Hi, I am getting errors using TVM with CUDA. Each time I call tvm.build(…, …, “cuda”), TVM compiler throws a similar TVMError message: Check failed: compile_res == NVRTC_SUCCESS (6 vs. 0) : : parse Invalid value
Here is the traceback info:
Traceback (most recent call last):
File "TE_and_Schedules.py", line 23, in <module>
fcuda = tvm.build(s, [A, B], "cuda")
File "/home/ning/scratch/tvm/python/tvm/driver/build_module.py", line 270, in build
rt_mod_host = _driver_ffi.preprocess_module(target_input_mod, target_host)
File "tvm/_ffi/_cython/./packed_func.pxi", line 323, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 257, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./packed_func.pxi", line 246, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 163, in tvm._ffi._cy3.core.CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
File "/home/ning/scratch/tvm/src/target/opt/build_cuda_on.cc", line 116
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: compile_res == NVRTC_SUCCESS (6 vs. 0) : <unnamed>: parse Invalid value
Here is the code of this error(Just from the How-to guide)
from __future__ import absolute_import, print_function
import numpy as np
import tvm
from tvm import te
from tvm.ir import register_op_attr, register_intrin_lowering
n = te.var("n")
m = te.var("m")
A = te.placeholder((n, m), name="A")
k = te.reduce_axis((0, m), "k")
B = te.compute((n,), lambda i: te.sum(A[i, k], axis=k), name="B")
s = te.create_schedule(B.op)
ko, ki = s[B].split(B.op.reduce_axis[0], factor=16)
BF = s.rfactor(B, ki)
xo, xi = s[B].split(s[B].op.axis[0], factor=32)
s[B].bind(xo, te.thread_axis("blockIdx.x"))
s[B].bind(xi, te.thread_axis("threadIdx.y"))
tx = te.thread_axis("threadIdx.x")
s[B].bind(s[B].op.reduce_axis[0], tx)
s[BF].compute_at(s[B], s[B].op.reduce_axis[0])
s[B].set_store_predicate(tx.var.equal(0))
fcuda = tvm.build(s, [A, B], "cuda")
print(fcuda.imported_modules[0].get_source())
I’ve also found that the error code 6 from NVRTC means NVRTC_ERROR_COMPILATION