On Sat, Sep 17, 2022 at 12:29 PM Nathan Bossart <nathandboss...@gmail.com> wrote: > > On Fri, Sep 16, 2022 at 02:54:14PM +0700, John Naylor wrote: > > v6 demonstrates why this should have been put off towards the end. (more below) > > Since the SIMD code is fresh in my mind, I wanted to offer my review for > 0001 in the "Improve dead tuple storage for lazy vacuum" thread [0]. > However, I agree with John that the SIMD part of that work should be left > for the end
As I mentioned in the radix tree thread, I don't believe this level of abstraction is appropriate for the intended use case. We'll want to incorporate some of the low-level simd.h improvements later, so you should get authorship credit for those. I've marked the entry "returned with feedback". -- John Naylor EDB: http://www.enterprisedb.com