srenblad
/
artiq
forked from M-Labs/artiq
1
0
Fork 0
Code Pull Requests Activity

subkernel: separate tags and data

This commit is contained in:
mwojcik 2023-10-17 17:46:56 +08:00 committed by Sébastien Bourdeauducq
parent 6705c9fbfb
commit b168f0bb4b
11 changed files with 134 additions and 88 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
artiq/compiler/ir.py
View File

@ -764,6 +764,23 @@ class GetOptArgFromRemote(GetArgFromRemote):
def opcode(self):
return "getoptargfromremote({})".format(repr(self.arg_name))
class SubkernelAwaitArgs(Instruction):
"""
A builtin instruction that takes min and max received messages as operands,
and a list of received types.
:ivar arg_types: (list of types) types of passed arguments (including optional)
"""
"""
:param arg_types: (list of types) types of passed arguments (including optional)
"""
def __init__(self, operands, arg_types, name=None):
assert isinstance(arg_types, list)
self.arg_types = arg_types
super().__init__(operands, builtins.TNone(), name)
class GetAttr(Instruction):
"""
An intruction that loads an attribute from an object,

5
artiq/compiler/transforms/artiq_ir_generator.py
View File

@ -2614,8 +2614,9 @@ class ARTIQIRGenerator(algorithm.Visitor):
min_args = ir.Constant(len(fn_typ.args)-offset, builtins.TInt8())
max_args = ir.Constant(fn_typ.arity()-offset, builtins.TInt8())
rcvd_count = self.append(ir.Builtin("subkernel_await_args", [min_args, max_args], builtins.TNone()))
arg_types = list(fn_typ.args.items())[offset:]
arg_types = list(fn_typ.args.items())[offset:]
arg_type_list = [a[1] for a in arg_types] + [a[1] for a in fn_typ.optargs.items()]
rcvd_count = self.append(ir.SubkernelAwaitArgs([min_args, max_args], arg_type_list))
# obligatory arguments
for arg_name, arg_type in arg_types:
args[index] = self.append(ir.GetArgFromRemote(arg_name, arg_type,

38
artiq/compiler/transforms/llvm_ir_generator.py
View File

@ -405,7 +405,7 @@ class LLVMIRGenerator:
elif name == "subkernel_await_finish":
llty = ll.FunctionType(llvoid, [lli32, lli64])
elif name == "subkernel_await_message":
llty = ll.FunctionType(lli8, [lli32, lli64, lli8, lli8])
llty = ll.FunctionType(lli8, [lli32, lli64, llsliceptr, lli8, lli8])
# with now-pinning
elif name == "now":
@ -1400,12 +1400,6 @@ class LLVMIRGenerator:
return self.llbuilder.call(self.llbuiltin("delay_mu"), [llinterval])
elif insn.op == "end_catch":
return self.llbuilder.call(self.llbuiltin("__artiq_end_catch"), [])
elif insn.op == "subkernel_await_args":
llmin = self.map(insn.operands[0])
llmax = self.map(insn.operands[1])
return self.llbuilder.call(self.llbuiltin("subkernel_await_message"),
[ll.Constant(lli32, 0), ll.Constant(lli64, 10_000), llmin, llmax],
name="subkernel.await.args")
elif insn.op == "subkernel_await_finish":
llsid = self.map(insn.operands[0])
lltimeout = self.map(insn.operands[1])
@ -1414,7 +1408,9 @@ class LLVMIRGenerator:
elif insn.op == "subkernel_retrieve_return":
llsid = self.map(insn.operands[0])
lltimeout = self.map(insn.operands[1])
self.llbuilder.call(self.llbuiltin("subkernel_await_message"), [llsid, lltimeout, ll.Constant(lli8, 1), ll.Constant(lli8, 1)],
lltagptr = self._build_subkernel_tags([insn.type])
self.llbuilder.call(self.llbuiltin("subkernel_await_message"),
[llsid, lltimeout, lltagptr, ll.Constant(lli8, 1), ll.Constant(lli8, 1)],
name="subkernel.await.message")
llstackptr = self.llbuilder.call(self.llbuiltin("llvm.stacksave"), [],
name="subkernel.arg.stack")
@ -1426,6 +1422,14 @@ class LLVMIRGenerator:
else:
assert False
def process_SubkernelAwaitArgs(self, insn):
llmin = self.map(insn.operands[0])
llmax = self.map(insn.operands[1])
lltagptr = self._build_subkernel_tags(insn.arg_types)
return self.llbuilder.call(self.llbuiltin("subkernel_await_message"),
[ll.Constant(lli32, 0), ll.Constant(lli64, 10_000), lltagptr, llmin, llmax],
name="subkernel.await.args")
def process_Closure(self, insn):
llenv = self.map(insn.environment())
llenv = self.llbuilder.bitcast(llenv, llptr)
@ -1505,6 +1509,24 @@ class LLVMIRGenerator:
return llfun, list(llargs), llarg_attrs, llcallstackptr
def _build_subkernel_tags(self, tag_list):
def ret_error_handler(typ):
printer = types.TypePrinter()
note = diagnostic.Diagnostic("note",
"value of type {type}",
{"type": printer.name(typ)},
fun_loc)
diag = diagnostic.Diagnostic("error",
"type {type} is not supported in subkernels",
{"type": printer.name(fun_type.ret)},
fun_loc, notes=[note])
self.engine.process(diag)
tag = b"".join([ir.rpc_tag(arg_type, ret_error_handler) for arg_type in tag_list])
lltag = self.llconst_of_const(ir.Constant(tag, builtins.TStr()))
lltagptr = self.llbuilder.alloca(lltag.type)
self.llbuilder.store(lltag, lltagptr)
return lltagptr
def _build_rpc_recv(self, ret, llstackptr, llnormalblock=None, llunwindblock=None):
# T result = {
# void *ret_ptr = alloca(sizeof(T));

6
artiq/firmware/ksupport/lib.rs
View File

@ -138,7 +138,7 @@ extern fn rpc_send_async(service: u32, tag: &CSlice<u8>, data: *const *const ())
rpc_queue::enqueue(|mut slice| {
let length = {
let mut writer = Cursor::new(&mut slice[4..]);
rpc_proto::send_args(&mut writer, service, tag.as_ref(), data)?;
rpc_proto::send_args(&mut writer, service, tag.as_ref(), data, true)?;
writer.position()
};
io::ProtoWrite::write_u32(&mut slice, length as u32)
@ -499,8 +499,8 @@ extern fn subkernel_send_message(id: u32, count: u8, tag: &CSlice<u8>, data: *co
}
#[unwind(allowed)]
extern fn subkernel_await_message(id: u32, timeout: u64, min: u8, max: u8) -> u8 {
send(&SubkernelMsgRecvRequest { id: id, timeout: timeout });
extern fn subkernel_await_message(id: u32, timeout: u64, tags: &CSlice<u8>, min: u8, max: u8) -> u8 {
send(&SubkernelMsgRecvRequest { id: id, timeout: timeout, tags: tags.as_ref() });
recv!(SubkernelMsgRecvReply { status, count } => {
match status {
SubkernelStatus::NoError => {

2
artiq/firmware/libproto_artiq/kernel_proto.rs
View File

@ -108,7 +108,7 @@ pub enum Message<'a> {
SubkernelAwaitFinishRequest { id: u32, timeout: u64 },
SubkernelAwaitFinishReply { status: SubkernelStatus },
SubkernelMsgSend { id: u32, count: u8, tag: &'a [u8], data: *const *const () },
SubkernelMsgRecvRequest { id: u32, timeout: u64 },
SubkernelMsgRecvRequest { id: u32, timeout: u64, tags: &'a [u8] },
SubkernelMsgRecvReply { status: SubkernelStatus, count: u8 },
Log(fmt::Arguments<'a>),

49
artiq/firmware/libproto_artiq/rpc_proto.rs
View File

@ -190,9 +190,9 @@ unsafe fn recv_value<R, E>(reader: &mut R, tag: Tag, data: &mut *mut (),
}
}
pub fn recv_return<R, E>(reader: &mut R, tag_bytes: &[u8], data: *mut (),
pub fn recv_return<'a, R, E>(reader: &mut R, tag_bytes: &'a [u8], data: *mut (),
alloc: &dyn Fn(usize) -> Result<*mut (), E>)
-> Result<(), E>
-> Result<&'a [u8], E>
where R: Read + ?Sized,
E: From<Error<R::ReadError>>
{
@ -204,14 +204,16 @@ pub fn recv_return<R, E>(reader: &mut R, tag_bytes: &[u8], data: *mut (),
let mut data = data;
unsafe { recv_value(reader, tag, &mut data, alloc)? };
Ok(())
Ok(it.data)
}
unsafe fn send_elements<W>(writer: &mut W, elt_tag: Tag, length: usize, data: *const ())
unsafe fn send_elements<W>(writer: &mut W, elt_tag: Tag, length: usize, data: *const (), write_tags: bool)
-> Result<(), Error<W::WriteError>>
where W: Write + ?Sized
{
writer.write_u8(elt_tag.as_u8())?;
if write_tags {
writer.write_u8(elt_tag.as_u8())?;
}
match elt_tag {
// we cannot use NativeEndian::from_slice_i32 as the data is not mutable,
// and that is not needed as the data is already in native endian
@ -230,14 +232,14 @@ unsafe fn send_elements<W>(writer: &mut W, elt_tag: Tag, length: usize, data: *c
_ => {
let mut data = data;
for _ in 0..length {
send_value(writer, elt_tag, &mut data)?;
send_value(writer, elt_tag, &mut data, write_tags)?;
}
}
}
Ok(())
}
unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const (), write_tags: bool)
-> Result<(), Error<W::WriteError>>
where W: Write + ?Sized
{
@ -248,8 +250,9 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
$map
})
}
writer.write_u8(tag.as_u8())?;
if write_tags {
writer.write_u8(tag.as_u8())?;
}
match tag {
Tag::None => Ok(()),
Tag::Bool =>
@ -269,12 +272,14 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
writer.write_bytes((*ptr).as_ref())),
Tag::Tuple(it, arity) => {
let mut it = it.clone();
writer.write_u8(arity)?;
if write_tags {
writer.write_u8(arity)?;
}
let mut max_alignment = 0;
for _ in 0..arity {
let tag = it.next().expect("truncated tag");
max_alignment = core::cmp::max(max_alignment, tag.alignment());
send_value(writer, tag, data)?
send_value(writer, tag, data, write_tags)?
}
*data = round_up_const(*data, max_alignment);
Ok(())
@ -286,11 +291,13 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
let length = (**ptr).length as usize;
writer.write_u32((**ptr).length)?;
let tag = it.clone().next().expect("truncated tag");
send_elements(writer, tag, length, (**ptr).elements)
send_elements(writer, tag, length, (**ptr).elements, write_tags)
})
}
Tag::Array(it, num_dims) => {
writer.write_u8(num_dims)?;
if write_tags {
writer.write_u8(num_dims)?;
}
consume_value!(*const(), |buffer| {
let elt_tag = it.clone().next().expect("truncated tag");
@ -302,14 +309,14 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
})
}
let length = total_len as usize;
send_elements(writer, elt_tag, length, *buffer)
send_elements(writer, elt_tag, length, *buffer, write_tags)
})
}
Tag::Range(it) => {
let tag = it.clone().next().expect("truncated tag");
send_value(writer, tag, data)?;
send_value(writer, tag, data)?;
send_value(writer, tag, data)?;
send_value(writer, tag, data, write_tags)?;
send_value(writer, tag, data, write_tags)?;
send_value(writer, tag, data, write_tags)?;
Ok(())
}
Tag::Keyword(it) => {
@ -319,7 +326,7 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
writer.write_string(str::from_utf8((*ptr).name.as_ref()).unwrap())?;
let tag = it.clone().next().expect("truncated tag");
let mut data = ptr.offset(1) as *const ();
send_value(writer, tag, &mut data)
send_value(writer, tag, &mut data, write_tags)
})
// Tag::Keyword never appears in composite types, so we don't have
// to accurately advance data.
@ -333,7 +340,7 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
}
}
pub fn send_args<W>(writer: &mut W, service: u32, tag_bytes: &[u8], data: *const *const ())
pub fn send_args<W>(writer: &mut W, service: u32, tag_bytes: &[u8], data: *const *const (), write_tags: bool)
-> Result<(), Error<W::WriteError>>
where W: Write + ?Sized
{
@ -350,7 +357,7 @@ pub fn send_args<W>(writer: &mut W, service: u32, tag_bytes: &[u8], data: *const
for index in 0.. {
if let Some(arg_tag) = args_it.next() {
let mut data = unsafe { *data.offset(index) };
unsafe { send_value(writer, arg_tag, &mut data)? };
unsafe { send_value(writer, arg_tag, &mut data, write_tags)? };
} else {
break
}
@ -482,7 +489,7 @@ mod tag {
#[derive(Debug, Clone, Copy)]
pub struct TagIterator<'a> {
data: &'a [u8]
pub data: &'a [u8]
}
impl<'a> TagIterator<'a> {

10
artiq/firmware/runtime/kernel.rs
View File

@ -307,8 +307,7 @@ pub mod subkernel {
pub struct Message {
from_id: u32,
pub tag_count: u8,
pub tag: u8,
pub count: u8,
pub data: Vec<u8>
}
@ -334,9 +333,8 @@ pub mod subkernel {
None => unsafe {
CURRENT_MESSAGES.insert(id, Message {
from_id: id,
tag_count: data[0],
tag: data[1],
data: data[2..length].to_vec()
count: data[0],
data: data[1..length].to_vec()
});
}
};
@ -404,7 +402,7 @@ pub mod subkernel {
let destination = unsafe { SUBKERNELS.get(&id).unwrap().destination };
// reuse rpc code for sending arbitrary data
rpc::send_args(&mut writer, 0, tag, message)?;
rpc::send_args(&mut writer, 0, tag, message, false)?;
// skip service tag, but overwrite first byte with tag count
let data = &mut writer.into_inner()[3..];
data[0] = count;

32
artiq/firmware/runtime/session.rs
View File

@ -502,7 +502,7 @@ fn process_kern_message(io: &Io, aux_mutex: &Mutex,
None => unexpected!("unexpected RPC in flash kernel"),
Some(ref mut stream) => {
host_write(stream, host::Reply::RpcRequest { async: async })?;
rpc::send_args(stream, service, tag, data)?;
rpc::send_args(stream, service, tag, data, true)?;
if !async {
session.kernel_state = KernelState::RpcWait
}
@ -608,10 +608,10 @@ fn process_kern_message(io: &Io, aux_mutex: &Mutex,
kern_acknowledge()
}
#[cfg(has_drtio)]
&kern::SubkernelMsgRecvRequest { id, timeout } => {
&kern::SubkernelMsgRecvRequest { id, timeout, tags } => {
let message_received = subkernel::message_await(io, _subkernel_mutex, id, timeout);
let (status, count) = match message_received {
Ok(ref message) => (kern::SubkernelStatus::NoError, message.tag_count),
Ok(ref message) => (kern::SubkernelStatus::NoError, message.count),
Err(SubkernelError::Timeout) => (kern::SubkernelStatus::Timeout, 0),
Err(SubkernelError::IncorrectState) => (kern::SubkernelStatus::IncorrectState, 0),
Err(SubkernelError::SubkernelFinished) => {
@ -628,11 +628,11 @@ fn process_kern_message(io: &Io, aux_mutex: &Mutex,
}
Err(_) => (kern::SubkernelStatus::OtherError, 0)
};
kern_send(io, &kern::SubkernelMsgRecvReply { status: status, count: count })?;
kern_send(io, &kern::SubkernelMsgRecvReply { status: status, count: count})?;
if let Ok(message) = message_received {
// receive code almost identical to RPC recv, except we are not reading from a stream
let mut reader = Cursor::new(message.data);
let mut tag: [u8; 1] = [message.tag];
let mut current_tags = tags;
let mut i = 0;
loop {
// kernel has to consume all arguments in the whole message
@ -643,7 +643,7 @@ fn process_kern_message(io: &Io, aux_mutex: &Mutex,
"expected root value slot from kernel CPU, not {:?}", other)
}
})?;
let res = rpc::recv_return(&mut reader, &tag, slot, &|size| -> Result<_, Error<SchedError>> {
let res = rpc::recv_return(&mut reader, current_tags, slot, &|size| -> Result<_, Error<SchedError>> {
if size == 0 {
return Ok(0 as *mut ())
}
@ -657,17 +657,19 @@ fn process_kern_message(io: &Io, aux_mutex: &Mutex,
})?)
});
match res {
Ok(_) => kern_send(io, &kern::RpcRecvReply(Ok(0)))?,
Ok(new_tags) => {
kern_send(io, &kern::RpcRecvReply(Ok(0)))?;
i += 1;
if i < message.count {
// update the tag for next read
current_tags = new_tags;
} else {
// should be done by then
break;
}
},
Err(_) => unexpected!("expected valid subkernel message data")
};
i += 1;
if i < message.tag_count {
// update the tag for next read
tag[0] = reader.read_u8()?;
} else {
// should be done by then
break;
}
}
Ok(())
} else {

55
artiq/firmware/satman/kernel.rs
View File

@ -6,7 +6,7 @@ use board_artiq::{mailbox, spi};
use board_misoc::{csr, clock, i2c};
use proto_artiq::{kernel_proto as kern, session_proto::Reply::KernelException as HostKernelException, rpc_proto as rpc};
use eh::eh_artiq;
use io::{Cursor, ProtoRead};
use io::Cursor;
use kernel::eh_artiq::StackPointerBacktrace;
use ::{cricon_select, RtioMaster};
@ -52,12 +52,12 @@ mod kernel_cpu {
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
#[derive(Debug, Clone, PartialEq, Eq)]
enum KernelState {
Absent,
Loaded,
Running,
MsgAwait { max_time: u64 },
MsgAwait { max_time: u64, tags: Vec<u8> },
MsgSending
}
@ -99,7 +99,6 @@ pub struct Sliceable {
/* represents interkernel messages */
struct Message {
count: u8,
tag: u8,
data: Vec<u8>
}
@ -201,8 +200,7 @@ impl MessageManager {
None => {
self.in_buffer = Some(Message {
count: data[0],
tag: data[1],
data: data[2..length].to_vec()
data: data[1..length].to_vec()
});
}
};
@ -264,7 +262,7 @@ impl MessageManager {
pub fn accept_outgoing(&mut self, count: u8, tag: &[u8], data: *const *const ()) -> Result<(), Error> {
let mut writer = Cursor::new(Vec::new());
rpc::send_args(&mut writer, 0, tag, data)?;
rpc::send_args(&mut writer, 0, tag, data, false)?;
// skip service tag, but write the count
let mut data = writer.into_inner().split_off(3);
data[0] = count;
@ -507,17 +505,18 @@ impl Manager {
}
fn process_external_messages(&mut self) -> Result<(), Error> {
match self.session.kernel_state {
KernelState::MsgAwait { max_time } => {
if clock::get_ms() > max_time {
match &self.session.kernel_state {
KernelState::MsgAwait { max_time, tags } => {
if clock::get_ms() > *max_time {
kern_send(&kern::SubkernelMsgRecvReply { status: kern::SubkernelStatus::Timeout, count: 0 })?;
self.session.kernel_state = KernelState::Running;
return Ok(())
}
if let Some(message) = self.session.messages.get_incoming() {
kern_send(&kern::SubkernelMsgRecvReply { status: kern::SubkernelStatus::NoError, count: message.count })?;
let tags = tags.clone();
self.session.kernel_state = KernelState::Running;
pass_message_to_kernel(&message)
pass_message_to_kernel(&message, &tags)
} else {
Err(Error::AwaitingMessage)
}
@ -538,7 +537,7 @@ impl Manager {
// returns Ok(with_exception) on finish
// None if the kernel is still running
kern_recv(|request| {
match (request, self.session.kernel_state) {
match (request, &self.session.kernel_state) {
(&kern::LoadReply(_), KernelState::Loaded) => {
// We're standing by; ignore the message.
return Ok(None)
@ -611,9 +610,9 @@ impl Manager {
Ok(())
}
&kern::SubkernelMsgRecvRequest { id: _, timeout } => {
&kern::SubkernelMsgRecvRequest { id: _, timeout, tags } => {
let max_time = clock::get_ms() + timeout as u64;
self.session.kernel_state = KernelState::MsgAwait { max_time: max_time };
self.session.kernel_state = KernelState::MsgAwait { max_time: max_time, tags: tags.to_vec() };
Ok(())
},
@ -695,10 +694,9 @@ fn slice_kernel_exception(exceptions: &[Option<eh_artiq::Exception>],
}
}
fn pass_message_to_kernel(message: &Message) -> Result<(), Error> {
fn pass_message_to_kernel(message: &Message, tags: &[u8]) -> Result<(), Error> {
let mut reader = Cursor::new(&message.data);
let mut tag: [u8; 1] = [message.tag];
let count = message.count;
let mut current_tags = tags;
let mut i = 0;
loop {
let slot = kern_recv_w_timeout(100, |reply| {
@ -712,8 +710,7 @@ fn pass_message_to_kernel(message: &Message) -> Result<(), Error> {
"expected root value slot from kernel CPU, not {:?}", other)
}
})?;
let res = rpc::recv_return(&mut reader, &tag, slot, &|size| -> Result<_, Error> {
let res = rpc::recv_return(&mut reader, current_tags, slot, &|size| -> Result<_, Error> {
if size == 0 {
return Ok(0 as *mut ())
}
@ -735,17 +732,19 @@ fn pass_message_to_kernel(message: &Message) -> Result<(), Error> {
})?)
});
match res {
Ok(_) => kern_send(&kern::RpcRecvReply(Ok(0)))?,
Ok(new_tags) => {
kern_send(&kern::RpcRecvReply(Ok(0)))?;
i += 1;
if i < message.count {
// update the tag for next read
current_tags = new_tags;
} else {
// should be done by then
break;
}
},
Err(_) => unexpected!("expected valid subkernel message data")
};
i += 1;
if i < count {
// update the tag for next read
tag[0] = reader.read_u8()?;
} else {
// should be done by then
break;
}
}
Ok(())
}

4
artiq/test/lit/embedding/subkernel_return.py
View File

@ -9,13 +9,13 @@ def entrypoint():
# CHECK: call void @subkernel_load_run\(i32 1, i1 true\), !dbg !.
# CHECK-NOT: call void @subkernel_send_message\(.*\), !dbg !.
returning()
# CHECK: call i8 @subkernel_await_message\(i32 1, i64 10000, i8 1, i8 1\), !dbg !.
# CHECK: call i8 @subkernel_await_message\(i32 1, i64 10000, { i8\*, i32 }\* nonnull .*, i8 1, i8 1\), !dbg !.
# CHECK: call void @subkernel_await_finish\(i32 1, i64 10000\), !dbg !.
subkernel_await(returning)
# CHECK-L: declare void @subkernel_load_run(i32, i1) local_unnamed_addr
# CHECK-NOT-L: declare void @subkernel_send_message(i32, i8, { i8*, i32 }*, i8**) local_unnamed_addr
# CHECK-L: declare i8 @subkernel_await_message(i32, i64, i8, i8) local_unnamed_addr
# CHECK-L: declare i8 @subkernel_await_message(i32, i64, { i8*, i32 }*, i8, i8) local_unnamed_addr
# CHECK-L: declare void @subkernel_await_finish(i32, i64) local_unnamed_addr
@subkernel(destination=1)
def returning() -> TInt32:

4
artiq/test/lit/embedding/subkernel_return_none.py
View File

@ -10,13 +10,13 @@ def entrypoint():
# CHECK-NOT: call void @subkernel_send_message\(.*\), !dbg !.
returning_none()
# CHECK: call void @subkernel_await_finish\(i32 1, i64 10000\), !dbg !.
# CHECK-NOT: call void @subkernel_await_message\(i32 1, i64 10000\), !dbg !.
# CHECK-NOT: call i8 @subkernel_await_message\(i32 1, i64 10000\, .*\), !dbg !.
subkernel_await(returning_none)
# CHECK-L: declare void @subkernel_load_run(i32, i1) local_unnamed_addr
# CHECK-NOT-L: declare void @subkernel_send_message(i32, { i8*, i32 }*, i8**) local_unnamed_addr
# CHECK-L: declare void @subkernel_await_finish(i32, i64) local_unnamed_addr
# CHECK-NOT-L: declare void @subkernel_await_message(i32, i64) local_unnamed_addr
# CHECK-NOT-L: declare i8 @subkernel_await_message(i32, i64, { i8*, i32 }*, i8, i8) local_unnamed_addr
@subkernel(destination=1)
def returning_none() -> TNone:
pass