[ARROW-10990] [Rust]: SIMD implementation of compare kernels reads out of bounds

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 3.0.0
• Component/s: Rust
• Labels: pull-request-available
• External issue URL: https://github.com/apache/arrow/issues/26912
• Assignee: Jörn Horstmann
• Reporter: Jörn Horstmann
• Created: 20/Dec/20 12:41
• Updated: 11/Jan/23 08:16
• Resolved: 01/Jan/21 11:05

Description

The simd compare kernels use the following pattern to handle the remainder that is not a multiple of the number of vector lanes:

    if rem > 0 {
        let simd_left = T::load(left.value_slice(len - rem, lanes));
        let simd_right = T::load(right.value_slice(len - rem, lanes));
        let simd_result = op(simd_left, simd_right);
        let rem_buffer_size = (rem as f32 / 8f32).ceil() as usize;
        T::bitmask(&simd_result, |b| {
            result.extend_from_slice(&b[0..rem_buffer_size]);
        });
    }

While this avoids writing into result out of bounds, it still reads from the left and right arrays at out of bounds indices and valgrind complains about that. I propose to rewrite the logic to use chunked iteration, with a scalar loop for the remainder, similar to the change for arithmetic kernels in ARROW-10914.

Issue Links

• links to: GitHub Pull Request #8975