1 |
Ryan Hill <dirtyepic.sk@×××××.com> posted efmrae$jff$1@×××××××××.org, |
2 |
excerpted below, on Sat, 30 Sep 2006 16:37:05 -0600: |
3 |
|
4 |
> If you want flags that just break |
5 |
> stuff with 4.1 you can include -ftree-vectorize. |
6 |
|
7 |
Could you point me at some info on this one (-ftree-vectorize)? It came |
8 |
up on the amd64 list a week or so ago, when someone asked what I thought |
9 |
of it and why I didn't have it in my cflags (which I had just explained). |
10 |
I said I didn't know enough about it to make a case either way, and as |
11 |
such, didn't choose to use it. However, after a bit of discussion, I |
12 |
decided to add it to my cflags on a very experimental basis. I haven't |
13 |
experienced any issues with it, but then I haven't done any major |
14 |
compiling since then either, only the routine updates. |
15 |
|
16 |
If I had rather more info on it, therefore, particularly on why it might |
17 |
break stuff, I'd be able to pass it on, telling the list and in particular |
18 |
the guy that asked, why it's NOT a good thing to use. Thus, point me at |
19 |
it, if you got it. Even something as simple as a list of bugs traced to |
20 |
it would be useful as something I could point at, if that's what you are |
21 |
basing your remark on. |
22 |
|
23 |
Or does the problem not necessarily apply to amd64? Even knowing that |
24 |
would be useful. I simply don't know anything much at all about it, beyond |
25 |
a generally vague idea that it means using mmx/sse/whatever vector |
26 |
instructions to parallelize loops. |
27 |
|
28 |
TIA. |
29 |
|
30 |
-- |
31 |
Duncan - List replies preferred. No HTML msgs. |
32 |
"Every nonfree program has a lord, a master -- |
33 |
and if you use the program, he is your master." Richard Stallman |
34 |
|
35 |
-- |
36 |
gentoo-dev@g.o mailing list |