nick.hudson@dsl.pipex.com said:
> What does the RAS look like for you?

It looks identical to yours:
(gdb) x/6i pthread__lock_ras_start
0x9da8 <pthread__lock_ras_start>:       mov    (%edx),%al
0x9daa <pthread__lock_ras_start+2>:     movb   $0x1,(%edx)
0x9dad <pthread__lock_ras_end>: dec    %al
0x9daf <pthread__lock_ras_end+2>:       setne  %al
0x9db2 <pthread__lock_ras_end+5>:       movzbl %al,%eax
0x9db5 <pthread__lock_ras_end+8>:       ret

> Do you use any gcc options when building?

No. As said, I've also tried -O0 (which should imply
no-reorder-blocks, according to the manpage), and it
didn't help.

best regards
Matthias




-----------------------------------------------------------------------------------------
-----------------------------------------------------------------------------------------
Forschungszentrum Juelich GmbH
52425 Juelich

Sitz der Gesellschaft: Juelich
Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
Vorsitzende des Aufsichtsrats: MinDirig'in Baerbel Brumme-Bothe
Vorstand: Prof. Dr. Achim Bachem (Vorsitzender), Dr. Ulrich Krafft (stellv. 
Vorsitzender)
-----------------------------------------------------------------------------------------
-----------------------------------------------------------------------------------------