Printable View
As soon as these are released in the US I'll probably pick up the 125w version as long as the price drops...
Amazing,6 cores (+turbo) @ 2.8Ghz and just 95W :). These should start to show up soon in EU and USA,wonder if there will be a price premium over 125W version.
in that currency, how much is the normal 1055T?
im sure that they just over rated the vcore, the VID on my 1090 is 1.300V but it can run stock at 1.185V so that has to be worth enough to drop atleast 9% so that should be around 110W (i think that its even lower than that) and with the 1055 being clocked lower it should be easy for that ratingQuote:
Originally Posted by informal
20,963, they had a link to the price chart http://akiba-pc.watch.impress.co.jp/...619/p_cpu.htmlQuote:
Originally Posted by Manicdan
6 cores at 2.8 GHz with a TDP of 95W and only costing ~200€?
Sounds really neat :D
JPY 19,680～21,300Quote:
Originally Posted by Manicdan
http://pc.watch.impress.co.jp/docs/t...22_375959.html
Yeah I wonder if they can clock a little bit higher than the 125w versions.
will we see a newer, lower tdp 965 (quad)?
i dont think so but if the 960t or whatever the cutdown hex was named i would think that it would be 95W or lower and so would the 1035t if it ever comes out. i cannot see amd coming out with a new quad that has l3Quote:
Originally Posted by ChinStrap
i wondered about the 125w vs 95w thuban differences when they just came out. still haven't found the answer on how they did this yet.
http://www.xtremesystems.org/forums/...d.php?t=251896
All this makes me remember the ADV4400DAA6CD conspiration. It was an A64X2 4400+ Processor with virtually everything the same Core and specifications than a regular one but it had a TDP rating of 89W instead of the 110W of the normal one. I think that even Voltage was the same for those, so I don't know how they were supposed to consume less. Maybe the original A64X2 4400+ had its TDP overrated and could fit the 89W category with no issues though borderlining it. Maybe something similar happens with these PIIX6.
Could be a small process tweak they had in pipeline, just not in time for first production batches.Quote:
Originally Posted by zir_blazer
wasnt there a thread about the 960T going into oem desktop only???Quote:
Originally Posted by zanzabar
It was, but was it true?Quote:
Originally Posted by Sn0wm@n
Sadly it was:Quote:
Originally Posted by Lightman
http://www.anandtech.com/show/3721/n...eneral-release
Maybe if they start getting a higher failure rate we will se crippled X6 as X4 and X3īs, but i dont think so:mad:
Dell has 1035T's in their lower-end desktops...I wish somebody would buy one and strip the CPU...replace it with a 965 or something :/
:rotf:
that just means that u get it through non traditional channels, like a bulk order or a replacement part order but i dont know how economical it would be as a 1055 is only a little more than a 965Quote:
Originally Posted by Sn0wm@n
I'm looking forward to the OC review of this bad boy. For the right price, I'd love to drop one in my old AM2+ board. Would help out a ton w/ virtual machines.
I would not hold out hope, from what i've heard msi is having major problems with 6core k9a2 platinum bios. I just ordered a foxconn 790fx/sb750 ddr2 with 6 core bios dirt cheapQuote:
Originally Posted by [XC] Synthetickiller
So i can finally use my thuban.
msi has having problems even with the gd70, my 1090 with cool and quiet from the bios it will go to 800mhz at 1.225V, that all the time, since its the summer i left it stock, turned turbo off and under volted to 1.875V and it went and raised the voltage to 1.225 with cool and quiet for 800mhz. that should never happen.Quote:
Originally Posted by Dainas
then its hard to find the beta bioses and the m-flash, windows flash and dos flash are all unstable so since my warranty is up im not sure if updating is even a good idea
the beta is working fine in my k9a2 plat, but i havnt tried any OCing yet, im using the stock cooling and dont want to mess with anything yet
Praz tested one two months ago:
http://www.xtremesystems.org/forums/...ighlight=1035t
What are the new popular boards to pair these bad boys too? $100~.................
This annoys me. I bought a 1055t the day it came out(thank you tigerdirect rebate!). I am always for lower temperatures. The Thurban already runs very cool, but this thing will be even better!
I can validate this. I have a 1055t running on mine currently OC'd to 3.6GHz.Quote:
Originally Posted by Manicdan
Head out here for 95W 1055T tests done by PcCI2iminal :).
How does it OC one might ask? Well,1.3V AND 4GHz in the same sentence should tell you all you need to know ;). Like someone else in that thread said,AMD silicon is just like a fine wine :D
this is crazy, today il try test my 1090t with this voltage...
w/c begs the obvious Q.Quote:
Originally Posted by informal
is AMD process really second rate?
or is it just marketing spin. :up:
Not bad :DQuote:
Originally Posted by informal
yes. IBM and intel are the best when it comes to process. just check out any IEEE symposium and see all of the cutting edge research they do. i am definitely not saying GloFo's fab's are not good but trying to beat intel in the game of process is a bad idea.Quote:
Originally Posted by wuttz
these 95W chips should put a massive dent in the perf/watt ratio of multithreaded benchmarks. they are actually damn near close to laptop efficiency with highend desktop power, for under 200$?
How do I identify the 95W version from the 125W version? Is there a code on the retail box where I can check for reference? I'm used to Intel cpus & always check at processorfinder.intel.com (it's ark.intel.com now)
Would like to know the equivalent site for AMD cpus and the codes for stepping and wattage. Thanks.
looks like:
HDT55TFBGRBOX = 125w
HDT55TWFGRBOX = 95w
is that spelling mistake intentional ? ;)Quote:
Originally Posted by informal
Nope,just an accident,edited now :).And you know that AMD's chips get better and better and better with time ;).
it was a good pun, intel people love the idea that amd stuff gets better the more the fanbois cryQuote:
Originally Posted by informal
yes guys i edited my whine to wine... LOLL i feel dumb now... :|
oh did i reference/mention intel? :ROTF:Quote:
Originally Posted by Chumbucket843
mighty defensive there. obviously, "better" for me has a different meaning than being on the cutting edge, and first everytime.
i wanna see a 980X at 95w..?
you did not mention intel or ibm but they are the only ones ahead of AMD. some people view AMD as an underdog which is stupid. they are only underdogs to intel.Quote:
Originally Posted by wuttz
are you implying that intel's fabs are not designed to be cost effective? manufacturing costs are kept secret, there is no sure way to argue that fab costs for amd is lower. judging by gross profit margins intel sells their cpu's at a premium because they can.
sure you do.Quote:
i wanna see a 980X at 95w..?
back on topic. most of the efficiency gains are from dropping the clockspeeds down, not black magic like electromigration proof "silicon". process refinements play into things to but only from a yield aspect. performance gains over time from higher binning levels off very quickly(logarithmically).
a quick overview of amd 45nm.Quote:
Originally Posted by Chumbucket843
started with:
940, quad-core@3.0GHz, 125W.
now... 945, quad-core@3.0GHz, 95w.
[30W delta while maintaining core count + clocks]
then:
920, quad-core@2.8GHz, 125w.
now... 925, quad-core@2.8GHz, 95w.
but add two more cores, same clock speed;
= 1055t, six-cores@2.8GHz, 95w.
[add two more cores, but cut 30W while maintaining clocks]
amd has a different strategy when it comes to process tech.
they dont have to be first to a smaller node. it's not their style.
but they can tweak the helloutof SOI to produce AMAZING products.
for me, what they did w/ 45nm is unparalleled!
even bodes better for them next year.
imagine AMD with 32nm+SOI+LowK+HKMG+Bulldozer.
:up:
:rofl: first post about intel, then this nonsense about AMD that couldnt be farther from the truth?? typical direction of AMD news threads :down::shakes:Quote:
Originally Posted by Chumbucket843
Yea, AMD continuously tweaks nearly everything. I remember reading something from an AMD rep about going from 130nm to 90nm. They had changed the 130nm chips so much since their launch that the power characteristics of a new 90nm and a late batch 130nm were really not much different. The only advantages of a smaller node was more potential for improvement and a smaller die.Quote:
Originally Posted by wuttz
I'll rather take that than an AMD CPU that needs six physical cores with higher clock speeds to keep up Intel's four, thanks. :DQuote:
Originally Posted by wuttz
we would all like to thank you for bringing this up, it will be the end of this thread as we know it.Quote:
Originally Posted by Clairvoyant129
Or intel needing 8 threads to compete with AMD's 6 :D.Glass half empty or half full anyone?
+1Quote:
Originally Posted by informal
http://www.overclock.net/9247823-post13.html
looks like amd is winning...
this "it takes intel x to beat amd's y" has got to stop. the multicore war is worse than the megahertz war.
i know they have done very well with their 45nm process. although there is a difference between physical design and process. all GloFo does is provide manufacturing capabilities with some design rules and possibly libraries for clients. AMD got used to 45nm node and then they designed their own faster, maybe smaller transistors and did some custom layout of critical circuits for maximum speed. most of these things are process specific due to how complex design rules have become, so much so that not one person knows all of the rules. fwiw i have scaling numbers from barcelona to llano. it seems that amd has continually gotten better at transitions.Quote:
Originally Posted by wuttz
flamebait? maybe you just dont like what i posted idk.Quote:
Originally Posted by crazydiamond
Intel doesn't create threads, software programs do! What prevents you from running 8 threads on your super efficient thuban? :p: You wanna eat your cake and have it too? "Real cores are better than fake cores," except when it comes to performance tests and then "fake cores" are the real deal again. Simple, i7 quad-cores can render 8 threads, well, because they can. :cool:Quote:
Originally Posted by informal
You think it's a fee lunch?Intel designed it that way and it costs die space.We have been over this 100x before. AMD's philosophy is to use more smaller cores while intel's is to use fewer big cores(one Nehalem core is 60% larger than one Shaghai core,is it 60% faster or as reality shows ~25% faster on average?).
if u want to do something other than basic int work than real cores are better, just look at gaming benches or some floating point or 64bit int, HT s a detriment to performance. sure if u only encode video HT is great, but gaming and anything native 64bit there is no meaning full difference.Quote:
Originally Posted by OhNoes!
It may not be free lunch, but you have two extra "real cores" plus about 500mhz x 6 (3GHZ :shocked:) advantage, and you're still complaining about some "fake cores." :stick:Quote:
Originally Posted by informal
What 500Mhz advantage?What CPUs are you compering here? ANd where did I complain about fake cores?Where did I say fake exactly? Use more facts and stop putting words into other people's mouths.I said threads,and that will be the measuring unit when 2011 hit.
No you didn't say it: An AMD exec. said it. Remember "Real men use real cores." ? I am comparing the almighty 1090t to a lowly 17 920 in overall benchmark tests conducted by many sites. Too many links have been posted for me to even bother. You haven't seen those?Quote:
Originally Posted by informal
Let me quote you:
You said I was still complaining meaning you are lying... I haven't used that term in this thread.Period.I do not care who used it,I haven't.Quote:
and you're still complaining about some "fake cores."
Also "the many benchmark sites" are those that use mostly applications with poor MT optimizations(if at all) and games in their reviews?
How about techreport's word about 1090T and 930:
Lost Circuits tests can be found here.They also show Thuban performing between 930 and 940 in many tests.Quote:
The scatter plot gives us a little more context and highlights another interesting matchup: that of the Phenom II X6 1090T versus the Core i7-930. While both processors perform roughly in the same ballpark in our test suite overall, the Intel chip requires relatively expensive X58 motherboards and triple-channel memory kits, while the AMD chip works happily in more affordable 890GX mobos (and even cheaper Socket AM3 offerings) with dual-channel RAM. The 1090T ends up looking somewhat more attractive as a result.
It's de ja vu all over again. No, you don't require triple channel kits on x58. I'm currently running dual-channel and my read bandwidth is in excess of 20,000mbs/sec. I also said I wasn't addressing you with that remark; the thing is there is so much anti Intel fud out there, sometimes I try to address them in one post - when it makes sense to do so.Quote:
Originally Posted by informal
"Real world" is a phrase you've used though, right? So how come when it comes to thuban you want ALL benchmarks to be run where Thuban is strongest. Mainstream apps, including gaming is where it's at. You want a processor that does everything very well, not just in one or two apps that the average mainstream user has no idea about. Also, in highly MT optimized apps, budget core i7 keeps up very well with high end thuban. That is all I'm saying. By the way even with the i7 930 as reference, that's still 400 x 6 = 2.4GHZ advantage to thuban.
Uh oh, aren't we a bit picky? Anyway, thanks for your indulgence.Quote:
Originally Posted by informal
No problem,any time mate :p:
?? Core size is irrelevant. Total die size and performance OTOH are very relevant.Quote:
Originally Posted by informal
How come a Shanghai takes 243mm^2 and Nehalem takes 246mm^2 ( according to Hans deVries) while Shanghai has 8MB total cache and Nehalem has 9 ?? :confused:
I can also add some extra features like :
-3 channel IMC vs. 2
-HT
-more advanced power management
And in the end, they have the same die size, while the performance difference is 20-40% in favor of Nehalem at the same clockspeed.
how is core size not relevant? the process of the cache is vastly different and very space consuming for AMD. if they used the same method Intel did would you still be able to use "theyre the same size" argument?Quote:
Originally Posted by savantu
EDIT: i think to better clarify, Informal was talking about the cost to add an extra thread, while you are just talking about the overall result of the chip.
The total die size mostly depends on the L3 sram cell size and intel (currently) reigns supreme here. Core logic die area in Nehalem is vastly larger than that one in Shanghai,but still Shanghai does not have 60% less performance than comparable Nehalem chip(the advantage varies and is between 20 to 25% ,on average,depending on the workload selection). Nehalem does have 3ch. IMC which is clearly advantage for server workloads.AMD dealt with this advantage when they transitioned to Opteron 6000 series.
Budget core i7? High end Thuban? Then why is the i7-930 MSRP $289.99?Quote:
Originally Posted by OhNoes!
X6-1055T ($200) = i7-930 ($290) > i5-750 ($200)
Intel has built in strong prefetchers for data (they have them on the L1 and L2 cache). They also have development tools that help to optimize data for those prefetchers. Using that you can get a higher hitrate for data in the L1 and L2 cache if data is ordered well.Quote:
Originally Posted by OhNoes!
Applications that are used in performance tests or when games are only drawing vertices these prefetching comes in handy, but most real world applications don't get that much advantage from these prefetchers.
Six cores are much better than 4 cores even if Intel has some tricks (80% market share makes a lot easier to add special tricks) to make those 4 cores to work a bit harder by not making them wait for data as much as AMD does in some scenarios.
thank you for pointing this out.Quote:
Originally Posted by gosh
does this mean the data here is squat diddly representative of real apps?
(how does one COPY data faster than you can READ it? :ROTF:)
http://www.xtremesystems.org/forums/...1&d=1278190047
Are you serious? Educate me, why not?Quote:
Originally Posted by wuttz
Um when I run everest benchmark my copy speeds are also higher than my read speeds.
so if i get it straight.. amd has 10x less $$$ for R&D ... has cores with 60% less die space yet they perform only 25% slower .... and people still think amd is a cheapo cpu maker??? LOLL drug is good in some part of the world
That's how much it can read and write at the same time combined. :rolleyes:Quote:
Originally Posted by wuttz
I don't know what to make of this post. So let's see, AMD doubles the size of their cores = double core performance? Stop grasping at straws. If VIA gets as much sympathy as AMD does, they may overtake AMD.Quote:
Originally Posted by Sn0wm@n
Snowman,the 60% die space refers to core logic die area(the core level stuff).Since intel has much better L3 sram cell density they can pack more cache in less space,so the total die area of Shanghai and Nehalem is similar(while one Nehalem core is massively larger than one Shanghai core :24.4mm2 Vs 15.3mm2)
copy is faster because multiported SRAM can read or write every half cycle. it would be 2x read speed but policies for accessing cache prevent it.
That times the speed for L1, L2 or L3 cacheQuote:
Originally Posted by wuttz
Ask lavalys, they have the code (latency for the L3 cache should be slower)Quote:
Originally Posted by wuttz
alright..thanks for the clarification.. but still its o a good thing that amd isnt too far away with such a difference in logic core sizeQuote:
Originally Posted by informal
I can personally tell you thats about it. I love my 930, but my 1055t has proven itself a real gem in the short time I've used it.Quote:
Originally Posted by Bobsama
1055t + a plethora overclock happy 790fx motherboards available for around $80 or less=enthusiast budget dream.
If you are so upset about people liking AMD, maybe you are in the wrong thread? Seriously, what are you trying to prove here?Quote:
Originally Posted by OhNoes!
Mojo strikes again.
And you didn't once again jump into an AMD thread to tell everyone how awesome Intel is? You can dump on threads all you want, mods don't care, but but don't be a hypocrite when you get called out on it.Quote:
Originally Posted by OhNoes!
Define "dump," hell, quote me.Quote:
Originally Posted by MrMojoZ
Posting this in a thread that was created to talk about a new AMD chip is an attempt to turn the thread into a fanboy garbage dumping ground. Why not leave this kinda crap at the door? Is that too much to ask?Quote:
Originally Posted by OhNoes!
It may help to bring your sense of humor with you into a forum. As it stands you seem a little too tight, sensitive, and defensive about "AMD Threads." Relax dude, it's just hardware. I could quote you funnier stuff from 'Intel threads' from pro AMD posters.Quote:
Originally Posted by MrMojoZ
We even have an i7 930 user(Danias,top of the page) who just loves his 1055T,how's that for a review ? :D
No, he "loves" his 930. Read it again. :stick:Quote:
Originally Posted by informal
Well I think that something being a real gem is even better then loving something else? :p:Quote:
Originally Posted by OhNoes!
He even wrote it in such a way(I have this and it's great but i got this other thing and it's awesome)
Aww poor youQuote:
Originally Posted by OhNoes!
HAHAHA! You made me laugh so hard. You're very funny! :rofl:Quote:
Originally Posted by Macadamia
when you do a number 2 on a threadQuote:
Originally Posted by OhNoes!
i could have swore ohnoes was told by movieman or another admin to stay out of amd threads
time to get booted!Quote:
Originally Posted by stangracin3
This poster seems like a real :banana::banana::banana::banana::banana:Quote:
Originally Posted by OhNoes!
I can find you dozens of industry standard benchmarks where Nehalem has close to 2x if not more the core performance of a Shanghai core. And in the end, that's what really matters. Purchase decisions are based on that, not on games. Good luck with corporate buyers selling them game performance.Quote:
Originally Posted by informal
Quote:
Originally Posted by Manicdan
All that matters is die size. That translates into $. You save some mm^2 on the core and lose on cache or the other way around, it doesn't matter if the end results are similar and one performs much better than the other.
Please explain what you mean by this, because in the end, it not only takes more space, but is slower.
Quote:
Originally Posted by informal
Well P55 is simply not an overclockers platform unless you spend soo much on the motherboard you'd be better served with an X58. Also patience for finicky stability is a must as what's linx/prime stable today most likely will not be tomorrow after a cold boot. Being that Intel is shoving even more onto the cpu package with P65 it will be worse if anything.
Because of that added with far better motherboards for the money AMDs effort are the only one to consider at the $200 mark. Better stepping is just icing on the cake. Core i7 1366 is godly, without peer and finally we can buy pride worthy X58's for under $200, but it cost as it should.
Yeah so not really an AMD fan. Back in the k7, k8 and p4 days I really did not have a choice. Intel was a joke trying to hide their true prodigy (p3 architecture) from the masses in favor of the ugly princess netburst. However it was a no brainer to ditch AMD when Core 2 came out and me being a 939 owner, was left needing to start anew anyways. Every build i do for people with 'budget' and gaming is all AMD/ATI though, with the odd G97 thrown in time to time.
Quote:
Originally Posted by savantu
here's what JF had to say about this matter, he explains it very clear and quite convincingly
Quote:
Originally Posted by JF-AMD
Dude, you dreamed it. Nice try though, trying to involve an admin to boot the other guy. Genius plan! :down: I'm sure the admins are watching this thread like hawks.Quote:
Originally Posted by stangracin3
and when you have enough horsepower, you buy for fun.Quote:
Originally Posted by Dainas
I been sitting with same friggin cpu and motherboard for soon 2 years, and there is no upgrades in sight, for any reasonable price.
so I go, maybe a 6 core amd with a smooth cheap overclockable motherboard is the fun again.
black edition, sexy, 6 cores and if I sell my current setup I guess I get money over.:)
I might buy one of the 95W core 1055T's if I can find one in AU, looks like a likely upgrade path from my Q9550
great usage of the quote feature ridney
Fair enough. Let me try to address some of the point he raised :Quote:
Originally Posted by ridney
Quote:
Originally Posted by JF-AMD
Intel gets something like 2500 Atom dies per wafer and sells them with $36 on average ( wild guess ); that's $90k revenue and $6k wafer costs.
AMD gets 150 Istanbul dies ( wild guess ) and sells them for $300-400 on average ( if they go into servers, otherwise it's half that ). $60k revenue and $7-8k wafer cost.
Am I missing something here?
Being behind on the process curve, means it's using a fully amortized FAB, on a fully mature process with maximum yield for its size class. But, the average ASP for Itanium is around $2k, while for Opteron is probably around $300 if not less. ( it was $400 back in 2006 when they were King of the Hill and had parts priced at over $1800 ).Quote:
In the fab business you maximize your revenue based on getting more wafer starts, driving down your cost per wafer and by driving more revenue per wafer.
In reality, the number of server wafers vs. client wafers probably makes this a moot point for both intel and AMD.
Take Intanium for instance. Higher wafer cost (lower yield because that product is behind the process curve), higher development costs because it is a more expensive product to build and support with much lower volumes.
I can guarantee you that if you look at the true (fully burdened) cost of building an Itanium that sells for $1500 and an Opteron that sells for $500, that we are most likely making far more profit on the Opteron. They might make more revenue, but their costs are going to be a lot higher.
I agree that the developments costs for Itanium are far higher and this will impact the profit ( if they are making any :D).
3000 and 5000 are identical; so it's only 2 sets for dies.Quote:
Then take the xeon line in general. 3000, 5000, 7000. Three different products to develop. Three sets of R&D. Three dies. Three sets of masks. Thress sets of different testers (one for each socket.) Three pieces of silicon to manage both in process and finished goods.
Yet, the 7000s command a huge premium over the 3/5000. Intel's Xeon MP always had a different die ( more cache, more RAS, scaling add-ons ). If you target the high end, you need to differentiate from the masses.
Who wants to replace their SUN servers with machines that have the RAS level of desktops ( ok, add ECC ) ?
Some will and it will work; but some will get burned like at the London Stock Exchange.
All is very true and this is the optimum road for AMD, but...Quote:
Then look at Opteron. 4000, 6000. A single die to manage. A single die that I can hold in the manufacturing process until the end to determine which product it goes in. You do realize that from die to finished good is only ~2 weeks. So by utilizing the same die, I can make a lot of final inventory decisions ~2 weeks before the product needs to be in a customers' hands. With 3 different discrete parts, all Xeon choices need to be made ~13 weeks ahead at the start of the process.
One die to develop. One die to manage. One die to process. And only 2 sets of testers. Inventory to minimum, cost to a minimum.
If you look at per die cost, you could argue that intel has an advantage because of the die size.
But if you want to look at fully burdened cost, our costs are a lot lower to get the Opeteron product to the streets than it is for Intel to get the Xeon product to the street. Every time someone argues that intel has "10X the resources of AMD" they are helping make the argument, because resources don't work for free - I know I don't and I am pretty sure everyone reading this wants to be paid for their work (and probably wants to be paid more.) Die cost is only one dimension of the total cost equation and as long as you don't look at the full picture, you will never see the actual impact.
Why isn't this reflected in the margins? One size fits all has limits and this are painfully obvious when we look at the benchmark scores and the product prices. AMD priced them at the level where they are competitive, not because they care so much for customers pockets. unless you've become a non-profit organization and we don't know that. It's nice to talk about value to customer, but product price is just one of the variables in calculating a solution cost.Quote:
We were able to compress the pricing and remove the 4P tax because of those efficiencies I just talked about. And while a lot of the intel fans seem to think that paying more for a product is a priviledge, when you sit down across from a real live paying customer, they disagree. Believe it or not, they actually appreciate paying less.
And the market simply doesn't show any gains for AMD in the server segment. How do you explain that ? When Opteron really kicked ass, the market share exploded. Now, Intel is making inroads with products priced 2-3x higher. Intel isn't Apple, so if people are paying more, it means they calculated they are getting more value ( performance/price).
To sum it up, I agree with JF about the benefits of having a single die across multiple product ranges, but the benefits are in this case out-weight by the inferior performance which they need to compensate by throwing silicon at the problem and lowering prices ( It means I disagree they reduced the 4P tax and prices overall out of generosity for the customer, as he nicely wraps it in PR talk ).
grats for clearly missing the point, i even explained it to you perfectly but you decided to ignore that part of my post.Quote:
Originally Posted by savantu
you took a discussion going over the extra die space to add the second thread per core by intel, and turned it right back into an argument about comparing companies again.