Re: [HACKERS] Improve hash-agg performance

2016-11-30 Thread Andres Freund
Hi, On 2016-11-03 04:07:21 -0700, Andres Freund wrote: > Hi, > > There's two things I found while working on faster expression > evaluation, slot deforming and batched execution. As those two issues > often seemed quite dominant cost-wise it seemed worthwhile to evaluate > them independently. > >

Re: [HACKERS] Improve hash-agg performance

2016-11-04 Thread Andres Freund
On 2016-11-04 15:18:49 +0200, Heikki Linnakangas wrote: > On 11/03/2016 01:07 PM, Andres Freund wrote: > > Hi, > > > > There's two things I found while working on faster expression > > evaluation, slot deforming and batched execution. As those two issues > > often seemed quite dominant cost-wise i

Re: [HACKERS] Improve hash-agg performance

2016-11-04 Thread Heikki Linnakangas
On 11/03/2016 01:07 PM, Andres Freund wrote: Hi, There's two things I found while working on faster expression evaluation, slot deforming and batched execution. As those two issues often seemed quite dominant cost-wise it seemed worthwhile to evaluate them independently. 1) We atm do one ExecPr

[HACKERS] Improve hash-agg performance

2016-11-03 Thread Andres Freund
Hi, There's two things I found while working on faster expression evaluation, slot deforming and batched execution. As those two issues often seemed quite dominant cost-wise it seemed worthwhile to evaluate them independently. 1) We atm do one ExecProject() to compute each aggregate's argument