| From: | Justin Pryzby <pryzby(at)telsasoft(dot)com> |
|---|---|
| To: | pgsql-hackers(at)postgresql(dot)org |
| Subject: | avoid some calls to memset with array initializer |
| Date: | 2020-01-02 16:38:35 |
| Message-ID: | 20200102163834.GA3183@telsasoft.com |
| Views: | Raw Message | Whole Thread | Download mbox | Resend email |
| Thread: | |
| Lists: | pgsql-hackers |
Is there any appetite for use of array initializer rather than memset, as in
attached ? So far, I only looked for "memset.*null", and I can't see that any
of these are hot paths, but saves a cycle or two and a line of code for each.
gcc 4.9.2 with -O2 emits smaller code with array initializer than with inlined
call to memset.
$ wc -l contrib/pageinspect/heapfuncs.S?
22159 contrib/pageinspect/heapfuncs.S0
22011 contrib/pageinspect/heapfuncs.S1
Also true of gcc 5.4. And 7.3:
25294 contrib/pageinspect/heapfuncs.S0
25234 contrib/pageinspect/heapfuncs.S1
| Attachment | Content-Type | Size |
|---|---|---|
| v1-0001-Avoid-some-calls-to-memset.patch | text/x-diff | 22.5 KB |
| v1-0002-Some-less-useful-changes-to-avoid-memset.patch | text/x-diff | 12.9 KB |
| From | Date | Subject | |
|---|---|---|---|
| Next Message | Merlin Moncure | 2020-01-02 16:59:35 | Re: Greatest Common Divisor |
| Previous Message | Justin Pryzby | 2020-01-02 16:27:01 | Re: error context for vacuum to include block number |