samvv/bolt
1
0
Fork 0
Code Issues 24 Pull requests Projects Releases Packages Wiki Activity Actions
bolt/deps/llvm-18.1.8/clang/test/CodeGenCXX/attr-target-clones-aarch64.cpp
Sam Vervaeck 174b6f4d4e
Embed LLVM 18.1.8
2025-02-14 19:21:04 +01:00

195 lines
10 KiB
C++
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals --include-generated-funcs
// RUN: %clang_cc1 -std=c++11 -triple aarch64-linux-gnu -emit-llvm %s -o - | FileCheck %s
int __attribute__((target_clones("ls64_v+fp16", "default"))) foo_ovl(int) { return 1; }
int __attribute__((target_clones("ls64_accdata+ls64"))) foo_ovl(void) { return 2; }
int bar() {
return foo_ovl(1) + foo_ovl();
}
template <typename T1, typename T2> struct MyClass {
int __attribute__((target_clones("frintts", "ssbs+sme-f64f64"))) foo_tml() { return 1; }
};
template <typename T> struct MyClass<int, T> {
int __attribute__((target_clones("frintts", "ssbs+sme-f64f64"))) foo_tml() { return 2; }
};
template <typename T> struct MyClass<float, T> {
int foo_tml() { return 3; }
};
template <> struct MyClass<double, float> {
int __attribute__((target_clones("default"))) foo_tml() { return 4; }
};
void run_foo_tml() {
MyClass<short, short> Mc1;
Mc1.foo_tml();
MyClass<int, short> Mc2;
Mc2.foo_tml();
MyClass<float, short> Mc3;
Mc3.foo_tml();
MyClass<double, float> Mc4;
Mc4.foo_tml();
}
// CHECK: @__aarch64_cpu_features = external dso_local global { i64 }
// CHECK: @_Z7foo_ovli = weak_odr ifunc i32 (i32), ptr @_Z7foo_ovli.resolver
// CHECK: @_Z7foo_ovlv = weak_odr ifunc i32 (), ptr @_Z7foo_ovlv.resolver
// CHECK: @_ZN7MyClassIssE7foo_tmlEv = weak_odr ifunc i32 (ptr), ptr @_ZN7MyClassIssE7foo_tmlEv.resolver
// CHECK: @_ZN7MyClassIisE7foo_tmlEv = weak_odr ifunc i32 (ptr), ptr @_ZN7MyClassIisE7foo_tmlEv.resolver
// CHECK-LABEL: @_Z7foo_ovli._Mfp16Mls64_v(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[TMP0:%.*]], ptr [[DOTADDR]], align 4
// CHECK-NEXT: ret i32 1
// CHECK-LABEL: @_Z7foo_ovli.default(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[TMP0:%.*]], ptr [[DOTADDR]], align 4
// CHECK-NEXT: ret i32 1
// CHECK-LABEL: @_Z7foo_ovli.resolver(
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 4503599627436032
// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 4503599627436032
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @_Z7foo_ovli._Mfp16Mls64_v
// CHECK: resolver_else:
// CHECK-NEXT: ret ptr @_Z7foo_ovli
// CHECK-LABEL: @_Z7foo_ovlv._Mls64Mls64_accdata(
// CHECK-NEXT: entry:
// CHECK-NEXT: ret i32 2
// CHECK-LABEL: @_Z7foo_ovlv.default(
// CHECK-NEXT: entry:
// CHECK-NEXT: ret i32 2
// CHECK-LABEL: @_Z7foo_ovlv.resolver(
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 11258999068426240
// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 11258999068426240
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @_Z7foo_ovlv._Mls64Mls64_accdata
// CHECK: resolver_else:
// CHECK-NEXT: ret ptr @_Z7foo_ovlv.default
// CHECK-LABEL: @_Z3barv(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_Z7foo_ovli(i32 noundef 1)
// CHECK-NEXT: [[CALL1:%.*]] = call noundef i32 @_Z7foo_ovlv()
// CHECK-NEXT: [[ADD:%.*]] = add nsw i32 [[CALL]], [[CALL1]]
// CHECK-NEXT: ret i32 [[ADD]]
// CHECK-LABEL: @_Z11run_foo_tmlv(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[MC1:%.*]] = alloca [[STRUCT_MYCLASS:%.*]], align 1
// CHECK-NEXT: [[MC2:%.*]] = alloca [[STRUCT_MYCLASS_0:%.*]], align 1
// CHECK-NEXT: [[MC3:%.*]] = alloca [[STRUCT_MYCLASS_1:%.*]], align 1
// CHECK-NEXT: [[MC4:%.*]] = alloca [[STRUCT_MYCLASS_2:%.*]], align 1
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_ZN7MyClassIssE7foo_tmlEv(ptr noundef nonnull align 1 dereferenceable(1) [[MC1]])
// CHECK-NEXT: [[CALL1:%.*]] = call noundef i32 @_ZN7MyClassIisE7foo_tmlEv(ptr noundef nonnull align 1 dereferenceable(1) [[MC2]])
// CHECK-NEXT: [[CALL2:%.*]] = call noundef i32 @_ZN7MyClassIfsE7foo_tmlEv(ptr noundef nonnull align 1 dereferenceable(1) [[MC3]])
// CHECK-NEXT: [[CALL3:%.*]] = call noundef i32 @_ZN7MyClassIdfE7foo_tmlEv(ptr noundef nonnull align 1 dereferenceable(1) [[MC4]])
// CHECK-NEXT: ret void
// CHECK-LABEL: @_ZN7MyClassIssE7foo_tmlEv.resolver(
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 36310271995674624
// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 36310271995674624
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @_ZN7MyClassIssE7foo_tmlEv._MssbsMsme-f64f64
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 16777216
// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 16777216
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
// CHECK-NEXT: ret ptr @_ZN7MyClassIssE7foo_tmlEv._Mfrintts
// CHECK: resolver_else2:
// CHECK-NEXT: ret ptr @_ZN7MyClassIssE7foo_tmlEv
// CHECK-LABEL: @_ZN7MyClassIisE7foo_tmlEv.resolver(
// CHECK-NEXT: resolver_entry:
// CHECK-NEXT: call void @__init_cpu_features_resolver()
// CHECK-NEXT: [[TMP0:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP1:%.*]] = and i64 [[TMP0]], 36310271995674624
// CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 36310271995674624
// CHECK-NEXT: [[TMP3:%.*]] = and i1 true, [[TMP2]]
// CHECK-NEXT: br i1 [[TMP3]], label [[RESOLVER_RETURN:%.*]], label [[RESOLVER_ELSE:%.*]]
// CHECK: resolver_return:
// CHECK-NEXT: ret ptr @_ZN7MyClassIisE7foo_tmlEv._MssbsMsme-f64f64
// CHECK: resolver_else:
// CHECK-NEXT: [[TMP4:%.*]] = load i64, ptr @__aarch64_cpu_features, align 8
// CHECK-NEXT: [[TMP5:%.*]] = and i64 [[TMP4]], 16777216
// CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[TMP5]], 16777216
// CHECK-NEXT: [[TMP7:%.*]] = and i1 true, [[TMP6]]
// CHECK-NEXT: br i1 [[TMP7]], label [[RESOLVER_RETURN1:%.*]], label [[RESOLVER_ELSE2:%.*]]
// CHECK: resolver_return1:
// CHECK-NEXT: ret ptr @_ZN7MyClassIisE7foo_tmlEv._Mfrintts
// CHECK: resolver_else2:
// CHECK-NEXT: ret ptr @_ZN7MyClassIisE7foo_tmlEv
// CHECK-LABEL: @_ZN7MyClassIfsE7foo_tmlEv(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 3
// CHECK-LABEL: @_ZN7MyClassIdfE7foo_tmlEv(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 4
// CHECK-LABEL: @_ZN7MyClassIssE7foo_tmlEv._Mfrintts(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 1
// CHECK-LABEL: @_ZN7MyClassIssE7foo_tmlEv._MssbsMsme-f64f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 1
// CHECK-LABEL: @_ZN7MyClassIssE7foo_tmlEv.default(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 1
// CHECK-LABEL: @_ZN7MyClassIisE7foo_tmlEv._Mfrintts(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 2
// CHECK-LABEL: @_ZN7MyClassIisE7foo_tmlEv._MssbsMsme-f64f64(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 2
// CHECK-LABEL: @_ZN7MyClassIisE7foo_tmlEv.default(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[THIS_ADDR:%.*]] = alloca ptr, align 8
// CHECK-NEXT: store ptr [[THIS:%.*]], ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: [[THIS1:%.*]] = load ptr, ptr [[THIS_ADDR]], align 8
// CHECK-NEXT: ret i32 2
// CHECK: attributes #0 = { mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+fp-armv8,+fullfp16,+neon" }
// CHECK: attributes #1 = { mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
// CHECK: attributes #2 = { mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+ls64" }
// CHECK: attributes #3 = { mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+fptoint" }
// CHECK: attributes #4 = { mustprogress noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-features"="+bf16,+sme,+sme-f64f64" }
Reference in a new issue View git blame Copy permalink