Hi,
James Lentini <mailto:[EMAIL PROTECTED]> wrote:
> On Tue, 2 Aug 2005, Guy German wrote:
>
>> Hi,
>>
>> [EMAIL PROTECTED] <> wrote:
>>> On Mon, 1 Aug 2005, Tom Duffy wrote:
>>>
>>>> On Fri, 2005-07-29 at 16:46 -0500, John Partridge wrote:
>>>>> I searched the archives and don't see a solution, but I think I've
>>>>> tracked it down to a bug in ulp/kdapl/ib/dapl_util.h
>>>>>
>>>>> root on mig133 > diff -ruN dapl_util.h dapl_util.h-johnip
>>>>
>>>> Please use diff -ruNp. See FAQ question 10.
>>>>
>>>>> =============== diff ===============================
>>>>>
>>>>> --- dapl_util.h 2005-07-29 16:36:17.514669886 -0500
>>>>> +++ dapl_util.h-johnip 2005-07-29 16:37:11.514578548 -0500 @@
>>>>> -71,7 +71,7 @@
>>>>>
>>>>> #ifdef __ia64__
>>>>>
>>>>> - current_value = ia64_cmpxchg("acq", v, match_value,
>>>>> new_value, 4); + current_value = ia64_cmpxchg(acq, v,
>>>>> match_value, new_value, 4);
>>>>>
>>>>> #elif defined (__PPC__)
>>>>
>>>> Please kill dapl_os_atomic_assign(). Just use cmpxchg() directly
>>>> instead.
>>>
>>> That sounds like a good idea. Any issues with this John?
>>
>> But what about other platforms (not ia64) - the code would have
>> ifdef in all the places it is used ?
>
> I think cmpxchg() is defined for each platform Linux runs on. Is that
> not true?
I guess you are right. I found this (in include/asm-ia64/intrinsics.h):
#define cmpxchg_acq(ptr,o,n) ia64_cmpxchg(acq, (ptr), (o), (n),
sizeof(*(ptr)))
#define cmpxchg_rel(ptr,o,n) ia64_cmpxchg(rel, (ptr), (o),
(n),sizeof(*(ptr)))
/* for compatibility with other platforms: */
#define cmpxchg(ptr,o,n) cmpxchg_acq(ptr,o,n)
dapl_evd_event_alloc
dapl_rbuf_alloc
struct dat_event *event;
int i;
int status = 0;
/* Allocate EVENTs */
event = vmalloc(evd->qlen * sizeof *event);
#define cmpxchg_acq(ptr,o,n) ia64_cmpxchg(acq, (ptr), (o), (n),
sizeof(*(ptr)))
#define cmpxchg_rel(ptr,o,n) ia64_cmpxchg(rel, (ptr), (o),
(n),sizeof(*(ptr)))
/* for compatibility with other platforms: */
#define cmpxchg(ptr,o,n) cmpxchg_acq(ptr,o,n)
"include/asm-ia64/intrinsics.h" 181L, 5355C
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
