[Bug] RPCTimeEvaluator signature error

[Priyadrasta-2111CS10]

Expected behavior

The output should be something as follows that is shown in the user tutorial https://tvm.apache.org/docs/tutorial/cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py

1.389e-07 secs/op

Actual behavior

I got an error as shown below.

  File "/home/priyadrasta/rpc cross compilation.py", line 51, in <module>
    time_f = func.time_evaluator(func.entry_name, dev, number=10)
  File "/home/priyadrasta/.local/lib/python3.10/site-packages/tvm/runtime/module.py", line 335, in time_evaluator
    feval = _ffi_api.RPCTimeEvaluator(
  File "/home/priyadrasta/.local/lib/python3.10/site-packages/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
    raise get_last_ffi_error()
tvm.error.RPCError: Traceback (most recent call last):
  11: TVMFuncCall
  10: _ZN3tvm7runtime13PackedFun
  9: tvm::runtime::TypedPackedFunc<tvm::runtime::PackedFunc (tvm::runtime::Optional<tvm::runtime::Module>, std::string, int, int, int, int, int, int, int, std::string)>::AssignTypedLambda<tvm::runtime::__mk_TVM0::{lambda(tvm::runtime::Optional<tvm::runtime::Module>, std::string, int, int, int, int, int, int, int, std::string)#1}>(tvm::runtime::__mk_TVM0::{lambda(tvm::runtime::Optional<tvm::runtime::Module>, std::string, int, int, int, int, int, int, int, std::string)#1}, std::string)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}::operator()(tvm::runtime::TVMArgs const, tvm::runtime::TVMRetValue) const
  8: tvm::runtime::RPCModuleNode::GetTimeEvaluator(std::string const&, DLDevice, int, int, int, int, int, std::string const&)
  7: tvm::runtime::RPCWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) const
  6: tvm::runtime::RPCClientSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
  5: tvm::runtime::RPCEndpoint::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)>)
  4: tvm::runtime::RPCEndpoint::HandleUntilReturnEvent(bool, std::function<void (tvm::runtime::TVMArgs)>)
  3: tvm::runtime::RPCEndpoint::EventHandler::HandleNextEvent(bool, bool, std::function<void (tvm::runtime::TVMArgs)>)
  2: tvm::runtime::RPCEndpoint::EventHandler::HandleProcessPacket(std::function<void (tvm::runtime::TVMArgs)>)
  1: tvm::runtime::RPCEndpoint::EventHandler::HandleReturn(tvm::runtime::RPCCode, std::function<void (tvm::runtime::TVMArgs)>)
  0: _ZN3tvm7runtime6deta
  11: TVMFuncCall
  10: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::__mk_TVM1::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::__mk_TVM1, tvm::runtime::TVMRetValue)
  9: tvm::runtime::RPCServerLoop(int)
  8: tvm::runtime::RPCEndpoint::ServerLoop()
  7: tvm::runtime::RPCEndpoint::HandleUntilReturnEvent(bool, std::function<void (tvm::runtime::TVMArgs)>)
  6: tvm::runtime::RPCEndpoint::EventHandler::HandleNextEvent(bool, bool, std::function<void (tvm::runtime::TVMArgs)>)
  5: tvm::runtime::RPCEndpoint::EventHandler::HandleProcessPacket(std::function<void (tvm::runtime::TVMArgs)>)
  4: tvm::runtime::RPCSession::AsyncCallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::RPCCode, tvm::runtime::TVMArgs)>)
  3: tvm::runtime::LocalSession::CallFunc(void*, TVMValue const*, int const*, int, std::function<void (tvm::runtime::TVMArgs)> const&)
  2: _ZN3tvm7runtime13PackedF
  1: tvm::runtime::TypedPackedFunc<tvm::runtime::PackedFunc (tvm::runtime::Optional<tvm::runtime::Module>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, int, int, int, int, int, int, int, int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)>::AssignTypedLambda<tvm::runtime::__mk_TVM0::{lambda(tvm::runtime::Optional<tvm::runtime::Module>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, int, int, int, int, int, int, int, int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)#1}>(tvm::runtime::__mk_TVM0::{lambda(tvm::runtime::Optional<tvm::runtime::Module>, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >, int, int, int, int, int, int, int, int, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)#1}, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMArgs const&) const
  0: _ZN3tvm7runtime6deta
  File "/workspace/tvm/src/runtime/rpc/rpc_endpoint.cc", line 376
RPCError: Error caught from RPC call:
[06:44:36] /home/pi/tvm/include/tvm/runtime/packed_func.h:1728: Function runtime.RPCTimeEvaluator(0: runtime.Module, 1: basic_string<char>, 2: int, 3: int, 4: int, 5: int, 6: int, 7: int, 8: int, 9: int, 10: basic_string<char>) -> runtime.PackedFunc expects 11 arguments, but 10 were provided.

Environment

I am using ubuntu 22.04 LTS as my local machine and Raspberry Pi 4 as my target remote device with an IP address : 192.168.91.173 and port: 9090

Steps to reproduce

1. build runtime on Raspberry Pi as shown in the tutorial
2. Set Up RPC Server on Raspberry Pi using the command : python -m tvm.exec.rpc_server --host 0.0.0.0 --port=9090
3. save the following code in local machine with LLVM enabled as rpc cross compilation.py and run :

import numpy as np

import tvm
from tvm import te
from tvm import rpc
from tvm.contrib import utils

n = tvm.runtime.convert(1024)
A = te.placeholder((n,), name="A")
B = te.compute((n,), lambda i: A[i] + 1.0, name="B")
s = te.create_schedule(B.op)


local_demo = False

if local_demo:
   target = "llvm"
else:
   target = "llvm -mtriple=aarch64-linux-gnu"

func = tvm.build(s, [A, B], target=target, name="add_one")
# save the lib at a local temp folder
temp = utils.tempdir()

path = temp.relpath("lib.tar")

func.export_library(path)


if local_demo:
   remote = rpc.LocalSession()
else:
   # The following is my environment, change this to the IP address of your target device
   host = "192.168.91.173"  #host IP address of my Raspberry Pi
   port = 9090
   remote = rpc.connect(host, port)
   
remote.upload(path)
func = remote.load_module("lib.tar")

# create arrays on the remote device
dev = remote.cpu()
a = tvm.nd.array(np.random.uniform(size=1024).astype(A.dtype), dev)
b = tvm.nd.array(np.zeros(1024, dtype=A.dtype), dev)
# the function will run on the remote device
func(a, b)
np.testing.assert_equal(b.numpy(), a.numpy() + 1)


time_f = func.time_evaluator(func.entry_name, dev, number=10)
cost = time_f(a, b).mean
print("%g secs/op" % cost)

[masahi]

I remember seeing this error, it was fixed by updating and recompiling the runtime code on the device. Have you updated the runtime on the device recently?