This web mail archive is frozen.
This page is part of a frozen web archive of this mailing list.
You can still navigate around this archive, but know that no new mails
have been added to it since July of 2016.
Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.
I'll get a patch to the list as soon as I have one
that works. In the meantime, here are a few of the
things I've turned up.
1. The MIPS.asm file needs to load asm/asm.h on Linux
boxes, so the config script needs to grab the OS for
the MIPS box to identify what header to use.
2. MIPS.asm, in the subroutine opal_atomic_cmpset_32,
there is a bne with the jump going to Lretry1. The L
needs to be dropped on GCC, and since the other jumps
don't have that, I'm guessing it'll work fine without
it on other compilers.
3. GCC requires the assembler file to be compiled
EITHER with a .S extension, OR with the flag "-x
assembler-with-cpp" passed to GCC. Otherwise, it
doesn't expand any macros. I'd suggest having an extra
define set in the configure, which includes this flag
if it's a Linux MIPS box, and where the define is
appended to the compile flags ONLY in the opal/asm
Makefile. (You don't want to accidently identify
everything as assembly!)
4. opal/class/opal_list.c is giving an error, saying
that "retry" and "done" are already defined. Still
looking into what is going on there.
5. The ROMIO turns out not to be as bad as I'd thought
- it just needs to detect if it's MIPS in the
configure and then set the MIPS flag.
Yahoo! Mail - PC Magazine Editors' Choice 2005