1
1
Граф коммитов

14 Коммитов

Автор SHA1 Сообщение Дата
Brian Barrett
35375f0653 * Fix bug in symbol generation code for default.conf where we weren't prefixing
function names with the GSYM (like we should be)
* Add support for PPC64/Linux in atomics

This should go to the beta branch.

This commit was SVN r6163.
2005-06-24 16:16:17 +00:00
Brian Barrett
d474b2c3fc AIX sed passes unmatched lines through unchanged, so first find the
lines we want

This commit was SVN r5411.
2005-04-17 22:14:13 +00:00
Brian Barrett
d737000a5e * fix to make platform detection work on Linux Sparc
This commit was SVN r5134.
2005-04-01 15:49:27 +00:00
Brian Barrett
ed7f80dddf * fix dumb typo
This commit was SVN r5041.
2005-03-26 20:07:31 +00:00
Jeff Squyres
3f5541349a Add UC copyright
This commit was SVN r5009.
2005-03-24 12:43:37 +00:00
Brian Barrett
60a1ca77e9 * Updates to make MIPS actually work. Could clean up the assembly a bit :)
This commit was SVN r4469.
2005-02-18 23:16:04 +00:00
Brian Barrett
dc3165f1ea * fix dumb warning printing mistake
This commit was SVN r4466.
2005-02-18 20:26:46 +00:00
Brian Barrett
927c5be6c8 NOTE: You need to re-autogen after this commit. Sorry :(
* SPARC Assembly fixes:
  - Use SPARC assembly type only when not able to use the SPARC v9
    instruction set (instead of previous whenever sizeof(void*) == 4
  - Use SPARCV9_32 (aka sparc v8plus) and SPARCV9_64 (aka sparc v9) when
    possible.  Already were doing so for the 64bit, but on 32bit we
    were falling back to SPARC.
  - Implemented SPARCV9_32 atomic operations
  - Emit warning if user is going to get SPARC atomic, as that probably
    isn't what the user wants for best performance.
* Started shell of MIPS assembly.  Does not work, but wanted something
  so that everyone would only have to re-autogen once today....

This commit was SVN r4465.
2005-02-18 20:10:29 +00:00
Brian Barrett
a2caf839c0 * Initial try at making OMPI atomic operations work properly on Solaris
- SPARC32 has spinlocks and "pseudo atomic" math
  - SPARC64 has spinlocks, compare & set, atomic math (still in s/w)

This commit was SVN r4433.
2005-02-14 22:07:08 +00:00
Brian Barrett
76054e0b31 * add a label to the assembly being tested for GCC inline assembly so that
the test barfs on AIX, since it has some strange non-mangling of the
  labels in the inline assembly that all the other platforms seem to be
  ok making right.  *sigh*

This commit was SVN r4365.
2005-02-10 00:38:44 +00:00
Brian Barrett
cd985bba51 * Fix some issues when there was a space in the asm format string
* Extend the generate-asm.pl script to allow for the AIX global
  function format

This commit was SVN r4256.
2005-01-31 04:16:54 +00:00
Brian Barrett
0c48499661 * change OMPI_POWERPC_SUPPORT_64BIT to OMPI_ASM_SUPPORT_64BIT, since it
looks like we need to do the same thing for UltaSparc / MIPS machines
* The atomic_cmpset_64 bit code made some assumptions about calling
  convention that wouldn't be true if the function was inlined.  Fix
  those assumptions, so we should work fine whether GCC inlines
  the function or not.

This commit was SVN r4249.
2005-01-30 04:56:38 +00:00
Rainer Keller
5c5cd76df3 Perl tries to create the generated assembler-ouput
in directory src/asm/generated/, which for VPATH-builds
is at configure-time not yet created.
mkdir -p it...

This commit was SVN r4197.
2005-01-28 00:43:49 +00:00
Brian Barrett
9c1a277804 * Update build system to support non-GCC inline assembly, including detection
of assembler format
* Fix minor bugs in AMD64, PPC, and IA32 assembly for atomic operations
* Clean up the #defines to look for when examining level of atomic operation
  support

This commit was SVN r4183.
2005-01-27 01:39:55 +00:00