Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex - Mailing list pgsql-hackers

From Jeremy Kerr
Subject Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex
Date
Msg-id 200907211308.12371.jk@ozlabs.org
Whole thread Raw
In response to Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex  (Greg Stark <gsstark@mit.edu>)
Responses Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex
List pgsql-hackers
Hi Greg,

Thanks for the benchmark app, thought I'd pitch in with some ppc 
results:

>                  clz 1.530s
>         lookup table 1.720s
>           float hack 4.424s
>             unrolled 5.280s
>               normal 5.369s

POWER5+:                clz 2.046s       lookup table 2.188s         float hack 7.786s           unrolled 6.353s
    normal 7.033s
 

POWER6:                clz 1.063s       lookup table 1.199s         float hack 3.575s           unrolled 2.290s
   normal 3.456s
 

Cheers,


Jeremy



pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: [PATCH v4] Avoid manual shift-and-test logic in AllocSetFreeIndex
Next
From: Robert Haas
Date:
Subject: Re: [PATCH] SE-PgSQL/tiny rev.2193