| WIKI | FAQ | Tech FAQ | |
 http://csua.com/feed/ | |
| ||||||
| 11/23 |
| 2012/3/29-6/4 [Computer/HW/Memory, Computer/HW/CPU, Computer/HW/Drives] UID:54351 Activity:nil |
3/29 A friend wants a PC (no mac). She doesn't want Dell. Is there a
good place that can custom build for you (SSD, large RAM, cheap video
card--no game)?
\_ As a side note: back in my Cal days more than two decades ago when
having a 387SX made me the only person with floating-point hardware,
most machines were custom built.
most machines were custom built. -- yuen
\_ did that make you a better programmer/gamer/etc?
\_ No. I was writing a pre-emptive multi-threading library as
part of an effort to port some floating-point-heavy Unix code
to DOS for CS199. I couldn't figure out how to save the
"context" of Borland C++'s floating-point emulation library.
The options were to either mask context switching around all
floating point operation or get a co-processor. I ended up
getting the co-procoessor. -- yuen
to DOS for CS199 (http://ssli.ee.washington.edu/~bilmes
mypubs/bilmes1992-icmcmood.pdf). I couldn't figure out how
to save the "context" of Borland C++'s floating-point
emulation library. The options were to either mask context
switching around all floating point operations or get a
co-processor. I ended up getting the co-procoessor. -- yuen
\_ Why not Dell? What is it about Dell she doesn't like?
\_ Fry's? HP? Lenovo? The only place I have done this is Lenovo. |
| 2011/11/15-30 [Computer/HW/CPU] UID:54229 Activity:nil |
11/15 40th Anniversary of the 4004:
http://preview.tinyurl.com/8yvr4k5 [arstechnica]
\_ When is the 40-year-and-4-month anniversary? |
| 2010/3/9-30 [Computer/HW/CPU, Computer/SW] UID:53748 Activity:nil |
3/9 http://www.engadget.com/2010/03/09/1024-bit-rsa-encryption-cracked-by-carefully-starving-cpu-of-ele I failed to see why you must starve the CPU of electricity. Why can't you just simulate that in software? \_ And if you can simulate that in software, why not just single- stepping the simulated CPU and get the key out? |
| 2009/6/30-7/15 [Computer/HW/CPU, Computer/SW/Unix] UID:53101 Activity:nil |
6/30 Thanks very much for all the volunteer work on soda! Two questions:
1. When will HTTP be up again?
\_ Probably not this week - 4th and all that. Next week?
2. There used to be a web page that describes the historical hardware
for soda machine. What's the URL again? I forgot.
\_ It's on the wiki now -
http://wiki.csua.berkeley.edu/index.php/Hardware
Not up to date with the most recent rev yet
Thanks again. |
| 2009/6/1-3 [Computer/HW/CPU] UID:53068 Activity:high |
5/31 History of winners and losers by *popularity*:
VHS > Beta Max
USB2 > Firewire
x86 > PowerPC > Everything Else > DEC Alpha > Itanium
BlueRay > HDDvd
\_ It's too early to tell RE: "Blue"Ray. They may both turn out to be
losers. If BluRay never catches on, the wrong format won or they
both turned out to be losers. Consumers may stick with DVDs as
good enough and in 5 years move to True HD netflix/ms/apl downloads.
\_ PC (DOS/Windows) > Mac
\_ XP > Vista
iPod > Zune (this isn't really fair)
\_ why not? Zune sucked so much...
IE > Netscape
QWERTY > Dvorak
135 > 126
Windows > Unix/Linux/etc. > NetWare
RISC > CISC
(p.s. Sorry! I typed it backward yesterday. Should be CISC > RISC.)
\_ This is not clear at all.
\_ It's quite clear that the above is wrong. Where are all the
RISC machines? Since CPU speed has outpaced memory and bus
speed, fetching is very expensive, which makes CISC a
performance win for now.
\_ It's still very unclear which will win. For mobile
devices, RISC is still very much alive.
\_ RISC is very much alive everywhere. Even king CISC
Intel is really RISC with a translation layer for
crappy CISC instructions that only still exist for
backwards compatability.
Ethernet > Token Ring
I suppose you're only talking about winning and losing, not about
which ones are actually better.
\_ Get your dates right.
\_ Nintendo > Sega
\_ Atari > Coleco
\_ Wii <?> PS3 |
| 2009/5/26-30 [Computer/HW/CPU] UID:53045 Activity:nil |
5/26 Engineering is HOT man! Super hot co-inventor of USB at Intel:
http://www.youtube.com/watch?v=jqLPHrCQr2I |
| 11/23 |
| 2009/5/13-20 [Computer/HW/CPU] UID:52993 Activity:nil |
5/12 THE AMD! USA! USA!
http://www.nytimes.com/2009/05/14/business/global/14compete.html |
| 2009/5/6 [Computer/HW/CPU] UID:52952 Activity:moderate |
5/5 Any idea why the AMD only added 8 more registers with the AMD64 arch.?
Why 16 registers and not, say, 32?
\_ To double the accessible register count, you need one more bit
in the instruction stream _per_ register field. x86 instruction
set is already packed like rat's nest as is. |
| 2009/5/2-6 [Computer/HW/CPU] UID:52936 Activity:nil |
5/2 why would my php application chew up 20-30 percent of my CPU when
run on a real machine, but will consitently take up 60-70 percent
of CPU when run in a vmware vm ?
\_ the real CPU has more capacity.
\_ Yes, did you allocate all of your CPU to the VM? Maybe you only
gave it one CPU or something like that.
\_ Overhead from VMWare using cycles. If you don't have vm extensions
for your CPU that's liable to make things slower too. |
| 2009/4/11-20 [Computer/HW/CPU, Computer/HW/Display] UID:52842 Activity:low |
4/10 What consumes less power on a LCD screen, showing an
all white scren or showing an all black screen?
\_ Depends what kind of LCD it is. Twisted-nematic displays (used in
everything from digital watches to good-quality monitors) use more
power for black, as you can guess by looking at a watch. In-plane
switching displays (popular in more expensive monitors) use more
power for white. Either way, it's a pretty small effect; most of
an LCD's power usage is the backlight. Here are some actual power
comparisons: http://techlogg.com/content/view/360/31
\_ Depends on the LCD technology. Twisted-nematic displays (found
in everything from digital watches to good-quality monitors) use
more power for black, as you can guess by looking at a watch.
In-plane switching displays (popular in more expensive monitors)
use more power for white. Either way, it's a pretty small effect;
the main power consumption is from the backlight. Here are some
actual power comparisons: http://techlogg.com/content/view/360/31
\_ Some LCD screens (ones with "dynamic contrast ratios") will dim
the backlight for dark/black images. |
| 2009/2/25-3/3 [Computer/HW/CPU, Computer/SW/OS/Linux] UID:52632 Activity:nil |
2/25 $100 Plug computer:
http://linuxdevices.com/news/NS9634061300.html
\_ Kind of cool, but also a bit misleading. Still,
outside of file serving that should be able to do
almost everything a home server needs to do |
| 2009/1/16-23 [Computer/HW/CPU] UID:52404 Activity:nil |
1/16 AMD to layoff 9%, suspend 401(k) match, cut engineer salaries 10%
\_ Awwww, too bad -Intel
\_ My heart bleeds for you. --transmeta.
\_ Wait, another sodan worked there? --ex-transmeta
\_ Hello transmeta-coward, meet another transmeta-coward.
http://www.theregister.co.uk/2009/01/16/amd_q1_2009_job_cuts_wage_reductions |
| 2008/12/10-16 [Computer/HW/CPU, Computer/HW/Drives] UID:52220 Activity:moderate |
12/9 Another idea for the CSUA that lets you spend money and maybe get some
cool toys. Instead of buying a beefy server (like say, a massive server
with 20 386DX processors), buy a few cheap machines (like the ones
mentioned below) that have good disks and work on failover / load
balancing. A netscaler or other piece of hardware is complete overkill,
but maybe hacking an OpenBSD box could do the trick. The idea is that
this project:
- Lets you learn a lot about failover/redundancy/scalability, which
are real-world, relevant skills and also interesting. The fake
CSUA head-hunter would be all over these real skills.
- Increases the reliability/performance of soda / csua machines.
- Gives a justification for buying new hardware.
- Give a cause for the CSUA.
Good idea: ..
Bad idea:
\_ 386DX is cool: http://csua.com/?entry=18447
\_ Too late, the server has already been ordered. We already have cheap
machines, and we're note exactly getting pounded on the web, nor do
we have sites to scale up. We already have stuff on FreeBSD as well
as backup LDAP. The point of failure is keg and the fact that we have
16 small disks. We've also ordered new disks to rectify that. I gat
16 small disks. We've also ordered new disks to rectify that. I got
the idea that you'd rather we work around a lack of resources than
exploit more than we think we need...or at least, that's what I keep
hearing. I don't think that's really going to help. --t
as backup LDAP. The point of failure is keg and the fact that we
have 16 small disks. We've also ordered new disks to rectify that.
I got the idea that you'd rather we work around a lack of resources
than exploit more than we think we need...or at least, that's what
I keep hearing. I don't think that's really going to help. --t
\_ Good decision. Especially good to just make a decision and
start fixing things, instead of debating endlessly.
\_ I like what you did more than my proposal! Stability, not speed,
should be the first factor. Good disks and stable builds are
two of the biggest contributors to stability. Do you still hit
up alums for donations? -op
\_ We were going to hit up alumni for donations for the server
before we got it, but the stability was (literally) getting us
down and so we decided to get the new server. Steven, last I
heard, plans on installing ESXi (the free one) on it setting
it up. It should be in place by mid-to-late-January, possibly
heard, plans on installing ESXi (the free one) on it setting it
up. It should be in place by mid-to-late-January, possibly
earlier. --t |
| 2008/12/4-10 [Computer/HW/CPU, Computer/HW/Drives] UID:52163 Activity:nil |
12/4 A question to you old crufy alumni: So lately we've suggested
VMs, and been asked why it's necessary. We've suggested top-of-the-line
hardware and been told we don't need that much power. So I'd like to
ask -- what exactly do you think the CSUA is supposed to _be_?
\_ Noone said VMs weren't needed. They suggested you use the
\_ No one said VMs weren't needed. They suggested you use the
there is quality, free VM software out there that you could
use. Asking for the for pay stuff is fine, but you aren't
likely to actually get it, so take what's free and works.
\_ I guess...would it hurt that much to ask for the expensive stuff,
though?
\_ When the company supplies a free version that works quite
well you will get a lot more traction towards getting the
expensive version if you have used the free version, shown
that it's actually getting some use beyond "we installed
it cause it was kewl" and that there would actually be
some advantage to having the pay version. VM stuff IS
really cool and worth playing with. The free version
exists because really, until you have a large install
there's really no need for expensive management tools.
\_ Offering a rant, then an answer for my own question:
Sure, VMs aren't strictly necessary, or people can go to
OCF if they want access to computing resources or practice
with sysadminning. But they'd be supported by OCF, which
has basically nothing to do with the CSUA (anymore), not
to mention they're bound by whatever the OCF is willing to
allow/install/support on their servers. VMs let us tinker w/o
worrying about giving root, or a bad program taking down the
server or monopolizing server resources. As a consequence
it is also useful for stability's sake, independently of
offering students VMs, as we can separate services out and
move them between servers as load necessitates. Do we need
the speed? We'd certainly see some benefit. Mail processing
is pretty laggy, and even with my donation of vermouth (with an
Athlon 64 2800+; it replaced a 500Mhz computer) it struggles
to keep up. Upgrading away from our failing 16-disk ~5TB array
to something newer and less failure-prone may not be manly -
but it certainly seems sane to me. If we're going to spend
$2k to replace our servers, why not spend $3k to replace our
servers and move the CSUA forward?
I doubt anyone objects to getting equipment so the servers
suck less, but I think that in order to keep the CSUA from
stagnating, we need to seriously move forward in what we offer
students. Attendance to helpsessions isn't what it once was,
and the computing services the CSUA currently offers simply
aren't as attractive to students anymore. Anyone can find a
UNIX login server offered by the campus with webspace (w/
CGI) and shell access. Most people now join the CSUA as a
social group or to use the office machines and hang out. At
this rate we're going to lose our technical relevance,
and what then? Regardless of overlap with the OCF, we
need to move our technical resources forward and attract
technically-minded students again, because at the moment,
we're not. The CSUA is wandering at the moment, without a
clearly-defined direction. If you guys are suggesting that we
don't need to do more for students in this area, then I'd like
to hear your thoughts on what we do (other than the obvious
'build better student-alumni relations' line).
\_ I dunno, the CSUA hasn't had a clear direction since I joined
in '98. (Web and email hosting wasn't terribly relevent then
either.) We started mentoring in 2002, but I it always seemed
either.) We started mentoring in 2002, but it always seemed
like a bit of a flop to me. I've noticed video games have been
more important since I left. Anyway, the CSUA is always trying
new things. I don't think that's a bad thing. I just don't
know if we need an i7 fileserver.
know if we need an i7 fileserver. I guess I don't really see
how improving the HW -> more members. I don't mind, really,
I'd like soda to work better, but I don't know who's going to
join because we have a nice fileserver or VMs for sys admining.
It's not a bad thing, but it's all stuff people can do at home
now. It's good for current members, but I don't really see it
as attractive to new members.
\_ I already talked about this down below. The primary function
of the CSUA is to be a social, community-building organization.
The machines exist to support that function. It used to be that
the services the CSUA provided on its hardware were directly
contributing to the community--there was a time when having an
email server and web hosting was a really cool thing, and people
would join the CSUA just for that. Then they'd get sucked into
using wall and MOTD and become part of the community. But now
most of the services the CSUA historically provided are no longer
interesting; everyone's got more email addresses than they want,
web hosting is free and better elsewhere, and wall and MOTD are
dead. Providing virtual machines isn't an inherently bad idea,
but what's the upshot? How will you use it to help build
community? What services will you provide that contribute to
community? -tom
I guess I don't really see how improving the HW -> more members.
I don't mind, really, I'd like soda to work better, but I don't
know who's going to join because we have a nice fileserver or VMs
for sys admining. It's not a bad thing, but it's all stuff people
can do at home now. It may be good for current members, which is
fine, but I don't really see it as attractive to new members.
\_ I already talked about this down below. The primary
function of the CSUA is to be a social,
community-building organization. The machines exist to
support that function. It used to be that the services
the CSUA provided on its hardware were directly
contributing to the community--there was a time when
having an email server and web hosting was a really cool
thing, and people would join the CSUA just for that.
Then they'd get sucked into using wall and MOTD and
become part of the community. But now most of the
services the CSUA historically provided are no longer
interesting; everyone's got more email addresses than
they want, web hosting is free and better elsewhere, and
wall and MOTD are dead. Providing virtual machines
isn't an inherently bad idea, but what's the upshot?
How will you use it to help build community? What
services will you provide that contribute to community?
-tom
\_ perhaps having VMs available would make more interesting
helpsessions feasible, as we could go in-depth on some topic
and provide an avenue for students to go further in-depth
after the fact (i.e. helpsession setting up X piece of cool
software and giving them a sandbox to play in). --toulouse
\_ As a crufty alum, I think the CSUA should encourage undergrads
to learn about software, cs, computing, &c. by providing ugs
with opportunities to try out and develop new things in a friendly
setting.
When I was an ug there were several CSUA projects, such as the
lottery scheduler, that offered such opportunities. I think
that the VM proposal would offer a similar opportunity and should
be pursued.
Re VM software - I agree with a pp that setting up a free sol'n,
such as Sun's virtual box, is probably a better idea than asking
for a VMWare donation. IMO, the process of learning how to make
free software work for one's needs teaches one about much more
about software and computing than installing and configuring a
pre-packaged commercial sol'n does.
Re HW - While I understand the attraction of getting the latest,
1337est hardware, my experience suggests that going with a sol'n
of the previous gen hardware is always preferable in terms of
maintainability and reliability.
maintainability and reliability. -crufty-alum
\_ :| Well, the Core i7 Xeons as I understand it will be coming out
some time after the Core i7 has been out, so perhaps that will
positively affect their quality? I see what you're saying, but
I've never really been burned by new hardware, other than lack
of drivers and the like. Care to share some stories? --toulouse
\_ Well, mostly the problems I've had are with the drivers for
the motherboards that are required to run the most recent
cpus. We had no end of problems with an Intel MB for the
first round of Xeon chips (there were no reliable linux
drivers for the onboard gig-e ethernet, the sata controller,
the scsi controller, or the lights out management module).
I had similar problems with nforce boards for AMD chips and
recall similar problems when the PPros and P2s first came
out as well.
For the record, I'm not opposed to the CSUA buying the latest
hardware. I'm just not convinced that the projects you want
to do (e.g. VM) require it, i.e., what is the difference btwn
getting a 4 core C2D system (or 2 C2D systems) and getting one
Core i7 system? [If there is a big difference, I apologize
for my ignorance - I am not an engineer anymore and have lost
touch with the details of recent cpu performance] -crufty-alum
\_ It seems practicality and wisdom are prevailing over our
nerd-rections, and we may go with a Dual C2Q Xeon server. We
await final word from the pupp--er, President. While we're
at it, we'll probably get new, better hard drives.
nerd-rections, and we may go with a Dual C2Q Xeon server.
We await final word from the pupp--er, President. While
we're at it, we'll probably get new, better hard drives.
--toulouse |
| 2008/12/3-8 [Computer/HW/CPU] UID:52157 Activity:kinda low |
12/3 Are any of you CSUA alums working at Intel? Is it possible that we
might be able to hit Intel up for donated/partially donated (reduced
price) Core i7 Xeons when they come out? Who would be a good person
to contact about something like that? We're of course willing to put
out for them - perhaps we'll tattoo an Intel logo on toulouse if that's
what they want :-p -- steven
\_ fyi my wife recently started there and they eliminated the employee
discount on CPUs a few months ago
\_ I work at Oracle and I can get you 25% discount on our license
and bronze level support. How many CPUs are you thinking? With
a 25% discount, each CPU support is only $75,000/year.
\_ Why are you guys so obsessed getting an i7-based machine?
You look like salivating hardware dweebs, rather than people
with a plan.
\_ Well, this is the CPU-Salivating Undergrad Association,
isn't it?
\_ Drool
\_ I love Oracle and Larry Ellison is my master. We're trained
samurais and we'll obliterate anyone who makes us lose
face. Shut up and buy Oracle. You have no choice.
\_ Because they're shiny. What, are you saying we should buy old
stuff? Because, as best I can tell, buying ghetto/janky
equipment is most of the reason our stuff goes down so often.
Why so much hate? Do you want us to buy more secondhand or
outdated gear that can't stay up for more than five minutes
at a time? If you're so convinced we don't have a plan,
why don't you suggest one?
\_ stop having a "cpu centric view" instead of a
"what problem are you trying to solve" centric view.
what is the csua's hardware budget? is you want
an i7 to play games, that makes logical sense although
seems politically objectionle, but all this stuff about
virtual machines and zfs etc doesnt make sense.
you arent trying to replicate the ocf on a single
machine.
\_ I don't imagine we'd buy Core i7 Xeons for the
purpose of playing games.
--toulouse
\_ So what are you going to do? Linear algebra
homework?
\_ On the contrary, it's often the shiny stuff that doesn't
have all the bugs worked out. Old/outdated and shiny/new
are not the only options here. I sense a third choice...
\_ Seconded. I was around when we bought a shiny new dual-
Xeon for (the current) soda. FreeBSD didn't support
some of the HW, so now we run Linux and it breaks all
the time.
\_ Seriously. You can go out today and spend < $1000 and
get a brand new computer with quality timetested
hardware that will fulfill csua's hardware needs
10x over. Spend a little more and you can get some
lower end machines to play with/learn how to sysadmin.
\_ Ironically, right now the two machines with the most problems
are keg and scotch. Those are our two remaining FreeBSD
machines. Soda has a month of uptime, which is definitely
not great, but it's certainly not crashing all the time.
I do like FreeBSD but it's certainly not being the all-star
right now. I suspect that scotch has a hardware problem but
keg is unclear whether it's a hardware or software problem.
\_ Ironically, right now the two machines with the most
problems are keg and scotch. Those are our two remaining
FreeBSD machines. Soda has a month of uptime, which is
definitely not great, but it's certainly not crashing all
the time. I do like FreeBSD but it's certainly not being
the all-star right now. I suspect that scotch has a
hardware problem but keg is unclear whether it's a
hardware or software problem.
\- the freebsd machine with problems isnt fbsd7+multicore
is it? we are trying to solve a diffcult problem with
that combination and would be interested in other cases.
although i assume this is ancient hw with bugs. btw in
my fairly long experience linux does worse things on
buggy hw than freebsd. like corrupt data without
detection. this may have gotten better in linux-recent
[i admit linux-recent doesnt drive me insane daily
like it used to]. --psb
\_ I miss those days when soda was a 20 * 386DX-25 machine.
\_ I certainly learned a lot. I remember when it was a big
deal that I had soda up for 100 days in a row. (wow!)
But that setup was due to necessity; I agree that a big
honking hardware purchase isn't really necessary. Start
by trying to get experience developing and sizing a
scalable configuration--that'll be more valuable than
throwing a huge piece of hardware at the problem. -tom
\_ Agreed. Sysadm is NEVER about getting the equipment and
the people you need. You almost NEVER get the resources
you requested for. Sysadm is taking what you have at hand
and try to make the best out of it while not bringing down
the organization.
\_ Scotch - broken. Keg - overloaded, and 16 disks amounting
to about 5TB of data; Lifesaver - dead. Making do with
broken computers is not a viable plan. Buying a server now
means it will be obsolete in a few months, and will be a
waste of money.
waste of money. --toulouse
\- so is buying a $3k computer to do a job
better done by 2 $1k computers.
\_ High end brand new computer components depreciate a
hell of a lot faster than middle of the road workhorse
components. Cheap computer hardware is insanely fast
these days.
\_ Look, it's your network to run, I'm not going to tell
you how to do it. But I think you probably haven't
looked at where your bottlenecks are; does CPU really
matter to the services you're running? I always buy
servers with CPUs two and three generations removed
from the cutting edge, unless the application will
be CPU-bound, which it rarely is. A server doesn't
become obsolete just because someone came out with
a new chipset; it becomes obsolete when it no longer
works for your application. -tom
\_ I rarely agree with tom because he's such a
stubborn ass but this is one time I'll say...
+1 to tom's advice. -anon sysadm
\_ I have to agree with Tom on this. The CPUs and
memory are unlikely to be the bottleneck. --jwm
memory speed are unlikely to be the bottleneck.
A slightly older chip would is likely to be fine
and more stable. --jwm
\_ On the other hand, the CSUA is a place for people
to experiment and try out the new stuff, even if
it is to a certain extent at the cost of
some reliability. -ausman
\_ "we want to 'try out' a really fast
processor because it is cool" isnt a
serious project. this smacks of geekery
not leadership. now if you spent a modest
amount on say a ps3 to get exposure to the
cell, i could see that might be interesting
[eventhough more likely than not such a
purchase would be to "test" video games].
\_ Computers are always obsolete "in a few months".
\_ Intel doesn't release a shiny new architecture that
finally catches up to AMD in many respects every few
months.
\_ Have you been hiding the last few processor
cycles? AMD hasn't exactly been on top of
its game.
\_ What difference does it make? How would the
services be different on a new processor?
Are CSUA people writing assembly code? This
isn't like a new game console where the
supported applications are totally different;
the applications won't care what the underlying
processor architecture is. -tom |
| 2008/9/20-23 [Computer/HW/Memory, Computer/HW/CPU] UID:51241 Activity:low |
9/20 I am running NAT on an Extreme Networks switch connected to a
Cisco switch at GigE speeds. Copying a file across the same link
w/o using NAT gets about 25 MB/sec, but with NAT turned on I get
2.5 MB/sec. The CPU is 98% idle and there is plenty of RAM. I know
that NAT in s/w has an overhead but could it realistically be a
factor of 10 slower?
\_ what kind of file copy?
\_ NFS or SFTP. Same symptoms with either.
\_ Are you sure it is not your test platform that is slower? This
seems really crappy. Are you perhaps having a duplex mismatch
problem on the switch the NAT is connected to?
\_ What test platform? You mean the one I am copying with? I
said that I get 25 MB/sec with NAT off and 2.5 MB/sec with
NAT on - using the exact same hardware. Therefore, I doubt
it is a duplex problem or it would be present both times. |
| 2008/9/16-19 [Computer/HW/CPU, Computer/HW/Display] UID:51184 Activity:nil |
9/16 Tim Sweeney on the future of GPUs
http://arstechnica.com/articles/paedia/gpu-sweeney-interview.ars
I like Sweeney, I don't care about Unreal, but ZZT was a heck of a
game
\_ Interesting. Co-processor-like units have come and gone
throughout the history of computing. GPU, co-processor, what-not,
will all be obviated by advances in processors and systems
integration. I've no doubt GPU-like units will come back in
time, but not for another decade or so.
\_ Unreal's renderer is pretty shit. Everything looks plastic,
polygon counts are pretty low, and framerate is very peaky.
It's amazing how much Unreal engine games all look the same. |
| 2008/8/14-21 [Computer/HW/CPU] UID:50872 Activity:nil |
8/14 WTF SUNW got renamed into JAVA? Even after a 1 for 4 shares _reverse_
stock split, JAVA trades at around $10. Nothing has changed.
Still trying to cling onto Java(TM). Losers.
\_ Any thoughts on AMD? I bought in around 4.5 a few weeks ago
after Ruiz kicked out. Debating whether to get out around +15%.
But a lot of new announcements, but in areas I don't understand
(GPUs). And now there is the "fabless" plan.
\_ Very high risk, but I doubt that Intel will want to kill their
only competitor and risk DoJ wrath.
\_ Intel can totally crush AMD any time it wants to. I worked
there for a while and the basic strategy is Intel always
has benchmarks and projects ahead of its time, and whenever
competitors release a new benchmark, they'd release an
even better one. They keep competitors around like cats
playing with 1/2 dead mice. It's no fun when you kill
them, so let them live a little.
\_ Yes, I agree with that ... that's what I told my
engineering friends: Intel can complete on two
axes, performance and price, while AMD only had
one hope ... combine that with the management and
operational disfunction. On the other hand, I think
it's a reasonable question to ask "Is AMD worth more
than $3.5 billion". Well, it's nice to be up another
6% today. It's a small position, since when I bought
in I was staring at the abyss.
\_ AMD has a very sexy atom competitor coming out soon. If
notebooks do take off like they are threatinging it could be
good news for amd.
\_ This was announced a year ago, wasn't it? |
| 2008/6/12-13 [Computer/HW/CPU] UID:50242 Activity:moderate |
6/12 Guantanamo Inmates May Seek Release, High Court Says
http://preview.tinyurl.com/6hq4cj
Hot damn.
\_ Yah, now we'll just have to kill them on the battlefield without
getting intel from them.
\_ Yah, now we'll just have to play Battlefield 2 to kill
using my awsome Intel processor.
\_ yah, now we'll just have to kill them on the battlefield without
getting intel from them. [don't delete my post asshole]
\_ Yah, now we'll just have to play Battlefield 2 to kill time
using my awsome Intel processor. [love wiping out assholes]
\_ Wipe your own asshole
\_ yah, now we'll just have to kill them on the battlefield without
getting intel from them. [don't delete my post asshole]
\_ Damn that rule of law.
\_ Which is ignored by the left when it's inconvenient, and lauded
when the courts change law to make them happy.
\_ Baseless claims are so much fun to make. |
| 2007/12/3-6 [Computer/HW/CPU, Computer/SW/OS/VM] UID:48736 Activity:kinda low |
12/3 Has anyone seen this VMware problem before? When I have one or two
VM session running, Task Manager on my host machine shows that the
vmware-vmx.exe processes uses 0% CPU time when the VMs are idle.
However, when I have more sesssions (maybe 4 or more) running, Task
Manager shows that each of the vmware-vmx.exe processes is using
10-20% CPU time even though all the VMs are idle. This eats up CPU
cycles from my other processes. I'm using VMware Server 1.0.3. I
have a HyperThread CPU and the "Number of processors" setting for my
VMs are set to 2. Thx.
\_ What do you think of VMWare in general? We are evaluating it now
for possible purchase.
\_ What are you going to use it for?
\_ Almost everything. Production servers, dev and test
environment. Probably not for the database servers though.
Does that answer your question?
\_ No. It doesn't. What are you hoping to gain by using
VMWare?
\_ Server consolidation, better ability to manage
dev and test environments, hopefully a better DR plan.
\_ Sounds like VMware might work for you then. I've
used VMware since version 3 and I've been pretty
happy with it. I don't know if I'd transition
all of my hosts to VMs just yet, but it excels
in meeting the needs you have.
\_ I've used VMware for about 4 years with debian as the host OS.
it is fantastic. on my new intel macbook i use VMware Fusion.
\_ Does TM say if this if kernel or user time? Are you swapping?
\_ Kernel time. No the host machine is not swapping. It has 2GB
RAM, and the Commit Charge Total is around 1.8GB. |
| 2007/11/30-12/6 [Computer/SW/Compilers, Computer/HW/CPU] UID:48719 Activity:moderate |
11/29 From the CSUA minutes:
- Next Gen Console
-- If we have $1800 in our accounts, should we buy a console:
4 votes passes.
-- Console voting: 2 votes each, neither passes
* 360 = 600, more games
* PS3 = 650, not as many games
Does this mean the CSUA already has a Wii?
Since when is, "more expensive, fewer games" an argument for something?
I guess if they're gonna install Linux and try some Cell development,
THAT would be cool, but I don't think that's what they want it for.
\_ Netrek is free.. but you need to have skills
\_ I think the decision should be based on which you can hack and/or
boot alternate OS's on. I think there is a clear answer here...
\- YMWTS: KYELICK et al paper "The potential of the cell processor
for scientific computing" on the POWER of the CELL. Interesting
and quick read. Note: KYELICK now the Director of NERSC.
\_ Yeah, but Roadrunner (A combo Opteron/Cell cluster proposed
at Los Alamos) is still a dumb idea.
\_ Why do you say that? I'd be more concerned about using
/panfs as the storage system. Panasas might be ok by the
time it is deployed. A lot of impressive people there,
but mixed experiences in practice.
\_ The Cell already has a perfectly good general processor
attached to it. (A dual core power 5). What's the
Opteron doing there? The last thing the Cell
development tool kit needs is another totally different
processor to work with. Yea! A third compiler! For
hevean's sake, they don't even have the same endianness!
processor to work with. Yeah! Another compiler! For
hevean's sake, the don't even have the same endianness!
\- ibm and amd are working together on a few things
like socket compat between POWER-tng and Opteron,
and Torrenza(sp?)/HTX rather than PCIe. the HPC space
is very different from the rest of the world ...
on a $100m computer you have a legion of programers
to work on tweaking code, compilers because they
are no longer dominated by "expensive programmer
time costs".
\_ While everything you say is true, I can't see how
that excuses creating a totally wacky, needlessly
difficult architecture. Even Los Alamos
doesn't have infinite resources, programmer time
still costs money, money Los Alamos doesn't have.
Not to mention, they're buying the whole machine,
whole hog. No small test prototype. On a totally
untestest architecture.
\- no offense intended here, but are you just
reading articles on the net or do you have
some experience with how large HPC procurements
are done? i dont have any specific knowledge
of Los Alamos/Roadrunner but two things dont
ring true: 1. los alamos being on the hook for
all the dev and tuning work 2. ibm just being
responsible for dropping the machine off at
the loading dock and being done ... the "whole
machine whole hog" part. usually there are
lots of partial milestones involved. although
the somewhat dirty not that secret part of
this is those milestones are never missed
with major consequences. [well maybe once,
but not with one of the main *hpc* vendors.
i cant mention which well known vendor it was].
\_ Sorry, I didn't mean to imply what you've
read into the 'whole hog' statement. I
guess that was really poor word choice. I
just meant that Los Alamos didn't buy a
small prototype cluster to see how well this
thing will work in production, as is
normally done. I'm aware IBM has milestones
and will support the cluster. |
| 2007/7/19-21 [Computer/HW/CPU] UID:47345 Activity:moderate |
7/19 75 year old Swedish women makes every soda geek green with envy, she
gets the world's fastest residential internet connection at 40
Gbits/sec:
http://tinyurl.com/2zkbx7
\_ and just uses it to check email...
\_ at the rate spam growth is happening, you'll need 40gb/s to keep
up with all the spam soon enough...
\_ I remember when I worked at Sun and the new Sparc-10s came out
(lighting fast compared to Sparc-2) -- the first person in my
department who got one was a manager who only used it to read
mail.
\_ But he read e-mail very fast!
\_ And no one logged in remotely to take advantage of the
unused hardware?
\_ That used to be the meanest thing you could say back when
differences in hardware speed actually made a huge difference
differences in hardware speed actually made a huge impact
in things like compiling:
"You can log in remotely to do a compile if you want" (smirk)
\_ In a place I used to work where we used a mixture of
Sparcs to do cross-compiling, the default setting for
the make tool was to export compilation jobs to 4 other
machines (chosen by current load and CPU speed) and
only link locally. (One could adjust the number
according to taste, or set it to 0 to compile locally.)
So having a fast machine means jobs would more likely go
to your machine. |
| 2007/7/9-12 [Computer/SW/OS/Solaris, Computer/HW/CPU] UID:47240 Activity:high |
7/9 Are 64-bit Linux servers popular compared to 32-bit ones? My company
has a server product that supports 32-bit, and we're trying to see if
it's worth supporting 64-bit as well. Thanks.
\_ in my company, everything linux is 64bit except the handful of
redhat satellite servers, because redhat's sat server product
doesn't support running on 64bit systems (yet). DOH!
\_ Compared to 32bit? No. Whether it is worth it to support or not
depends on a lot of things, but mostly the desires of your
customers and the cost of doing supporting it.
customers and the cost of supporting it.
\_ It has more bits so it must be better! Seriously though, now that
64 bit is here I think you'll find most places doing 64 bit. The
best people to ask are your current customers. Unless you're
making a pre-packaged toaster product, then it doesn't matter.
\_ No, you will not find most places doing 64bit. It's still early.
\_ Maybe at your place. See the person below for an exmaple.
\_ I went to USENIX recently and 64bit is still far from
the norm.
\_ No 64bit at all in most of the places of USENIX
attendees? You know this how?
\_ Did I say: "No 64bit at all?" No, I did not. However,
the topic came up in a session and only a few
people said they used it in production.
\_ Representing how many servers and which companies?
Was this the "64 bit linux" session?
\_ How many are represented by you and two other
MOTD trolls?
\_ Oh, ah, personal attack! Way to go! You
are right, 64 bit is DOA. How many? Like
the other poster we have been building only
64 bit boxes in the last few months and
have the remaining non-64 bit scheduled for
termination over the coming months. Maybe
your place of business is just too small or
doesn't do real work?
\_ I never said it was DOA. It will
gradually become the standard.
However, it is currently not the
standard. Even you admit that you
only started to switch over a few months
ago.
\_ You trolled. I sarcastically trolled
back with the DOA overstatement. I
admit nothing. I told you we've been
at it for a few months which started
last year and continues forward as we
have time for it and new machines come
online. I expect most places will be
doing similar gradual rollouts. The
idea that a few usenix attendees at
a single session is representative of
industry is no more likely than your
'motd trolls' as you call us are
representative of industry. Less so
since we're actually here to discuss
it with you, not a vague 'please
raise your hand' at a session. Again,
this isn't rocket science stuff. 64
bit linux is a big thing for some
people, nice for most and harmless to
most of the rest. Only a few with
custom apps or low loads won't get
anything from it. Unless you *know*
you don't want 64 bit, you want 64
bit. And just because it isn't being
rolled out in bulk doesn't mean it
isn't the thing to do. Quite the
opposite, that means it is the thing
that is being done right now as we
speak and doing a gradual rollout is
the smart way to go in most shops.
\_ I was disputing the "most
places are doing 64 bit" statement
above. Most places are not
doing 64 bit for production. You
allude to that above with your
gradual rollout statement. 32
bit is still far more pervasive
than 64 bit at this time.
\_ If they've got 64 bit in
production right now as part of
a long term roll out then they
are doing 64 bit in production.
Just because they didn't flip
1000+ machines in a day doesn't
mean they're not doing 64 bit.
They're being smart. Any place
with that many machines is going
to do almost any change like
this in a gradual rollout. Why
is 'production' so hard to
grasp? What is your tech focus?
Programming? Sysadmin? Manage-
ment? Something else?
\_ We are 3/4 the way to converting to 64-bit everywhere. We should
be done by end of year. -Ops guy at company with 1000+ servers
\_ Why are you converting?
\_ Because the 32 bit limits suck for real computing. !gp
\_ Then you should've been running Solaris all along. Why
was 32 bit okay 12 months ago and suddenly not good
enough now? I can think of some reasons why you'd have
to upgrade to a 64 bit OS on a 32 bit processor, but they
are not common ones - mostly a need to address massive
files or memory - hardly a reason to upgrade every
server at a company for the hell of it.
\_ Solaris = not free. 32 bit 12 months ago = sucked then
with lots of work arounds. 64 bit now = it just works.
Convert everything because it is easier to maintain
fewer images/builds. This isn't rocket science. Why
do you think a place with 1000+ servers doesn't have
'a need to address massive files or memory'? 2 gigs
is hardly 'massive'. I've got games that require more
ram than that..
\_ Solaris is free. You can have more than 2GB of
RAM or a 2GB file with a 32 bit OS. You don't
need a 64 bit OS for that.
\_ Solaris is not free when you have to buy real
hardware to run it and you knew that. If you're
talking the x86 version, get off the motd.
\_ I didn't know Linux came with free hardware.
\_ The OS is now free, x86 or not. The hardware
is not free, but neither is Intel hardware. If
you are worried about x86, what does Linux
64 bit buy you?
\_ The OS has been 'free' for years but
useless without the hardware. And Sun
hardware is way more expensive than x86.
If I want a production quality system
running Solaris it will cost more than
a linux 64 bit system. That is why Sun
is dead and linux continues to grow.
\_ You can run Solaris on x86 and the
hardware costs will be the same. If
\_ Solaris x86? Whatever. We are
talking about production 24/7 systems
that real people support, not your
Quake4 server.
\_ The code is the same. I repeat,
this is not x86 circa 1992.
\_ Quake4 server. 2007.
you want the Sun hardware then the
premium is not as bad as it used to
be. An Ultra45 costs maybe $6K
versus almost $5K for a high-end Dell.
\_ Great, I just spent an extra $1k for
what exactly? And how much does Sun
support cost on that box?
\_ For a true 64 bit CPU.
A Linux 64 bit system running on a
32 bit chip is not true 64. If you
\_ Who said these are 32 bit chips?
Where'd you get that idea from?
\_ Which 64 bit chip are you
running on then?
\_ So you're going to claim that
the current gen Intel/AMD x86
chips aren't 64 bit? This is
going to turn into a philosophy
debate on instructions sets now,
huh?
\_ Yes, I would claim that
the current gen chips
are not true 64 bit chips.
They are 32 bit chips
with 64 bit extensions.
\_ distinction being? as in,
why should I care?
want 64 bit Linux you need to run on
something like Itanium and that's
not cheap either. However, did you
\_ Who said Itanium? Did we flash back
to 1998? This is 2007. Both AMD and
Intel are selling true 64 bit chips.
Hello?
\_ Yes, and Intel's is called the
Itanium - IA64.
\_ See above.
realize that Solaris x86 is not the
same crappy product it was 15 years ago?
\_ Sun is hardly dead. You can get a 16
\_ Solaris x86 is the same crappy
product it always was. It is a niche
product which makes no sense in 99%
of the real world.
\_ Solaris has a lot of features
that Linux does not have.
\_ Solaris does but who is running
Solaris x86 in a real production
environment? I'd be surprised
to hear of any place with more
than a handful in 24x7 and have
a heart attack plus a stroke if
anyone is doing thousands of
solaris x86 anywhere.
\_ Why does Solaris x86
bother you so much? It's
the same OS as Solaris
SPARC. A lot of Canadian
companies are using it,
FWIW. I would consider
using it in order to use
some Solaris features
like ZFS (until Linux
gets it), the scheduler,
and containers.
\_ Sun is hardly dead. You can get a 8
core T1000 for $5k these days and its
operating costs will be less than 1/4th
what 4 dual core Intel boxes would be.
\_ What about 1 dual chip quad box? :)
The T1000 is not so useful for
floating point, but it was good
to mention it. I had almost
forgotten, since I mostly care
about floating point. Also, IBM's
new Power6 chip will run Linux,
too. To claim you need 64 bit
computing and then run it on a 32 bit
CPU is laughable. I will
eventually run 64 bit Linux on
i386, too, but to think that most
people (or even a sizeable fraction)
are doing so now is deluded. We
are just now starting to port over
most of our major s/w, although
we started a year ago, and it
will probably be another two or
three years before we can drop 32 bit
entirely because of all the testing.
A rule of thumb is that it takes
about 5 years to throw old
hardware/software out the door,
so I expect there will be a lot
of 32 bit Linux for some time
yet. Realize that there are companies
still running VMS and DOS.
\_ Our older 32-bit servers needed to be upgraded, so we decided
to roll out new 64-bit servers with 16GB of RAM. We have lots
of apps that need to address more than 2GB of RAM, or we can
make better use of the new faster boxes by addressing more
RAM in the java container. It is easier in the long run to
only have to support one platform, rather than two, also. |
| 2007/4/17-19 [Computer/HW/CPU] UID:46347 Activity:nil |
4/17 Intel to release new chips about 40% faster!!!!!!! Go Penryn
processors YAY BABY!!!!!!!!!! It's the WORLD'S FIRST 45 nm processor!!!
http://www.msnbc.msn.com/id/18157813/from/RS.2
\_ I know you're all jazzed, but what is the big deal? Are you an
Intel employee? Did you work on this chip line? |
| 2007/3/29-4/2 [Computer/HW/Laptop, Politics/Domestic, Computer/HW/CPU] UID:46140 Activity:nil |
3/28 A kind reminder that CSUA stands for Computer Science Undergrad
Association. It is not the Political Science [aka I hate Democrats
and I hate Republicans] Undergrad Association.
In other news AMD is releasing a new laptop chip! EXCITING!!!
http://www.engadget.com/2007/03/29/amds-laptop-ready-m690-chipset-unveiled
\_ that's chipset. and CS students like to talk politics.
\_ Piss off.
\_ Well someone is pissy. If this is representative, I think I
know why I chose to hang out with CS types as opposed to
poli-sci types. -dans |
| 2007/3/1-3 [Computer/HW/CPU, Computer/HW/Scanner] UID:45842 Activity:nil |
3/1 Backup MX servers: should I have one (y/n, given that most isps
spool mail for a couple of days), and if so, how should I go about
having one (are there commercial backup MX servers, and if so,
how much?) - linxu
\_ Yes, you should have one. You're right that most ISPs spool
mail for a couple days, but the situation where I've found a
backup MX server to be most useful is when I relocate a mail
server. I'd be happy to run a secondary for your domains on
my box if you'll do the same for me, assuming, of course, we
don't share the same upstream provider. :) See also:
http://www.joreybump.com/code/howto/nolisting.html
Probably one of the best, most elegant anti-spam measures anyone
has come up with in years. -dans |
| 2006/11/7 [Computer/HW/CPU] UID:45223 Activity:nil |
11/7 Yay, Dell unveils OptiPlex 740 with Athlon 64 X2, although it's
rated at the same speed as Pentium D dual core (but still naturally
lower than Core 2 Duo) |
| 2006/10/27-11/1 [Computer/SW/OS/VM, Computer/HW/CPU] UID:45019 Activity:nil |
10/30 Can a hyper-threading CPU run two threads in two separate apps at the
same time? How does it handle the two different virtual memory
mapping? If I mostly run processes where only one thread is active,
(e.g. compilation, SETI@home in background, VirtualPC or VMware
instances), does hyper-threading help or hurt performance? (I know I
really should profile to find out, but I want to know the theoretical
answer.) Thx.
\_ They get interleaved the same as anything else. Go look up Intel's
*very* well written white papers on the topic. You won't find
better answers anywhere else.
\_ Intel has published several white papers on their site that explain
in easily read English exactly how HT works. You are unlikely to
find a better explanation anywhere else. Kudos to their doc
writers on that one.
\_ Virtual memory is not an issue. As to the rest, unless you are
doing stuff where getting about 1 percent more out of your cpu
matters, don't worry about it. Hyperthreading has a bit of
performance hit in most cases but makes up for it by making
the computer much more responsive at high load. In a gui environment
this makes you computer feel zippier and is worth the performance
cost.
\_ Actually, it makes the computer less responsive under a high
load. Why? Because the CPU is trying to execute more
processes than it has processors. Try this experiment: Run
three jobs with a nice level of 20. Then run one interactive
job. See how (un)responsive it is? Now turn off HT and
repeat the experiment. I guarantee you it will be more
responsive in the latter case. |
| 2006/10/24-26 [Computer/HW/CPU] UID:44947 Activity:moderate |
10/24 http://en.wikipedia.org/wiki/Symmetric_multiprocessing "With the exception of a few rare 80486 systems, the x86 SMP market began with the Intel Pentium processor supporting up to two processors ....." Wasn't soda an 8-CPU 386SX machine more than a decade ago? \_ I think at peak it had 20 processors, and yes, they were 386. -tom \_ Yes, that would be the Sequent era (1992-1997). Soda Mark 2 had 8 386s, Soda Mark 3 had 16 386s and Soda Mark 4 had 20 386s. http://www.csua.berkeley.edu/computing/hardware/soda-mark-ii.html http://www.csua.berkeley.edu/computing/hardware/soda-mark-iii.html http://www.csua.berkeley.edu/computing/hardware/soda-mark-iv.html "[W]e must mustn't forget the days when the dry and cracked skin that we just shed were vigorous and bright with new colors. The next chance you have, hold a glass high to the past and drink to Soda MkIV, the last of the great Sequents." \_ I'm obviously too young. 22 386s in one machine? In 1995? Huh? I guess it was really good a multi-tasking. \_ Remember that it was *free* in 1995. The machine was built the late 80s, when the 386 was top-of-the-line. \_ and yes, those sequent systems were awesome at multitasking. Unfortunately the slow-ass cpu's were very slow at single tasks. However, it was ideal for its use as a multi-user, multi-purpose system. \_ Did the fastest Pentium-something CPU in 1995 perform twenty times as fast as a 386DX 20MHz (in terms of mips, I guess)? I don't remember which Pentium was top-of-the-line back then. \_ iirc, 1995 the fastest Pentium was 133 MHz. This was about as fast as a 486 running at 266 MHz or a 386 running at 533 MHz (ie nearly 25x faster than a 386 running at 20MHz). \_ I google'd for "8088 SMP", and I found "The SNC is an Intel 8088 based SMP system ..." in a non-free article. Can 8088 really support SMP??? \_ Why not? SMP is an old old old concept in CS. \_ I was just puzzled because Intel advertised one of the recent Pentium-whatever chip as the first x86 chip to support SMP. |
| 2006/10/24-26 [Computer/HW/CPU] UID:44943 Activity:nil |
10/24 Why does hyperthreading slow things down? I can imagine why it may not
be faster than a one-thread CPU (maybe too many bottlenecks), but how
can it be even slower than a one-thread CPU?
\_ When two procs are doing the same thing, they'll gain no benefit
from HT and HT simply adds overhead. Two dissimilar procs will do
well.
\_ (Where pp says 'proc', read 'process', not 'processor')
\_ Useless overhead.
\_ Did Intel not test its own design before releasing it to the
market?
\_ Of course they did. In most circumstances HT is worth using
but for some applications it is just overhead and should be
disabled. *In general* HT is good for applications where UI
responsiveness is more important than shaving over a few
microseconds or increasing FPS by 1.5. It is bad for a
situation where your single threaded application is cpu
bound and the only process running on a machine. There are
many other in between cases of course and YMMV but overall
HT is a good thing and should be turned on unless you know
it will hurt your use. Profile and test if you care.
\_ We found the opposite. We found that in most instances
HT hurt performance and so by default we turn it off.
YMMV.
\_ What was Intel thinking??? |
| 2006/10/13 [Computer/HW/CPU] UID:44813 Activity:nil |
10/13 This goes back to the last Intel cpu release and everyone's #s on
temps, etc. Just a reminder that those #s are based on a clean box.
I just cleaned out a ton of dust and fluff from my case and temps
dropped about 8F back to about what they were when it was all new. |
| 2006/10/12-14 [Computer/HW/CPU] UID:44789 Activity:nil |
10/12 On a dual-processor PC, the two CPUs can concurrently run one thread
and one interrupt handler, or two interrupt handlers. Can a dual-core
processor PC and a hyperthreading processor PC do the same things?
Thanks.
\_ Dual-core is basically dual processor sharing the same socket, so
I don't see why not. Hyperthreading is weird, I dunno. |
| 2006/9/15-19 [Computer/HW/CPU, Computer/HW/Drives] UID:44395 Activity:nil |
9/15 Dell once again stocks AMD consumer-grade boxes
http://tinyurl.com/zc6r8 (dell.com) |
| 2006/9/10-12 [Computer/HW/Drives, Computer/HW/CPU] UID:44341 Activity:nil |
9/11 For those who run his/her own server. Has any of you tried to run a
fanless system that uses AMD Operon or Pentium M that is clocked more
than 1GHz? where to get chassis like these? can't find it at Fry's.
\_ No, but I have a fanless 800 MHz Via C3, with a big Zalman heatsink.
Got the CPU on ebay for about $50 and got the heatsink (CNPS-6000AlCu
Flower Cooler) from http://endpcnoise.com for about $40.. Runs great.
There is one fan in the system, the power supply exhaust, because
unless you are conducting heat to the case, you need some airflow to
keep things cool. If you want zero fans, take a look at Hush.
\_ No, but I have a fanless 800 MHz Via C3, with a big Zalman copper
heatsink. Got the CPU on ebay for about $50. and got the heatsikn
(Zalman CNPS-6000AlCu Flower Cooler) from http://endpcnoise.com for about
$40.. Runs great. There is one fan in the system, the power supple
exhaust, because unless you are conducting heat to the exterior, you
need some airflow.. If you wanted zero fans, take a look at Hush.
\_ I used to run on 600MHz VIA C3 in Antec ARIA. It was
incredibly slow. I now have a bunch of K8 systems
(RevCG Mobile Athlon64 0.9V 1GHz, RevE6 Turion64 800MHz,
RevE6 Sempron64 256kL2 1.1V 1GHz). Due to other factors
like power supply inefficiency and northbridge power
consumption, power draw measured using Fluke meter at
the plug is virtually the same for the VIA C3 vs Sempron64.
Turion64 800MHz may even eat less power (7.8W) than the
VIA. Even at 800MHz, K8 kicks C3's arse! I'd say it's
over 5x faster! To me, even 800MHz K8 is plenty fast
for most things. I also used to have a HUSH system. It
was noisier than ARIA because HDD whine (Seagate 7200.7)
dominated. And in the end, the unreliability the heat
added was not worth it. My quietest system (C3 fanless,
HDD-less using CF->IDE converter) is slow, but it has
its uses. Basically, except for the exceptional cases,
one slow fan won't be a bad thing at all. Just hide it
properly.
\_ I've been very happy with my Kurobox:
http://kurobox.com
It's a small PPC system that runs Linux -- Gentoo and Debian are the
best supported. It's $150 without a harddrive -- which is nice if you
have one lying around. It's a little tight on the RAM, but it can
happily do streaming and serving and such. And it's only got one
very-quiet fan -- the harddrive is the louder part. Plus it's cute!
--michener
\_ Nice link, thx. I was thinking of something like this, but I
could never find a reasonably priced external SATA RAID-5 drive
array/enclosure. -John
\_ Out of curiosity, what do you use it for? |
| 2006/9/7-12 [Computer/HW/CPU] UID:44314 Activity:nil |
9/7 FYI, the Athlon 64 X2 4600+ 65W (energy-efficient) retail CPU is now
available on http://mwave.com for $250 (zipzoomfly has been advertising $295+
for several weeks, newegg doesn't have it)
\_ Nooo! It's all about the E6600! /me rubs his E6600 all over his
pale, naked body.
\_ Well the E6600 is somewhat faster than the 4600+. A fairer
comparison would probably be the E6300 which should be available
under $200.
\_ don't forget mobo cost for Core 2 Duo and quality being
a concern (basically all the "my e6300 is 50+ deg C" wtf
posts on http://hardforum.com and the C2D being the fastest ramp
Intel has ever had to perform and a major architectural
change). AMD has had no quality issues recently.
fyi, if you do get C2D, get E6600 or above, I don't see as
many posts about temp issues. dgies maxes @ 40C at load.
I'm speculating, but I think there are many e6300/e6400's out
there that are e6600+'s with the shitty half of 4MB-shared-
cache turned off. You will need to research a reasonable
price/perf mobo (for non-overclockers) which is the other
1/2 of the eqn.
\_ Why would I want to put it in my computer? I'm too busy
pleasuring myself with it.
\_ ob what you do with the thermal gel is your business
\_ my chip runs at 37C, baby. |
| 2006/9/1-5 [Computer/HW/CPU] UID:44240 Activity:nil |
9/1 How many of you bought one of those new Intel CPUs, whatd you pay
and what are you doing with it? --Just curious
\_ E6600, $380 on release day, games and replacing old machine mostly.
\_ didn't buy, leery of initial CPU/mobo releases and especially the
strange mobo pricing for Core 2 Duo. The dev and ramping of C2D
seem unusually rushed.
seem worryingly rushed. Also, review sites need to perform reviews
on anonymously ordered CPUs, not on CPUs donated by Intel which
probably have lowest power draw for its stepping, the donations
occurring far in advance of widespread product availability. |
| 2006/8/31-9/5 [Computer/HW/CPU] UID:44222 Activity:nil |
8/31 Intel to have internal webcast Tuesday, presenting results of 90-day
efficiency review. <= 10,000 or 20,000 employees rumored to be laid
off.
http://news.zdnet.com/2100-9595_22-6111478.html
http://www.theregister.co.uk/2006/08/31/intel_fire
\- clever headline. nice use of "decimate" in the classical sense
["to kill one in 10"]. worthy of the e'ist. --psb
\_ INTC up $0.17. |
| 2006/8/30-9/3 [Computer/HW/Memory, Computer/HW/CPU] UID:44208 Activity:nil |
8/30 I just configured a Dell XPS M1710 with the 2.0-GHz 4MB-cache
Core 2 Duo with WinXP Pro and 3 years warranty. $3,106 after tax!
Dang, some rich kids will be spending bux on their computer for
undergrad WoW.
\_ Excuse my lameness, but it this faster than a 3GHz Pentium D ?
I know MHz doesn't matter anymore, but it doesn't feel right.
\_ I believe all Pentium D's up to 3.6 Ghz are blown out of the
water by a 2.0-GHz C2D with 4MB-cache.
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2795&p=12
The above has desktop Core 2 Duo vs. Pentium D, not mobile C2D,
but you also need to consider the 1.86 C2D desktop has only
2MB of cache.
\_ In my (limited) experience, Core (1) Duo 1.86GHz >> Dual Xeon 3.0 |
| 2006/8/21-24 [Computer/HW/CPU] UID:44082 Activity:nil |
8/21 So I was looking for a good distributed computing project to join.
SETI@Home looks like a waste of effort (just my opinion)
Folding@Home is poorly set up for multiproc systems.
Can someone suggest a project that is worthwhile, has a multithreaded
computation, doesn't use boatloads of RAM, and preferably has a
halfway decent screensaver?
\_ If we can harness all the idle computers to render 3D graphics
porn, like Final Fantasy Porn, imagine all the wonderful
changes we'd make to mankind!
\_ http://www.electricsheep.org It _is_ a screensaver.
\_ Looks neat but all the main work is done in a single thread
according to their research paper.
\_ It doesn't even use all of a single CPU -- it's currently
limited by the network bandwidth of the server, not by the
processing speed of the clients. But hey, that means you
could run Electric Sheep as your screensaver and something
more useful in the background.
\_ I have a dual-processor XP machine, and I run one instance of
SETI@home (BOINC) and one instance of FightAIDS@home (World
Community Grid).
\_ Why is seti a waste?
\_ I have pessimistic paramaters for the Drake Equation. |
| 2006/8/17-22 [Computer/HW/CPU] UID:44058 Activity:nil |
8/17 Predictions on much down in % that DELL will open at tomorrow morning
compared to today's close? It's already down 5.8% in after-hours.
\_ Maybe they should liquidate the company and give the money back to
the share holders - SJOBS
\_ And that's all because of the Sony batteries!!!
\_ I thought Sony was paying for that
\_ In other news, Dell announced they'll be shipping desktops with AMD
chips.
\_ They've done that for a while but you had to know who to talk
to. Kinda weird that Dell finally caught up with the market
right after Intel finally came out with some decent chips.
\_ That'd be funny, if Intel "told" on Dell because they went with
AMD again. It's not like Intel's doing anything illegal by
reporting on their partner. |
| 2006/8/8-11 [Computer/HW/CPU] UID:43944 Activity:nil |
8/8 http://csua.org/u/gna (Fortune via http://cnn.com) Review of AMD anti-trust lawsuit against Intel filed last year |
| 2006/8/7-11 [Computer/HW/CPU] UID:43933 Activity:nil |
8/7 Microcenter in Santa Clara has E6600 processors, OEM for $379. I just
got one. If they still have some, you can request a "one day hold".
-dgies
\_ I'm still wondering what use everyone has for a CPU like this that
a CPU at half the cost won't do. I understand this is the bang for
the buck price point. What's all that bang for anyway?
\_ Games, multitasking a bit too much, and replacing an old box.
\_ Well, what looks nice is that it's the cheapest chip of the
next generation that just came out. So you get that "next-gen"
boost, but are still coming in on the bottom rung (which is
the best price/perf at that level)
\_ No it isn't, there is the E6300 etc.
\_ Right, but those are 2M cache, IIRC
\_ And again I ask, so? What do you need 4M cache for?
What is all this bang going to bang on, so to speak?
\_ I'm not the OP, but... why do you ever buy a new
computer? And when you do, don't you ever buy a
middle-to-new spec'ed one so that it'll last that
little bit longer?
\_ Then you should have said "cheapest chip of the next
Intel generation with 4MB cache".
\_ pls report on the CPU temp and cooler you're using. I'm reading
on http://hardforum.com about three E6300's running > 60 degrees C at load.
\_ Haven't assembled yet, but my cooler is rated for <0.25C/W so
given 65W TDP and 30C case, I'd expect the mid 40's. With bad
case cooling and a less efficient cooler, I could imagine 60C.
But keep in mind the Athlon X2s are rated at what, 89W?
\_ you haven't heard the big argument about TDP for Intel and
AMD having two different meanings?
http://blogs.zdnet.com/Ou/?p=273
anyway, pls do report. i'm really curious about whether
anyway, pls do report. i'm concerned about whether
all the reviewers got super-clean CPUs, while the rabble
are getting crap. thanks.
\_ Better than my old-process Athlon XP which runs @ 82C
\_ Better than my old-process Athlon XP 2100+ which runs @ 82C
\_ AMD 4400+, ~20C idle, ~32C under full load.
\_ I have a little trouble believing the accuracy of that
measurement. At idle, it should be no cooler than the
interior of your case, and 20C is pretty low for a case.
What case fans do you have and what is the ambient temp?
\_ Case: ExtremEngine 3T. Temps are as measured by the
motherboard and cpu sensors. I don't care enough to
stick a contact thermometer in the case to get more
accurate readings. Ambient is about 20C, often
cooler.
\_ I guess with that case I can believe your case temp
is that low. -pp
\_ i'm gonna guess he's water cooling!
\_ My 3.6GHz P4 is only -40C!*
(* When cooled with liquid nitrogen)
\_ My penis is 2 inches flaccid and 5 inches erect. |
| 2006/8/4-6 [Computer/HW/CPU] UID:43909 Activity:nil |
8/4 http://www.hardforum.com/showthread.php?t=1084137 "There is about a 1% chance that we'll actually ship these on the 7th. (The E6600/E6700's I mean). None of the distributors have them yet. It's a mess. I'm working my best still to get these darn things, but my word, Intel and the distributors just can't get this sorted out. ... From Tankguy's Ben" However, you can still get E6300 now, if you don't mind the 25% mark-up ... it only ends up being $229 on http://mwave.com ... down from a 35% mark-up from two days ago. \_ Sucks. But Fry's is supposeadly getting them on Monday 8/7. We shall see. \_ BTW, http://outpost.com shows OEM E6300 as "In Stock", shipping 8/7, for $20 less than http://mwave.com. All other types are not listed or Pre-Order. \_ I like Fry's. -proud American |
| 2006/8/1-2 [Computer/HW/CPU] UID:43856 Activity:nil |
8/1 Bin Laden with the Democrats, so Israel needs to punish Iran. But
remember that they should tip at least 20%, especially when searching
for the new Intel processor at Fry's. RIDE BIKE!
\_ and use Linux
\_ Conroe. Learn the name, damnit.
\_ I guess the geek community basically just rejected "Core 2 Duo"?
\_ Conroe is 2 unaspirated sylables, Core 2 Duo is 4 sylables and
sounds confusingly similar to both their previous chip and
the generic term "dual core". So I want Conroe, but my
search term is Core 2 Duo.
\_ Flash drive has dreamhost data which sucks, and parents'
anniversaray on flickr is bad because picasaweb is superior,
renewable energy renews gmail interests because it's eco-friendly,
and the breakins on a bunch of Cal sites is because minijets
are coming. Use E6600, drink beer, and do lots of drugs so that
you can die early and save the environment from pollution! |
| 2006/7/28-8/2 [Computer/HW/Laptop, Computer/HW/CPU] UID:43829 Activity:nil 80%like:43827 |
7/28 Where is a reputable place to pre-order a E6600 processor?
\_ I'm still curious what everyone plans to do with these chips.
Not that I wouldn't buy one if I was in the market for a new
computer right now but I keep computers for a loooong time.
\_ I'm in the market for a new (self-built) computer.
\_ My current machine can't run the latest games, I'm building a
a new one.
\_ Everyone seems to point to http://www.tankguys.com I don't know if they
are reputable.
\_ http://newegg.com|mwave.com|zipzoomfly.com, and now http://tigerdirect.com.
There are none in stock, though, and I believe there is a embargo
date of Aug 7. You could buy an OEM E6300 yesterday from
http://tigerdirect.com but they're all out. See http://hardforum.com, Intel
board for more info.
\_ http://tigerdirect.com had both OEM E6300 and E6600 yesterday and shipped
them out. See http://hardforum.com, Intel board for more info. I don't
know how hard it is to cancel a pre-order. Rumors are that
significantly more stock will be available come Aug 7.
\_ http://tigerdirect.com had OEM E6300 yesterday and shipped them out, so
you could try them for OEM E6600. See http://hardforum.com, Intel board
for more info. I don't know how hard it is to cancel a pre-order.
know how hard it is to cancel a pre-order. Consensus seems to be
that significantly more stock will be available come Aug 7.
\_ I've never used them, but I've read some bad critiques of their
customer service online--no clue if they're for real or not
but you might consider researching before ordering there. -John
\_ I bought several items, returned several items and also got
my mail-in rebate money from tiger with no problems at all.
Every company on the net has complaints posted about them.
You need to examine the nature and consistency of the
issues and ignore the random insane ranter or you'll never
buy anything from anyone.
\_ http://Tigerdirect.com is notorious for ripping people off
when it comes to rebate coupons. They've been involved
in much litigation about this. -proud American |
| 2006/7/28 [Computer/HW/CPU] UID:43827 Activity:nil 80%like:43829 |
7/28 Where is a reputable place to pre-order a Tickle-me^H^H^H^H^H^H^H^H^H
E6600 processor?
\_ I'm still curious what everyone plans to do with these chips.
Not that I wouldn't buy one if I was in the market for a new
computer right now but I keep computers for a loooong time.
\_ I'm in the market for a new (self-built) computer.
\_ My current machine can't run the latest games, I'm building a
a new one.
\_ Everyone seems to point to http://www.tankguys.com I don't know if they
are reputable. |
| 2006/7/26-28 [Science/GlobalWarming, Computer/HW/CPU] UID:43810 Activity:nil |
7/26 Re the AMD price cuts Monday, http://newegg.com shows the Athlon X2 4600+ Socket AM2 Windsor as $330 and out of stock, but http://mwave.com has it in stock for $240. Also, the energy-efficient variants are only supposed to have a 10% mark-up, but no word on availability. Don't get screwed. \_ How much MORE efficient? \_ 89W vs. 65W TDP in general, 35W for a special 3800+ CPU also, although the AMD press release gave May availability, they only appeared in early July in Japan on store shelves. the same release said the 35W part drew 14W for someone doing office apps. \_ NICE. Very nice. I'm definitely getting the 35W version when it is available. This is pretty exciting!!! \_ ob for yermom! -1337 g4m3r |
| 2006/7/25-28 [Computer/HW/CPU] UID:43795 Activity:nil |
7/25 I want to buy a quiet PC. It doesn't have to be completely silent,
just quieter than the one I have now (something I could put in a
bedroom and still fall asleep). Can someone recommend a prebuilt
but configurable computer (Dell etc) that isn't loud? I've seen some
websites like http://silentpcreview.com but those seem very focused on
building your own system, which I don't have time to deal with right
now. (Low power consumption is a plus).
\_ have you considered a mac mini? run bootcamp if you need windows
\_ All of the Dells I have experience with are very, very quiet.
\_ In case you don't know, Dell (and mega corporations like
Walmart and Olive Garden) donates a huge % of money to
the Republican Party, the party for big businesses.
\_ Ask me if I care.
\_ Agreed, but I haven't bought a Pentium D system and ran it
100% on both cores.
\_ I have a 380N Dual Core and it's as quiet as any other Dell.
\_ what's the processor model number, and does it stay
quiet when doing 3D gaming, let's say.
\_ Personal built is ALWAYS better. You can control any component.
Pre-built never guarantees quiet components that meet your
stringent specification. For example they could have shipped
a noisy HD and you're screwed. Go for personal built systems:
http://csua.com/?entry=37454
http://csua.com/?entry=37246
http://csua.com/?entry=37274
http://csua.com/?entry=26756
http://csua.com/?entry=26584
Otherwise if you really want, Dells are decent:
http://csua.com/?entry=37704
\_ One thing people are forgetting to say is that Dell only builds
Intel (right now), and Intel desktop CPUs suck (right now), except
perhaps the 65nm NetBurst dual-core line.
The Intel CPUs that don't suck are to be released Thursday --
suggest you login to the Dell web site then and look for Core Duo
suggest you login to the Dell web site then and look for Core 2 Duo
platforms and ETA.
Otherwise, the best question is, who produces a quiet AMD Athlon
64 X2 system?
\_ For most uses, Intel's CPUs are just fine. Opterons are
better if you're running a 64 bit OS. I don't understand
why people feel a need to run a 4.0 GHz system to play
Minesweeper. To say that Intel CPUs sucks just reeks of
gamer boy nastiness.
\_ I didn't say "Intel CPUs suck". I said Intel desktop CPUs suck
(right now), except perhaps the 65nm NetBurst dual-core line
(and add any 65nm single core, and any 90nm slow-clocked
single-cores).
\_How about a mini-itx...they seem to be really quiet.
\_ watch out. some SFF systems get loud under 100% load. |
| 2006/7/24-28 [Computer/HW/CPU] UID:43781 Activity:nil |
7/24 http://csua.org/u/gin (amd.com) AMD releases new price list, effective today FYI, Conroe is launching Thursday, but it's unclear when inventory can satisfy demand, especially for the E6600 "sweet spot". \_ I want the E6600, bitch, hands off! It's the nerd equivalent of "tickle-me-Elmo" \_ No! It's MY processor!!! Seriously though, does anyone know from experience if Fry's tends to get a good allocation of new CPUs early at a fair price? \_ I needed a new computer 6 months ago so I bought an AMD 4400+. I game but don't program or do anything heavy calculations on it I game but don't program or do any heavy calculations on it and it runs great. Just curious: what are the E6600 buyers planning to do with your snazzy new cpu? An E6600 wouldn't run my very piggy games any faster. \_ Presuming you are CPU bound and not GPU bound, yes it would. The E6600 is benching slightly faster than an A64x2 5000 in most games. \_ I'm neither. I've seen the artificial benchmarks. I'm wondering what other people plan to do with their new toy. \_ But most real world gaming situations will be GPU limited. People with high end machines will tend to push the graphics to higher resolutions and such, something the CPU benchmarks don't show. I'm not too excited about Conroe because it won't make much difference in my usage. I like how they triggered a price war though. I heard Intel is sitting on a giant stockpile of Netburst-era processors. I wonder how much they will lose on that. This article is kinda silly but makes a point: http://enthusiast.hardocp.com/article.html?art=MTEwOCwsLGhlbnRodXNpYXN0 \_ The 4MB of shared L2 cache significantly improves execution time on things like zipping files and encoding audio/video. I expect compile time improvements to be similar, although I haven't seen any compile-time benches yet. Performance per watt is also outstanding. All that's left is if Intel can crank out these E6600 parts in sufficient quantity without going bust and any weird stability / compatibility issues. \_ Well they're definitely going to take a loss on the Great Netburst Fire Sale of '06, but it's not going to ruin the company. Agreed that Core2 availability is an important question. An awful lot of volume goes on in sub-$100 CPUs and it will be interesting to see how much cheap Netbursts can stymie low-end A64s and Semprons. \_ News update: Fry's pricing on E6600 is $379. Not yet in stock. |
| 2006/6/22-29 [Computer/HW/CPU] UID:43472 Activity:nil |
6/22 http://www.theinquirer.net/?article=32536 "Size of AMD's Dell hook-up set to shock ... AMD will be a big winner come autumn" Inquirer reports it has seen documents in Taipei indicating Dell has placed design orders with several Taiwanese companies for desktop and notebook systems with AMD CPUs. \_ err... you know that AMD is not taking any new order from OEMs because they couldn't meet the demand \_ err... you do know AMD is building fabs, and the one in new york is part of the reason its stock dipped a bit |
| 2006/6/22-26 [Computer/HW/CPU] UID:43465 Activity:nil |
6/22 http://www.theinquirer.net/?article=32566 Intel hosts LAN party on Arizona campus. 60% bring AMD computers, 37% bring Intel. \_ Semi-related factoid: The Windows Startup sound was created on an Apple Macintosh. |
| 2006/6/16-19 [Computer/HW/CPU] UID:43421 Activity:nil |
6/16 http://www.digit-life.com/articles2/cpu/intel-conroe-2-13-ghz.html "Here you can see the quintessence of Conroe's triumphal hymn. While the efficiency of Athlon 64 FX is higher by 58% versus Pentium eXtreme Edition 965, Conroe's efficiency is higher by 23% versus Athlon 64 FX! It seemed impossible to create something more efficient than the AMD K8 core, but Intel engineers managed to do it." (June 15, 2006) \_ The damn intellitxt links on this page was the last straw to get me to install adblock. Man I hate those things. \_ intelli-what links? oh those, yeah I ad blocked them the very first time I saw them. crazy obnoxious shit. \_ You're gonna need all that efficiency cuz Windows Vista, at least right now, is a dog. \_ Don't you mean Vista Server 2009? Then again, with Gates semi-retiring into charity work, maybe they'll actually get it done sometime before we have a new President. \_ Previewers have noted that Vista sucks up ~ 40% more juice from your notebook battery in Aero mode. |
| 2006/6/14-17 [Computer/HW/CPU] UID:43392 Activity:nil |
6/14 I have old computer hardwares that I am getting rid of before my move.
1. ASUS A7V mobo with K6 processor around 733MHz
2. Intel desktop mobo with P3 833MHz
3. Tyan S2500 mobo with 2x P3 ~800-1GHz cpus
4. Cyrix 586 133MHz system
It's free for whoever wants it and can pick it up on campus. They
are mounted on the case, and you must take the whole combo (mobo, case
cpu) #1 has a working power supply as well. #3 requires registered
ECC RAM, and I have 2x512MB that'll be included as well. #1 and #2
should be working, but no guarantee. #3 and #4 were working when
last turned off. Anything
not picked up by Friday will go to ACCRC. Email johndkim. |
| 2006/6/7-9 [Computer/HW/CPU] UID:43310 Activity:nil |
6/7 INTC drops to three-year low. Time to buy?
\_ depends whether you think they'll gain the momentum back from
AMD. Sometimes there's a reason a company is at a three-year
low. -tom
\_ I want to kill all white male and inseminate as many hot blonde
women as possible as a revenge on the fall of
our glorious Eastern Empire.
\_ Kewl: http://tinyurl.com/o2jop (see below.) -John
\_ Yes, I suppose the current price reflects market uncertainty
about whether Conroe is the real shiznit. The latest test dated
yesterday is a bit more independent, with machines assembled and
software installed "without the help of Intel":
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2771
Then read the http://tomshardware.com and http://firingsquad.com previews
released on Monday:
http://csua.org/u/g3y (anandtech.com)
Hey, prime time to buy, right? Think critically about what
you've read so far, then see:
http://sharikou.blogspot.com/2006/06/our-coverage-of-anand.html
My conclusion from all the hard work some individuals have done
is that Conroe will perform at or below comparable AMD offerings,
will probably be less available, but will probably be cheaper -
but take that advice as from someone unwilling to sign.
but that's advice from someone who's unwilling to sign.
\- FYI, there is an interesting paper worth glacing at
by YELICK and some other berkeley/lbl people about the
IBM CELL PROCESSOR ... a little bit on the interesting
design [espe of the memory bus] and some bmarks on various
standarized scientific computations. obgoogle if interested. |
| 2006/5/24 [Computer/HW/CPU] UID:43178 Activity:nil 66%like:43179 |
5/24 http://www.engadget.com/2006/05/24/msi-releases-12-1-inch-dual-core-s271-laptop Hot hot hot!!!!!!! \_ boring \_ they need a battery life comparison for Turion 64 X2 vs. Core Duo and the weight of the systems |
| 2006/5/7-10 [Computer/HW/CPU] UID:42966 Activity:nil |
5/7 Conroe CPUs will kick ass. -- recently bought INTC
\_ but all the performance tests have been where Intel controlled both
the Conroe and the AMD box, right? Previously Intel would mail an
actual CPU to a reviewer site and they could play with it as much as
they wanted, but as far as I know this hasn't happened. |
| 2006/3/2-5 [Computer/HW/CPU] UID:42078 Activity:moderate |
3/2 How is an Opteron different from an Athlon64?
\_ Most Opterons require registered DIMM (940pin) and most
have 3 HT links. 1xx series only have 1 usable one, though.
There're some 939pin Opterons, which are basically identical
to Athlon 64. All Athlon 64s have 1 HT link only and use
unbuffered DIMMs. Internally, they're identical other than
cache size and missing HT link logic. DRAM controller is
actually the same, but depending on which pads get routed to
the pins, it turns into A64 or Opteron. -- AMD employee.
\_ one has more vowel than the other
\_ Thanks! Can you answer one more question though? I thought
the 939 pin opterons (165,170,175) had 3 HT links (not that
it matters) and the only difference between those and 940 pins
was the pin count and memory required? Is there any difference
between any of 165,170,175 and the same speed/cache X2? -!op
\_ There is practically no difference between 939pin
Opteron and 939pin A64. Apparently, MANIDs are
different, though, which some BIOS may not like. I
believe Opteron 939pin is multiplier unlocked, but
don't quote me on that. FX parts are all multiplier
unlocked. All 939pin parts have only 1 HT link, so
939pin Opterons can only be used on 1 socket systems.
Also, in case anybody cares, the biggest win for 939pin
is that vendors can build cheap 4-layer motherboards for
them. 940pin requires more layers. Layers on motherboard
are relatively expensive. Also, unbuffered DIMMs are
cheaper. All K8 is capable of supporting ECC memory, but
not many BIOS in the consumer boards enable it.
\_ I've seen references to layer counts in motherboards at
review sites and all they ever said was "more is better!".
What's it really mean? Thanks again.
\_ This is pretty simple. Think all those tightly
packed pins. Now, you need to route them a
certain way without them colliding. Obviously,
if they collide, that's an electrical short. Any
short you didn't intend is bad. There are only
so many ways to route them in our 3-dimensional
world. In fact, it's more like 2-dimension +
however many layers you add. More layer really
shouldn't imply better quality other than the
fact that you can isolate the power and ground
planes better. You can also route things in
such ways to reduce noise (add more inductive
loops and keep certain signals away from each
other). If you're current limited (crazy
overclockers and what not), more may be of some
use, too. More layers can also be bad since
there will be more points of failures,
particularly the layer-to-layer connections.
\_ http://tinyurl.com/mcgr3 (amd.com)
Opteron has more HT links (3 v. 1) and more cache than a
Athlon64.
\_ I think the above link is dated. The reason I think so is
that when comparing prices I found the Athlon64 FX60 to
cost more than the equivalent dual-core Opteron. Why is
that? Also, along those lines, anyone have links comparing
the performance of a Opteron 280 to an Opteron 250? They
are the same clock speed, but the 280 is dual core. Are you
better off with a 254 (unicore but 20% faster CPU)? This is
for pure floating point computing, let's say monte carlos
running threaded.
\_ You can unscrew an Athlon64! |
| 2006/3/1-2 [Computer/HW/CPU] UID:42039 Activity:high |
2/28 So this new Intel Mac Mini... didn't the old one have better
graphics and also cost less?
\_ I think Apple is overcharging for it, since the new model is $100
more from the last base priced model. As components go down in
price, so should the unit, or the specs should go up with a flat
price. However, keep in mind you do get 256MB more ram ($75),
\_ $75 for 256MB!? What country are you from? You can get 1GB
with that kind of money.
\_ Where? The new mini uses DDR2 5300 ram. The cheapest I've
seen 1 GB is $120 or so. I agree that $75 is overpriced
for 256MB ram, you can get that for around $45.
\_ newegg (first hit, didn't continue searching) CORSAIR
ValueSelect 1GB 240-Pin DDR2 SDRAM System Memory - Retail
$100... c'mon do a little searching
\_ The x86 mini and the x86 iMac use 200 pin DDR2 ram
not 240 pin DDR2 ram.
20GB more space, 2 more USB ports, and the new Intel processor
supposedly "delivers two times the performance of the original Mac
mini." The last part I don't get because it's the Intel Core Solo
is a single 1.5Ghz chips, while the original was a single PowerPC
G4 chip (1.42Ghz). I thought, RISC processors allowed computers
to get more processing out of the same raw Ghz? At least that's
what Apple was touting at the pinacle of the Intel vs PowerPC
wars. So how does a single 1.5Ghz chip double performance from a
1.42Ghz chip, especially a RISC based one? And yes, the new mini
uses shared video RAM, but it is an entry level machine, even if
it's not priced like one.
\_ If I understand correctly RISC chips tend to get their speed
from being superscalar (multiple piplines). And the pentium4
is a RISC chip BTW, just has decoders on it for x86. --jwm.
\_ There are a couple of other changes that make the single
proc x86 mini faster than the PPC mini. The x86 mini has a
667MHz system bus, while the PPC had a 167MHz system bus.
The x86 mini uses a 5400 rpm SATA2 HD, while the PPC had a
4200 rpm laptop drive. The x86 mini also has 2 MB L2, while
the PPC only had 512KB L2.
\_ There are a few other changes that make the single proc x86
mini faster than the PPC mini:
1. 2MB l2 v. 512KB l2
2. 667 MHz system bus v. 167 MHz system bus
3. PC5300 DDR2 ram v. PC2700 ram
4. 5400 rpm sata2 HD v. 4200 rpm ata-100 hd
Personally the attractive features for me are the upgrade to
GigE, the 4 usb2 ports and the builtin bluetooth. I don't
know what to make of the shared video b/c it might be faster
than the Raedon 9200 in the PPC mini, but then again you have
to give up around 80 MB of main memory.
If I didn't own a PPC mini, I would probably have bought the
single proc one by now.
single proc one.
\_ Fundamentally, the fact that Apple switched to Intel chips,
\_ Fundamentally, the fact is that Apple switched to Intel chips
ostensibly to save money and because of better heat
performance in small form factors, and the best they
can come up with is a machine that may or may not be faster
than an identical-looking box they released over a year ago
for $100 less, is pissing a lot of people off. -tom
\_ I think that the focus on the $100 price increase
for the base model misses something crucial.
The base model x86 mini has the same specs as the
high end PPC mini and costs almost $200 less. In
addition, the base x86 mini comes w/ gigE, optical
audio out, 4 usb ports, and builtin bt. Personally,
I think apple has done a good job in reducing the
price of the mini.
\_ wow, increasing the price by $100 for no clear
advantage in performance is "reducing the price."
Do you work for Bush? (Here's a hint: in the
computer industry, generally computers get
significantly faster and cheaper in a year). -tom
\_ Apparently tom not only flunked out of UCB, but
even basic H.S. economics. The new Mac mini base
is functionally comparable to the old Mac mini
"deluxe", not to the old Mac mini base. Since
the new Mac mini base costs less than the old Mac
mini "deluxe", there is a drop in price. You get
more value for your dollar, but the unsophisticated
buyer like yourself can only focus on the base
price.
\_ Who gives a shit about that? The reality of it
is that the entry price went up $100. Is the
user getting $100 more value? Basically just
256MB more RAM. Considering how time works
in the computer world and the age of the old
system, this deal stinks.
\_ I think the user is getting more than $100
in value in comparison to the base model
PPC mini:
in value and performance in comparison to
the base model PPC mini:
1. 300 extra MHz - 1.5GHz x86 v. 1.2 GHz
PPC [in addition, the x86 has 2MB l2,
instead of the 512KB l2 in the PPC,
which should make the base mini seem
"snappier"]
2. 20GB extra HD - 60GB sata2 (faster) hd
v. 40GB ata-100 hd (the 4200 rpm hd in
the PPC can be painfully slow) In the
PPC mini, the upgrade to a 60GB HD was
around $40-$50.
3. 256MB extra (faster) RAM - in the PPC
mini a 512MB Dimm was around $50.
mini a 512MB Dimm was around $50. The
extra ram was sorely needed b/c the
mini was very slow w/ 256MB RAM.
4. Builtin Airport and BT - in the PPC
mini these were BTO options that added
about $50.
5. 4 USB2 ports - don't need to buy a
ugly usb hub, which saves $20 or so.
6. gigE instead of 10/100
7. optical audio out
Even if one says that Apple's BTO prices
were 2x the real cost for RAM and HD and
NO additional price should be added for
the faster processor, the price difference
($20-$25 HD + $25 RAM + $50 BT/Airport
~ $100) is easily made up by the add'l
features of the base model x86 mini.
I still think that the correct comparision
is between the old deluxe PPC mini (1.42,
1.5 GHz) and the new base model x86 mini.
The PPC deluxe model cost $599 and did not
come w/ airport, bt, 512MB of ram, gigE or
optical audio out. The only feature that
the the deluxe PPC mini had was a bigger
HD. Arguably, all the extras in the x86
mini more than make up for these 20GBs.
To get a 1.5GHz PPC mini that w/ a config
similar to the base x86 mini, one had to
spend nearly $800 (I know I bought one).
optical audio out.
1.5 GHz w/o superdrive) and the new base
model x86 mini. The PPC deluxe model cost
$599 and did not come w/ airport, bt, 512MB
of ram, gigE or optical audio out.
The only feature that the deluxe PPC mini
had was a bigger HD. Arguably, all the
extras in the x86 mini more than make up
for the smaller HD, even if there is NO
performance upgrade (ie you are getting
a x86 mini w/ many more features today
than you would have if you bought a 1.5
GHz PPC mini on monday).
Furthermore, to get a 1.5GHz PPC mini
that w/ a config similar to the base x86
mini, one had to spend nearly $800 (I
know I bought one).
w/ a config similar to the base x86 mini
one had to spend nearly $800 (I know b/c
I bought one), which is why I say that
the base model today is $200 cheaper than
the comparable PPC model.
To me the base mini easily demonstrates
that every year you get more computer at
cheaper prices.
that every year you get more computer
at cheaper prices.
If you just want to focus on the cost of
entry, you are right it is $100 more. I
think that such an inquiry is basically
useless b/c it ignores almost all of the
relevant facts.
\_ The thing that kept me from getting
an mac mini before was that I was
worried the G4 would be slow. That's
corrected now, and all the extra
goodies look good!
\_ The old 1.4GHz PPC mini was pretty
good provided you got enough ram.
The new 1.5GHz core solo mini should
be quite nice if you get 1 GB of ram.
The addition of front row and the
remote make it fairly attractive (to
me) as a htpc.
\_ why is it that tom always seem to have a
stick up his arse?
\_ He says it's $200 less. You say it's $100 more.
Only one of you can be correct.
\_ The entry-level model is $100 more than the
old entry-level model. He claims that the
entry-level model is now faster than the high-end
\_ The entry-level model is $100 more than the old
entry-level model. He claims that the entry-
level model is now faster than the high-end
model was before, so it's $200 cheaper. He
ignores the fact that by Moore's Law, the
machine should be almost twice as fast for
the same cost by this point, not $100 more
for a possible incremental speed increase.
And it's not like the old entry-level Mac Mini
was a great deal to begin with. -tom
machine should be almost twice as fast for the
same cost by this point, not $100 more for a
possible incremental speed increase. And it's
not like the old entry-level Mac Mini was a
great deal to begin with. -tom
\_ I'm not claiming that the entry level x86
system is faster than the high end PPC
system. I'm claiming that they are comp-
arable. I get the $200 savings b/c a
similarly spec'ed 1.5 GHz PPC mini would
have cost about $799.
Re Moore's Law - Is this your argument:
1. 1.2GHz/1.4GHz PPC mini released in
Jan 2005
2. ~ 12 months have passed
3. The proc should be 2.4GHz/2.8GHz
Please note, the period for Moore's law
is 24 mo these days, not 18 mo or 12 mo
as in the past. Also note that Moore's
law says nothing about cooling and power.
There is no way Apple/Intel could pack
in a 2.4 GHz P4 in that form factor w/o
a huge ps and hideously loud fans.
If your argument is that the low end
mini ought to have had a core duo proc,
I think this is unrealistic, considering
Moore's own company cannot make these
chips cheap enough for this price point.
Re the mini not a good deal -
I've owned numerous SFF PC's and I never
had one that was as silent as the mini
w/ equiv power (sure you can get a 800
MHz via c3, but it not nearly as fast
as a 1.4GHz PPC G4). Personally I think
the PPC mini was a great deal for a
completely silent and totally integrated
package. The addition of front row make
this far more desirable as a HT pc than
a xbox or a pc running mythtv/windows
media center b/c it is small and quiet.
\_ Look, I'm glad you're happy with it.
Buy one and enjoy it. But to claim it's
a good deal is ridiculous. -tom |
| 2006/2/22-27 [Computer/HW/CPU, Computer/SW/OS/Solaris] UID:41954 Activity:nil |
2/22 Can someone give me a link to a ISO of opensolaris
that I can burn and boot on my PC? thanks
\_ Opensolaris distributions are still pretty much for developers only.
If you want Solaris for your PC, download Solaris 10/x86 from Sun
ISO(s) from Sun.
\_ The closest thing to an official ISO for openSolaris is
sxcr. You have to register w/ sun to d/l it:
link:tinyurl.com/nswzr (javashoplm.sun.com)
One of my friends on the openSolaris team suggested that
you try nexenta instead |
| 2006/2/10-13 [Computer/HW/CPU] UID:41795 Activity:moderate |
2/10 What was your computer configuration during your UCB years?
\_ None.
\_ 286, 5.25" disk drives
\_ 486-66, upgraded to 100MHz. Worked far better than the HPUX
machines compiling over NFS at the time (graduated in '97).
\_ hah, me too, except I also did the DX3 (33 MHz FSB) to
DX2 (50 MHz FSB) hack that was all the rage back then.
\_ 386SX-16, then a 486-66. i think i had a P133 by the end, or
shortly after UCB.
\_ 386SX-16, 4MB RAM, 185MB HD, 5.25" and 3.5" floppies, 2400baud
modem, HCG monitor, serial mouse, Epson LX-810. Worked great.
Ironically, I had a composite color monotor for my Apple II+ in my
high school days, so I "downgraded" my monitor when switching to PC.
--- Class of '93
\_ typewriter the first semester (mostly for English 1A),
then 286, then 386DX
\_ Mac SE, PowerBook 180 ('93); Quadra 650 ('95), Pentium 150
running RH3 ('97) --class of '97
\_ Mac SE -> Mac Classic II -> Mac IIcx -> Pentium II -- Class of '98
\_ why did you finally convert to the WINTEL world?
\_ I went to go buy a Powermac, and decided I was willing to
spend about $2500 bucks. I wanted to run UN*X, and figured
spend about $2500. I wanted to run UN*X, and figured
I'd be stuck running Yellowdog Linux or something. Most of
my friends ran FreeBSD, so I figured I'd at least _look_ at
what I could get for $2500 in a PC. It turned out to be like
4x the machine.
\_ P133 that I played Quake on, then a Celeron 300A @450 that I played
Half-Life on. School? yeah I think I went to some sort of classes
sometimes, kind of hazy.
\_ Commodore 128, later replaced by an Amiga3000UX. -ERic
\_ I was too poor for my own computer, so I just hung out in The Web.
\_ In my days even people who had computers had to hang out in the
Web, because there was no such thing as a PPP dialup or free X
server for Windoze. Actually, even if these two existed,
performance would be terrible over a 2400baud connection anyway.
--- Class of '93
\_ I worked 'near' the guy who was responsible for the EECS modem
bank around then and pushed hard to get everything upgraded to
9600 to no avail. He only ended up destroying half the modem
bank and oh nevermind... it hurts to think about it.
\_ 486-33. Too wimpy to even play Doom when it came out.
\_ That was perfectly sufficient for playing doom.
\_ With a math co-processor, yes. Without, no. -!op
\_ http://www.faqs.org/faqs/games/doom/RGCD-faq
"Does DOOM benefit from a FPU for floating point
calculations?
No. All calculations in DOOM 1.1 and beyond
use integers."
... so did doom 1.0 use fp?
\_ Presumably. Either that or something like a 16.16
integer representation of real numbers.
\_ First 2 years, a TI portable with 12.5MHz 286 CPU, 640KB of RAM, 40MB
hard drive and a monorchrone screen. The following 1 year 233MHz
Pentium MMX PC with 32MB of RAM, 2GB disk (made by Micron). The
remaining two years (after a long perdiod out of school), 933MHz
Dell with 512MB of RAM.
\_ ADM-3A terminal plugged into a modem for dialup access.
\_ TVI 925 dialup terminal with 1200 baud, later upgraded to 14.4! |
| 2006/1/25-27 [Computer/HW/CPU] UID:41521 Activity:nil |
1/25 AMD kicking INTC's ass
http://finance.yahoo.com/q/bc?s=AMD&t=3m&l=on&z=m&q=l&c=intc
\_ AMD should. Intel used to punish AMD by hurting AMD's side
businesses, but AMD has spun off all the major side businesses
now. So Intel can't hurt AMD except in cpu, and AMD has better
technology and has not screwed up execution. The "Intel inside"
cachet is gone, and AMD has regular consumer acceptance.
cachet is gone, and AMD has regular consumer acceptance. I'm not
sure what Intel has within the next generation or two to unfuck
itself, and there's no way Intel can grab back the lost market
share.
\_ It's a bit premature to signal the death of Intel. It used to
be that Intel made more profit in 2 weeks than AMD cumulatively
for its entire existance, I doubt that has radically changed.
Intel has massively screwed up and mis-executed for a long time
but they are still doing quite well.
\_ all he's saying was that Intel can't grab back that lost
market share, and that the "Intel inside" cachet is gone.
Maybe he's wrong, but then again you have blogs like:
http://sharikou.blogspot.com
\_ "AMD ISBETTER" (old CPUID in 1994)
\_ don't dismiss INTC yet. they still have control over laptop
market and they have better OEM program in place for hardware
cookie cutters to use their chip. One interesting sign is that
on the Server side, INTC is pre-integrating all the I/O onto
their south-bridge chipset...
\_ The bigger they are, the longer it takes to fall.... |
| 2006/1/11-13 [Computer/HW/CPU] UID:41333 Activity:kinda low |
1/11 Anyone knows what happens to Apple's chipset design team
now that the Intel Macs are official?
\_ Who says Apple still wouldn't be using their own chipsets for
Intel chips? And wouldn't it be likely that the x86 version of
Mac OS X would require, say, an Apple chipset to prevent it from
running on non-Apple hardware?
\_ It would sound like a great waste of efficiency if Apple
plans to use its own instead of Intel. Just as with the case
of CPUs, Intel can achieve better economies of scale in
motherboard chipsets than about anyone and always stay on
top in price/performance. As for Apple specific mods, I'd be
surprised if Intel wouldn't be willing to accommodate them.
\_ Just looking at Asus' line of motherboards, I see motherboards
with chipsets by VIA, SIS, Nvidia, ATI, and ULI (oh, and
Intel). I wouldn't be surprised if Apple makes enough x86
motherboards to find it worthwhile to use a custom chipset
(whether they design it themselves or pay someone else to
do it).
\_ I've been told some of them are doing other things, others are not |
| 2006/1/5-7 [Science/Electric, Computer/HW/CPU] UID:41246 Activity:nil |
1/5 Intel releases pricing details for dual-core notebook Yonah CPUs,
dual-core 1.66Ghz at $241:
http://news.zdnet.com/2100-9584_22-6019832.html?tag=nl.e589
You lose in power consumption / battery life:
http://news.com.com/Yonah+to+suck+up+more+power/2100-1006_3-5893308.html |
| 2006/1/3-5 [Computer/HW/CPU, Computer/HW/Drives] UID:41210 Activity:nil |
1/3 I noticed firefox on certain pages left idle will start to consume
100% cpu, and cpu usage will drop back to normal after I close
that tab. Anyone seen similar problem? This is 1.5 but I've
seen it since 1.04.. I seem to have it on http://www.techbargain.com
and today http://Gizmodo.com.
\_ I've seen this happen with java applets. Perhaps those pages have
applets on their pages?
\_ not sure if it is related, but with 1.5 I've noticed that
when I return from standby both firefox and thunderbird go
crazy w.r.t. cpu usage (until I close and restart them, which
is a real hassle since I usually have multiple tab sessions
open).
\_ Have you tried waiting a while to see if they're just swap-crazy?
\_ Disk isn't spinning - the machine just sits. It might still
be swap related, but I'm thinking likely not. Just looked,
there are a few things in the forums that refer to a possible
problem with flash, trying the flash-block extension.
\_ I noticed the same thing, and now have the habit of
quitting firefox before I enter standby. -op
\_ Same thing happens in Opera sometimes. It appears to depend on
what's open. My guess is that it has to do with auto-refresh
pages--that when you resume, the browser queues up a bunch of
refresh events that gum up the system.
\_ Nope. Maybe evil broken Javascript? Actually, as of 1.5, it'll
start noticing things like javascript loops and offer to nuke the
page for you. |
| 2005/12/23-28 [Computer/HW/CPU] UID:41128 Activity:moderate |
12/22 Anyone know of a vendor which sells AMD boxes (dual package, dual core)
for resale (both in the US and internationally)?
\_ What kind of AMD boxes are you looking for? desktop? server?
consumer? embedded? industrial? enterprise?
\_ Number-crunching workstation for use in hospitals.
\_ so, essentially high end desktops? does hospital has any
special requirements? how many of those boxes are you
looking at?
\_ How about Sun? The Ultra 20 is supposed to be pretty nice.
\_ i can assure you generic AMD boxes is going to be a lot
cheaper :p
\_ Yeah, but he wanted a vendor that sells AMD boxes
for resale both domestically and internationally.
Other than Sun, I think that the only major vendor
who meets that criteria is HP.
\_ if you are serious about this, shoot me an email. I have contacts
with many server OEMs in Taiwan. kngharv |
| 2005/12/9-11 [Computer/SW/Languages, Computer/HW/CPU] UID:40938 Activity:nil |
12/9 Does anyone know if there are FOSS diff tools that are somewhat
syntax-aware? E.g., it would understand that comments and whitespace
don't matter (well, for languages where it doesn't), and that
expressions can span several lines but still be the same? It doesn't
even have to be smart enough to strip redundant sets of parentheses
or anything. Thanks.
\_ Compile the code and "cmp" the binaries. :-)
\_ Canonicalize the sources and diff those, e.g. run through a
pre-processor and auto-indenter? Or, get your hands on MOSS,
depending on what you're trying to do? |
| 2005/9/23-27 [Computer/HW/Memory, Computer/HW/CPU, Consumer/TV] UID:39841 Activity:nil |
9/23 Anyone ever built their own TiVo/PVR? any suggestions/advice
before I build one? I'm reading my way through http://byopvr.com
trying to figure out how to build one.
\- isnt the hardware heavily subsidized? why would you want
to build one from scratch? or is this a geek learning exercise?
\_ definitely the latter. granted I won't have to pay a
monthly service fee, I'll probably pay more up front
if I build one.
\_ I built mine out of mythtv because for some reason, I've
generally been against paying for a subscription of any kind.
You also get more features from building your own. Another
reason these days with TiVo adding various restrictions is
that you're not under direct control of some corporation's
whim. I admit, TiVo probably is more stable, but mythtv is
what works for me.
\_ How much did you spend on the hardware?
\_ I've used parts that are just laying about few times.
The latest incarnation I'm working on cost me about $400
for the shuttle-like case, cpu, and memory, I believe.
\_ I like to be able to watch recorded programs remotely :)
\_ You mean like mythtv?
\_ Decide on size of machine and noise level you find acceptable.
\_ how about those VIA C3 chip. I know that you can run
800Mhz without any fans. The newer 1GHz chip from
xxx nm fab reportly can run without fan neither. tried it? |
| 11/23 |