time to save $$$ for a new system : p
Printable View
time to save $$$ for a new system : p
Same 133 BCLK. So same multipliers. Thats actually something that is history I think. Lowend OCs via high multi.Quote:
Originally Posted by Spacemaster
That's because Pentium D was such utter :banana::banana::banana::banana: to begin with that it seemed like such a huge jump. This thing actually provides the same performance jump in many benchmarks, but obviously not all of them..Quote:
Originally Posted by George_o/c
I knew it is same the BCKL, but this is mainstream CPU, mainstream CPUs always have lower multi then high end CPUs. This ES have default 16 multi. So if new the i5 CPUs will have 20, 22, 24 and higher multi, that will be excellently for the overclock. :)Quote:
Originally Posted by Shintai
Only in the past. And you had that due to different FSB speeds (800, 1066, 1333, 1600). Now its all the same BCLK. No 80Mhz BLCK, 106Mhz BLCK, 133BLCK, 160Mhz BLCK etc.Quote:
Originally Posted by Spacemaster
Only 133.
So no. Its all a multi x of the BCLK.
Quote:
Originally Posted by Shintai
Ok, do you have any information that you can share about names of i5 models, and default clock frequency (multipliers)?Quote:
Originally Posted by Shintai
Not really no.Quote:
Originally Posted by Spacemaster
I expect i5 to peak at 2.80Ghz or so. Maybe 2.93Ghz if lucky. And then else down in 133Mhz increments. Maybe as low as 2.00 or 2.13Ghz.
You think that clock can be default clock?Quote:
Originally Posted by Shintai
Yes ofcourse. The roadmap also shows i5 rival lowend i7. Because their segments are different.Quote:
Originally Posted by Spacemaster
Could anyone confirm Lynnfield and Havendale are LGA1156 or 1160? :shrug:
1160Quote:
Originally Posted by Vozer
Thank you. :)Quote:
Originally Posted by Donnie27
I'm too lazy to count the number of pins on Lynnfield CPU in this picture. :D
http://i245.photobucket.com/albums/g...ehalem/L_5.jpg
Lynnfield is 1156 actually.
Why do they keep calling it 1160, rounded?Quote:
Originally Posted by STaRGaZeR
At the beginning it was 1160, but Intel made some changes and it is 1156 now. If you have seen 1160 in a recent article is because the autor is misinformed or something.Quote:
Originally Posted by Donnie27
OK, thanks!Quote:
Originally Posted by STaRGaZeR
Things look very promising. Especially for us 775 users... :D
IM curios, can you post upload i5 "MultiCore Benchmark" file/score to the site?Quote:
Originally Posted by sxs112
http://www.xtremesystems.org/forums/...d.php?t=210021
This close to Phenom II and there's more info on this thing thats at least 8 months from shipping:rolleyes:Quote:
Originally Posted by Ego
Deneb will be the new top of the line from AMD, the i5 is a downgrade from what is already out, the i7. That is the difference here.Quote:
Originally Posted by Donnie27
The miniaturization and those oval lands is just awesome. That thing looks so yummy in the foreground...it almost makes you wish they were edible. :DQuote:
Originally Posted by Vozer
Not exactly - certain A0 samples (which this one actually is) were 1160-pin. All later parts will be 1156.Quote:
Originally Posted by STaRGaZeR
better off going 775Quote:
Originally Posted by Spacemaster
Interesting. Do you know the reasons for the change?Quote:
Originally Posted by Mumak
Yep - at least what Intel says ;)Quote:
Originally Posted by STaRGaZeR
But I suppose I can't say that...
Pity :(Quote:
Originally Posted by Mumak
I saw where Tweaktown.com stole the OP's content and put it up on there site. LOL
One year from now, thats like 2 years technology development.
and besides, good luck overclocking i5 to 4ghz+
I get a new videocard, before that which will enhance my fps more than any new cpu coming out the next 2 years.
;)
Unless amd pulls a rabbit out of the hat with their new p2
Thanks +2! When or if the NDA is lifted please fill us in.Quote:
Originally Posted by Mumak
That's no real difference at all! There was a lot of info on i7 months before its launch as well.Quote:
Originally Posted by 003
H'mm wonder if i5 will use the newer low voltage DDR3? wonder if it's safe to use the higher voltage DDR3 2x2gb sticks in dual channel. :shrug:
There is no reason why i5 would use different memory voltage than i7. If i7 can't take x amount of volts, i5 can't take them.Quote:
Originally Posted by Nelly
[QUOTE=Donnie27;3491860]Thanks +2! When or if the NDA is lifted please fill us in.
Sure, I guess that happens only when I die :ROTF:
not correct!Quote:
Originally Posted by thebluemeanie1
"problem" with i7 is that QPI voltage is connected with DRAM voltage... if you rise DRAM voltage you rise QPI voltage also... i5 doesn't have QPI!
The good thing with i5 is that'll bring true sucssesor to LGA775 platform... LGA13xx will stay only for server/WS market, and LGA1156 (previously LGA1160) will be the mainstream platform... current Bloomfield platform is death end for mainstream desktop just as Socket940 was for AMD... LGA 1156 is the way of the future for intel desktop users...
Thats not true...Quote:
Originally Posted by Nedjo
LGA1366 will stay for the enthutiasts and SLI/Crossfire users. LGA1156 is basicly for everyone without crossfire/sli. Plus cheap.
maximises the appeal for multicard users thats for sure (1366)
pff Lindfield's integrated PCIe bridge support 8x/8x PEG 2.0 split and that's sufficient for CFX and SLI! (efectively that's same BW as with 16x/16x PEG1.1, and that's enough for CrossFire and SLi)...Quote:
Originally Posted by Shintai
and what will benchmarking of i5 prove is that clock-4-clock it gives same performance as Bloomfield for the less price, alnd since LGA1156 mobos wiil be much more affordable it rise the question of reasoning behind purchase of any futurre Bloomfield CPU and LGA1366 mobo...
First of all far from all Lynnfield CPUs support it. Secondly. Alot of mobo makers wont do 8/8 but just 16. And trichannel still wins alittle bit over dualchannel.Quote:
Originally Posted by Nedjo
1366 is the choice for multi GPU. Just like people before bought 975x, X38, X48.
what are you saying, that some Lynnfields will not have PEG ctrl. with 16 PEG 2.0 lanes in it?Quote:
Originally Posted by Shintai
No, but just like P43 vs P45 chipset. One can be divided into 8/8. The other can only be in 16 mode.Quote:
Originally Posted by Nedjo
what chipset got to do with the fact that PEG ctr. is inside CPU?Quote:
Originally Posted by Shintai
You can say the same about P43 vs P45. But that doesnt change the fact. Its an example of 2 chips with both 16 lanes for GFX. One can divide into 8/8 the other cant.Quote:
Originally Posted by Nedjo
Its not exactly rocket science to know its no different on a chipset than ondie on a CPU.
The P43 is just lacking the crossfire controller on the motherboard, not on the chip. The Chip is the same exact chip as the P45. Possibly lower binned tho.
so you're telling that Intel will be selling two kinds of Lynnfield - one capable of splitting the PEG lanes, and other restricted to 16x only?Quote:
Originally Posted by Shintai
:clap:Quote:
Originally Posted by Nedjo
Just like AMD, MS, nVidia whatever. Its called segmentation and artificial limits.
and you think it makes sense to segmentation on the base of enabling / disabling PEG lanes splitting, and not other features, like HT on/off, turbo on/off... etc... is PEG ctr. so critical and complex part of the CPU that Intel needs to create differentiation in CPU lineup on the base of PEG capabilities... yeah right!Quote:
Originally Posted by Shintai
for a reminder AMD, NVIDIA, INEL are doing differentiation on the base of harvesting good transistors, and not artificial enabling / disabling features... only Apple is doing that with their DVDRW's capable of writing only 8x on cheaper machines :)
Segmentation should be done on the mobo. Otherwise it would be a complete messup. :/
Intel's smarter than this.
As if 1366 vs 1156 wasn't enough, now you got 1366 with or without SLi, and 1156 with or without SLi, or without MGPU. So no.
Sorry, but didnt AMD and NVIDIA use to "laserlock" parts of the GPUs, thus producing the low-performance mainstream parts (I cba to look up in which series they did it)?? What about Nvidia having special drivers with opengl overlay optimizations just for the Quadro series, when it works perfectly on the Geforce series? I bet there are more examples :P.Quote:
Originally Posted by Nedjo
PS I think I might have read your post wrong :p You probably meant "unlike AMD and NVIDIA, INTEL are doing differentiation on the base of harvesting good transistors, and not artificial enabling / disabling features..." :P. Oh well, figures :up:
Quote:
Originally Posted by Donnie27
:rofl::ROTF: Hehehehe!Quote:
Originally Posted by Mumak;3493863Sure
LGA1156, LGA1160.. What a cluster:banana::banana::banana::banana:, can't they decide?
http://www.fudzilla.com/index.php?op...10915&Itemid=1
http://smartmanufacturing.net/Gen3VRTestToolParts.html
Apparently Intel Design and Development tools use the 'LGA1160' socket, now I'm not going to count those pins but still. Is this some outdated site, is Fuad stumbling again?
That's made by the mobo manufacturers , not Intel.:rolleyes:Quote:
Originally Posted by Nedjo
Who cares? The socket is 1160 pins.If they only use 1156 or 666 who gives a f**k ? It's not like it matters for you.Quote:
Originally Posted by bowman
If anything it will allow future revisions on power and data delivery to be activated without changing the socket.
Shintai was not claiming that.Quote:
Originally Posted by savantu
Quote:
First of all far from all Lynnfield CPUs support it.
Hah, that's the point. The new socket is 1156 and there have been other pins changed as well, so it's not compatible with 1160.Quote:
Originally Posted by savantu
agree...it may be suitable for multi gpu too, but its aimed at the mainstream market indeed. Like p35/p45 vs x38/x48.Quote:
Originally Posted by Shintai
Base on every data I saw, if you want SLI or Xfire, you got to be crazy not to get a Core i7 ... :yepp:Quote:
Originally Posted by Tonucci
First off Dr. Enthusiast doesn't mean folks with more money than Brains. Some of us aren't rich and the economy affects many of us here as well. Most Geeks aren't 14 to 18 still living at home with Mom and Dad with unlimited budgets.Quote:
Originally Posted by Drwho?
What if I want a Power System with the fastest processor in the world and I DON'T game. Current X58 are fine for power Gamers but not many others who don't make Games their number one priority.
And your wish will come to summer then. Patience is a virtue.Quote:
Originally Posted by Donnie27
but how about i5's GPU to CPU latency :eleph:Quote:
Originally Posted by Drwho?
wtb: i7 with on-die PCI-e controller ;)
so you're saying that i5 @ say 2.6 GHz can't serve in a same fashion two, lets say, HD 4850 as i7 can at the same frequency?! How on Earth that can be possible when all that we know so far about i5 is saying that basically it's the same CPU as i7 but w/o QPI and with PEG ctrl. inside?Quote:
Originally Posted by Drwho?
Maybe due to the avalible bandwidth for the GPU(s) to both memory and CPU. :rolleyes:Quote:
Originally Posted by Nedjo
yep, even with today cards....imagine with 3 or 4x of next gen cards :yepp:Quote:
Originally Posted by Drwho?
I don't buy it!
8x/8x Crossfire works just fine until you get to extreme resolution like 2560x1600.
"Non benching" people will enjoy i5 regardless of the "huge benefits" to get a i7 for multi gpu.
http://www.xtremesystems.org/forums/...d.php?t=202249
My only fear is that in order to get SLI support mobo makers will have to use the nForce200, since there will be so much diferent boards that NVIDIA won't do the SLI licensing like on X58 boards...
Still, I think the secound non 8x/8x capable Lynnfield is the Havendale, wich will be Dual Core only with MCM northbridge (with integrated graphics).
Someone who has the cash to get multiple video cards is assumed to be able to afford the price difference and get an i7.Quote:
Originally Posted by doompc
If thats not your case, the product is not aimed at you.
Its for enthusiasts who pay hundreds of dollars for ~15% performance increases. There is enough demand for these products...low volume compared to mainstream platforms but its their flagship :)
I vote for Fuad stumbling again, he does it daily.Quote:
Originally Posted by bowman
Actually, depending on my next car purchase (left over funds), I'm not waiting until late summer or early fall. I do fully understand what you're saying here. I waited for Nehalem and Deneb so far, i5 can wait until late 2009 or early 2010. Unless it really sucks, I'm getting a Phenom II LOL! In fact, the order I'd place them in for my next upgrade is;Quote:
Originally Posted by Shintai
Phenom II
Q9550
i5
i7
Until 35 days ago, i7 was at the top and nothing else was really considered.
Have you seen Phenom II performance numbers with SLI/CF?Quote:
Originally Posted by Drwho?
Based on what AMD is showing, you'd be crazy spending a whole crap load of money for a small bump in frame rate (if any) that you'd get with a core i7.
You either haven't understood the data you have seen or didn't understand Dr.Who's statement.Quote:
Originally Posted by taurus_sel
There is a huge advantage when using SLI and CF with Core i7.Quote:
Originally Posted by taurus_sel
http://www.guru3d.com/article/core-i...ance-review/19
:rolleyes: a small bump huh? While Phenom II will get a good boost over Phenom, it will still be lagging behind Core 2 Quads.
If you want the best, you need to spend the money for it. This is Xtremesystems, not Lamesystems or Bangforbucksystems.
What if I want i7 for something other than games? What if I want a real Power User system, with triple channel, two 1.5TB HDDs (they didn't follow motherboard trends) and maybe a Raptors or that reasonable compared to the motherboard. X-Fi, Multi-Camera Security Card, Analog Capture Card? I don't want Crossfire or SLI and if I did, the Green has aren't that much slower:rofl:. Hehehe, I already got 6GB of RAM.Quote:
Originally Posted by taurus_sel
Let me put this a Different way. I want a power USER board, not a Power Gamer Board or even a cheap board. WTF is on this board to make the cheapest one $244?
Thank goodness the rest of the market hasn't followed motherboard trends. I'm NOT bad mouthing the Processor here. I'm saying the board is overpriced for you folks will be getting. Namely, last years tech for cutting edge prices.
To think of it I'd buy one @ $200 if it had scantily clad women on it (has to be life-sized)Quote:
Originally Posted by Donnie27
But I agree. Isn't X58 SUPPOSED to be cheaper, granted that the chipset itself is massively cheaper and requires less cooling? "More PCB Layers" is not an excuse- the extra layers are probably cheap, definitely less than 10USD for the additions.
This is what market segmentation brings you, I guess. S754 and S939 also had this problem to an extent, so it's not just Intel.
who says 3way sli is also not scaling much better on phenom2?Quote:
Originally Posted by Clairvoyant129
Dreamland is a sweet place :rofl:, I saw ... I smiled.Quote:
Originally Posted by taurus_sel
It won't. I'm sure under SLI/CF Phenom II will lag behind current Core 2 Quads and will scale similarly with current Phenoms.Quote:
Originally Posted by duploxxx
Let's be realistic, Phenom II, while an improvement is the same as Kentsfield -> Yorkfield, die shrink with cache increase and some core optimizations. Core i7 on the other hand is a monster.
What are you expecting? A miracle?
Not to mention, most people who will be spending tons of money for high end SLI and CF systems will not be going for the "bang for buck" systems. They will want exploit every bit of performance out of their SLI/CF systems.
better change that to 3-way sli....Quote:
Originally Posted by Drwho?
your post quality is going down :rofl:Quote:
Originally Posted by Drwho?
the performance was always havy cpu limited, this has changed a lot know with phenom2 also 890 chipset adds some additional to the cf part.Quote:
Originally Posted by Clairvoyant129
check i7 and k10 bus architecture except for a bit faster bus the difference is not that big.....
So, here is some detail:Quote:
Originally Posted by DrWho?
On games, the Phenom II will do better than phenom just because the L3 cache is large enough, it is not going to be any better than a Conroe with 4Mb cache, at same frequency. Of course, you can find corner case, but those are rare.
It looks like the 2nd Load port of the phenom I or II is not helping it, due the the fact that its decoding bandwidth is becoming a problem on 64bits. (the extra byte increase by 25% the bandwitdh required). The lack of wilder decoder engine does not feed properly their back end of the processor. The next step for AMD is to copy hyperthreading, if they don't do so, they will never come back to competitive position, and if they do so, they will have to pay attention to be power efficent when doing it. Doubling the number of decoders would be a power catastrophy.
The next Core mainstream will have no problem there :up:
This is my personal opinion, my employer is not responsible for this posting. :clap:
enough quality for you? If you ask details, you get them, don't complain about it. :up: :rofl: (We are in a Core thread, i did notice :) )
im sorry but how that answers this:Quote:
Originally Posted by Drwho?
Quote:
Have you seen Phenom II performance numbers with SLI/CF?
Based on what AMD is showing, you'd be crazy spending a whole crap load of money for a small bump in frame rate (if any) that you'd get with a core i7.
Quote:
Originally Posted by Cooper
answer was already posted:
http://www.guru3d.com/article/core-i...ance-review/19
:)
I don't see how dual-channel would cripple performance of a desktop system. But castrated pci-e b/w is definately good point. Guess intel wants those spending $250 on CF or SLI setup spend another $700-800 in i7 rig instead of $300-$400 in PH2/i5.Quote:
Originally Posted by Shintai
250$ on CF/SLI? That would be very very lowend wouldnt it. And most likely with a faster singlecard option thats better :D Plus you wouldnt get much i5/Ph2 for 300-400$. In that case the i7 should be 500-600$.Quote:
Originally Posted by Cooper
But basicly its the issue due to speed. Since GPus needs to fetch the textures from main memory.
However one thing you gotta relalize with the rest. i5 is just another tiny step of where AMD/Intel is going. The IMC before that was yet another.
The average consumer will get less and less flexibility as time passes. Simply because we are moving forward towards SoC designs. GPUs moving to the CPU, later on southbridge functions etc etc.
I dont see how HD4850 CF is very low-end, but you are right - price tag is a bit low. 4850 CF can be had for $300 and 260GTX SLI for $400 at newegg.
Quote:
Originally Posted by Cooper
if you look here: http://www.guru3d.com/article/core-i...ance-review/19
a core i7 even the 920 will give you a big boost on Crisis ... it is more than adding one additional card on Core 2 ... the Core i7 920 is around 300$ ... it should be the beginning of a new rig if you plan SLI or Xcross fire, the data is obvious. :up:
"Core 2 Quad QX 9770 versus Core i7 965"Quote:
Originally Posted by Drwho?
:shrug: Seems bench's of the 920 would be more relevant.
Well I think we already went through the "CPU is more important for gaming than graphics" phase. Secondly that's 3.2GHz i7 on that chart.Quote:
Originally Posted by Drwho?
Not so fast pls. :DQuote:
Originally Posted by Cooper
If AND can't optimize their drivers to use multicore processor that dosn't mean that CPU dosn't important for gaming at all.
http://media.bestofmicro.com/1/X/165...l/image021.png
http://media.bestofmicro.com/1/T/165...l/image017.png
http://media.bestofmicro.com/1/R/165...l/image015.png
The difference between a phenom and a Core i7 at 1920x1200 with a single card is over 10 FPS? Furthermore, how does this effect diminish with more cards added? Shouldn't the trend be reversed?
Wow, you know so much that you know how AMD designed their yet unreleased processor. How is that?Quote:
Originally Posted by Drwho?
And yeah, maybe AMD needs to copy hyperthreading, if not to even out the copying going on lately. The core i7 looks a lot like a Phenom, except more than a year later. Native quad core, integrated memory controller, QPI (just like HT), same L3 cache structure. Hmmm, maybe dreamland is at AMD HQ. Did you go and see, then smile?
Ummm, hang on....
OK, had to check to be sure this was an i5 thread. For a second there I thought I was seeing posts about AMD stuff again...wait a minute! I was!
AMD has nothing to do with i5. It wasn't designed by AMD, so the "copying" BS is just that...pure 100% grade A farm fresh BS. Some may not be aware of this, but Intel isn't in a position where they have to "copy" anything. They are doing extremely well on their own.
Please take the Fanboi BS elsewhere. Preferably another forum where they allow that kind of thing. This isn't one of them.
Just stop trolling already....:shakes:Quote:
Originally Posted by taurus_sel
Final warning, fwiw.
That's an interesting point about the decode bandwidth, especially since AMD increased the I-cache bandwidth to 256bits. Why doesn't Intel have a similar problem? You seem to be implying that AMD is bottlenecked by the front-end. That seems like some low-hanging fruit though: increasing the number of decoders is simple. They don't need to double the number of decoders: why not just add one more? Both AMD and Intel chips are heavily optimized, so I doubt that the bottleneck is huge.Quote:
Originally Posted by Drwho?
Also, although I doubt that they will need to double the number of decoders, let's assume that this is the best method for performance and area for now. Why would this be a "power catastrophy"? First of all, let me acknowledge t hat decoders use up tons of power in the CPU (~20%, last time I checked). However, decoders are highly parallel, unlike the back-end of the CPU. They can also easily be gated when not in use. In addition, designers can optimize them for low power by removing dynamic logic and high Vt transistors and keep high clock speeds by adding another pipeline stage (since each macro-op is independent of each other, so no slowdown other than branch mispredictions due to a longer pipeline).
In summary, two main points:
1. Decoders will be gated when not in use.
2. Decoders can be made to be power efficient.
I agree that AMD needs to add SMT though, or use some sort of clustering or shared resource technique.
http://www.realworldtech.com/page.cf...1607033728&p=3
Because its basicly 100% identical to the released Shanghai...:rolleyes:Quote:
Originally Posted by taurus_sel
And if i7 looks like a Phenom. Then a cow looks like a monkey. They are both animals, they both fart and they both have bad breath. How can they not be 100% identical? :rofl:
It is an i5 thread...so why is the Intel rep talking about (sorry :banana::banana::banana::banana: talking) a Phenom II? And also why is the Intel rep saying that a core i7 is best for Xfire/SLI? I wonder how many people are complaining about that. Exactly....Quote:
Originally Posted by T_Flight
Or is it that there's different rules for different people. Exactly...
Because at the moment, i7 is the best for SLI and CF. No one is talking about price/performance ratio, we are talking what is the best for multi GPU scenarios and it is i7. Did you look at the review I posted? Or is your fanboyism blinding you? :rolleyes:Quote:
Originally Posted by taurus_sel
And you were the one who brought up the issue about Phenom II. Why don't you check your own posts? DrWho isn't wrong when he said i7 is the best for SLI and CF.
Yeah but I thought it was an i5 thread? So he can mention i7 and I can't mention Phenom II? And I question if i7 really is better based on what AMD showed and what people who were there and saw (from this forum). But I already said that in my original posts.Quote:
Originally Posted by Clairvoyant129
Sorry this has probably already been discussed, but I don't really understand the point of the i5. The i7 offers a decent performance boost over the C2D and C2Q processors, but from my understanding the i5 series will offer less in performance gains than the i7 series. Won't that be putting the performance of the i5 in or around the C2D/C2Q range? I don't see why anyone with a decent system right now would upgrade to an i5 series chip. :shrug:
For basically every task this chip will be just as good as current Nehalems. Memory bandwidth, a dual-channel DDR3 IMC is still gonna be great for desktop applications, and that's basically the only practical difference.Quote:
Originally Posted by scarywoody
Only reason I bought this thing was because I couldn't stand the old setup a second longer. :p: As long as it'll overclock and the socket will be maintained in the future the Lynnfield should be a better buy.
Ok, I guess I'll have to wait for more i5 series details before I start judging and loading this thread up with already answered questions. cheers
decoders are not highly parrallel if you try to extract early some code fusion, like it is done since Conroe. Phenom I/II is limited by its 3 large decodes, Conroe/Penryn and Nehalem are up to 5 large ... with code fusion. That is a severe difference that they pay.Quote:
Originally Posted by Shadowmage
decoders are not so cold, if highly efficent. The problem is to feed your out of order buffers, early enough to extract parralelism. At this, AMD is really late. They did catch up when they acquired the design of Athlon, but they now need to get into a serious improvement rebuild, and that is not easy, it takes years.
I keep thinking that with the threading taking off in the software community, Hyperthreading is a must for everbody now, this is why i am convinced they will implement it too. Doing it the way the Intel guys did it is very complexe, it toke many stepping and try error to figure out from the P4 to Nehalem. I think AMD will try a more brutal approche, and duplicate the decoders, because the lack of time to design it. They should have started at P4 time frame, when it showed some promissing improvement for 5% transistor in the core.
Again, this is my personal opinion, It may be bias, if you think so, I try to keep it honnest, as I got to keep it honnest for my own understanding of the industry.
:up:
I'm wondering what's the difference between an AMD decode unit and an Intel "simple decoder" unit. It seems from the RWT link from my previous post that the AMD decoder unit is more complex than the Intel counterpart (1-2uops instead of just 1). Also, AMD does have some code fusion, although I don't think it's as heavy as Intel's version.Quote:
Originally Posted by Drwho?
As for the "serious improvement rebuild", I have on good word that Bulldozer is a complete redesign which should "put AMD back into the lead". Until then, Shanghai and its derivatives are band-aids to stem off the bleeding until it arrives.
Sidenote: the necessity of uop fusion just proves how out-of-date x86 has become... yes I know that x86 is Intel's biggest asset and will never die out... :shakes:
My personal theory is that they'll double the issue width to 6-way with parallel 3-instruction packets (instead of the current single-issue "packet"). Each packet has a single thread-ID for multithreading. I think that this will put AMD in the lead while keeping it a logical evolution of their back-end.Quote:
I keep thinking that with the threading taking off in the software community, Hyperthreading is a must for everbody now, this is why i am convinced they will implement it too.
Pardon me for saying so, but AMD's architecture has always been much more aggressive than Intel's, especially after Intel's P4 "mistake". This is because AMD needs to make up for their 20% clock speed deficiency due to manufacturing. IIRC AMD's K8 had a similar FO4 delay to Northwood (about 10-ish), despite its obvious lead in IPC. Currently Intel has the more evolved architecture, so to speak, but that's probably the fault of AMD's execution lately rather than their architects' design aggressiveness. I'm not trying to downplay the awesome work done by Ronak and the rest of the guys in ORCA but as far as their general architecture is concerned, it's pretty conservative especially when compared to academia or even the DEC Alphas from the 1990's: same Tomasulo algorithms, not even a physical register file (although with a new matrix scheduler, very nice) :)Quote:
Doing it the way the Intel guys did it is very complexe, it toke many stepping and try error to figure out from the P4 to Nehalem. I think AMD will try a more brutal approche, and duplicate the decoders, because the lack of time to design it. They should have started at P4 time frame, when it showed some promissing improvement for 5% transistor in the core.
Some time, I don t follow you ... For example, why saying that x86 is out of date? it is design to use the legacy of the code, you can boot Dos 3.1 on your Core i7, it is the power of it, you never have to worry about back compatibility. Look at the cellphone business, where the lack of compatibility makes a market so fragmented that when you buy a phone, you are hostage of the brand you are buying it from... I am not going to point on Opera not being release on iPhone ... oh! i just did ...Quote:
Originally Posted by Shadowmage
x86 and its legacy is what make sure this does not happen, imagine if all PCs were running its own version of manufacture ... a dell version, an HP version ... it would be a nightmare.
fortunatly, Intel and AMD are smart enough to agree every few years together, some time intel take it from AMD, sometime the other way around (Fanboys in both side stupidly argue all the time about this, the reality is that the engineers behind it deal with this in a very elegant matter, and with respect for each other. I am in this pool, I have buddies working in Austin, with a greenbadge)
The strenght of x86 is that you describe as its weakness. :shrug:
For the rest, you got to understand that making a decoder "larger" introduce a lot of issue in the speed path way, it is not so easy to do without slowing down the frequency of the CPU, barcelona was a very good demonstration of this.
We will see what our buddies in Green will show up with, I like competition, it allows me to ask more toys to my management, so, let s see :up:
Today, I fixed my Play & watch Nintendo from 1981
http://www.nooperation.com/games/bab...watch-fire.jpg
My mom gave it to me when i was 12 ... dude! I am just having as much fun as I did at this time!!!!
I played that exact game too :oQuote:
Originally Posted by Drwho?
It was my favourite and I broke records on it in a train between denmark and germany.
Also had the one with snoopy and tennis.