1 |
On Sunday 26 June 2011 13:36:22 Frank Peters wrote: |
2 |
> On Sun, 26 Jun 2011 19:04:48 +0200 |
3 |
> |
4 |
> Volker Armin Hemmann <volkerarmin@××××××××××.com> wrote: |
5 |
> > btw, have you tried ekopath? The compiler entered portage shortly after |
6 |
> > its open sourcing? Maybe it is more correct. According to some it is |
7 |
> > faster than gcc when it comes to math heavy workloads. |
8 |
> |
9 |
> I took a look at it in the past and it was proprietary. But looking |
10 |
> again I see that it is in portage as a binary package. I'll check it |
11 |
> out for sure. |
12 |
> |
13 |
> The Intel compiler was always an interest of mine but it can run |
14 |
> on only Gentoo multilib. |
15 |
> |
16 |
> Then there is LLVM which I am not sure about. I'll have to research |
17 |
> this one. |
18 |
> |
19 |
> Frank Peters |
20 |
|
21 |
ok, I tried ekopath: |
22 |
|
23 |
UCBFAIL indicates problems! |
24 |
/tmp/usbtest/ccos_DP.output: ucbtest UCBFAIL in COS(X) at line 444 for generic |
25 |
/tmp/usbtest/cexp_DP.output: ucbtest UCBFAIL in EXP(X) at line 444 for generic |
26 |
/tmp/usbtest/clib_DP.output: ucbtest UCBFAIL in ceild at line 701 for double |
27 |
/tmp/usbtest/clib_DP.output: ucbtest UCBFAIL in coshd at line 701 for double |
28 |
/tmp/usbtest/clib_DP.output: ucbtest UCBFAIL in floord at line 701 for double |
29 |
/tmp/usbtest/clib_DP.output:UCBFAIL clib_DP.output , 25 out of 25 tests |
30 |
completed |
31 |
/tmp/usbtest/csin_DP.output: ucbtest UCBFAIL in SIN(X) at line 444 for generic |
32 |
|
33 |
only 10 out of 14 show UCBPASS! |
34 |
|
35 |
|
36 |
options: |
37 |
make="make" |
38 |
cpp="cpp -traditional" |
39 |
#cc=gcc |
40 |
cc=/opt/ekopath-bin-4.0.10_pre20110612/bin/pathcc |
41 |
#fcc=gfortran |
42 |
f77=/opt/ekopath-bin-4.0.10_pre20110612/bin/pathf90 |
43 |
opts="-m64 -O2 -pipe -march=k8" |
44 |
|
45 |
|
46 |
-- |
47 |
#163933 |