Minor improvements for PyTorch (#643)

Add cuCtxCreate_v4 and exit and a broken printf implementation

Add cuDeviceGetPCIBusId (#645)

Fix clz.b64 and add bfind.shiftamt (#644)

Implement match.any.sync, fix popc.b64 (#642)

Fix typo: overriden -> overridden in zluda_redirect (#641)

Fix typo: compatiblity -> compatibility in xtask comment (#639)

32 bit support in the compiler (#637)

This does not add full 32 bit support, just support in the compiler for a special 32bit on 64 bit mode. I expected the changes to be much smaller, but since they are so wide-reaching I prefer to get this piece out as soon as possible

Remove redundant map_err(CompilerError::from) calls in compiler (#635)

The `?` operator already converts the error type via the `From` trait,
and `CompilerError` has `#[from]` impls (or explicit From impls) for
`io::Error`, `Utf8Error`, `Vec<PtxError<'_>>`, `TranslateError`, and
trivially for `CompilerError` itself. The explicit map_err calls are
no-ops. No behavior change.

Fix typo: vec_acccess -> vector_read in emit_vector_read (#633)

Rename the parameter to match the function name and align with the
sibling functions emit_vector_write and emit_vector_repack which name
their parameters after their argument types/intent. No behavior change.

Update tests (#632)