[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2015-06-09 Thread via Digitalmars-d-bugs
https://issues.dlang.org/show_bug.cgi?id=3742

Andrei Alexandrescu and...@erdani.com changed:

   What|Removed |Added

Version|future  |D2

--


[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2012-02-01 Thread d-bugmail
http://d.puremagic.com/issues/show_bug.cgi?id=3742


Don clugd...@yahoo.com.au changed:

   What|Removed |Added

 Status|NEW |RESOLVED
 Resolution||INVALID


--- Comment #5 from Don clugd...@yahoo.com.au 2012-02-01 22:30:23 PST ---
Invalid - processor specific, belongs in a library, too vague to be actionable.

-- 
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
--- You are receiving this mail because: ---


[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2011-02-06 Thread d-bugmail
http://d.puremagic.com/issues/show_bug.cgi?id=3742


Brad Roberts bra...@puremagic.com changed:

   What|Removed |Added

   Platform|x86_64  |x86


--- Comment #4 from Brad Roberts bra...@puremagic.com 2011-02-06 15:40:00 PST 
---
Mass migration of bugs marked as x86-64 to just x86.  The platform run on isn't
what's relevant, it's if the app is a 32 or 64 bit app.

-- 
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
--- You are receiving this mail because: ---


[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2010-02-04 Thread d-bugmail
http://d.puremagic.com/issues/show_bug.cgi?id=3742


Don clugd...@yahoo.com.au changed:

   What|Removed |Added

 CC||clugd...@yahoo.com.au


--- Comment #3 from Don clugd...@yahoo.com.au 2010-02-04 06:44:53 PST ---
I'm not sure that this is terribly relevant to D.
For in-depth analysis, this feature is nowhere near as comprehensive as the
hardware performance counters which have existed since the Pentium MMX days
(and which seem very under-utilized -- they are really fantastic). I think AMD
is being deliberately misleading. I take offence to this section:
These counters are used by the AMD CodeAnalyst Performance Analyzer and
provide deep insight into application
and system performance. However, each time a data sample is gathered, the
processor must take an interrupt to a kernel-mode driver, and that takes
hundreds or thousands of cycles.

It *sounds* as though this is talking about the hardware performance counters.
But it ISNT!! It's talking about their performance analyzer. It is possible
to get the same data they're talking about, without calling into kernel mode
all the time. You do NOT need to use their driver.

So, it's maybe a 5-10% improvement over what already exists. May be useful for
JIT compilers, but it isn't really anything to get terribly excited about.

-- 
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
--- You are receiving this mail because: ---


[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2010-01-25 Thread d-bugmail
http://d.puremagic.com/issues/show_bug.cgi?id=3742


nick barbalich nick.barbal...@gmail.com changed:

   What|Removed |Added

   Keywords||performance
 CC||nick.barbal...@gmail.com


--- Comment #1 from nick barbalich nick.barbal...@gmail.com 2010-01-25 
16:50:07 PST ---
Correction.  The current version is 3.04 dated August 2009.

-- 
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
--- You are receiving this mail because: ---


[Issue 3742] Please add support for 'Lightweight Profiling' which adds a set of user-controlled counters to the AMD64 architecture

2010-01-25 Thread d-bugmail
http://d.puremagic.com/issues/show_bug.cgi?id=3742


Brad Roberts bra...@puremagic.com changed:

   What|Removed |Added

 CC||bra...@puremagic.com


--- Comment #2 from Brad Roberts bra...@puremagic.com 2010-01-25 17:38:52 PST 
---
I think you're going to need to be a lot more specific about what you think
needs to be done with D.  Chances are high it's not a compiler change but
rather some library changes in either the core runtime or in phobos.  However,
whatever it is, it'd need to be done in a cpu agnostic manner with the
potential to be optimized for AMD.

-- 
Configure issuemail: http://d.puremagic.com/issues/userprefs.cgi?tab=email
--- You are receiving this mail because: ---