Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
14.65k
stars
3.56k
forks
source link
[Rust] SIMD aggregate kernel produces flawed results. #26999
Open
asfimport opened 3 years ago
I don't know if this is still accurate on master, but Arrow 2.0 simd sum gives me flawed results when compiled with SIMD.
When SIMD is toggled off I get correct results.
When I have more time I can get a reproducible example if requested. Dataset on which this shows different results (as numpy array)
Output of np.nansum is 39. Output of SIMD kernel is 37.
Reporter: Ritchie / @ritchie46
Note: This issue was originally created as ARROW-11087. Please see the migration documentation for further details.