Cookiee235 opened a new issue, #17322:
URL: https://github.com/apache/tvm/issues/17322

   The relax IR crashed when the input tensor size was larger than 1024.  If 
this `tir` is illegal, do we have a corresponding legality-checking mechanism 
to alert early?
   
   A similar issue is found here: https://github.com/mlc-ai/mlc-llm/issues/971
   
   ### Actual behavior
   ```
   Traceback (most recent call last):
     File 
"/share_container/optfuzz/res/res_0830/optfuzz_nnsmith/res_executions/881_test.py",
 line 260, in <module>
       before_outputs, infer_time1 = compile_mod(mod, 'main', 'llvm', 
input_0,input_1,input_2)
                                     
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
     File 
"/share_container/optfuzz/res/res_0830/optfuzz_nnsmith/res_executions/881_test.py",
 line 251, in compile_mod
       mod_outputs = vm[f'{func_name}'](*inputs)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^
     File "/software/tvm/python/tvm/_ffi/_ctypes/packed_func.py", line 239, in 
__call__
       raise_last_ffi_error()
     File "/software/tvm/python/tvm/_ffi/base.py", line 481, in 
raise_last_ffi_error
       raise py_err
   tvm.error.InternalError: Traceback (most recent call last):
     14: 
tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::relax_vm::VirtualMachineImpl::_LookupFunction(tvm::runtime::String
 const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> 
>::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, 
tvm::runtime::TVMRetValue*)
     13: 
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeClosurePacked(tvm::runtime::ObjectRef
 const&, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
     12: 
tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::relax_vm::VirtualMachineImpl::GetClosureInternal(tvm::runtime::String
 const&, bool)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> 
>::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, 
tvm::runtime::TVMRetValue*)
     11: tvm::runtime::relax_vm::VirtualMachineImpl::InvokeBytecode(long, 
std::vector<tvm::runtime::TVMRetValue, 
std::allocator<tvm::runtime::TVMRetValue> > const&)
     10: tvm::runtime::relax_vm::VirtualMachineImpl::RunLoop()
     9: 
tvm::runtime::relax_vm::VirtualMachineImpl::RunInstrCall(tvm::runtime::relax_vm::VMFrame*,
 tvm::runtime::relax_vm::Instruction)
     8: 
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeClosurePacked(tvm::runtime::ObjectRef
 const&, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
     7: 
tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::relax_vm::VirtualMachineImpl::GetClosureInternal(tvm::runtime::String
 const&, bool)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}> 
>::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, 
tvm::runtime::TVMRetValue*)
     6: tvm::runtime::relax_vm::VirtualMachineImpl::InvokeBytecode(long, 
std::vector<tvm::runtime::TVMRetValue, 
std::allocator<tvm::runtime::TVMRetValue> > const&)
     5: tvm::runtime::relax_vm::VirtualMachineImpl::RunLoop()
     4: 
tvm::runtime::relax_vm::VirtualMachineImpl::RunInstrCall(tvm::runtime::relax_vm::VMFrame*,
 tvm::runtime::relax_vm::Instruction)
     3: 
tvm::runtime::relax_vm::VirtualMachineImpl::InvokeClosurePacked(tvm::runtime::ObjectRef
 const&, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
     2: _ZN3tvm7runtime13PackedFuncObj9ExtractorINS0_1
     1: tvm::runtime::TypedPackedFunc<tvm::runtime::NDArray 
(tvm::runtime::memory::Storage, long, tvm::runtime::ShapeTuple, 
DLDataType)>::AssignTypedLambda<tvm::runtime::Registry::set_body_method<tvm::runtime::memory::Storage,
 tvm::runtime::memory::StorageObj, tvm::runtime::NDArray, long, 
tvm::runtime::ShapeTuple, DLDataType, void>(tvm::runtime::NDArray 
(tvm::runtime::memory::StorageObj::*)(long, tvm::runtime::ShapeTuple, 
DLDataType))::{lambda(tvm::runtime::memory::Storage, long, 
tvm::runtime::ShapeTuple, 
DLDataType)#1}>(tvm::runtime::Registry::set_body_method<tvm::runtime::memory::Storage,
 tvm::runtime::memory::StorageObj, tvm::runtime::NDArray, long, 
tvm::runtime::ShapeTuple, DLDataType, void>(tvm::runtime::NDArray 
(tvm::runtime::memory::StorageObj::*)(long, tvm::runtime::ShapeTuple, 
DLDataType))::{lambda(tvm::runtime::memory::Storage, long, 
tvm::runtime::ShapeTuple, DLDataType)#1}, std::__cxx11::basic_string<char, 
std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runti
 me::TVMArgs const&, 
tvm::runtime::TVMRetValue*)#1}::operator()(tvm::runtime::TVMArgs const, 
tvm::runtime::TVMRetValue) const
     0: tvm::runtime::memory::StorageObj::AllocNDArray(long, 
tvm::runtime::ShapeTuple, DLDataType)
     File "/software/tvm/src/runtime/memory/memory_manager.cc", line 117
   InternalError: Check failed: (offset + needed_size <= this->buffer.size) is 
false: storage allocation failure, attempted to allocate 36480 at offset 0 in 
region that is 4096bytes
   ```
   
   ### Steps to reproduce
   
   ```
   import tvm
   from tvm import relax
   import numpy as np
   from tvm.script import ir as I
   from tvm.script import tir as T
   from tvm.script import relax as R
   
   @I.ir_module
   class Module:
       @T.prim_func
       def add_one(x_handle: T.handle, y_handle: T.handle):
           m = T.int64()
           x = T.match_buffer(x_handle, (m,))
           y = T.match_buffer(y_handle, (m,))
           # with T.block("root"):
           for i in range(m):
               with T.block("add"):
                   vi = T.axis.spatial(m, i)
                   T.reads(x[vi])
                   T.writes(y[vi])
                   y[vi] = x[vi] + T.float32(1)
   
       @R.function
       def main(x: R.Tensor(("m",), dtype="float32")) -> R.Tensor(("m",), 
dtype="float32"):
           m = T.int64()
           R.func_attr({"relax.force_pure": 1, 
"relax.rewrite_cuda_graph.capture_symbolic_vars": ["m"]})
           cls = Module
           storage: R.Object = R.memory.alloc_storage(R.shape([16]), 
R.prim_value(0), R.str("global"), R.dtype("float32"))
           alloc1: R.Tensor((m,), dtype="float32") = 
R.memory.alloc_tensor(storage, R.prim_value(0), R.shape([m]), 
R.dtype("float32"))
           cls.add_one(x, alloc1)
           storage1: R.Object = R.memory.alloc_storage(R.shape([16]), 
R.prim_value(0), R.str("global"), R.dtype("float32"))
           alloc2: R.Tensor((m,), dtype="float32") = 
R.memory.alloc_tensor(storage1, R.prim_value(0), R.shape([m]), 
R.dtype("float32"))
           cls.add_one(alloc1, alloc2)
           alloc3: R.Tensor((m,), dtype="float32") = 
R.builtin.alloc_tensor(R.shape([m]), R.dtype("float32"), R.prim_value(0), 
R.str("global"))
           cls.add_one(alloc2, alloc3)
           return alloc3
   
   mod = Module
   mod = tvm.tir.analysis.OOBChecker()(mod)
   
   def compile_mod(mod, func_name, target, *inputs):
       ex = relax.build(mod, target='llvm')
       vm = relax.VirtualMachine(ex, tvm.cpu())
       mod_outputs = vm[f'{func_name}'](*inputs)
       mod_outputs = mod_outputs.numpy()
   
   input_ = tvm.nd.array(np.random.random([1025]).astype('float32'))  # 
tensor_size > 1024 will lead to crash
   compile_mod(mod, 'main', 'llvm', input_)
   ```
   
   CC @Lunderberg @junrushao 
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to