It's great to see this type of evolution in database performance, maybe this will become the standard someday. The only thing missing is that there isn't a comparable project for MySQL.
PG-Strom: SSD-To-GPU Direct SQL Execution
11–20 of 38 posts
Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#12It's great to see this type of evolution in database performance, maybe this will become the standard someday. The only thing missing is that there isn't a comparable project for MySQL.
Not trying to be a snoot here, but what is the point of using MySQL today? I can't think of something that I'm aware it does better than Postgres.
Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#13Earlier quoted context omitted.
Not trying to be a snoot here, but what is the point of using MySQL today? I can't think of something that I'm aware it does better than Postgres.
Interoperating with code and data files that were made for/by MySQL.
If you could change the shape of your tables to suit this approach, then surely you could adopt Postgres.
Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#14Wondering how much the "moving data to the GPU" overhead won't help to make things significantly faster
Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#15Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#16Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#17Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#18Wondering how much the "moving data to the GPU" overhead won't help to make things significantly faster
The major performance gain is doing SSD-to-GPU direct memory access bypassing the need for data to needlessly transfer over PCI-Express twice.
Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#19Re: PG-Strom: SSD-To-GPU Direct SQL Execution
#20This seems like a perfect fit for AMD's SSG architecture (1TiB flash storage directly on the GPU board).