A PATENT has shown up at the US repository of such thing$ that gives us some more clues as to the nature of the technology that Microsoft and ATI will employ with its next generation Xbox and the R520 component.
The patent is for a method and apparatus for determining a processing speed of an integrated circuit.
Sounding bizarrely like John Kerry, the patented circuit includes 'a first flip flop having an input port... an output port providing a flip flop output signal..." and other such indecipherable phrases.
The patent goes all the way back to a story that we covered last year concerning ATI's partnership with Intrisity.
The patent, we think, is part of the effort to get CMOS processing - as in traditional processors - and dynamic logic processing - as in supercomputers - working on the same chip. Dynamic logic works at far faster speeds, hence the need for an integrated circuit to regulate the switching between the two.
The discovery of this patent is the first hard proof that ATI is treading down this road of chip design, as its deal with Intrinsity was surrounded in speculation as to the exact nature of the technology being licensed and which way the information was flowing. The patent appears to confirm that the R500/R520 part will be something substantially different to anything we've seen in the past. µ
A method and apparatus for determining a processing speed of an integrated circuit includes a first flip flop having an input port receiving an input signal, an output port providing a flip flop output signal and a timing port receiving an incoming clock signal. The method and apparatus further includes a delay circuit operably coupled to the output port of the first flip flop, such that the delay circuit receives the flip flop output signal, generating a delayed timing signal. Further included is at least one clock speed adjusting circuit operably coupled to the delay circuit and a multiplexer coupled to the at least one clock speed adjusting circuit and the delay circuit, wherein the multiplexer receives a select delay signal in a selective delay input port. Based on the select delay signal, a multiplexer output signal is chosen and provided to an input port of a second flip flop.
A READER HAS DROPPED us ? and AMD Zone a line ? about why Microsoft decided to go with the PowerPC microprocessor for the Xbox 2 rather than an X86 based processor.
It seems that ATI which will be supplying the graphics chip to the Xbox 2, and desiring the chip to be much faster than the upcoming R400 chip, has tapped Intrinsity's Fast14 dynamic logic process in the construction of this new chip.
Intrinsity as you may know is an Austin, TX based firm that has in its employ quite a few engineers from another Austin based firm known formerly as Exponential Technology. Those guys, back in the mid 90s, were trying to design the next generation PowerPC chip known as the X704 which would have leapfrogged all other processors both X-86 and PowerPC by coming in clocked at the then unheard of speed of 533 MHz, effectively more than double other processors of that time.
They were trying to do this by employing a technique of chip making from the mainframe and supercomputing world known as bi-polar logic, a form of dynamic logic. This form of chip making produces a much higher performance chip than the standard CMOS chip.
However, it is much more difficult to make chips this way, at least back then, and the chips come out running very hot. Before Exponential could perfect this chip for mass market production, the PowerPC G3 from IBM had nearly caught up with it in terms of clock speed, and Apple refused to let clone makers Umax and Power Computing (formerly of Austin) to modify the Apple ROM chips to let the Exponential chip work on existing Apple motherboards.
Thus Exponential went belly up and the patents were auctioned off. What is intriguing is that a handful of those patents dealt with the Exponential chip's ability to execute both RISC and X-86 instructions down one pipeline, basically a RISC chip that could emulate an Intel chip.
Now fast forward to today. Intrinsity which employs many ex-Exponential Technology guys with a lot of PowerPC knowledge have this Fast14 dynamic logic process using standard cheap CMOS manufacturing which has allowed them to make the world's fastest embedded general purpose CPU which acts like a DSP. Known as the FastMIPS chip, it's clocked at 2GHz (2.5 by the end of April) with an integrated Matrix and Vector math unit running at full clock speed as well. It has 1MB of embedded memory, an embedded memory controller supporting up to 1GB of DDR SDRAM, and a dual I/O bus with up to 4GB of throughput....all on one single programmable chip!
This chip is marketed to company's that need high performance, small packages and low heat. Some of these markets include real time to near real time medical imaging, high speed storage and networking, array processing for radar and increasing cellular network bandwidth by a factor of 2-3 times.
Now let's put the pieces all together. Microsoft has chosen IBM, a long time maker of mainframes and supercomputers to manufacture the XBOX 2's CPU...a variant of the Power4 CPU known as the G5. It is high performance and highly efficient, and thus much cooler than any X-86 chip which allows a multi-CPU design to be put into a much smaller form factor than a comparable multi X-86 design. The G5 has embedded in it a Vector Math unit which processes multimedia instructions much like Intel's SSE instructions.
Once again the AltiVec units in the G5 are much more efficient and high performance and share a mainframe and supercomputer pedigree. Enter now the graphics chip side of things. The new ATI GPU using Intrensity's Fast14 dynamic logic process is a fantastic technological compliment to IBM's G5.
The GPU will also employ technology culled from the world of mainframes and supercomputers such as dynamic logic for much higher performance and vector math processing like the G5's Altivec multimedia units. Plus the Fast14 process allows for this much higher performance of dynamic logic without the once associated heat buildup. Once again, an important design criteria when building a small form factor console. Helping to make the new ATI Fast14 GPU that much cooler will be the Black Diamond low-K dielectric insulating process that ATI and its foundry partner TSMC uses.
Without a doubt the Xbox 2 will be the world's first consumer supercomputer ever. Everything about it reeks of supercomputer....Multiple Power4/G5 RISC CPU's processing in parallel and employing vector math processing. Those CPU's designed by supercomputer manufacturer IBM. Graphics processor employing dynamic logic and vector math processing from the world of supercomputers, manufactured by ATI which is now primarily run by ex-SGI engineers, again a manufacturer of supercomputers. Can't wait until someone hacks into it and installs 64 bit Linux. Can you imagine a Beowulf Cluster built of multiple Xbox 2s ?!!!
__________________
The patent is for a method and apparatus for determining a processing speed of an integrated circuit.
Sounding bizarrely like John Kerry, the patented circuit includes 'a first flip flop having an input port... an output port providing a flip flop output signal..." and other such indecipherable phrases.
The patent goes all the way back to a story that we covered last year concerning ATI's partnership with Intrisity.
The patent, we think, is part of the effort to get CMOS processing - as in traditional processors - and dynamic logic processing - as in supercomputers - working on the same chip. Dynamic logic works at far faster speeds, hence the need for an integrated circuit to regulate the switching between the two.
The discovery of this patent is the first hard proof that ATI is treading down this road of chip design, as its deal with Intrinsity was surrounded in speculation as to the exact nature of the technology being licensed and which way the information was flowing. The patent appears to confirm that the R500/R520 part will be something substantially different to anything we've seen in the past. µ
A method and apparatus for determining a processing speed of an integrated circuit includes a first flip flop having an input port receiving an input signal, an output port providing a flip flop output signal and a timing port receiving an incoming clock signal. The method and apparatus further includes a delay circuit operably coupled to the output port of the first flip flop, such that the delay circuit receives the flip flop output signal, generating a delayed timing signal. Further included is at least one clock speed adjusting circuit operably coupled to the delay circuit and a multiplexer coupled to the at least one clock speed adjusting circuit and the delay circuit, wherein the multiplexer receives a select delay signal in a selective delay input port. Based on the select delay signal, a multiplexer output signal is chosen and provided to an input port of a second flip flop.
A READER HAS DROPPED us ? and AMD Zone a line ? about why Microsoft decided to go with the PowerPC microprocessor for the Xbox 2 rather than an X86 based processor.
It seems that ATI which will be supplying the graphics chip to the Xbox 2, and desiring the chip to be much faster than the upcoming R400 chip, has tapped Intrinsity's Fast14 dynamic logic process in the construction of this new chip.
Intrinsity as you may know is an Austin, TX based firm that has in its employ quite a few engineers from another Austin based firm known formerly as Exponential Technology. Those guys, back in the mid 90s, were trying to design the next generation PowerPC chip known as the X704 which would have leapfrogged all other processors both X-86 and PowerPC by coming in clocked at the then unheard of speed of 533 MHz, effectively more than double other processors of that time.
They were trying to do this by employing a technique of chip making from the mainframe and supercomputing world known as bi-polar logic, a form of dynamic logic. This form of chip making produces a much higher performance chip than the standard CMOS chip.
However, it is much more difficult to make chips this way, at least back then, and the chips come out running very hot. Before Exponential could perfect this chip for mass market production, the PowerPC G3 from IBM had nearly caught up with it in terms of clock speed, and Apple refused to let clone makers Umax and Power Computing (formerly of Austin) to modify the Apple ROM chips to let the Exponential chip work on existing Apple motherboards.
Thus Exponential went belly up and the patents were auctioned off. What is intriguing is that a handful of those patents dealt with the Exponential chip's ability to execute both RISC and X-86 instructions down one pipeline, basically a RISC chip that could emulate an Intel chip.
Now fast forward to today. Intrinsity which employs many ex-Exponential Technology guys with a lot of PowerPC knowledge have this Fast14 dynamic logic process using standard cheap CMOS manufacturing which has allowed them to make the world's fastest embedded general purpose CPU which acts like a DSP. Known as the FastMIPS chip, it's clocked at 2GHz (2.5 by the end of April) with an integrated Matrix and Vector math unit running at full clock speed as well. It has 1MB of embedded memory, an embedded memory controller supporting up to 1GB of DDR SDRAM, and a dual I/O bus with up to 4GB of throughput....all on one single programmable chip!
This chip is marketed to company's that need high performance, small packages and low heat. Some of these markets include real time to near real time medical imaging, high speed storage and networking, array processing for radar and increasing cellular network bandwidth by a factor of 2-3 times.
Now let's put the pieces all together. Microsoft has chosen IBM, a long time maker of mainframes and supercomputers to manufacture the XBOX 2's CPU...a variant of the Power4 CPU known as the G5. It is high performance and highly efficient, and thus much cooler than any X-86 chip which allows a multi-CPU design to be put into a much smaller form factor than a comparable multi X-86 design. The G5 has embedded in it a Vector Math unit which processes multimedia instructions much like Intel's SSE instructions.
Once again the AltiVec units in the G5 are much more efficient and high performance and share a mainframe and supercomputer pedigree. Enter now the graphics chip side of things. The new ATI GPU using Intrensity's Fast14 dynamic logic process is a fantastic technological compliment to IBM's G5.
The GPU will also employ technology culled from the world of mainframes and supercomputers such as dynamic logic for much higher performance and vector math processing like the G5's Altivec multimedia units. Plus the Fast14 process allows for this much higher performance of dynamic logic without the once associated heat buildup. Once again, an important design criteria when building a small form factor console. Helping to make the new ATI Fast14 GPU that much cooler will be the Black Diamond low-K dielectric insulating process that ATI and its foundry partner TSMC uses.
Without a doubt the Xbox 2 will be the world's first consumer supercomputer ever. Everything about it reeks of supercomputer....Multiple Power4/G5 RISC CPU's processing in parallel and employing vector math processing. Those CPU's designed by supercomputer manufacturer IBM. Graphics processor employing dynamic logic and vector math processing from the world of supercomputers, manufactured by ATI which is now primarily run by ex-SGI engineers, again a manufacturer of supercomputers. Can't wait until someone hacks into it and installs 64 bit Linux. Can you imagine a Beowulf Cluster built of multiple Xbox 2s ?!!!
__________________
Turtle, if you link an article that's fine, but giving no information about the article and simply pasting it verbatim is a big no-no. First off, it's technically plagarism, secondly quoting something at random has no point, because it may be horribly outdated. In the case of your above post, it talks about the upcoming R400...which makes the article at least 18 months old and utterly useless, since we knew frankly nothing of XBox360 (your old article still calls it XBox2) nor of the unified arch at that time.
Swing and a miss.
Swing and a miss.
So now I hope this sheds a little light on what we will see from ATI in the near future. I know I contribute little to these forms as most of you guys already know all about this stuff . But fot those of you who do not I thought I would Add this page.
If no posters says their not interested in this sort of post. I well do what the above poster suggest. If you guys want this kind of outdated info. SAY SO!!
This is from above Article it looks up to date to me . It does go threw the steps of were we were to get to were ATI is at PRESENT
The discovery of this patent is the first hard proof that ATI is treading down this road of chip design, as its deal with Intrinsity was surrounded in speculation as to the exact nature of the technology being licensed and which way the information was flowing. The patent appears to confirm that the R500/R520 part will be something substantially different to anything we've seen in the past. µ
If no posters says their not interested in this sort of post. I well do what the above poster suggest. If you guys want this kind of outdated info. SAY SO!!
This is from above Article it looks up to date to me . It does go threw the steps of were we were to get to were ATI is at PRESENT
The discovery of this patent is the first hard proof that ATI is treading down this road of chip design, as its deal with Intrinsity was surrounded in speculation as to the exact nature of the technology being licensed and which way the information was flowing. The patent appears to confirm that the R500/R520 part will be something substantially different to anything we've seen in the past. µ
Originally posted by: keysplayr2003
Originally posted by: M0RPH
NVIDIA Corp.?s chief architect David Kirk called the unified graphics engines as an implementation detail, not a feature, but admitted the unified architecture would be nice for programmers, who would have one instruction set for vertex and pixel shaders.
?It?s not clear to me that an architecture for a good, efficient, and fast vertex shader is the same as the architecture for a good and fast pixel shader. A pixel shader would need far, far more texture math performance and read bandwidth than an optimized vertex shader. So, if you used that pixel shader to do vertex shading, most of the hardware would be idle, most of the time. Which is better ? a lean and mean optimized vertex shader and a lean and mean optimized pixel shader or two less-efficient hybrid shaders? There is an old saying: ?Jack of all trades, master of none?,? Mr. Kirk said in an interview with ExtremeTech web-site.
----
Nvidia questions the effectiveness of unified shaders but Microsoft is promoting the unified shader approach and it will likely be an important part of DX10. Therefore it will be easier for programmers to code for a unified shader GPU. So Nvidia will end up giving in and going with the flow and I'd bet they are already hard at work on developing it. Since ATI has embraced the unified shader approach from the beginning they may end up having a bit of an advantage in bringing a unified shader GPU to market.
Disclaimer: Most of the above is pure speculation on my part
Ok, but the G80 is said to be unified and ready to go. (I'm talking desktops here, we can discuss consoles in a minute).
So Nvidia may be reluctant to do it, but has to go with the flow because MicroSmurf is boss. Got it.
If you could show a link of specs or something other than PR here say .We all would be interested no one here is interested in vaporware . POST A LINK about G80
Gamingphreek
Lifer
- Mar 31, 2003
- 11,679
- 0
- 81
Turtle 1, you have posted the MOST useless info ever. YOu have simply quoted articles that have something remotely to do with R520 or US. You dont provide any commentary for those articles on top of that.
Well quoting 18month old articles about a previous generation doesn't. None of these articles say anything concrete. They merely say the SAME EXACT things that we have been speculating the entire time.
I have absolutely no idea what you are trying to post here. No one asked or was interested in you simply posting whole articles with no commentary and with little to do with the topic at hand.
Yet again, i still have no clue what you are saying:
LEARN TO TYPE!!
Hmm now thats interesting. It would seem that you got that from the inquire as there is no grammatical errors, no spelling errors, vocbulary well above your leve, yet no quote tags. Nice try though.
Oh yeah, im still waiting for that FI thread to get me banned, or a call for a lawsuit. What happened with that huh?
-Kevin
Well quoting 18month old articles about a previous generation doesn't. None of these articles say anything concrete. They merely say the SAME EXACT things that we have been speculating the entire time.
I have absolutely no idea what you are trying to post here. No one asked or was interested in you simply posting whole articles with no commentary and with little to do with the topic at hand.
Yet again, i still have no clue what you are saying:
LEARN TO TYPE!!
Hmm now thats interesting. It would seem that you got that from the inquire as there is no grammatical errors, no spelling errors, vocbulary well above your leve, yet no quote tags. Nice try though.
Oh yeah, im still waiting for that FI thread to get me banned, or a call for a lawsuit. What happened with that huh?
-Kevin
thxdd
Member
- Sep 24, 2005
- 91
- 29
- 91
Oh good lord the PR people are at it again. Wasn't it just a few years ago that we had another claim like this? The Power Macintosh G4 claimed it was the "first consumer supercomputer" too. Xbox 360 is late to the party!
Supercomputers for the masses, woah!
As for the humbug surrounding the release of ATi's R520 and its neutered brethren...
If it has a unified shader architecture, great! It wouldn't surprise me in the least if Microsoft has teamed up with ATi to give them a headstart on something like this. Afterall, they are working together on the Xbox 360 and Micro$oft and nVidia are far from the bed partners they were at the release of the original Xbox.
If it doesn't have a unified shader architecture, oh well! I don't think it should be a dealbreaker like everyone is making it out to be. It's definitely not going to be the reason the R520 does or doesn't perform well.
I'm sure the R520 will at least give the 7800GTX a run for its money which is better for all of us in the end. Competition = Good!
For the record, I'm far from a fanboy, I own a 9700 Pro (love it) and a 6800GT (love it). Both are great pieces of hardware and I would buy from both companies again.
Gamingphreek
Lifer
- Mar 31, 2003
- 11,679
- 0
- 81
Gaming what ever. This was about the patent that ati has . Than some backround about that patent as it partains to the R500/R520. So its not outdated at all.
You don't know whether I have permissioon to use that article or not . I have a lot of resources at my disposal.
You don't know whether I have permissioon to use that article or not . I have a lot of resources at my disposal.
Gamingphreek
Lifer
- Mar 31, 2003
- 11,679
- 0
- 81
The R400 wasn't even released yet!!!!
It is way outdated. You dont believe it is because you hear the word R5xx mentioned 2x in the entire article; even though there is no information pertaining to it.
-Kevin
Edit:
And the stupidity continues. Lol seriously, you are really making me laugh...law suit, ban, and now you have permission to just randomly post articles word for word.
-Kevin
Gamingphreek
Lifer
- Mar 31, 2003
- 11,679
- 0
- 81
Why in the world are you linking us to another forum. Not only that, but one where the last post was in may. Not only that, but one that tells us absolutely nothing about the topic.
-Kevin
-Kevin
Kelvin beings how its all old news to you...cough Explain what embedded memory is going to do for us gamers.
Avalon
Diamond Member
- Jul 16, 2001
- 7,571
- 178
- 106
No, your source is NOT quoted, which means you're giving even LESS credit to the author of it, and comitting plagiarism. I can't believe you have the nerve to ask people to post links to something they quote, when you can't even do the same. You're a hypocrit and a complete moron.
At no time do I take credit for authoring that article . It comes from my employers archives and have full permission to use it.
http://xbox360.ign.com/articles/617/617951p3.html
http://xbox360.ign.com/articles/617/617951p3.html
Originally posted by: Turtle 1
Originally posted by: keysplayr2003
Originally posted by: M0RPH
NVIDIA Corp.?s chief architect David Kirk called the unified graphics engines as an implementation detail, not a feature, but admitted the unified architecture would be nice for programmers, who would have one instruction set for vertex and pixel shaders.
?It?s not clear to me that an architecture for a good, efficient, and fast vertex shader is the same as the architecture for a good and fast pixel shader. A pixel shader would need far, far more texture math performance and read bandwidth than an optimized vertex shader. So, if you used that pixel shader to do vertex shading, most of the hardware would be idle, most of the time. Which is better ? a lean and mean optimized vertex shader and a lean and mean optimized pixel shader or two less-efficient hybrid shaders? There is an old saying: ?Jack of all trades, master of none?,? Mr. Kirk said in an interview with ExtremeTech web-site.
----
Nvidia questions the effectiveness of unified shaders but Microsoft is promoting the unified shader approach and it will likely be an important part of DX10. Therefore it will be easier for programmers to code for a unified shader GPU. So Nvidia will end up giving in and going with the flow and I'd bet they are already hard at work on developing it. Since ATI has embraced the unified shader approach from the beginning they may end up having a bit of an advantage in bringing a unified shader GPU to market.
Disclaimer: Most of the above is pure speculation on my part
Ok, but the G80 is said to be unified and ready to go. (I'm talking desktops here, we can discuss consoles in a minute).
So Nvidia may be reluctant to do it, but has to go with the flow because MicroSmurf is boss. Got it.
If you could show a link of specs or something other than PR here say .We all would be interested no one here is interested in vaporware . POST A LINK about G80
Whoaaaaa....If this isn't the pot calling the kettle black...You want to take your arse back to those other threads you turned into flame wars and prove anything you said there??? I didn't think so...therefore SHUT IT!!!!
The way I look at it anyone with a brain can see why the market leader would not want to embrace this and why the perennial second place does.....Do not misinterpret reluctance with difficulty in getting them in place....nvidia sees this as a way to take away dominance of design and level things out....Unfortunately if it gets into that Nvidia can still always outsupply them, much like Intel does to AMD...
I personally Microsuck has a hard enough time getting the sh^t we buy now fromthem to work try to get more things to offload to software and the OS...they should stay out of it...
Originally posted by: Duvie
Originally posted by: Turtle 1
Originally posted by: keysplayr2003
Originally posted by: M0RPH
NVIDIA Corp.?s chief architect David Kirk called the unified graphics engines as an implementation detail, not a feature, but admitted the unified architecture would be nice for programmers, who would have one instruction set for vertex and pixel shaders.
?It?s not clear to me that an architecture for a good, efficient, and fast vertex shader is the same as the architecture for a good and fast pixel shader. A pixel shader would need far, far more texture math performance and read bandwidth than an optimized vertex shader. So, if you used that pixel shader to do vertex shading, most of the hardware would be idle, most of the time. Which is better ? a lean and mean optimized vertex shader and a lean and mean optimized pixel shader or two less-efficient hybrid shaders? There is an old saying: ?Jack of all trades, master of none?,? Mr. Kirk said in an interview with ExtremeTech web-site.
----
Nvidia questions the effectiveness of unified shaders but Microsoft is promoting the unified shader approach and it will likely be an important part of DX10. Therefore it will be easier for programmers to code for a unified shader GPU. So Nvidia will end up giving in and going with the flow and I'd bet they are already hard at work on developing it. Since ATI has embraced the unified shader approach from the beginning they may end up having a bit of an advantage in bringing a unified shader GPU to market.
Disclaimer: Most of the above is pure speculation on my part
Ok, but the G80 is said to be unified and ready to go. (I'm talking desktops here, we can discuss consoles in a minute).
So Nvidia may be reluctant to do it, but has to go with the flow because MicroSmurf is boss. Got it.
If you could show a link of specs or something other than PR here say .We all would be interested no one here is interested in vaporware . POST A LINK about G80
Whoaaaaa....If this isn't the pot calling the kettle black...You want to take your arse back to those other threads you turned into flame wars and prove anything you said there??? I didn't think so...therefore SHUT IT!!!!
The way I look at it anyone with a brain can see why the market leader would not want to embrace this and why the perennial second place does.....Do not misinterpret reluctance with difficulty in getting them in place....nvidia sees this as a way to take away dominance of design and level things out....Unfortunately if it gets into that Nvidia can still always outsupply them, much like Intel does to AMD...
I personally Microsuck has a hard enough time getting the sh^t we buy now fromthem to work try to get more things to offload to software and the OS...they should stay out of it...
Links please . 10 days left and I will keep this Thread alive
Dude it would kept aloive without you.....Which is what I recommend...
I stated nothing that needs to be linked....You styill have 3 threads to go back to and support your other statements...Dont worry we are keeping tally....You are not very crdible cause you tuck and run from all the other questions of providing proof....
Nice day Turtelia...
I would like the mods to edit your name to that!!! Please..Belated B-day gift!!!
I stated nothing that needs to be linked....You styill have 3 threads to go back to and support your other statements...Dont worry we are keeping tally....You are not very crdible cause you tuck and run from all the other questions of providing proof....
Nice day Turtelia...
I would like the mods to edit your name to that!!! Please..Belated B-day gift!!!
Duvie I have not flamed 1 person . Your constant acrimonious statements .Will not go unnoticed by the management of Anandtech. The fact there has been flame here is true but none by me.
The links a gave in those threads had every bit of information in them .To back up everything I said.
5150Joker
Diamond Member
Because the assumption is if they have a unified shader part, the card would be DX10 compliant rather than compatible. That's why I mentioned in my initial post that if the unified shader part were true by some remote chance and since DX 10 is essentially done, it would mean it had forward looking features.
Thats exactly correct . Than the flamers jumped in to hijack the thread. This had all the earmarks of a great thread till it was hijacked! Joker I am still thinking if the OP post is correct. It will be SM3+ and not SM4 . But until we know if its unified shaders its all just smoke. If it is than the embedded memory and stuff is nothing more than a topic for those interested in ATI products to discuss. Also if R520 has 300-350 million transistors that would be inline with what the R500 has.
TRENDING THREADS
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 25K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads
- Started by Tigerick
- Replies: 22K
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 23K
-
-
News NVIDIA and Intel to Develop AI Infrastructure and Personal Computing Products- Started by poke01
- Replies: 411
Facebook
Twitter