Article: Hot Chips XXI Preview
By: Linus Torvalds (torvalds.delete@this.linux-foundation.org), August 16, 2009 7:12 am
Room: Moderated Discussions
EduardoS (no@spam.com) on 8/16/09 wrote:
>
>Very interesting data about branches, so 90% of all
>conditional branches goes always to the same path?
.. for a specific load!
The thing is, for some cases, branches always go the same
way. Imagine some load like gcc - and think about the fact
that gcc uses all the same back-end code for C and C++,
and how some issues will basically never happen for one or
the other.
So when you do something like a SpecInt run, and you run
the gcc tests, yes, a lot of branches will go only one way
for that run. But that does not mean that they go
only one way in general!
Under other loads, they might well be unpredictable, or
predict well, but go the other way entirely! It might be
a conditional branch that tests for a specific flag or
mode, and if you run it in that mode, it will obviously
always go just one way. But other people may well care
about the "other case", the one that never happened when
you did your benchmark run.
>Doing a good branch predictor isn't that hard so...
I'm sorry, but you're totally wrong.
Doing a good branch predictor is very very hard, and the
spec runs don't show any of it.
What makes good branch predictors hard is exactly the
fact that actual users do odd (and often stupid - but hey,
they care about their own loads) things. And they don't
just run one single benchmark that they first could warm
up the caches for. No, they run things cold-cache, and they
run tons of other things in between.
And they may share the same code (dynamically loaded shared
libraries, anyone?) with different users and different
applications that have totally different behavior, and that
thus have different branch prediction.
>Also look on how badly static predictors was.
Exactly. Static prediction sucks. You can improve it by
doing PGO, but I suspect that paper had essentially already
done that (ie the "static prediction" was to predict a
particular branch as well as you could from the trace, but
always predict it one way).
And it sucks exactly because circumstances change. But that
is also why dynamic prediction is never easy. You not only
have cold-cache cases, but let's say that your branch
prediction table is 4k entries in size - now think about
how many branches you are actually going to predict when
that system is busy with anything serious that actually has
IO delays etc.
Why do IO delays matter? They matter because they affect
the working set enormously. If you run something like Spec,
where you run only one program at a time, and where you
have warm caches, then your working set is literally just
that single program.
Now think about usage on real high-end machines, and ask
yourself if they ever run a single program. They
generally don't. Even if it's technically a single program
(like a single database), it's going to have lots of threads
and run all those different parts of the same program at
once.
Do you think those 4k branch prediction entries are going
to capture all those conditional branches? Really? Or do
you think that maybe you have to just realize that your
predictor is going to miss a whole lot more on real loads
than you'll miss on something controlled like a specint run?
In other words: the branch prediction numbers from specint
should be considered absolutely "best possible case". Not
"oh, I could improve on that in an afternoon".
Linus
>
>Very interesting data about branches, so 90% of all
>conditional branches goes always to the same path?
.. for a specific load!
The thing is, for some cases, branches always go the same
way. Imagine some load like gcc - and think about the fact
that gcc uses all the same back-end code for C and C++,
and how some issues will basically never happen for one or
the other.
So when you do something like a SpecInt run, and you run
the gcc tests, yes, a lot of branches will go only one way
for that run. But that does not mean that they go
only one way in general!
Under other loads, they might well be unpredictable, or
predict well, but go the other way entirely! It might be
a conditional branch that tests for a specific flag or
mode, and if you run it in that mode, it will obviously
always go just one way. But other people may well care
about the "other case", the one that never happened when
you did your benchmark run.
>Doing a good branch predictor isn't that hard so...
I'm sorry, but you're totally wrong.
Doing a good branch predictor is very very hard, and the
spec runs don't show any of it.
What makes good branch predictors hard is exactly the
fact that actual users do odd (and often stupid - but hey,
they care about their own loads) things. And they don't
just run one single benchmark that they first could warm
up the caches for. No, they run things cold-cache, and they
run tons of other things in between.
And they may share the same code (dynamically loaded shared
libraries, anyone?) with different users and different
applications that have totally different behavior, and that
thus have different branch prediction.
>Also look on how badly static predictors was.
Exactly. Static prediction sucks. You can improve it by
doing PGO, but I suspect that paper had essentially already
done that (ie the "static prediction" was to predict a
particular branch as well as you could from the trace, but
always predict it one way).
And it sucks exactly because circumstances change. But that
is also why dynamic prediction is never easy. You not only
have cold-cache cases, but let's say that your branch
prediction table is 4k entries in size - now think about
how many branches you are actually going to predict when
that system is busy with anything serious that actually has
IO delays etc.
Why do IO delays matter? They matter because they affect
the working set enormously. If you run something like Spec,
where you run only one program at a time, and where you
have warm caches, then your working set is literally just
that single program.
Now think about usage on real high-end machines, and ask
yourself if they ever run a single program. They
generally don't. Even if it's technically a single program
(like a single database), it's going to have lots of threads
and run all those different parts of the same program at
once.
Do you think those 4k branch prediction entries are going
to capture all those conditional branches? Really? Or do
you think that maybe you have to just realize that your
predictor is going to miss a whole lot more on real loads
than you'll miss on something controlled like a specint run?
In other words: the branch prediction numbers from specint
should be considered absolutely "best possible case". Not
"oh, I could improve on that in an afternoon".
Linus
Topic | Posted By | Date |
---|---|---|
Hot Chips XXI Preview online | David Kanter | 2009/08/12 01:55 PM |
Hot Chips XXI Preview online | Groo | 2009/08/12 04:27 PM |
Hot Chips XXI Preview online | David Kanter | 2009/08/12 05:17 PM |
recent POWER7 info. from IBM | M.Isobe | 2009/08/16 01:04 AM |
Hot Chips XXI Preview online | slacker | 2009/08/12 07:11 PM |
Attending hot chips | David Kanter | 2009/08/12 07:53 PM |
Power7 vs. single threaded performance and licensing | Daniel Bizó | 2009/08/12 11:05 PM |
Power7 vs. single threaded performance and licensing | Wes Felter | 2009/08/13 10:17 AM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/13 02:25 PM |
Power7 vs. single threaded performance and licensing | Linus Torvalds | 2009/08/13 02:48 PM |
How much IPC | E | 2009/08/14 12:16 AM |
How much IPC | hobold | 2009/08/14 02:03 AM |
How much IPC | a reader | 2009/08/15 09:26 AM |
How much IPC | hobold | 2009/08/15 09:58 AM |
How much IPC | Linus Torvalds | 2009/08/15 11:09 AM |
How much IPC | hobold | 2009/08/15 11:45 AM |
How much IPC | Euronymous | 2009/08/15 12:41 PM |
How much IPC | ? | 2009/08/16 12:13 AM |
How much IPC | Anonymous | 2009/08/16 01:07 AM |
How much IPC | ? | 2009/08/16 02:49 AM |
How much IPC | EduardoS | 2009/08/16 06:04 AM |
How much IPC | Anonymous | 2009/08/16 04:26 PM |
How much IPC | Linus Torvalds | 2009/08/16 06:49 AM |
How much IPC | ? | 2009/08/16 08:32 AM |
How much IPC | EduardoS | 2009/08/16 06:09 AM |
How much IPC | Linus Torvalds | 2009/08/16 07:12 AM |
How much IPC | a reader | 2009/08/16 10:41 AM |
How much IPC | Linus Torvalds | 2009/08/16 11:21 AM |
How much IPC | none | 2009/08/16 12:30 PM |
How much IPC | ? | 2009/08/16 10:32 PM |
How much IPC | ? | 2009/08/16 11:09 PM |
How much IPC | none | 2009/08/17 01:29 AM |
How much IPC | ? | 2009/08/17 04:25 AM |
Speculation and waste | David Kanter | 2009/08/17 09:03 AM |
Speculation and waste | ? | 2009/08/18 10:59 AM |
Speculation and waste | David Kanter | 2009/08/18 11:22 AM |
Speculation and waste | anon | 2009/08/19 01:52 AM |
Speculation and waste | TruePath | 2009/09/27 05:23 AM |
How much IPC | none | 2009/08/18 12:55 AM |
How much IPC | anon | 2009/08/18 01:27 AM |
How much IPC | anon | 2009/08/16 09:05 PM |
How much IPC | Linus Torvalds | 2009/08/17 09:17 AM |
How much IPC | _Arthur | 2009/08/17 02:23 PM |
How much IPC | David Kanter | 2009/08/17 02:38 PM |
How much IPC | Michael S | 2009/08/17 02:39 PM |
How much IPC | David Kanter | 2009/08/17 02:48 PM |
How much IPC | Michael S | 2009/08/17 04:03 PM |
How much IPC | _Arthur | 2009/08/17 04:33 PM |
How much IPC | Michael S | 2009/08/17 04:56 PM |
How much IPC | _Arthur | 2009/08/17 07:48 PM |
How much IPC | Michael S | 2009/08/18 02:07 AM |
limits of sorting | hobold | 2009/08/18 03:26 AM |
limits of sorting | Michael S | 2009/08/18 04:26 AM |
limits of sorting | _Arthur | 2009/08/18 05:03 AM |
limits of sorting | Richard Cownie | 2009/08/18 05:32 AM |
limits of sorting | Michael S | 2009/08/18 06:17 AM |
limits of sorting | Richard Cownie | 2009/08/18 07:22 AM |
limits of sorting | _Arthur | 2009/08/18 07:57 AM |
limits of sorting | Richard Cownie | 2009/08/18 08:30 AM |
limits of sorting | Richard Cownie | 2009/08/18 08:45 AM |
limits of sorting | Michael S | 2009/08/18 08:50 AM |
limits of sorting | Richard Cownie | 2009/08/18 09:09 AM |
limits of sorting | Michael S | 2009/08/18 09:33 AM |
limits of sorting | Richard Cownie | 2009/08/18 09:53 AM |
limits of sorting | Michael S | 2009/08/18 10:28 AM |
limits of sorting | Richard Cownie | 2009/08/18 11:01 AM |
limits of sorting | JasonB | 2009/08/18 05:40 PM |
limits of sorting | Richard Cownie | 2009/08/18 06:22 PM |
You work on EDA right Richard? | David Kanter | 2009/08/18 06:49 PM |
You work on EDA right Richard? | Richard Cownie | 2009/08/19 04:56 AM |
You work on EDA right Richard? | David Kanter | 2009/08/19 07:26 AM |
You work on EDA right Richard? | Richard Cownie | 2009/08/19 07:47 AM |
You work on EDA right Richard? | slacker | 2009/08/19 08:52 AM |
You work on EDA right Richard? | Richard Cownie | 2009/08/19 09:10 AM |
You work on EDA right Richard? | slacker | 2009/08/19 10:36 PM |
You work on EDA right Richard? | slacker | 2009/08/19 10:45 PM |
You work on EDA right Richard? | Richard Cownie | 2009/08/20 04:28 AM |
You work on EDA right Richard? | slacker | 2009/08/20 05:32 AM |
You work on EDA right Richard? | Aaron Spink | 2009/08/19 11:08 PM |
You work on EDA right Richard? | Rob Thorpe | 2009/08/20 07:31 AM |
You work on EDA right Richard? | David Kanter | 2009/08/20 08:58 AM |
You work on EDA right Richard? | Rob Thorpe | 2009/08/20 03:10 PM |
limits of sorting | rwessel | 2009/08/18 06:56 PM |
limits of sorting | JasonB | 2009/08/18 10:11 PM |
limits of sorting | JasonB | 2009/08/18 10:25 PM |
limits of sorting | Richard Cownie | 2009/08/19 05:32 AM |
limits of sorting | Rob Thorpe | 2009/08/19 06:12 AM |
limits of sorting | Richard Cownie | 2009/08/19 06:46 AM |
limits of sorting | JasonB | 2009/08/19 07:43 PM |
limits of sorting | Richard Cownie | 2009/08/20 06:47 AM |
limits of sorting | JasonB | 2009/08/20 07:20 PM |
limits of sorting | Richard Cownie | 2009/08/20 10:12 PM |
limits of sorting | JasonB | 2009/08/21 01:08 AM |
limits of sorting | Richard Cownie | 2009/08/21 04:15 AM |
limits of sorting | JasonB | 2009/08/22 05:24 PM |
limits of sorting | Richard Cownie | 2009/08/22 06:27 PM |
limits of sorting | Richard Cownie | 2009/08/22 07:39 PM |
limits of sorting | ? | 2009/08/23 04:07 AM |
limits of sorting | Richard Cownie | 2009/08/23 04:53 AM |
limits of sorting | anonymous | 2009/08/23 10:42 AM |
useful link, thanks | Richard Cownie | 2009/08/23 04:23 PM |
limits of sorting | ? | 2009/09/04 03:05 AM |
limits of sorting | JasonB | 2009/08/23 08:26 AM |
wacky C++ features | Richard Cownie | 2009/08/24 06:13 AM |
wacky C++ features | a reader | 2009/08/24 08:59 PM |
wacky C++ features | Richard Cownie | 2009/08/25 02:18 AM |
wacky C++ features | a reader | 2009/08/25 06:04 AM |
wacky C++ features | Potatoswatter | 2009/08/25 09:21 PM |
wacky C++ features | none | 2009/08/26 04:47 AM |
wacky C++ features | Richard Cownie | 2009/08/26 07:09 AM |
wacky C++ features | Potatoswatter | 2009/08/27 05:25 AM |
wacky C++ features | Andi Kleen | 2009/08/24 11:06 PM |
wacky C++ features | Richard Cownie | 2009/08/25 02:10 AM |
wacky C++ features | Octoploid | 2009/08/25 02:40 AM |
wacky C++ features | Richard Cownie | 2009/08/25 04:15 AM |
wacky C++ features | Andi Kleen | 2009/08/25 06:58 AM |
thanks | Richard Cownie | 2009/08/25 07:07 AM |
thanks | Andi Kleen | 2009/08/25 10:28 AM |
wacky C++ features | anon | 2009/08/25 02:34 PM |
wacky C++ features | Andi Kleen | 2009/08/25 09:25 PM |
wacky C++ features | JasonB | 2009/08/25 12:13 AM |
wacky C++ features | Richard Cownie | 2009/08/25 01:32 AM |
exception | a reader | 2009/08/25 06:32 AM |
exception | Richard Cownie | 2009/08/25 06:57 AM |
exception | Potatoswatter | 2009/08/25 07:30 AM |
wacky C++ features | JasonB | 2009/08/25 07:56 PM |
correction | JasonB | 2009/08/25 08:47 PM |
correction | c++ | 2009/08/26 08:53 AM |
correction | JasonB | 2009/08/26 06:48 PM |
(new char[10]) does not have array type (NT) | Potatoswatter | 2009/08/27 05:27 AM |
correction | Potatoswatter | 2009/08/27 06:52 AM |
correction | c++ | 2009/08/27 08:29 AM |
comeau bugs and gcc features | Potatoswatter | 2009/08/27 08:51 AM |
comeau bugs and gcc features | Potatoswatter | 2009/08/27 10:28 AM |
wacky C++ features | Richard Cownie | 2009/08/26 08:17 AM |
wacky C++ features | JasonB | 2009/08/26 06:46 PM |
wacky C++ features | Richard Cownie | 2009/08/27 08:41 AM |
wacky C++ features | JasonB | 2009/08/27 08:33 PM |
wacky C++ features | Richard Cownie | 2009/08/28 12:24 AM |
wacky C++ features | Richard Cownie | 2009/08/28 12:27 AM |
wacky C++ features | Michael S | 2009/08/28 05:05 AM |
wacky C++ features | EduardoS | 2009/08/28 05:45 AM |
wacky C++ features | Richard Cownie | 2009/08/28 06:50 AM |
wacky C++ features | JasonB | 2009/08/28 03:56 PM |
wacky C++ features | JasonB | 2009/08/28 04:55 PM |
wacky C++ features | Richard Cownie | 2009/08/28 06:44 PM |
wacky C++ features | Konrad Schwarz | 2009/09/07 03:24 AM |
wacky C++ features | EduardoS | 2009/08/26 02:22 PM |
wacky C++ features | JasonB | 2009/08/26 05:47 PM |
wacky C++ features | Jukka Larja | 2009/08/26 11:03 PM |
wacky C++ features | JasonB | 2009/08/27 12:17 AM |
wacky C++ features | EduardoS | 2009/08/27 02:26 PM |
wacky C++ features | JasonB | 2009/08/27 05:31 PM |
wacky C++ features | EduardoS | 2009/08/28 02:25 PM |
wacky C++ features | JasonB | 2009/08/28 05:20 PM |
wacky C++ features | JasonB | 2009/08/27 08:56 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/21 06:33 AM |
Windows vs Unix/Linux culture | Michael S | 2009/08/21 07:07 AM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/21 07:33 AM |
Windows vs Unix/Linux culture | Paul | 2009/08/22 03:12 AM |
Windows vs Unix/Linux culture | anon | 2009/08/21 10:18 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/21 10:45 PM |
Windows vs Unix/Linux culture | anon | 2009/08/21 11:48 PM |
Windows vs Unix/Linux culture | Paul | 2009/08/22 03:25 AM |
Windows vs Unix/Linux culture | Gian-Carlo Pascutto | 2009/08/22 06:02 AM |
Windows vs Unix/Linux culture | Paul | 2009/08/22 07:13 AM |
Windows vs Unix/Linux culture | rwessel | 2009/08/24 02:09 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/22 04:28 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/22 05:22 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/22 05:52 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/22 06:47 PM |
Encapsulation | Konrad Schwarz | 2009/09/03 03:49 AM |
Encapsulation | anon | 2009/09/03 09:05 AM |
Encapsulation | ? | 2009/09/03 10:38 AM |
Encapsulation | Andi Kleen | 2009/09/04 12:41 AM |
Encapsulation | anon | 2009/09/04 06:24 AM |
Encapsulation | Richard Cownie | 2009/09/04 06:34 AM |
Encapsulation | Konrad Schwarz | 2009/09/07 02:28 AM |
Encapsulation | Richard Cownie | 2009/09/07 03:04 PM |
Windows vs Unix/Linux culture | ? | 2009/09/03 10:51 AM |
Windows vs Unix/Linux culture | no thanks | 2009/08/23 09:36 AM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/23 03:23 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/23 07:31 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/23 11:10 PM |
Windows vs Unix/Linux culture | Jukka Larja | 2009/08/24 09:13 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/24 10:35 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/25 02:04 AM |
Windows vs Unix/Linux culture | JasonB | 2009/08/25 10:48 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/26 07:28 AM |
Windows vs Unix/Linux culture | JasonB | 2009/08/26 09:31 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/26 07:43 AM |
Windows vs Unix/Linux culture | anon | 2009/08/26 12:48 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/26 02:28 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/26 07:06 PM |
Windows vs Unix/Linux culture | Richard Cownie | 2009/08/27 02:44 AM |
Windows vs Unix/Linux culture | Rob Thorpe | 2009/08/27 04:51 AM |
Windows vs Unix/Linux culture | JasonB | 2009/08/23 08:07 PM |
Windows vs Unix/Linux culture | no thanks | 2009/08/23 08:44 PM |
Windows vs Unix/Linux culture | JasonB | 2009/08/23 11:34 PM |
Windows vs Unix/Linux culture | anon | 2009/08/23 08:46 PM |
limits of sorting | Richard Cownie | 2009/08/20 06:59 AM |
limits of sorting | Richard Cownie | 2009/08/20 08:27 AM |
limits of sorting | JasonB | 2009/08/20 07:55 PM |
limits of sorting | Richard Cownie | 2009/08/20 10:22 PM |
limits of sorting | JasonB | 2009/08/20 11:15 PM |
limits of sorting | Richard Cownie | 2009/08/21 03:47 AM |
limits of sorting | ? | 2009/08/20 10:42 PM |
limits of sorting | Richard Cownie | 2009/08/21 06:51 AM |
limits of sorting | Michael S | 2009/08/21 07:11 AM |
limits of sorting | Richard Cownie | 2009/08/21 07:38 AM |
limits of sorting | dmsc | 2009/08/20 06:56 PM |
limits of sorting | Richard Cownie | 2009/08/20 07:20 PM |
limits of sorting | Rob Thorpe | 2009/08/20 07:09 AM |
limits of sorting | Aaron Spink | 2009/08/19 11:19 PM |
limits of sorting | JasonB | 2009/08/20 12:55 AM |
limits of sorting | Michael S | 2009/08/18 06:12 AM |
limits of sorting | hobold | 2009/08/18 06:55 AM |
limits of sorting | rwessel | 2009/09/08 01:52 PM |
maximal theoretical sorting efficiency | Emil | 2009/09/08 06:06 PM |
maximal theoretical sorting efficiency | rwessel | 2009/09/08 09:04 PM |
maximal theoretical sorting efficiency | hobold | 2009/09/09 03:56 AM |
maximal theoretical sorting efficiency | Richard Cownie | 2009/09/09 08:10 AM |
maximal theoretical sorting efficiency | hobold | 2009/09/10 04:39 AM |
maximal theoretical sorting efficiency | Richard Cownie | 2009/09/10 07:05 AM |
maximal theoretical sorting efficiency | Potatoswatter | 2009/09/10 12:23 PM |
maximal theoretical sorting efficiency | dmsc | 2009/09/13 07:04 AM |
limits of sorting | Potatoswatter is back! | 2009/08/21 05:07 PM |
indeed it doesn't succeed in partitioning at all, but you get the idea ;) (NT) | Potatoswatter is back! | 2009/08/21 05:12 PM |
indeed it doesn't succeed in partitioning at all, but you get the idea ;) (NT) | Jouni Osmala | 2009/08/22 12:01 AM |
limits of sorting | hobold | 2009/08/22 06:25 AM |
limits of sorting | Potatoswatter | 2009/08/22 07:45 AM |
limits of sorting | David Kanter | 2009/08/22 09:16 AM |
limits of sorting | Jouni Osmala | 2009/08/22 11:01 AM |
Oops that was counting sort not bucket sort ;( | Jouni Osmala | 2009/08/22 11:07 AM |
close enough for my purposes | hobold | 2009/08/22 01:15 PM |
select vs. cmove | hobold | 2009/08/22 01:25 PM |
How much IPC | Gian-Carlo Pascutto | 2009/08/18 02:25 AM |
How much IPC | Vincent Diepeveen | 2009/08/19 05:46 AM |
How much IPC | _Arthur | 2009/08/19 08:32 AM |
How much IPC | hobold | 2009/08/18 03:17 AM |
How much IPC | Michael S | 2009/08/18 04:33 AM |
How much IPC | hobold | 2009/08/18 06:35 AM |
How much IPC | ? | 2009/08/18 11:20 AM |
How much IPC | _Arthur | 2009/08/18 11:33 AM |
Nit picking | David Kanter | 2009/08/18 01:17 PM |
Nit picking | _Arthur | 2009/08/18 01:37 PM |
Nit picking | Michael S | 2009/08/18 02:02 PM |
Nit picking | S. Rao | 2009/08/18 04:02 PM |
Nit picking | anon | 2009/08/19 02:03 AM |
Nit picking | Michael S | 2009/08/18 01:53 PM |
Nit picking | JasonB | 2009/08/18 06:16 PM |
How much IPC | ? | 2009/08/18 01:37 PM |
How much IPC | _Arthur | 2009/08/18 03:23 PM |
How much IPC | Matt Sayler | 2009/08/18 05:09 PM |
How much IPC | ? | 2009/08/18 10:59 PM |
nick's testcase | a reader | 2009/08/17 04:47 PM |
How much IPC | TruePath | 2009/09/27 09:00 AM |
Explicit dependency chains | David Kanter | 2009/09/30 06:56 PM |
How much IPC | TruePath | 2009/09/27 09:00 AM |
How much IPC | hobold | 2009/08/17 05:38 AM |
How much IPC | anon | 2009/08/16 08:59 PM |
Speeing Up Single Threads | TruePath | 2009/09/27 07:58 AM |
How much IPC | anon | 2009/08/15 07:01 PM |
How much IPC | EduardoS | 2009/08/16 06:06 AM |
How much IPC | sJ | 2009/08/16 08:48 PM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/14 02:26 PM |
Power7 vs. single threaded performance and licensing | Linus Torvalds | 2009/08/14 03:04 PM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/21 02:43 PM |
Power7 vs. single threaded performance and licensing | Linus Torvalds | 2009/08/21 03:08 PM |
Power7 vs. single threaded performance and licensing | Linus Torvalds | 2009/08/21 03:33 PM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/22 07:57 AM |
Power7 vs. single threaded performance and licensing | Jukka Larja | 2009/08/22 10:04 PM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/25 11:33 AM |
Power7 vs. single threaded performance and licensing | ? | 2009/08/21 11:51 PM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/22 09:56 AM |
Power7 vs. single threaded performance and licensing | Linus Torvalds | 2009/08/22 10:38 AM |
Power7 vs. single threaded performance and licensing | ? | 2009/08/23 03:05 AM |
Power7 vs. single threaded performance and licensing | EduardoS | 2009/08/23 03:28 AM |
Programming Larrabee | ? | 2009/08/23 05:48 AM |
Programming Larrabee | EduardoS | 2009/08/23 06:41 AM |
Programming Larrabee | anon | 2009/08/23 07:29 AM |
Programming Larrabee | Potatoswatter | 2009/08/23 06:47 AM |
Programming Larrabee | Richard Cownie | 2009/08/23 08:11 AM |
Programming Larrabee | Potatoswatter | 2009/08/23 11:49 PM |
Programming Larrabee | ? | 2009/08/23 08:59 AM |
Programming Larrabee | Potatoswatter | 2009/08/23 11:44 PM |
Programming Larrabee | hobold | 2009/08/24 05:41 AM |
Programming Larrabee | none | 2009/08/24 07:15 AM |
Programming Larrabee | Richard Cownie | 2009/08/24 07:33 AM |
Programming Larrabee | Jukka Larja | 2009/08/24 09:30 PM |
Programming Larrabee | none | 2009/08/25 01:53 AM |
Programming Larrabee | mpx | 2009/08/25 08:16 AM |
Power7 vs. single threaded performance and licensing | Joe | 2009/08/24 08:38 AM |
Power7 vs. single threaded performance and licensing | Gabriele Svelto | 2009/08/14 03:35 AM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/14 08:18 AM |
Power7 vs. single threaded performance and licensing | EduardoS | 2009/08/14 04:34 PM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/15 06:30 AM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/15 07:23 AM |
improving Netburst | AM | 2009/08/15 01:36 AM |
improving Netburst | anon | 2009/08/15 07:10 AM |
improving Netburst | Euronymous | 2009/08/15 08:35 AM |
improving Netburst | Michael S | 2009/08/15 01:18 PM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/21 03:10 PM |
Power7 vs. single threaded performance and licensing | anon | 2009/08/22 09:46 AM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/25 09:39 AM |
Power7 vs. single threaded performance and licensing | slacker | 2009/08/26 04:50 AM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/26 08:12 AM |
Power7 vs. single threaded performance and licensing | Jonathan Kang | 2009/08/26 08:45 AM |
Power7 vs. single threaded performance and licensing | someone | 2009/08/26 10:29 AM |
Power7 vs. single threaded performance and licensing | David Kanter | 2009/08/26 10:47 AM |
Not necessarily | Daniel Bizó | 2009/08/14 02:53 AM |
new POWER7 info .. | Thu Nguyen | 2009/08/25 03:05 AM |
new POWER7 info .. | someone | 2009/08/25 05:47 AM |
new POWER7 info .. | hobold | 2009/08/25 06:50 AM |
new POWER7 info .. | G Webb | 2009/08/25 11:49 PM |
new POWER7 info .. | mpx | 2009/08/25 07:36 AM |
new POWER7 info .. | someone | 2009/08/25 08:16 AM |
new POWER7 info .. | Jesper Frimann | 2009/08/27 08:18 AM |
new POWER7 info .. | Linus Torvalds | 2009/08/27 10:53 AM |
new POWER7 info .. | someone | 2009/08/27 12:00 PM |
new POWER7 info .. | a reader | 2009/08/27 03:21 PM |
new POWER7 info .. | David Kanter | 2009/08/27 08:32 PM |
new POWER7 info .. | a reader | 2009/08/28 07:45 AM |
new POWER7 info .. | hobold | 2009/08/28 04:00 AM |
new POWER7 info .. | someone | 2009/08/28 05:51 AM |
new POWER7 info .. | hobold | 2009/08/28 06:44 AM |
new POWER7 info .. | someone | 2009/08/28 07:10 AM |
Non Autopar submissions for Nehalem | IlleglWpns | 2009/08/28 09:41 AM |
Non Autopar submissions for Nehalem | David Kanter | 2009/08/28 10:07 AM |
Non Autopar submissions for Nehalem | someone | 2009/08/28 11:00 AM |
new POWER7 info .. | mas | 2009/08/25 11:25 PM |
An EV8 lite? (NT) | anon | 2009/08/26 08:21 AM |
An EV8 lite? => Piranha? | M. | 2009/08/30 03:54 AM |
new POWER7 info .. | Mark Roulo | 2009/08/27 05:51 AM |
new POWER7 info .. | someone | 2009/08/27 06:03 AM |
new POWER7 info .. | a reader | 2009/08/27 08:55 AM |
new POWER7 info .. | someone | 2009/08/27 10:58 AM |
new POWER7 info .. | a reader | 2009/08/27 03:11 PM |
new POWER7 info .. | Gabriele Svelto | 2009/08/27 11:17 PM |
new POWER7 info .. | someone | 2009/08/28 04:27 AM |
new POWER7 info .. | a reader | 2009/08/28 08:07 AM |
OOOE for low power | David Kanter | 2009/08/28 10:15 AM |
OOOE for low power | someone | 2009/08/28 10:39 AM |
OOOE for low power | David Kanter | 2009/08/28 12:55 PM |
OOOE for low power | Mark Roulo | 2009/08/28 02:16 PM |
OOOE for low power | Mark Roulo | 2009/08/28 02:44 PM |
Atom uarch | David Kanter | 2009/08/28 07:19 PM |
OOOE for low power | David Kanter | 2009/08/28 07:07 PM |
OOOE for low power | someone | 2009/08/28 03:18 PM |
OOOE for low power | David Kanter | 2009/08/29 12:55 AM |
OOOE for low power | someone | 2009/08/29 06:21 AM |
OOOE for low power | a reader | 2009/08/29 08:14 AM |
OOOE for low power | someone | 2009/08/29 08:56 AM |
OOOE for low power | David Kanter | 2009/08/29 09:08 AM |
OOOE for low power | Michael S | 2009/08/29 10:27 AM |
OOOE for low power | a reader | 2009/08/29 03:50 PM |
OOOE for low power | anonymous | 2009/08/29 06:17 PM |
OOOE for low power | Michael S | 2009/08/29 11:07 PM |
OOOE for low power | Jonathan Kang | 2009/09/01 04:44 AM |
OOOE for low power | Michael S | 2009/09/01 03:21 PM |
OOOE for low power | Mark Roulo | 2009/09/01 04:53 PM |
OOOE for low power | Wilco | 2009/09/02 01:27 AM |
OOOE for low power | Mark Roulo | 2009/09/02 07:46 AM |
OOOE for low power | Wilco | 2009/09/02 03:52 PM |
Define "emulate" (NT) | Michael S | 2009/09/02 10:44 PM |
Define "emulate" | Wilco | 2009/09/02 11:33 PM |
Define "emulate" | none | 2009/09/03 03:46 AM |
Define "emulate" | Adrian | 2009/09/03 09:45 AM |
Define "emulate" | Wilco | 2009/09/03 01:20 PM |
Define "emulate" | none | 2009/09/03 09:41 PM |
Define "emulate" | Wilco | 2009/09/04 02:30 AM |
low power ARM chips | Michael S | 2009/10/31 01:32 PM |
low power ARM chips | Gabriele Svelto | 2009/10/31 03:05 PM |
low power ARM chips | Michael S | 2009/10/31 03:45 PM |
low power ARM chips | t | 2009/10/31 04:21 PM |
OOOE for low power | David Kanter | 2009/08/29 09:07 AM |
OOOE for low power | someone | 2009/08/29 11:40 AM |
OOOE for low power | a reader | 2009/08/29 04:03 PM |
OOOE for low power | anonymous | 2009/08/29 06:13 PM |
OOOE for low power | someone | 2009/08/30 06:35 AM |
OOOE for low power | David Kanter | 2009/08/30 01:32 PM |
OOOE for low power | Matt Sayler | 2009/08/31 12:38 PM |
OOOE for low power | David Kanter | 2009/08/30 11:07 AM |
OOOE for low power | Michael S | 2009/08/29 10:44 AM |
TTM | Michael S | 2009/08/29 11:24 AM |
TTM | Foo_ | 2009/08/29 12:40 PM |
TTM | Michael S | 2009/08/29 01:10 PM |
TTM | anon | 2009/08/29 06:33 PM |
TTM | Jukka Larja | 2009/08/29 08:49 PM |
TTM | anon | 2009/08/30 05:07 AM |
TTM | Jukka Larja | 2009/08/30 08:31 PM |
Area, power and Atom | David Kanter | 2009/08/30 09:36 PM |
Area, power and Atom | Michael S | 2009/08/30 11:18 PM |
Area, power and Atom | a reader | 2009/08/31 07:44 AM |
Area, power and Atom | Michael S | 2009/08/31 11:19 AM |
Area, power and Atom | a reader | 2009/08/31 01:53 PM |
Area, power and Atom | anonymous | 2009/08/31 03:17 PM |
Area, power and Atom | Gabriele Svelto | 2009/08/31 02:41 PM |
64-bit disabled Atoms | Foo_ | 2009/09/02 03:38 AM |
64-bit disabled Atoms | Robert David Graham | 2009/09/02 11:56 AM |
64-bit disabled Atoms | anon | 2009/09/02 01:14 PM |
64-bit disabled Atoms | anonymous | 2009/09/02 03:30 PM |
TTM | Michael S | 2009/08/30 10:49 PM |
TTM | Jukka Larja | 2009/08/31 10:23 PM |
TTM | Paul | 2009/08/30 05:38 AM |
TTM | Paul | 2009/08/30 05:40 AM |
TTM | Mark Roulo | 2009/08/30 08:50 AM |
TTM | Paul | 2009/08/30 08:54 AM |
TTM | Mark Roulo | 2009/08/30 09:16 AM |
TTM | Foo_ | 2009/09/02 03:31 AM |
OOOE for low power | Rob Thorpe | 2009/08/30 08:19 AM |
OOOE for low power | Michael S | 2009/08/29 10:16 AM |
OOOE for low power | Jukka Larja | 2009/08/29 08:40 PM |
OOOE for low power | Michael S | 2009/08/29 11:04 PM |
OOOE and cache/mem sizes | Richard Cownie | 2009/08/28 04:30 PM |
OOOE and cache/mem sizes | Linus Torvalds | 2009/08/31 09:53 PM |
OOOE and cache/mem sizes | Richard Cownie | 2009/09/01 03:15 AM |
OOOE and pipe length etc. | AM | 2009/09/01 07:35 AM |
OOOE and pipe length etc. | Jouni Osmala | 2009/09/01 07:57 AM |
OOOE and clock rate | AM | 2009/09/02 12:34 AM |
OOOE and clock rate | Jouni Osmala | 2009/09/02 04:35 AM |
OOOE and clock rate | Martin Høyer Kristiansen | 2009/09/02 05:19 AM |
OOOE and clock rate | anon | 2009/09/02 08:43 PM |
OOOE and clock rate | AM | 2009/09/03 01:52 AM |
OOOE and clock rate | Jouni Osmala | 2009/09/03 06:34 AM |
OOOE impacts | AM | 2009/09/04 01:04 AM |
OOOE impacts | David Kanter | 2009/09/04 09:12 AM |
OOOE impacts | Jouni Osmala | 2009/09/06 11:16 AM |
OOOE impacts | AM | 2009/09/07 02:47 AM |
OOOE impacts | Martin Høyer Kristiansen | 2009/09/07 05:03 AM |
Does IBM lie about PPC603 being OoO chip? | AM | 2009/09/08 02:13 AM |
No, but... | Michael S | 2009/09/08 06:05 AM |
No, but... | hobold | 2009/09/09 04:09 AM |
OOOE impacts | JS | 2009/09/07 05:34 AM |
Are Sandpile and others wrong about 0.28 um? | AM | 2009/09/08 02:12 AM |
OOOE impacts | someone | 2009/09/08 05:43 AM |
OOOE impacts | Jouni Osmala | 2009/09/07 06:48 AM |
OOOE costs | David Kanter | 2009/09/07 11:07 AM |
OOOE impacts | AM | 2009/09/08 02:11 AM |
OOOE impacts | Jouni Osmala | 2009/09/10 12:53 AM |
OOOE impacts | AM | 2009/09/11 03:35 AM |
OOOE impacts | Jouni Osmala | 2009/09/11 07:38 AM |
OOOE impacts | AM | 2009/09/12 04:06 AM |
OOOE impacts | Jouni Osmala | 2009/09/12 10:36 PM |
OOOE impacts | AM | 2009/09/14 03:39 AM |
OOOE impacts | Jouni Osmala | 2009/09/14 05:18 AM |
if-ex distance | AM | 2009/09/15 04:16 AM |
small addendum | AM | 2009/09/19 02:54 AM |
small addendum | Jouni Osmala | 2009/09/19 08:51 PM |
small addendum | AM | 2009/09/20 05:54 AM |
small addendum | Jouni Osmala | 2009/09/20 12:16 PM |
small addendum | Thiago Kurovski | 2009/09/20 03:51 PM |
small addendum | Jouni Osmala | 2009/09/20 08:21 PM |
small addendum | Thiago Kurovski | 2009/09/21 05:59 AM |
small addendum | AM | 2009/09/21 02:14 AM |
small addendum | Jukka Larja | 2009/09/21 09:21 PM |
small addendum | AM | 2009/09/22 02:01 AM |
small addendum | Jukka Larja | 2009/09/22 10:31 PM |
small addendum | AM | 2009/09/23 07:35 AM |
small addendum | Jukka Larja | 2009/09/23 09:31 PM |
small addendum | AM | 2009/09/23 11:13 PM |
OT metadiscussion | Jukka Larja | 2009/09/24 08:39 PM |
OT metadiscussion | AM | 2009/09/25 04:18 AM |
Back to bits | Michael S | 2009/09/25 06:14 AM |
Back to bits | Thiago Kurovski | 2009/09/25 10:24 AM |
Back to bits | Wilco | 2009/09/25 02:18 PM |
Back to bits | Thiago Kurovski | 2009/09/26 08:12 AM |
Back to bits | Michael S | 2009/09/26 07:54 AM |
Back to bits | Thiago Kurovski | 2009/09/26 08:05 AM |
Back to bits | Michael S | 2009/09/26 08:16 AM |
Agree, with very minor change. | Jouni Osmala | 2009/09/25 08:37 PM |
Back to bits | AM | 2009/09/26 05:16 AM |
Back to bits | Michael S | 2009/09/26 08:13 AM |
OT metadiscussion | David Kanter | 2009/09/25 11:23 AM |
OT metadiscussion | AM | 2009/09/26 04:55 AM |
OT metadiscussion | Jukka Larja | 2009/09/25 10:33 PM |
OT metadiscussion | AM | 2009/09/26 04:50 AM |
OT metadiscussion | Jukka Larja | 2009/09/27 01:16 AM |
OT metadiscussion | Michael S | 2009/09/27 03:58 AM |
OT metadiscussion | AM | 2009/09/28 03:07 AM |
OT metadiscussion | AM | 2009/09/28 02:43 AM |
OT metadiscussion | Jukka Larja | 2009/09/28 11:45 PM |
OT metadiscussion | AM | 2009/09/30 02:13 AM |
OT metadiscussion | Jukka Larja | 2009/10/01 12:34 AM |
OT metadiscussion | AM | 2009/10/01 03:05 AM |
OT metadiscussion | Jukka Larja | 2009/10/01 11:38 PM |
OT metadiscussion | AM | 2009/10/03 06:19 AM |
OT metadiscussion | Jukka Larja | 2009/10/04 02:38 AM |
OT metadiscussion | AM | 2009/10/04 07:27 AM |
OT metadiscussion | Jukka Larja | 2009/10/04 10:48 PM |
OT metadiscussion | AM | 2009/10/05 06:13 AM |
About teaching | Jukka Larja | 2009/10/05 10:36 PM |
About teaching | AM | 2009/10/06 03:37 AM |
About teaching | Jukka Larja | 2009/10/07 02:15 AM |
About teaching | anon | 2009/10/07 11:39 AM |
About teaching | AM | 2009/10/08 02:11 AM |
About teaching | Jukka Larja | 2009/10/09 03:10 AM |
About teaching | AM | 2009/10/09 04:40 AM |
About teaching | Jukka Larja | 2009/10/09 08:02 PM |
About teaching | AM | 2009/10/09 10:24 PM |
About teaching | Jukka Larja | 2009/10/10 09:50 PM |
About teaching | AM | 2009/10/12 01:02 AM |
About teaching | Jukka Larja | 2009/10/12 09:51 PM |
About teaching | AM | 2009/10/13 03:06 AM |
About teaching | Jukka Larja | 2009/10/13 10:33 PM |
About teaching | AM | 2009/10/14 02:36 AM |
About teaching | Jukka Larja | 2009/10/14 07:19 PM |
About teaching | AM | 2009/10/15 03:22 AM |
About teaching | Salvatore De Dominicis | 2009/10/12 01:23 AM |
About teaching | Dean Kent | 2009/10/12 11:25 AM |
About teaching | Salvatore De Dominicis | 2009/10/13 01:11 AM |
OT metadiscussion | Seni | 2009/09/26 05:26 AM |
OT metadiscussion | Wilco | 2009/09/26 07:08 AM |
OT metadiscussion | Jukka Larja | 2009/09/27 01:18 AM |
OT metadiscussion | Michael S | 2009/09/27 04:12 AM |
small addendum | Jouni Osmala | 2009/09/24 09:04 PM |
small addendum | AM | 2009/09/25 04:04 AM |
extra stage in EV6 | AM | 2009/09/26 05:29 AM |
PPC603 does OoOE | hobold | 2009/09/08 04:40 AM |
OOOE impacts | someone | 2009/09/08 04:39 AM |
EV6 | AM | 2009/09/09 03:33 AM |
OOOE and clock rate | Seni | 2009/09/02 08:11 AM |
OOOE and clock rate | Linus Torvalds | 2009/09/02 05:48 PM |
OOOE and clock rate | anon | 2009/09/02 10:55 PM |
OOOE and clock rate | Wilco | 2009/09/02 11:44 PM |
OOOE and clock rate | Jouni Osmala | 2009/09/03 12:02 AM |
OOOE and Itanium | AM | 2009/09/03 12:27 AM |
OOOE and clock rate | Martin Høyer Kristiansen | 2009/09/03 02:41 AM |
OOOE and clock rate | anon | 2009/09/03 12:12 AM |
OOOE and clock rate | Wilco | 2009/09/03 01:10 AM |
POWER6 skewed pipeline | Paul A. Clayton | 2009/09/03 10:22 AM |
POWER6 skewed pipeline | Anon4 | 2009/09/03 06:00 PM |
OOOE and clock rate | Mr. Camel | 2009/09/03 02:40 AM |
OOOE and clock rate | Richard Cownie | 2009/09/03 05:42 AM |
OOOE and pipe length etc. | Richard Cownie | 2009/09/01 08:01 AM |
OOOE and pipe length etc. | AM | 2009/09/02 12:32 AM |
OOOE and pipe length etc. | Richard Cownie | 2009/09/02 06:49 AM |
LRB choice of P54 | AM | 2009/09/03 12:40 AM |
LRB choice of P54 | Gian-Carlo Pascutto | 2009/09/03 12:45 AM |
LRB choice of P54 | AM | 2009/09/03 02:18 AM |
LRB choice of P54 | Gian-Carlo Pascutto | 2009/09/03 02:55 AM |
LRB choice of P54 | AM | 2009/09/03 03:28 AM |
LRB choice of P54 | Gian-Carlo Pascutto | 2009/09/03 04:29 AM |
Amount of cache per core matters,and mem bandwith too (NT) | Jouni Osmala | 2009/09/03 06:44 AM |
LRB choice of P54 | rwessel | 2009/09/03 01:31 PM |
LRB choice of P54 | AM | 2009/09/04 01:24 AM |
LRB choice of P54 | anon | 2009/09/03 05:40 AM |
LRB choice of P54 | a reader | 2009/09/03 08:20 AM |
LRB choice of P54 | anon | 2009/09/03 04:57 PM |
LRB choice of P54 | Jonathan Kang | 2009/09/03 01:30 PM |
LRB choice of P54 | David Kanter | 2009/09/03 03:38 PM |
LRB choice of P54 | Jonathan Kang | 2009/09/04 07:16 AM |
LRB choice of P54 | anon | 2009/09/03 05:07 PM |
LRB choice of P54 | AM | 2009/09/04 01:20 AM |
LRB choice of P54 | Jonathan Kang | 2009/09/04 07:13 AM |
LRB choice of P54 | Dan Downs | 2009/09/04 07:38 AM |
LRB choice of P54 | Dan Downs | 2009/09/05 03:36 AM |
LRB choice of P54 | Anon | 2009/09/05 01:44 PM |
LRB choice of P54 | AM | 2009/09/04 11:12 PM |
LRB choice of P54 | AM | 2009/09/04 01:18 AM |
LRB choice of P54 | anon | 2009/09/04 07:18 PM |
LRB choice of P54 | AM | 2009/09/04 10:53 PM |
LRB choice of P54 | anon | 2009/09/05 03:06 AM |
LRB choice of P54 | AM | 2009/09/05 08:14 AM |
LRB choice of P54 - Layout? | Anonymous | 2009/09/03 01:40 PM |
LRB choice of P54 - Layout? | anonymous | 2009/09/03 02:54 PM |
LRB choice of P54 | Jukka Larja | 2009/09/03 08:58 PM |
LRB choice of P54 | mpx | 2009/09/04 03:07 AM |
LRB choice of P54 | anon | 2009/09/03 01:02 AM |
OOOE and pipe length etc. | Gian-Carlo Pascutto | 2009/09/03 12:40 AM |
Larrabee: Pentium vs 486 vs 386 | Mark Roulo | 2009/09/03 03:26 PM |
Larrabee: Pentium vs 486 vs 386 | Michael S | 2009/09/03 04:14 PM |
Larrabee: Pentium vs 486 vs 386 | Mark Roulo | 2009/09/04 09:05 AM |
Larrabee: Pentium vs 486 vs 386 | Jonathan Kang | 2009/09/04 09:59 AM |
Larrabee: Pentium vs 486 vs 386 | Michael S | 2009/09/05 08:58 AM |
Larrabee: Pentium vs 486 vs 386 | James | 2009/09/07 02:15 AM |
Larrabee: Pentium vs 486 vs 386 | Mark Roulo | 2009/09/07 06:44 PM |
OOOE and pipe length etc. | Michael S | 2009/09/03 04:42 PM |
LRB core | AM | 2009/09/04 01:09 AM |
LRB core | Michael S | 2009/09/04 04:07 AM |
LRB core | anon | 2009/09/04 07:27 PM |
LRB core | Michael S | 2009/09/05 09:12 AM |
LRB core | anon | 2009/09/05 10:03 PM |
reasons for split I/D L1 caches | Michael S | 2009/09/06 03:10 AM |
reasons for split I/D L1 caches | anon | 2009/09/06 05:32 AM |
reasons for split I/D L1 caches | ? | 2009/09/06 09:35 AM |
reasons for split I/D L1 caches | megol | 2009/09/06 02:39 PM |
reasons for split I/D L1 caches | ? | 2009/09/07 03:20 AM |
reasons for split I/D L1 caches | anon | 2009/09/07 05:25 AM |
cache hinting | ? | 2009/09/07 06:10 AM |
cache hinting | anon | 2009/09/07 06:35 AM |
cache hinting | ? | 2009/09/07 08:10 AM |
cache hinting | anon | 2009/09/07 08:49 AM |
cache hinting | ? | 2009/09/07 09:37 AM |
Split and unified caches | David Kanter | 2009/09/06 12:38 PM |
Split and unified caches | anon | 2009/09/06 10:15 PM |
Split and unified caches | Michael S | 2009/09/06 11:40 PM |
Split and unified caches | anon | 2009/09/07 01:24 AM |
Split and unified caches | David Kanter | 2009/09/06 11:51 PM |
Split and unified caches | anon | 2009/09/07 01:13 AM |
LRB core | AM | 2009/09/04 11:08 PM |
LRB core | Linus Torvalds | 2009/09/05 09:47 AM |
LRB core | David Kanter | 2009/09/04 12:23 PM |
LRB core | Anon | 2009/09/04 05:32 PM |
LRB core | David Kanter | 2009/09/04 09:15 PM |
LRB core | Michael S | 2009/09/05 09:21 AM |
OOOE and cache/mem sizes | a reader | 2009/09/01 08:19 AM |
OOOE and cache/mem sizes | Richard Cownie | 2009/09/01 08:43 AM |
snapdraon? | Michael S | 2009/08/28 05:10 AM |
snapdraon? | a reader | 2009/08/28 07:51 AM |
Thanks (NT) | Michael S | 2009/08/29 11:53 AM |
snapdraon? | Paul | 2009/08/28 12:12 PM |
new POWER7 info .. | EduardoS | 2009/08/27 02:41 PM |
new POWER7 info .. | Jesper Frimann | 2009/08/28 04:03 AM |
Single threaded performance | David Kanter | 2009/08/28 09:52 AM |
Hot Chips XXI Preview online | hobold | 2009/08/13 06:30 AM |