Stuck on an issue?

Lightrun Answers was designed to reduce the constant googling that comes with debugging 3rd party libraries. It collects links to all the places you might be looking at while hunting down a tough bug.

And, if you’re still stuck at the end, we’re happy to hop on a call to see how we can help out.

libnvvm segfault compiling this kernel

See original GitHub issue

Reporting a bug

I am using the latest released version of Numba (most recent is visible in the change log (https://github.com/numba/numba/blob/master/CHANGE_LOG).
I have included below a minimal working reproducer (if you are unsure how to write one see http://matthewrocklin.com/blog/work/2018/02/28/minimal-bug-reports).

From gitter https://gitter.im/numba/numba?at=5ebef15eeb9b6f316225be0e

Reproducer:

from numba import cuda
import numba

# Compiling this will segfault inside libnvvm
@cuda.jit(argtypes=[numba.float64[:]])
def kernel(arr):
    arr[cuda.threadIdx.x] = cuda.threadIdx.x / 100.0 + 2
    a_local = 0
    if round(arr[cuda.threadIdx.x], 2) > 0.09:
        a_local += 1
        arr[cuda.threadIdx.x] = a_local

lldb shows:

Process 50672 stopped
* thread #1, queue = 'com.apple.main-thread', stop reason = EXC_BAD_ACCESS (code=1, address=0x0)
    frame #0: 0x000000011809b3ef libnvvm.3.2.0.dylib`llvm::NVPTXTargetLowering::getArgumentAlignment(llvm::SDValue, llvm::ImmutableCallSite const*, llvm::Type*, unsigned int) const + 31
libnvvm.3.2.0.dylib`llvm::NVPTXTargetLowering::getArgumentAlignment:
->  0x11809b3ef <+31>: movq   (%rcx), %rax
    0x11809b3f2 <+34>: movq   %rax, %r13
    0x11809b3f5 <+37>: andq   $-0x4, %r13
    0x11809b3f9 <+41>: leaq   -0x18(%r13), %rcx

Happened on windows with cudatoolkit 10.2 and MBP with cudatoolkit 9.0.