On Tue, Mar 9, 2021 at 5:00 AM Amit Khandekar <amitdkhan...@gmail.com> wrote: > > Hi, > > Just a quick question before I move on to review the patch ... The > improvement looks like it is only meant for x86 platforms.
Actually it's meant to be faster for all platforms, since the C fallback is quite a bit different from HEAD. I've found it to be faster on ppc64le. An earlier version of the patch was a loser on 32-bit Arm because of alignment issues, but if you could run the test script attached to [1] on 64-bit Arm, I'd be curious to see how it does on 0002, and whether 0003 and 0004 make things better or worse. If there is trouble building on non-x86 platforms, I'd want to fix that also. (Note: 0001 is not my patch, and I just include it for the tests) > Can this be > done in a portable way by arranging for auto-vectorization ? Something > like commit 88709176236caf. This way it would benefit other platforms > as well. I'm fairly certain that the author of a compiler capable of doing that in this case would be eligible for some kind of AI prize. :-) [1] https://www.postgresql.org/message-id/06d45421-61b8-86dd-e765-f1ce527a5...@iki.fi -- John Naylor EDB: http://www.enterprisedb.com
