mirror of
https://github.com/llvm/llvm-project.git
synced 2025-04-25 22:06:06 +00:00
4583f6d344
the `ptx_kernel` calling convention is a more idiomatic and standard way of specifying a NVPTX kernel than using the metadata which is not supposed to change the meaning of the program. Further, checking the calling convention is significantly faster than traversing the metadata, improving compile time. This change updates the clang and mlir frontends as well as the NVPTXCtorDtorLowering pass to emit kernels using the calling convention. In addition, this updates all NVPTX unit tests to use the calling convention as well.
24 lines
1.1 KiB
C
24 lines
1.1 KiB
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
|
|
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -o - | FileCheck %s
|
|
|
|
// CHECK: Function Attrs: convergent noinline nounwind optnone
|
|
// CHECK-LABEL: define {{[^@]+}}@foo
|
|
// CHECK-SAME: (ptr noundef [[RET:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[RET_ADDR:%.*]] = alloca ptr, align 8
|
|
// CHECK-NEXT: store ptr [[RET]], ptr [[RET_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[RET_ADDR]], align 8
|
|
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
__attribute__((nvptx_kernel)) void foo(int *ret) {
|
|
*ret = 1;
|
|
}
|
|
|
|
//.
|
|
// CHECK: attributes #[[ATTR0]] = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="sm_61" "target-features"="+ptx32,+sm_61" }
|
|
//.
|
|
// CHECK: [[META0:![0-9]+]] = !{i32 1, !"wchar_size", i32 4}
|
|
// CHECK: [[META1:![0-9]+]] = !{!"{{.*}}clang version {{.*}}"}
|
|
//.
|