TY]] @llvm.spv.wave.reduce.umin.i64([[TY]]) #[[#attr:]] + +// Test basic lowering to runtime function call with array and float value. + +// CHECK-LABEL: test_floatv4 +float4 test_floatv4(float4 expr) { + // CHECK-SPIRV: %[[RET1:.*]] = call reassoc nnan ninf nsz arcp afn spir_func [[TY1:.*]] @llvm.spv.wave.reduce.min.v4f32([[TY1]] %[[#]] + // CHECK-DXIL: %[[RET1:.*]] = call reassoc nnan ninf nsz arcp afn [[TY1:.*]] @llvm.dx.wave.reduce.min.v4f32([[TY1]] %[[#]]) + // CHECK: ret [[TY1]] %[[RET1]] + return WaveActiveMin(expr); +} + +// CHECK-DXIL: declare [[TY1]] @llvm.dx.wave.reduce.min.v4f32([[TY1]]) #[[#attr]] +// CHECK-SPIRV: declare [[TY1]] @llvm.spv.wave.reduce.min.v4f32([[TY1]]) #[[#attr]] + +// CHECK: attributes #[[#attr]] = {{{.*}} convergent {{.*}}} + diff --git a/clang/test/CodeGenOpenCL/preserve_vec3.cl b/clang/test/CodeGenOpenCL/preserve_vec3.cl index e76aa81..0017169 100644 --- a/clang/test/CodeGenOpenCL/preserve_vec3.cl +++ b/clang/test/CodeGenOpenCL/preserve_vec3.cl @@ -12,7 +12,7 @@ typedef float float4 __attribute__((ext_vector_type(4))); // CHECK-SAME: ptr addrspace(1) noundef readonly align 16 captures(none) [[A:%.*]], ptr addrspace(1) noundef writeonly align 16 captures(none) initializes((0, 16)) [[B:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] !kernel_arg_addr_space [[META7:![0-9]+]] !kernel_arg_access_qual [[META8:![0-9]+]] !kernel_arg_type [[META9:![0-9]+]] !kernel_arg_base_type [[META10:![0-9]+]] !kernel_arg_type_qual [[META11:![0-9]+]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[TMP0:%.*]] = load <3 x float>, ptr addrspace(1) [[A]], align 16 -// CHECK-NEXT: [[EXTRACTVEC1_I:%.*]] = shufflevector <3 x float> [[TMP0]], <3 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC1_I:%.*]] = shufflevector <3 x float> [[TMP0]], <3 x float> <float undef, float poison, float poison>, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x float> [[EXTRACTVEC1_I]], ptr addrspace(1) [[B]], align 16, !tbaa [[CHAR_TBAA12:![0-9]+]] // CHECK-NEXT: ret void // @@ -24,7 +24,7 @@ void kernel foo(global float3 *a, global float3 *b) { // CHECK-SAME: ptr addrspace(1) noundef writeonly align 16 captures(none) initializes((0, 16)) [[A:%.*]], ptr addrspace(1) noundef readonly align 16 captures(none) [[B:%.*]]) local_unnamed_addr #[[ATTR0]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META13:![0-9]+]] !kernel_arg_base_type [[META14:![0-9]+]] !kernel_arg_type_qual [[META11]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[TMP0:%.*]] = load <3 x float>, ptr addrspace(1) [[B]], align 16, !tbaa [[CHAR_TBAA12]] -// CHECK-NEXT: [[EXTRACTVEC_I:%.*]] = shufflevector <3 x float> [[TMP0]], <3 x float> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC_I:%.*]] = shufflevector <3 x float> [[TMP0]], <3 x float> <float undef, float poison, float poison>, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x float> [[EXTRACTVEC_I]], ptr addrspace(1) [[A]], align 16, !tbaa [[CHAR_TBAA12]] // CHECK-NEXT: ret void // @@ -60,7 +60,7 @@ void kernel float3_to_double2(global float3 *a, global double2 *b) { // CHECK-SAME: ptr addrspace(1) noundef writeonly align 8 captures(none) initializes((0, 8)) [[A:%.*]], ptr addrspace(1) noundef readonly align 8 captures(none) [[B:%.*]]) local_unnamed_addr #[[ATTR0]] !kernel_arg_addr_space [[META7]] !kernel_arg_access_qual [[META8]] !kernel_arg_type [[META17:![0-9]+]] !kernel_arg_base_type [[META18:![0-9]+]] !kernel_arg_type_qual [[META11]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[TMP0:%.*]] = load <3 x i16>, ptr addrspace(1) [[B]], align 8, !tbaa [[CHAR_TBAA12]] -// CHECK-NEXT: [[EXTRACTVEC_I:%.*]] = shufflevector <3 x i16> [[TMP0]], <3 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[EXTRACTVEC_I:%.*]] = shufflevector <3 x i16> [[TMP0]], <3 x i16> <i16 undef, i16 poison, i16 poison>, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i16> [[EXTRACTVEC_I]], ptr addrspace(1) [[A]], align 8, !tbaa [[CHAR_TBAA12]] // CHECK-NEXT: ret void // @@ -71,8 +71,8 @@ void kernel char8_to_short3(global short3 *a, global char8 *b) { // CHECK-LABEL: define dso_local spir_func void @from_char3( // CHECK-SAME: <3 x i8> noundef [[A:%.*]], ptr addrspace(1) noundef writeonly captures(none) initializes((0, 4)) [[OUT:%.*]]) local_unnamed_addr #[[ATTR2:[0-9]+]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i8> [[A]], <3 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> -// CHECK-NEXT: store <4 x i8> [[EXTRACTVEC]], ptr addrspace(1) [[OUT]], align 4, !tbaa [[INT_TBAA3:![0-9]+]] +// CHECK-NEXT: [[TMP0:%.*]] = shufflevector <3 x i8> [[A]], <3 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: store <4 x i8> [[TMP0]], ptr addrspace(1) [[OUT]], align 4, !tbaa [[INT_TBAA3:![0-9]+]] // CHECK-NEXT: ret void // void from_char3(char3 a, global int *out) { @@ -82,8 +82,8 @@ void from_char3(char3 a, global int *out) { // CHECK-LABEL: define dso_local spir_func void @from_short3( // CHECK-SAME: <3 x i16> noundef [[A:%.*]], ptr addrspace(1) noundef writeonly captures(none) initializes((0, 8)) [[OUT:%.*]]) local_unnamed_addr #[[ATTR2]] { // CHECK-NEXT: [[ENTRY:.*:]] -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i16> [[A]], <3 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> -// CHECK-NEXT: store <4 x i16> [[EXTRACTVEC]], ptr addrspace(1) [[OUT]], align 8, !tbaa [[LONG_TBAA19:![0-9]+]] +// CHECK-NEXT: [[TMP0:%.*]] = shufflevector <3 x i16> [[A]], <3 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: store <4 x i16> [[TMP0]], ptr addrspace(1) [[OUT]], align 8, !tbaa [[LONG_TBAA19:![0-9]+]] // CHECK-NEXT: ret void // void from_short3(short3 a, global long *out) { @@ -94,7 +94,8 @@ void from_short3(short3 a, global long *out) { // CHECK-SAME: i32 noundef [[A:%.*]], ptr addrspace(1) noundef writeonly captures(none) initializes((0, 4)) [[OUT:%.*]]) local_unnamed_addr #[[ATTR2]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[TMP0:%.*]] = bitcast i32 [[A]] to <4 x i8> -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <4 x i8> [[TMP0]], <4 x i8> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[ASTYPE:%.*]] = shufflevector <4 x i8> [[TMP0]], <4 x i8> poison, <3 x i32> <i32 0, i32 1, i32 2> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i8> [[ASTYPE]], <3 x i8> <i8 undef, i8 poison, i8 poison>, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i8> [[EXTRACTVEC]], ptr addrspace(1) [[OUT]], align 4, !tbaa [[CHAR_TBAA12]] // CHECK-NEXT: ret void // @@ -106,7 +107,8 @@ void scalar_to_char3(int a, global char3 *out) { // CHECK-SAME: i64 noundef [[A:%.*]], ptr addrspace(1) noundef writeonly captures(none) initializes((0, 8)) [[OUT:%.*]]) local_unnamed_addr #[[ATTR2]] { // CHECK-NEXT: [[ENTRY:.*:]] // CHECK-NEXT: [[TMP0:%.*]] = bitcast i64 [[A]] to <4 x i16> -// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <4 x i16> [[TMP0]], <4 x i16> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison> +// CHECK-NEXT: [[ASTYPE:%.*]] = shufflevector <4 x i16> [[TMP0]], <4 x i16> poison, <3 x i32> <i32 0, i32 1, i32 2> +// CHECK-NEXT: [[EXTRACTVEC:%.*]] = shufflevector <3 x i16> [[ASTYPE]], <3 x i16> <i16 undef, i16 poison, i16 poison>, <4 x i32> <i32 0, i32 1, i32 2, i32 3> // CHECK-NEXT: store <4 x i16> [[EXTRACTVEC]], ptr addrspace(1) [[OUT]], align 8, !tbaa [[CHAR_TBAA12]] // CHECK-NEXT: ret void // diff --git a/clang/test/DebugInfo/Generic/bit-int.c b/clang/test/DebugInfo/Generic/bit-int.c new file mode 100644 index 0000000..88ecc13 --- /dev/null +++ b/clang/test/DebugInfo/Generic/bit-int.c @@ -0,0 +1,8 @@ +// RUN: %clang_cc1 -x c++ %s -debug-info-kind=standalone -gno-column-info -emit-llvm -o - | FileCheck %s +// RUN: %clang_cc1 -x c %s -debug-info-kind=standalone -gno-column-info -emit-llvm -o - | FileCheck %s + +unsigned _BitInt(17) a; +_BitInt(2) b; + +// CHECK: !DIBasicType(name: "_BitInt(2)", size: 8, dataSize: 2, encoding: DW_ATE_signed) +// CHECK: !DIBasicType(name: "unsigned _BitInt(17)", size: 32, dataSize: 17, encoding: DW_ATE_unsigned) diff --git a/clang/test/Driver/aarch64-mlr-for-calls-only.c b/clang/test/Driver/aarch64-mlr-for-calls-only.c new file mode 100644 index 0000000..e71a4cd --- /dev/null +++ b/clang/test/Driver/aarch64-mlr-for-calls-only.c @@ -0,0 +1,3 @@ +// RUN: %clang --target=aarch64-none-gnu -mlr-for-calls-only -### %s 2> %t +// RUN: FileCheck --check-prefix=CHECK < %t %s +// CHECK: "-target-feature" "+reserve-lr-for-ra" diff --git a/clang/test/Driver/aarch64-ptrauth.c b/clang/test/Driver/aarch64-ptrauth.c index b080a77..a67e98f 100644 --- a/clang/test/Driver/aarch64-ptrauth.c +++ b/clang/test/Driver/aarch64-ptrauth.c @@ -4,7 +4,8 @@ // NONE: "-cc1" // NONE-NOT: "-fptrauth- -// RUN: %clang -### -c --target=aarch64 \ +//// -fptauth-* driver flags on Linux are only supported with pauthtest ABI. +// RUN: %clang -### -c --target=aarch64-linux -mabi=pauthtest \ // RUN: -fno-ptrauth-intrinsics -fptrauth-intrinsics \ // RUN: -fno-ptrauth-calls -fptrauth-calls \ // RUN: -fno-ptrauth-returns -fptrauth-returns \ @@ -15,9 +16,43 @@ // RUN: -fno-ptrauth-indirect-gotos -fptrauth-indirect-gotos \ // RUN: -fno-ptrauth-init-fini -fptrauth-init-fini \ // RUN: -fno-ptrauth-init-fini-address-discrimination -fptrauth-init-fini-address-discrimination \ +// RUN: -fno-ptrauth-elf-got -fptrauth-elf-got \ // RUN: -fno-aarch64-jump-table-hardening -faarch64-jump-table-hardening \ -// RUN: %s 2>&1 | FileCheck %s --check-prefix=ALL -// ALL: "-cc1"{{.*}} "-fptrauth-intrinsics" "-fptrauth-calls" "-fptrauth-returns" "-fptrauth-auth-traps" "-fptrauth-vtable-pointer-address-discrimination" "-fptrauth-vtable-pointer-type-discrimination" "-fptrauth-type-info-vtable-pointer-discrimination" "-fptrauth-indirect-gotos" "-fptrauth-init-fini" "-fptrauth-init-fini-address-discrimination" "-faarch64-jump-table-hardening" +// RUN: %s 2>&1 | FileCheck %s --check-prefix=ALL-LINUX-PAUTHABI +// RUN: %clang -### -c --target=aarch64-linux-pauthtest \ +// RUN: -fno-ptrauth-intrinsics -fptrauth-intrinsics \ +// RUN: -fno-ptrauth-calls -fptrauth-calls \ +// RUN: -fno-ptrauth-returns -fptrauth-returns \ +// RUN: -fno-ptrauth-auth-traps -fptrauth-auth-traps \ +// RUN: -fno-ptrauth-vtable-pointer-address-discrimination -fptrauth-vtable-pointer-address-discrimination \ +// RUN: -fno-ptrauth-vtable-pointer-type-discrimination -fptrauth-vtable-pointer-type-discrimination \ +// RUN: -fno-ptrauth-type-info-vtable-pointer-discrimination -fptrauth-type-info-vtable-pointer-discrimination \ +// RUN: -fno-ptrauth-indirect-gotos -fptrauth-indirect-gotos \ +// RUN: -fno-ptrauth-init-fini -fptrauth-init-fini \ +// RUN: -fno-ptrauth-init-fini-address-discrimination -fptrauth-init-fini-address-discrimination \ +// RUN: -fno-ptrauth-elf-got -fptrauth-elf-got \ +// RUN: -fno-aarch64-jump-table-hardening -faarch64-jump-table-hardening \ +// RUN: %s 2>&1 | FileCheck %s --check-prefix=ALL-LINUX-PAUTHABI +// ALL-LINUX-PAUTHABI: "-cc1"{{.*}} "-fptrauth-intrinsics" "-fptrauth-calls" "-fptrauth-returns" "-fptrauth-auth-traps" "-fptrauth-vtable-pointer-address-discrimination" "-fptrauth-vtable-pointer-type-discrimination" "-fptrauth-type-info-vtable-pointer-discrimination" "-fptrauth-indirect-gotos" "-fptrauth-init-fini" "-fptrauth-init-fini-address-discrimination" "-fptrauth-elf-got"{{.*}} "-faarch64-jump-table-hardening" + +// RUN: %clang -### -c --target=aarch64-linux \ +// RUN: -fno-aarch64-jump-table-hardening -faarch64-jump-table-hardening \ +// RUN: %s 2>&1 | FileCheck %s --check-prefix=ALL-LINUX +// ALL-LINUX: "-cc1"{{.*}} "-faarch64-jump-table-hardening" + +//// Some -fptrauth-* flags are supported for ARM64 Darwin. +// RUN: %clang -### -c --target=arm64-darwin \ +// RUN: -fno-ptrauth-intrinsics -fptrauth-intrinsics \ +// RUN: -fno-ptrauth-calls -fptrauth-calls \ +// RUN: -fno-ptrauth-returns -fptrauth-returns \ +// RUN: -fno-ptrauth-auth-traps -fptrauth-auth-traps \ +// RUN: -fno-ptrauth-vtable-pointer-address-discrimination -fptrauth-vtable-pointer-address-discrimination \ +// RUN: -fno-ptrauth-vtable-pointer-type-discrimination -fptrauth-vtable-pointer-type-discrimination \ +// RUN: -fno-ptrauth-type-info-vtable-pointer-discrimination -fptrauth-type-info-vtable-pointer-discrimination \ +// RUN: -fno-ptrauth-indirect-gotos -fptrauth-indirect-gotos \ +// RUN: -fno-aarch64-jump-table-hardening -faarch64-jump-table-hardening \ +// RUN: %s 2>&1 | FileCheck %s --check-prefix=ALL-DARWIN +// ALL-DARWIN: "-cc1"{{.*}} "-fptrauth-intrinsics" "-fptrauth-calls" "-fptrauth-returns" "-fptrauth-auth-traps" "-fptrauth-vtable-pointer-address-discrimination" "-fptrauth-vtable-pointer-type-discrimination" "-fptrauth-type-info-vtable-pointer-discrimination" "-fptrauth-indirect-gotos"{{.*}} "-faarch64-jump-table-hardening" // RUN: %clang -### -c --target=aarch64-linux -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=PAUTHABI1 // RUN: %clang -### -c --target=aarch64-linux-pauthtest %s 2>&1 | FileCheck %s --check-prefix=PAUTHABI1 @@ -40,7 +75,7 @@ // RUN: -fno-aarch64-jump-table-hardening %s 2>&1 | FileCheck %s --check-prefix=PAUTHABI2 //// Non-linux OS: pauthtest ABI has no effect in terms of passing ptrauth cc1 flags. -//// An error about unsupported ABI will be emitted later in pipeline (see ERR2 below) +//// An error about unsupported ABI will be emitted later in pipeline (see ERR3 below) // RUN: %clang -### -c --target=aarch64 -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=PAUTHABI2 // PAUTHABI2: "-cc1" @@ -55,10 +90,11 @@ // PAUTHABI3-NOT: "-fptrauth- // PAUTHABI3-NOT: "-faarch64-jump-table-hardening" -// RUN: not %clang -### -c --target=x86_64 -fptrauth-intrinsics -fptrauth-calls -fptrauth-returns -fptrauth-auth-traps \ +//// Non-pauthtest ABI. +// RUN: not %clang -### -c --target=aarch64-linux -fptrauth-intrinsics -fptrauth-calls -fptrauth-returns -fptrauth-auth-traps \ // RUN: -fptrauth-vtable-pointer-address-discrimination -fptrauth-vtable-pointer-type-discrimination \ // RUN: -fptrauth-type-info-vtable-pointer-discrimination -fptrauth-indirect-gotos -fptrauth-init-fini \ -// RUN: -fptrauth-init-fini-address-discrimination -faarch64-jump-table-hardening %s 2>&1 | FileCheck %s --check-prefix=ERR1 +// RUN: -fptrauth-init-fini-address-discrimination -fptrauth-elf-got %s 2>&1 | FileCheck %s --check-prefix=ERR1 // ERR1: error: unsupported option '-fptrauth-intrinsics' for target '{{.*}}' // ERR1-NEXT: error: unsupported option '-fptrauth-calls' for target '{{.*}}' // ERR1-NEXT: error: unsupported option '-fptrauth-returns' for target '{{.*}}' @@ -69,59 +105,64 @@ // ERR1-NEXT: error: unsupported option '-fptrauth-indirect-gotos' for target '{{.*}}' // ERR1-NEXT: error: unsupported option '-fptrauth-init-fini' for target '{{.*}}' // ERR1-NEXT: error: unsupported option '-fptrauth-init-fini-address-discrimination' for target '{{.*}}' -// ERR1-NEXT: error: unsupported option '-faarch64-jump-table-hardening' for target '{{.*}}' +// ERR1-NEXT: error: unsupported option '-fptrauth-elf-got' for target '{{.*}}' +//// Non-AArch64. +// RUN: not %clang -### -c --target=x86_64-linux -faarch64-jump-table-hardening %s 2>&1 | FileCheck %s --check-prefix=ERR2 +// ERR2: error: unsupported option '-faarch64-jump-table-hardening' for target '{{.*}}' + +//// Only support PAuth ABI for Linux as for now. +// RUN: not %clang -c --target=aarch64 -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=ERR3 +// ERR3: error: unknown target ABI 'pauthtest' -// RUN: not %clang -c --target=aarch64 -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=ERR2 //// The ABI is not specified explicitly, and for non-Linux pauthtest environment does not correspond //// to pauthtest ABI (each OS target defines this behavior separately). Do not emit an error. -// RUN: %clang -c --target=aarch64-pauthtest %s -o /dev/null -// ERR2: error: unknown target ABI 'pauthtest' +// RUN: %clang -c --target=aarch64-pauthtest %s -o /dev/null //// PAuth ABI is encoded as environment part of the triple, so don't allow to explicitly set other environments. -// RUN: not %clang -### -c --target=aarch64-linux-gnu -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=ERR3 -// ERR3: error: unsupported option '-mabi=pauthtest' for target 'aarch64-unknown-linux-gnu' +// RUN: not %clang -### -c --target=aarch64-linux-gnu -mabi=pauthtest %s 2>&1 | FileCheck %s --check-prefix=ERR4 +// ERR4: error: unsupported option '-mabi=pauthtest' for target 'aarch64-unknown-linux-gnu' // RUN: %clang -### -c --target=aarch64-linux-pauthtest -mabi=pauthtest %s //// The only branch protection option compatible with PAuthABI is BTI. // RUN: not %clang -### -c --target=aarch64-linux -mabi=pauthtest -mbranch-protection=pac-ret %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR4_1 +// RUN: FileCheck %s --check-prefix=ERR5_1 // RUN: not %clang -### -c --target=aarch64-linux-pauthtest -mbranch-protection=pac-ret %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR4_1 +// RUN: FileCheck %s --check-prefix=ERR5_1 // RUN: not %clang -### -c --target=aarch64 -fptrauth-returns -mbranch-protection=pac-ret %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR4_2 -// ERR4_1: error: unsupported option '-mbranch-protection=pac-ret' for target 'aarch64-unknown-linux-pauthtest' -// ERR4_2: error: the combination of '-mbranch-protection=pac-ret' and '-fptrauth-returns' is incompatible +// RUN: FileCheck %s --check-prefix=ERR5_2 +// ERR5_1: error: unsupported option '-mbranch-protection=pac-ret' for target 'aarch64-unknown-linux-pauthtest' +// ERR5_2: error: the combination of '-mbranch-protection=pac-ret' and '-fptrauth-returns' is incompatible // RUN: not %clang -### -c --target=aarch64-linux -mabi=pauthtest -mbranch-protection=gcs %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR5_1 +// RUN: FileCheck %s --check-prefix=ERR6_1 // RUN: not %clang -### -c --target=aarch64-linux-pauthtest -mbranch-protection=gcs %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR5_1 +// RUN: FileCheck %s --check-prefix=ERR6_1 // RUN: not %clang -### -c --target=aarch64 -fptrauth-returns -mbranch-protection=gcs %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR5_2 -// ERR5_1: error: unsupported option '-mbranch-protection=gcs' for target 'aarch64-unknown-linux-pauthtest' -// ERR5_2: error: the combination of '-mbranch-protection=gcs' and '-fptrauth-returns' is incompatible +// RUN: FileCheck %s --check-prefix=ERR6_2 +// ERR6_1: error: unsupported option '-mbranch-protection=gcs' for target 'aarch64-unknown-linux-pauthtest' +// ERR6_2: error: the combination of '-mbranch-protection=gcs' and '-fptrauth-returns' is incompatible // RUN: not %clang -### -c --target=aarch64-linux -mabi=pauthtest -mbranch-protection=standard %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR6_1 +// RUN: FileCheck %s --check-prefix=ERR7_1 // RUN: not %clang -### -c --target=aarch64-linux-pauthtest -mbranch-protection=standard %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR6_1 +// RUN: FileCheck %s --check-prefix=ERR7_1 // RUN: not %clang -### -c --target=aarch64 -fptrauth-returns -mbranch-protection=standard %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR6_2 -// ERR6_1: error: unsupported option '-mbranch-protection=standard' for target 'aarch64-unknown-linux-pauthtest' -// ERR6_2: error: the combination of '-mbranch-protection=standard' and '-fptrauth-returns' is incompatible +// RUN: FileCheck %s --check-prefix=ERR7_2 +// ERR7_1: error: unsupported option '-mbranch-protection=standard' for target 'aarch64-unknown-linux-pauthtest' +// ERR7_2: error: the combination of '-mbranch-protection=standard' and '-fptrauth-returns' is incompatible // RUN: not %clang -### -c --target=aarch64-linux -mabi=pauthtest -msign-return-address=all %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR7 +// RUN: FileCheck %s --check-prefix=ERR8 // RUN: not %clang -### -c --target=aarch64-linux-pauthtest -msign-return-address=all %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR7 -// ERR7: error: unsupported option '-msign-return-address=all' for target 'aarch64-unknown-linux-pauthtest' +// RUN: FileCheck %s --check-prefix=ERR8 +// ERR8: error: unsupported option '-msign-return-address=all' for target 'aarch64-unknown-linux-pauthtest' // RUN: not %clang -### -c --target=aarch64-linux -mabi=pauthtest -msign-return-address=non-leaf %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR8 +// RUN: FileCheck %s --check-prefix=ERR9 // RUN: not %clang -### -c --target=aarch64-linux-pauthtest -msign-return-address=non-leaf %s 2>&1 | \ -// RUN: FileCheck %s --check-prefix=ERR8 -// ERR8: error: unsupported option '-msign-return-address=non-leaf' for target 'aarch64-unknown-linux-pauthtest' +// RUN: FileCheck %s --check-prefix=ERR9 +// ERR9: error: unsupported option '-msign-return-address=non-leaf' for target 'aarch64-unknown-linux-pauthtest' // RUN: %clang -### -c --target=aarch64-linux -mabi=pauthtest -msign-return-address=none %s // RUN: %clang -### -c --target=aarch64-linux-pauthtest -msign-return-address=none %s diff --git a/clang/test/Driver/fuchsia.c b/clang/test/Driver/fuchsia.c index d0fec18..99e5018 100644 --- a/clang/test/Driver/fuchsia.c +++ b/clang/test/Driver/fuchsia.c @@ -130,6 +130,11 @@ // RUN: -resource-dir=%S/Inputs/resource_dir_with_per_target_subdir \ // RUN: -fuse-ld=ld \ // RUN: | FileCheck %s -check-prefix=CHECK-SAFESTACK +// RUN: %clang -### %s --target=x86_64-unknown-fuchsia -m32 \ +// RUN: -fsanitize=safe-stack 2>&1 \ +// RUN: -resource-dir=%S/Inputs/resource_dir_with_per_target_subdir \ +// RUN: -fuse-ld=ld \ +// RUN: | FileCheck %s -check-prefix=CHECK-SAFESTACK // CHECK-SAFESTACK: "-resource-dir" "[[RESOURCE_DIR:[^"]+]]" // CHECK-SAFESTACK: "-fsanitize=safe-stack" // CHECK-SAFESTACK-NOT: "[[RESOURCE_DIR]]{{/|\\\\}}lib{{/|\\\\}}x86_64-unknown-fuchsia{{/|\\\\}}libclang_rt.safestack.a" diff --git a/clang/test/Frontend/aarch64-ignore-branch-protection-attribute.c b/clang/test/Frontend/aarch64-ignore-branch-protection-attribute.c index 32cc98d..e6605ce 100644 --- a/clang/test/Frontend/aarch64-ignore-branch-protection-attribute.c +++ b/clang/test/Frontend/aarch64-ignore-branch-protection-attribute.c @@ -1,7 +1,11 @@ // REQUIRES: aarch64-registered-target -// RUN: %clang -target aarch64-linux-pauthtest %s -S -emit-llvm -o - 2>&1 | FileCheck --implicit-check-not=warning: %s -// RUN: %clang -target aarch64 -fptrauth-returns %s -S -emit-llvm -o - 2>&1 | FileCheck --implicit-check-not=warning: %s +// RUN: %clang -target aarch64-linux-pauthtest %s -S -emit-llvm -o - 2>&1 | FileCheck --implicit-check-not=warning: %s +// RUN: not %clang -target aarch64 -fptrauth-returns %s -S -emit-llvm -o - 2>&1 | FileCheck --implicit-check-not=warning: --check-prefix=PTRAUTH-RETURNS %s + +// Clang fails early, no LLVM IR output produced. +// PTRAUTH-RETURNS: clang: error: unsupported option '-fptrauth-returns' for target 'aarch64' +// PTRAUTH-RETURNS-NOT: attributes /// Unsupported with pauthtest, warning emitted __attribute__((target("branch-protection=pac-ret"))) void f1() {} diff --git a/clang/test/Frontend/diag-wrap-colors.cpp b/clang/test/Frontend/diag-wrap-colors.cpp new file mode 100644 index 0000000..e3dccb1 --- /dev/null +++ b/clang/test/Frontend/diag-wrap-colors.cpp @@ -0,0 +1,6 @@ +// RUN: not %clang_cc1 %s -fmessage-length=50 -fcolor-diagnostics -fno-show-source-location -o - 2>&1 | FileCheck %s + +struct F { + float a : 10; +}; +// CHECK: bit-field 'a' has non-integral type 'float' diff --git a/clang/test/Interpreter/pretty-print.c b/clang/test/Interpreter/pretty-print.c index d0712fb..9a7bf75 100644 --- a/clang/test/Interpreter/pretty-print.c +++ b/clang/test/Interpreter/pretty-print.c @@ -78,14 +78,16 @@ int * null_ptr = (int*)0; null_ptr union U { int I; float F; } u; u.I = 12; u.I // CHECK-NEXT: (int) 12 -// TODO: _Bool, _Complex, _Atomic, and _BitInt -// struct S1{} s1; s1 -// TODO-CHECK-NEXT: (S1 &) @0x{{[0-9a-f]+}} +struct S1{} s1; s1 +// CHECK-NEXT: (S1 &) @0x{{[0-9a-f]+}} + +struct S2 {int d;} E = {22}; E +// CHECK-NEXT: (S2 &) @0x{{[0-9a-f]+}} -// struct S2 {int d;} E = {22}; E -// TODO-CHECK-NEXT: (struct S2 &) @0x{{[0-9a-f]+}} -// E.d -// TODO-CHECK-NEXT: (int) 22 +E.d +// CHECK-NEXT: (int) 22 + +// TODO: _Bool, _Complex, _Atomic, and _BitInt // ----------------------------------------------------------------------------- // Tentative definition handling (C99 6.9.2) diff --git a/clang/test/OpenMP/task_ast_print.cpp b/clang/test/OpenMP/task_ast_print.cpp index 30fb7ab..b059f18 100644 --- a/clang/test/OpenMP/task_ast_print.cpp +++ b/clang/test/OpenMP/task_ast_print.cpp @@ -1,8 +1,10 @@ // RUN: %clang_cc1 -verify -Wno-vla -fopenmp -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -verify -Wno-vla %s -ast-print | FileCheck %s // RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -verify -Wno-vla %s -ast-print | FileCheck %s // RUN: %clang_cc1 -triple x86_64-pc-linux-gnu -fopenmp -ast-dump %s | FileCheck %s --check-prefix=DUMP @@ -101,8 +103,8 @@ T tmain(T argc, T *argv) { a = 2; #pragma omp task default(none), private(argc, b) firstprivate(argv) shared(d) if (argc > 0) final(S<T>::TS > 0) priority(argc) affinity(argc, argv[b:argc], arr[:], ([argc][sizeof(T)])argv) foo(); -#pragma omp taskgroup task_reduction(-: argc) -#pragma omp task if (C) mergeable priority(C) in_reduction(-: argc) +#pragma omp taskgroup task_reduction(+: argc) +#pragma omp task if (C) mergeable priority(C) in_reduction(+: argc) foo(); return 0; } @@ -119,8 +121,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<T>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(T)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(C) mergeable priority(C) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(C) mergeable priority(C) in_reduction(+: argc) // CHECK-NEXT: foo() // CHECK: template<> int tmain<int, 5>(int argc, int *argv) { // CHECK-NEXT: int b = argc, c, d, e, f, g; @@ -134,8 +136,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<int>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(int)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(5) mergeable priority(5) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(5) mergeable priority(5) in_reduction(+: argc) // CHECK-NEXT: foo() // CHECK: template<> long tmain<long, 1>(long argc, long *argv) { // CHECK-NEXT: long b = argc, c, d, e, f, g; @@ -149,8 +151,8 @@ T tmain(T argc, T *argv) { // CHECK-NEXT: a = 2; // CHECK-NEXT: #pragma omp task default(none) private(argc,b) firstprivate(argv) shared(d) if(argc > 0) final(S<long>::TS > 0) priority(argc) affinity(argc,argv[b:argc],arr[:],([argc][sizeof(long)])argv) // CHECK-NEXT: foo() -// CHECK-NEXT: #pragma omp taskgroup task_reduction(-: argc) -// CHECK-NEXT: #pragma omp task if(1) mergeable priority(1) in_reduction(-: argc) +// CHECK-NEXT: #pragma omp taskgroup task_reduction(+: argc) +// CHECK-NEXT: #pragma omp task if(1) mergeable priority(1) in_reduction(+: argc) // CHECK-NEXT: foo() enum Enum {}; @@ -199,6 +201,14 @@ int main(int argc, char **argv) { #pragma omp task depend(inout: omp_all_memory) foo(); // CHECK-NEXT: foo(); +#ifdef OMP60 +#pragma omp task threadset(omp_pool) +#pragma omp task threadset(omp_team) + foo(); +#endif + // CHECK60: #pragma omp task threadset(omp_pool) + // CHECK60: #pragma omp task threadset(omp_team) + // CHECK60-NEXT: foo(); return tmain<int, 5>(b, &b) + tmain<long, 1>(x, &x); } diff --git a/clang/test/OpenMP/task_codegen.cpp b/clang/test/OpenMP/task_codegen.cpp index c3e6d9e6b..ba8e694 100644 --- a/clang/test/OpenMP/task_codegen.cpp +++ b/clang/test/OpenMP/task_codegen.cpp @@ -41,6 +41,9 @@ // RUN: -emit-llvm -o - -DOMP51 | FileCheck %s \ // RUN: --implicit-check-not="{{__kmpc|__tgt}}" +// RUN: %clang_cc1 -verify -Wno-vla -triple x86_64-apple-darwin10 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK6 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK6 // expected-no-diagnostics #ifndef HEADER @@ -65,6 +68,7 @@ struct S { S(const S &s) : a(s.a) {} ~S() {} }; + int a; int main() { char b; @@ -147,6 +151,7 @@ int main() { + // s1 = S(); @@ -215,6 +220,19 @@ void test_omp_all_memory() } } #endif // OMP51 + +#ifdef OMP60 +void test_threadset() +{ +#pragma omp task threadset(omp_team) + { + } +#pragma omp task threadset(omp_pool) + { + } +} +#endif // OMP60 + #endif // CHECK1-LABEL: define {{[^@]+}}@main // CHECK1-SAME: () #[[ATTR0:[0-9]+]] { @@ -10243,3 +10261,18 @@ void test_omp_all_memory() // CHECK4-51-NEXT: call void @__cxx_global_var_init() // CHECK4-51-NEXT: ret void // +// CHECK6-LABEL: define void @_Z14test_threadsetv() +// CHECK6-NEXT: entry: +// CHECK6-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_23:%.*]], align 1 +// CHECK6-NEXT: [[AGG_CAPTURED2:%.*]] = alloca [[STRUCT_ANON_25:%.*]], align 1 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: [[TMP0:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %omp_global_thread_num, i32 1, i64 40, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %0, i32 0, i32 0 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: call i32 @__kmpc_omp_task(ptr @1, i32 %omp_global_thread_num1, ptr %0) +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR2:[0-9]+]]) +// CHECK6-NEXT: [[TMP3:%.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %omp_global_thread_num3, i32 129, i64 40, i64 1, ptr @.omp_task_entry..[[ENTRY2:[0-9]+]]) +// CHECK6-NEXT: getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %3, i32 0, i32 0 +// CHECK6-NEXT: call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR2:[0-9]+]]) +// CHECK6-NEXT: call i32 @__kmpc_omp_task(ptr @1, i32 %omp_global_thread_num4, ptr %3) +// CHECK6-NEXT: ret void diff --git a/clang/test/OpenMP/task_threadset_messages.cpp b/clang/test/OpenMP/task_threadset_messages.cpp new file mode 100755 index 0000000..f553a2d --- /dev/null +++ b/clang/test/OpenMP/task_threadset_messages.cpp @@ -0,0 +1,99 @@ +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp -fopenmp-version=45 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp -fopenmp-version=50 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp51 -fopenmp -fopenmp-version=51 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected -DOMP60 -fopenmp -fopenmp-version=60 -std=c++11 -ferror-limit 200 -o - %s + +// RUN: %clang_cc1 -verify=expected,omp45 -fopenmp-simd -fopenmp-version=45 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp50 -fopenmp-simd -fopenmp-version=50 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected,omp51 -fopenmp-simd -fopenmp-version=51 -std=c++11 -ferror-limit 200 -o - %s +// RUN: %clang_cc1 -verify=expected -DOMP60 -fopenmp-simd -fopenmp-version=60 -std=c++11 -ferror-limit 200 -o - %s + +#ifdef OMP60 +struct ComplexStruct { + int data[10]; + struct InnerStruct { + float value; + } inner; +}; + +// Template class with member functions using 'threadset'. +template <typename T> +class TemplateClass { +public: + void foo() { + #pragma omp task threadset(omp_pool) + { + T temp; + } + } + void bar() { + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) {} + } +}; + +// Valid uses of 'threadset' with 'omp_pool' and 'omp_team' in task directive. +void test_task_threadset_valid() { + int a; + #pragma omp task threadset(omp_pool) + #pragma omp task threadset(omp_team) + #pragma omp task threadset(omp_pool) if(1) + #pragma omp task threadset(omp_team) priority(5) + #pragma omp task threadset(omp_pool) depend(out: a) + #pragma omp parallel + { + #pragma omp task threadset(omp_pool) + { + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 5; ++i) {} + } + } + + TemplateClass<int> obj; + obj.foo(); + obj.bar(); +} + +// Invalid uses of 'threadset' with incorrect arguments in task directive. +void test_task_threadset_invalid_args() { + #pragma omp task threadset(invalid_arg) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + #pragma omp task threadset(123) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + #pragma omp task threadset(omp_pool, omp_team) // expected-error {{expected ')'}} expected-note {{to match this '('}} + #pragma omp task threadset() // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + {} +} + +// Valid uses of 'threadset' with 'omp_pool' and 'omp_team' in taskloop directive. +void test_taskloop_threadset_valid() { + #pragma omp taskloop threadset(omp_pool) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool) grainsize(5) + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_team) num_tasks(2) + for (int i = 0; i < 10; ++i) {} +} + +// Invalid uses of 'threadset' with incorrect arguments in taskloop directive. +void test_taskloop_threadset_invalid_args() { + #pragma omp taskloop threadset(invalid_arg) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(123) // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool, omp_team) // expected-error {{expected ')'}} expected-note {{to match this '('}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset() // expected-error {{expected 'omp_pool' or 'omp_team' in OpenMP clause 'threadset'}} + for (int i = 0; i < 10; ++i) {} +} + +#else +void test_threadset_not_supported() { + #pragma omp task threadset(omp_pool) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} + #pragma omp task threadset(omp_team) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp task'}} + #pragma omp taskloop threadset(omp_team) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} + for (int i = 0; i < 10; ++i) {} + #pragma omp taskloop threadset(omp_pool) // omp45-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp50-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} omp51-error {{unexpected OpenMP clause 'threadset' in directive '#pragma omp taskloop'}} + for (int i = 0; i < 10; ++i) {} +} +#endif diff --git a/clang/test/OpenMP/taskloop_ast_print.cpp b/clang/test/OpenMP/taskloop_ast_print.cpp index 1b6d724..e4bf20a 100644 --- a/clang/test/OpenMP/taskloop_ast_print.cpp +++ b/clang/test/OpenMP/taskloop_ast_print.cpp @@ -1,8 +1,10 @@ // RUN: %clang_cc1 -verify -fopenmp -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp -std=c++11 -include-pch %t -verify %s -ast-print | FileCheck %s // RUN: %clang_cc1 -verify -fopenmp-simd -ast-print %s | FileCheck %s +// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=60 -DOMP60 -ast-print %s | FileCheck %s --check-prefix=CHECK60 // RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -std=c++11 -include-pch %t -verify %s -ast-print | FileCheck %s // expected-no-diagnostics @@ -87,6 +89,20 @@ int main(int argc, char **argv) { // CHECK-NEXT: #pragma omp cancel taskgroup // CHECK-NEXT: #pragma omp cancellation point taskgroup // CHECK-NEXT: foo(); +#ifdef OMP60 +#pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) { +#pragma omp taskloop threadset(omp_pool) + for (int j = 0; j < 10; ++j) { + foo(); + } +} +#endif + // CHECK60: #pragma omp taskloop threadset(omp_team) + // CHECK60-NEXT: for (int i = 0; i < 10; ++i) { + // CHECK60: #pragma omp taskloop threadset(omp_pool) + // CHECK60-NEXT: for (int j = 0; j < 10; ++j) { + // CHECK60-NEXT: foo(); return (tmain<int, 5>(argc) + tmain<char, 1>(argv[0][0])); } diff --git a/clang/test/OpenMP/taskloop_codegen.cpp b/clang/test/OpenMP/taskloop_codegen.cpp index 69f8d3b..d119760 100644 --- a/clang/test/OpenMP/taskloop_codegen.cpp +++ b/clang/test/OpenMP/taskloop_codegen.cpp @@ -5,7 +5,12 @@ // RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -x c++ -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s // RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s + // SIMD-ONLY0-NOT: {{__kmpc|__tgt}} + +// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK6 +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s +// RUN: %clang_cc1 -fopenmp -fopenmp-version=60 -DOMP60 -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK6 // expected-no-diagnostics #ifndef HEADER #define HEADER @@ -241,4 +246,52 @@ void taskloop_with_class() { } } +#ifdef OMP60 +void test_threadset() +{ +#pragma omp taskloop threadset(omp_team) + for (int i = 0; i < 10; ++i) { + } +#pragma omp taskloop threadset(omp_pool) + for (int i = 0; i < 10; ++i) { + } +} +#endif // OMP60 +// CHECK6-LABEL: define void @_Z14test_threadsetv() +// CHECK6-NEXT: entry: +// CHECK6-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 1 +// CHECK6-NEXT: %[[TMP:.*]] = alloca i32, align 4 +// CHECK6-NEXT: [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1 +// CHECK6-NEXT: %[[TMP2:.*]] = alloca i32, align 4 +// CHECK6-NEXT: %[[TID0:.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB_PTR:[0-9]+]]) +// CHECK6-NEXT: call void @__kmpc_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: %[[TID1:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[TID0:.*]], i32 1, i64 80, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: %[[TID2:.*]] = getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %[[TID1:.*]], i32 0, i32 0 +// CHECK6-NEXT: %[[TID3:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 5 +// CHECK6-NEXT: store i64 0, ptr %[[TID3:.*]], align 8 +// CHECK6-NEXT: %[[TID4:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 6 +// CHECK6-NEXT: store i64 9, ptr %[[TID4:.*]], align 8 +// CHECK6-NEXT: %[[TID5:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 7 +// CHECK6-NEXT: store i64 1, ptr %[[TID5:.*]], align 8 +// CHECK6-NEXT: %[[TID6:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID2:.*]], i32 0, i32 9 +// CHECK6-NEXT: call void @llvm.memset.p0.i64(ptr align 8 %[[TID6:.*]], i8 0, i64 8, i1 false) +// CHECK6-NEXT: %[[TID7:.*]] = load i64, ptr %[[TID5:.*]], align 8 +// CHECK6-NEXT: call void @__kmpc_taskloop(ptr @1, i32 %[[TID0:.*]], ptr %[[TID1:.*]], i32 1, ptr %[[TID3:.*]], ptr %4, i64 %[[TID7:.*]], i32 1, i32 0, i64 0, ptr null) +// CHECK6-NEXT: call void @__kmpc_end_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: call void @__kmpc_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: %[[TID8:.*]] = call ptr @__kmpc_omp_task_alloc(ptr @1, i32 %[[TID0:.*]], i32 129, i64 80, i64 1, ptr @.omp_task_entry..[[ENTRY1:[0-9]+]]) +// CHECK6-NEXT: %[[TID9:.*]] = getelementptr inbounds nuw %struct.kmp_task_t_with_privates{{.*}}, ptr %[[TID8:.*]], i32 0, i32 0 +// CHECK6-NEXT: %[[TID10:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 5 +// CHECK6-NEXT: store i64 0, ptr %[[TID10:.*]], align 8 +// CHECK6-NEXT: %[[TID11:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 6 +// CHECK6-NEXT: store i64 9, ptr %[[TID11:.*]], align 8 +// CHECK6-NEXT: %[[TID12:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 7 +// CHECK6-NEXT: store i64 1, ptr %[[TID12:.*]], align 8 +// CHECK6-NEXT: %[[TID13:.*]] = getelementptr inbounds nuw %struct.kmp_task_t{{.*}}, ptr %[[TID9:.*]], i32 0, i32 9 +// CHECK6-NEXT: call void @llvm.memset.p0.i64(ptr align 8 [[TID13:.*]], i8 0, i64 8, i1 false) +// CHECK6-NEXT: %[[TID14:.*]] = load i64, ptr [[TID12:.*]], align 8 +// CHECK6-NEXT: call void @__kmpc_taskloop(ptr @1, i32 %[[TID0:.*]], ptr %[[TID8:.*]], i32 1, ptr %[[TID10:.*]], ptr %[[TID11:.*]], i64 %[[TID14:.*]], i32 1, i32 0, i64 0, ptr null) +// CHECK6-NEXT: call void @__kmpc_end_taskgroup(ptr @1, i32 %[[TID0:.*]]) +// CHECK6-NEXT: ret void + #endif diff --git a/clang/test/Preprocessor/bpf-predefined-macros.c b/clang/test/Preprocessor/bpf-predefined-macros.c index cd8a2ec..a9ae8c5 100644 --- a/clang/test/Preprocessor/bpf-predefined-macros.c +++ b/clang/test/Preprocessor/bpf-predefined-macros.c @@ -70,6 +70,9 @@ int u; #ifdef __BPF_FEATURE_LOAD_ACQ_STORE_REL int v; #endif +#ifdef __BPF_FEATURE_GOTOX +int w; +#endif // CHECK: int b; // CHECK: int c; @@ -110,6 +113,7 @@ int v; // CPU_V4: int u; // CPU_V4: int v; +// CPU_V4: int w; // CPU_GENERIC: int g; diff --git a/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl b/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl new file mode 100644 index 0000000..3b12faf --- /dev/null +++ b/clang/test/SemaHLSL/BuiltIns/WaveActiveMin.hlsl @@ -0,0 +1,29 @@ +// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.6-library %s -emit-llvm-only -disable-llvm-passes -verify + +int test_too_few_arg() { + return __builtin_hlsl_wave_active_min(); + // expected-error@-1 {{too few arguments to function call, expected 1, have 0}} +} + +float2 test_too_many_arg(float2 p0) { + return __builtin_hlsl_wave_active_min(p0, p0); + // expected-error@-1 {{too many arguments to function call, expected 1, have 2}} +} + +bool test_expr_bool_type_check(bool p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'bool'}} +} + +bool2 test_expr_bool_vec_type_check(bool2 p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'bool2' (aka 'vector<bool, 2>')}} +} + +struct S { float f; }; + +S test_expr_struct_type_check(S p0) { + return __builtin_hlsl_wave_active_min(p0); + // expected-error@-1 {{invalid operand of type 'S' where a scalar or vector is required}} +} + diff --git a/clang/test/SemaTemplate/concepts.cpp b/clang/test/SemaTemplate/concepts.cpp index becf546..c90af41 100644 --- a/clang/test/SemaTemplate/concepts.cpp +++ b/clang/test/SemaTemplate/concepts.cpp @@ -1632,3 +1632,29 @@ void fn3() { } } + +namespace GH165238 { + +namespace std { +template <typename, typename _Tp> +concept output_iterator = requires(_Tp __t) { __t; }; +template <typename _Out> struct basic_format_context { + static_assert(output_iterator<_Out, int>); + using char_type = _Out; +}; +template <typename> class basic_format_parse_context; +template <typename, typename _Context, typename _Formatter, + typename = basic_format_parse_context<typename _Context::char_type>> +concept __parsable_with = requires(_Formatter __f) { __f; }; +template <typename _Tp, typename _CharT, + typename _Context = basic_format_context<_CharT>> +concept __formattable_impl = __parsable_with<_Tp, _Context, _Context>; +template <typename _Tp, typename _CharT> +concept formattable = __formattable_impl<_Tp, _CharT>; +} // namespace std +struct { + void operator()(std::formattable<char> auto); +} call; +void foo() { call(""); } + +} |