BTW,
[EMAIL PROTECTED]:~# pfmon -i RS_UOPS_DISPATCHED
Name : RS_UOPS_DISPATCHED_CYCLES
Code : 0xa1
Counters : [ 0 ]
Desc : Cycles micro-ops dispatched for execution
Umask-00 : 0x01 : [PORT_0] : on port 0
Umask-01 : 0x02 : [PORT_1] : on port 1
Umask-02 : 0x04 : [PORT_2] : on port 2
Umask-03 : 0x08 : [PORT_3] : on port 0
Umask-04 : 0x10 : [PORT_4] : on port 4
Umask-05 : 0x20 : [PORT_5] : on port 5
Umask-06 : 0x3f : [ANY] : on any port
PEBS : No
I think the red place should be "on port 3", right?
On Wed, Jul 16, 2008 at 10:33 AM, Hucheng Zhou <[EMAIL PROTECTED]>
wrote:
> Thanks, Eranian, statically link work fine.
>
> BTW, I check the Intel manual, there is a even to count
> "Cycles_not_issuing_uops":
>
> Cycles_not_issuing_uops: This can be measured by event RS_UOPS_DISPATCHED,
> setting the INV bit and specifying a counter mask(CMASK) value of 1 in the
> target performance event select (IA32_PERFEVSELx) MSR. In Vtune, this event
> name is RS_UOPS_DISPATCHED.CYCLES_NONE;
> Cycles_issuing_uops: Counter part of the above metrics.
>
> But I just found the event RS_UOPS_DISPATCHED_CYCLES:PORT[0, 5]/ANY, no
> RS_UOPS_DISPATCHED.CYCLES_NONE. How can I get
> RS_UOPS_DISPATCHED.CYCLES_NONE?
>
> Thanks.
>
>
> On Mon, Jul 14, 2008 at 4:23 PM, stephane eranian <[EMAIL PROTECTED]>
> wrote:
>
>> What about you build statically with -static?
>>
>>
>> On Tue, Jul 15, 2008 at 1:07 AM, Hucheng Zhou <[EMAIL PROTECTED]>
>> wrote:
>> > Hi Eranian:
>> >
>> > I build the binary using -g option of gcc, but triggering the same
>> > warning.
>> >
>> > [EMAIL PROTECTED]:~# gcc -g unroll4_p_good.c
>> >
>> > [EMAIL PROTECTED]:~# pfmon ./a.out
>> > cannot install code breakpoints @ 0xffffffffffffffff
>> > 65501801218 UNHALTED_CORE_CYCLES
>> >
>> > Thanks.
>> >
>> > On Mon, Jul 14, 2008 at 2:54 PM, stephane eranian <
>> [EMAIL PROTECTED]>
>> > wrote:
>> >>
>> >> Hi,
>> >>
>> >> On Mon, Jul 14, 2008 at 11:47 PM, Hucheng Zhou <[EMAIL PROTECTED]
>> >
>> >> wrote:
>> >> > Hi @ll:
>> >> >
>> >> > Each time I use the pfmon, it complains that "cannot install code
>> >> > breakpoints @ 0xffffffffffffffff", what's wrong here? How to fix it?
>> >> > [EMAIL PROTECTED]:~# uname -a
>> >> > Linux yrnw20 2.6.24-smp-DEV #1 [4048897] SMP Mon Jun 30 17:57:29 PDT
>> >> > 2008
>> >> > x86_64 unknown
>> >> > Thanks in advance.
>> >> >
>> >> I have since reports of this. It appears to depend on how the binary
>> >> you're monitoring has been compiled.
>> >> Could you recompile it? If so, make sure you have the symbol table. I
>> >> think the problem maybe in how the
>> >> libraries were compiled. I don't have a system that exhibits this
>> >> behavior unfortunately.
>> >
>> >
>> >
>> > --
>> > Institute of High Performance Computing,
>> >
>> > Department of Computer Science and Technology,
>> >
>> > Tsinghua University, Beijing, China, 100084.
>>
>
>
>
> --
> Institute of High Performance Computing,
>
> Department of Computer Science and Technology,
>
> Tsinghua University, Beijing, China, 100084.
>
--
Institute of High Performance Computing,
Department of Computer Science and Technology,
Tsinghua University, Beijing, China, 100084.
-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/
_______________________________________________
perfmon2-devel mailing list
perfmon2-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/perfmon2-devel
