Nvidia castrates Fermi to 448SPs

[Kakkoii]

edit: delete this

 

[Lonbjerg]

Keys It would have been better that you adderess the statement you made above, Lets see that link or retract that statement. I recieved a warning , Did you not know that? Now lets keep this ontopic without pushing my buttons ok.

I predict a ban in your future...for the good of the board...

 

[tviceman]

I have an intel IGP here that does all the things you say it cann't do . HD playback it does everthing better than ION .

Because it's paired with a core i7? TROLL. Nice talking with you.

 

[Nemesis 1]

http://www.digitimes.com/news/a20091228PD207.html

Just As I said , Befor ANYONE ELSE SAID IT . The thread is here to back it up . I even gave the logic behind the reasoning . Intel can take all the time it needs with larrabee AMD can take more time with the 6000thousand series . Because we won't see FErmi in March either . YES Yes YES.

 

[Nemesis 1]

Because it's paired with a core i7? TROLL. Nice talking with you.

Befor you start slinging shit at me ya better match me first , You guys always revert to this when getting beat up in a debate.

Stay on topic . Match me. research or use that thing that seperates your hears. Why is Fermi delayed Cough till march now . My MAY June is really looking good now for fermi release / AM I happy . YES I am . ITs A CHANGE you can count on . I have no IGP here paired with i7 . Nice thinking tho.

 

[nOOky]

I'm bored at work, so editing Nemesis 1's posts for grammar and spelling should occupy my free time
Thanks for the busy work!
My point is that to argue intelligently, it looks better to take the time to make your argument appear well thought out and constructed properly.
Why do I bring it up? Because sifting through these posts just pains my eyes to read so much I lose sight of what you're trying to convey.

 

[Nemesis 1]

I predict a ban in your future...for the good of the board...

I don't have a future, only destiny. I have been banned many times. But only 1 time was justifieable. The First Time . I did deserve that but not lifetime. But Please stay ontopic or you will be helping with your own predition . Ya want to continue this lets take it to P/N and I won't predict your future I will tell you your future. and its a very short future you have.

 

[Nemesis 1]

I'm bored at work, so editing Nemesis 1's posts for grammar and spelling should occupy my free time
Thanks for the busy work!
My point is that to argue intelligently, it looks better to take the time to make your argument appear well thought out and constructed properly.
Why do I bring it up? Because sifting through these posts just pains my eyes to read so much I lose sight of what you're trying to convey.

Stay ontopic.

 

[Lonyo]

I'm bored at work, so editing Nemesis 1's posts for grammar and spelling should occupy my free time
Thanks for the busy work!
My point is that to argue intelligently, it looks better to take the time to make your argument appear well thought out and constructed properly.
Why do I bring it up? Because sifting through these posts just pains my eyes to read so much I lose sight of what you're trying to convey.

Someone once did translate one of his posts, and it was very helpful.

Nemesis 1: n00ky is right, you would be a lot more persuasive, and I expect a lot of confusion could be avoided if you took a bit more time over your posts. You could probably get away with making less than half the number of posts if you took some more time over the ones you do make, and it would also help other people understand your position.

 

[Voo]

Someone once did translate one of his posts, and it was very helpful.

That'd be helpful.. I always get headaches if I try to understand what he's saying

 

[Keysplayr]

Stay ontopic.

Stay on topic???? On topic!!!???

What is the name of this thread??

Does it have ION in the title? Anything about Intel? ATI S120???? IBM????

Give.....me.....a.....break.

Your quotes in this thread, in order:

"Well the good news is in a thread@ Xs forums it seems the yield problems for ATI gpus has been resolved and there ramping up. Good news for ALL."
Introduced ATI ramping up in a Fermi thread

"I thought you would be happy . I thought The Problem was The FAB if ATI is ramping on 40nm . So should NV Fermi. So now we can't point fingers at the Fab saying its all there fault . This is much better . For you I would think . Clearly this means NV is ready to go now that the 40nm issue is resolved. No dead horse to kick around . Is this not a good thing . Time will show all. Now that the Fab problems are resolved"
Making sure you continue the ATI plug

"http://www.patentstorm.us/patents/6989838/claims.html

With above statements I agree . But man this thing with Intel /NV and the FTC is going to get ugly read the above patent. You think maybe that NV has infringed on this patent . As I understand it that is the case. I wish NV would close that can of whoop ass as its going to stall the industry."
Introduced the Intel/Nvidia patent lawsuit out of freaking nowhere, TWICE. After the first post was moved to an appropriate already existing thread.

"Ya I new you moved that . Why isn't it relavent here . Isn't NV doing something with the memory on fermi. I think this is relavent. I am sure they did it on other models also . But now that war has broke out we may find that NV was using Intel IP or parts there of. Do you know differantly . In post you said you new nothing of Fermi . After all this is a 2003 rastershell that Intel can't have because Ben says all rasterizing belongs to NV .

ECC memory was talked about above. So this does belong here as well as the other thread, Do you really think anyone knows more about caches and memory allocation than Intel . Maybe IBM ."

Insisting that the war breaking out between Nvidia/Intel has anything to do with Fermi at 448sp. Oh, and look.. IBM has entered the dialouge.

"Hay why are you confused, IGP are not for gaming . They are for cheap graphics and low power. You have a bit of a shock coming real soon . You guys are confusing as all hell . Ya talk about netbooks like they should be gaming Pcs LOL. I think mainly NV has alot of cheerleaders. Were there is NO game. But puff it up . But all of us have a right to opinion . and Ihave a strong hunch that NV is using Intel IP on fermi. I also believe NV had right to use it . But I think maybe that will change shortly. Once the courts clear the nehalem bus claims . Because if Intel wins that part. Than NVs countersuite works in Intels favor and Intel can legeally remove from NV all of its IP . Just as NV is claiming about intel . The winner her is going to be a winner nothing more . The loser tho may get smashed be it Intel or NV. Intel will not settle this out of court if their claims are infact in the contract . Intel may very well if they win the Nehalem ondie memory thing . Sue on the same grounds that NV is using now to counter intels move. NV may have sold the farm ."
This little gem slipped in here about Nvidia using Intel IP on Fermi, which has NOTHING to do with this topic

"Lets cut threw the BS here OK . You hook up ION to a real monitor like we use here. 19" at native res turn on the EyecandyTell all about IONs amazing power.

I have my old set up reinstalled on this online rig. P4C 3.2 x1950 26" monitor. It does everthing OK . But just for the hell of it. For 1 month I used 19"crt. and a ATI S120.

I tell I believe that the ATI S120 is stronger than ION. Its a piece of shit for anything other than everyday browsing . Now here what I well do . I will give you that S120 free. you want it. Its nobetter than Intels IGP . It well play a game like Black hawk down . But not well at all and crashes in less than an hour at low res and setting .

Heres what I think . I think you guys are young and trying to influence what people buy and precieve . The S120 ATI is a piece of crap because of its cost comparred to intels IGP it won't do HD It won't open full window on you tube and play video just sound.

Now don't say I am knocking ATI because I ATI fanbois. But these cards are a rip off. Comparred to intels IGP . I will give you the S120 free or anyone else that wants it."
Wonderful. Now we have ION, ATI S120, Offer to give it away, and Intels IGP. It just keeps getting thicker and thicker

"http://www.digitimes.com/news/a20091228PD207.html

Just As I said , Befor ANYONE ELSE SAID IT . The thread is here to back it up . I even gave the logic behind the reasoning . Intel can take all the time it needs with larrabee AMD can take more time with the 6000thousand series . Because we won't see FErmi in March either . YES Yes YES."
Intel again with Larabee, ATI 6000 series. Ugh...

"Stay ontopic."
This took some serious guts to post. You are aggravating the heck out of other members here. You come up with no less than 8 other subjects off topic from this thread, and have the audacity to cry, "Stay ontopic.".

I know this is all probably fun for you, BUT, you can't keep it up. The members aren't going to stand for it much longer. You post out of order, off topic, and wandering off the tracks comments out of absolutely nowhere.

I am asking you to stop. If you do not, I'm just going to advise any and all members who you are upsetting, to post complaints. This is getting absolutely ridiculous and needs to come to an end. Final conclusion. End game. Done.

 

[Soleron]

Do you know something that I do not? Just out of curiousity, what makes a person blurt out this stuff? You do know that you don't really know anything about Fermi's architecture, yet you feel free to say "They didn't change the shader architecture."
Are you under the impression that a Fermi is going to be simply two GT200 cores doubled up on one chip at 40nm with DX11 support? If so, where did you hear this info?
I'm sorry for the sarcasm here, but I'm just a wee bit tired of someone commenting as factual before anyone actually knows, or CAN know, yet.

OK, you're right, I have no idea.

I just thought Nvidia would have mentioned a single change or improvement to the shaders by now if that was the case, since they've been so happy to go in depth on cache, memory and programming issues. But I agree, if the shaders are different by a lot (new architecture kind of thing) then we can't even estimate the performance.

 

[v8envy]

OK, you're right, I have no idea.

I just thought Nvidia would have mentioned a single change or improvement to the shaders by now if that was the case, since they've been so happy to go in depth on cache, memory and programming issues. But I agree, if the shaders are different by a lot (new architecture kind of thing) then we can't even estimate the performance.

Yes, we can. We know the targeted SP and DP performance + specs of the workstation part. Those pieces of data let us guestimate the efficiency of the shaders, and those guestimates strongly support the "no radical changes/improvements" theory.

I'd be surprised to see a 5-10% clock for clock improvement myself (my personal guess is closer to 0%), but we can always hope for magic.

 

[nOOky]

Stay ontopic.

I think others posted a much better rebuttal than I needed to come up with. While I haven't contributed to the original topic, I enjoy sifting through these type of threads. To have to read through a paragraph of disjointed goblety beloved patriot is frustrating. I appreciate an opinion or viewpoint whether I agree with it or not, if it's presented in a decent manner.

 

[Keysplayr]

Yes, we can. We know the targeted SP and DP performance + specs of the workstation part. Those pieces of data let us guestimate the efficiency of the shaders, and those guestimates strongly support the "no radical changes/improvements" theory.

I'd be surprised to see a 5-10% clock for clock improvement myself (my personal guess is closer to 0%), but we can always hope for magic.

Bold ^

In what way does that tell you the "shader" performance? Or even if it's the same shader?
Can you please demonstrate to us what you're thinking?
How you came to your conclusion that SP and DP performance of a workstation part corresponds to the GF100.

 

[Nemesis 1]

Stay on topic???? On topic!!!???

What is the name of this thread??

Does it have ION in the title? Anything about Intel? ATI S120???? IBM????

Give.....me.....a.....break.

Your quotes in this thread, in order:

"Well the good news is in a thread@ Xs forums it seems the yield problems for ATI gpus has been resolved and there ramping up. Good news for ALL."
Introduced ATI ramping up in a Fermi thread

"I thought you would be happy . I thought The Problem was The FAB if ATI is ramping on 40nm . So should NV Fermi. So now we can't point fingers at the Fab saying its all there fault . This is much better . For you I would think . Clearly this means NV is ready to go now that the 40nm issue is resolved. No dead horse to kick around . Is this not a good thing . Time will show all. Now that the Fab problems are resolved"
Making sure you continue the ATI plug

"http://www.patentstorm.us/patents/6989838/claims.html

With above statements I agree . But man this thing with Intel /NV and the FTC is going to get ugly read the above patent. You think maybe that NV has infringed on this patent . As I understand it that is the case. I wish NV would close that can of whoop ass as its going to stall the industry."
Introduced the Intel/Nvidia patent lawsuit out of freaking nowhere, TWICE. After the first post was moved to an appropriate already existing thread.

"Ya I new you moved that . Why isn't it relavent here . Isn't NV doing something with the memory on fermi. I think this is relavent. I am sure they did it on other models also . But now that war has broke out we may find that NV was using Intel IP or parts there of. Do you know differantly . In post you said you new nothing of Fermi . After all this is a 2003 rastershell that Intel can't have because Ben says all rasterizing belongs to NV .

ECC memory was talked about above. So this does belong here as well as the other thread, Do you really think anyone knows more about caches and memory allocation than Intel . Maybe IBM ."

Insisting that the war breaking out between Nvidia/Intel has anything to do with Fermi at 448sp. Oh, and look.. IBM has entered the dialouge.

"Hay why are you confused, IGP are not for gaming . They are for cheap graphics and low power. You have a bit of a shock coming real soon . You guys are confusing as all hell . Ya talk about netbooks like they should be gaming Pcs LOL. I think mainly NV has alot of cheerleaders. Were there is NO game. But puff it up . But all of us have a right to opinion . and Ihave a strong hunch that NV is using Intel IP on fermi. I also believe NV had right to use it . But I think maybe that will change shortly. Once the courts clear the nehalem bus claims . Because if Intel wins that part. Than NVs countersuite works in Intels favor and Intel can legeally remove from NV all of its IP . Just as NV is claiming about intel . The winner her is going to be a winner nothing more . The loser tho may get smashed be it Intel or NV. Intel will not settle this out of court if their claims are infact in the contract . Intel may very well if they win the Nehalem ondie memory thing . Sue on the same grounds that NV is using now to counter intels move. NV may have sold the farm ."
This little gem slipped in here about Nvidia using Intel IP on Fermi, which has NOTHING to do with this topic

"Lets cut threw the BS here OK . You hook up ION to a real monitor like we use here. 19" at native res turn on the EyecandyTell all about IONs amazing power.

I have my old set up reinstalled on this online rig. P4C 3.2 x1950 26" monitor. It does everthing OK . But just for the hell of it. For 1 month I used 19"crt. and a ATI S120.

I tell I believe that the ATI S120 is stronger than ION. Its a piece of shit for anything other than everyday browsing . Now here what I well do . I will give you that S120 free. you want it. Its nobetter than Intels IGP . It well play a game like Black hawk down . But not well at all and crashes in less than an hour at low res and setting .

Heres what I think . I think you guys are young and trying to influence what people buy and precieve . The S120 ATI is a piece of crap because of its cost comparred to intels IGP it won't do HD It won't open full window on you tube and play video just sound.

Now don't say I am knocking ATI because I ATI fanbois. But these cards are a rip off. Comparred to intels IGP . I will give you the S120 free or anyone else that wants it."
Wonderful. Now we have ION, ATI S120, Offer to give it away, and Intels IGP. It just keeps getting thicker and thicker

"http://www.digitimes.com/news/a20091228PD207.html

Just As I said , Befor ANYONE ELSE SAID IT . The thread is here to back it up . I even gave the logic behind the reasoning . Intel can take all the time it needs with larrabee AMD can take more time with the 6000thousand series . Because we won't see FErmi in March either . YES Yes YES."
Intel again with Larabee, ATI 6000 series. Ugh...

"Stay ontopic."
This took some serious guts to post. You are aggravating the heck out of other members here. You come up with no less than 8 other subjects off topic from this thread, and have the audacity to cry, "Stay ontopic.".

I know this is all probably fun for you, BUT, you can't keep it up. The members aren't going to stand for it much longer. You post out of order, off topic, and wandering off the tracks comments out of absolutely nowhere.

I am asking you to stop. If you do not, I'm just going to advise any and all members who you are upsetting, to post complaints. This is getting absolutely ridiculous and needs to come to an end. Final conclusion. End game. Done.

Keys whats the point of this Post . YOU know dam well that I recieved a warning . Deny That. Also I stll waiting on that Link were as you said I said The 300 series was just a refresh . Were is that Link Keys. Rules only apply to US and not you. Holy Moly .

Everthing you posted here was befor the warning . What was that warning for . Seems to me you have done the exact same thing . So drop stay on topic Please.

 

[v8envy]

Fermi: 448 shaders at 1.2-1.4 ghz, "up to 600 GFlop single precision" -- spec sheet for C2050/2070 up on nvidia's site.

GTX280: 240 shaders at 1.3 ghz. 933 SP GFlop.

I'm not sure how you can read vastly increased shader efficiency (per unit) from that.

If you're fishing for a "we don't precisely know" you can have it. You can have my admission that they're not the same shaders. But still I stand by my statement that lower SP performance ratings do not bode well for vast "improvements." The GF100 would have to have its 448 shaders clocked at about 2 ghz to match the current product, in other words. While possible I see it highly unlikely.

Anyway, more will become clear as we approach Q2 of 2010. There's still time for redesigns, changes, and improvements in process. But from the above I can clearly see why we didn't get a Fermi desktop part this year.

 

[Nemesis 1]

I think others posted a much better rebuttal than I needed to come up with. While I haven't contributed to the original topic, I enjoy sifting through these type of threads. To have to read through a paragraph of disjointed goblety beloved patriot is frustrating. I appreciate an opinion or viewpoint whether I agree with it or not, if it's presented in a decent manner.

Ge thanks isur enuff apresheate your addvise and i will work real hard so your compiller can trasnilliominate my machine langog

 

[yh125d]

Fermi: 448 shaders at 1.2-1.4 ghz, "up to 600 GFlop single precision" -- spec sheet for C2050/2070 up on nvidia's site.

GTX280: 240 shaders at 1.3 ghz. 933 SP GFlop.

I'm not sure how you can read vastly increased shader efficiency (per unit) from that.

If you're fishing for a "we don't precisely know" you can have it. You can have my admission that they're not the same shaders. But still I stand by my statement that lower SP performance ratings do not bode well for vast "improvements." The GF100 would have to have its 448 shaders clocked at about 2 ghz to match the current product, in other words. While possible I see it highly unlikely.

Anyway, more will become clear as we approach Q2 of 2010. There's still time for redesigns, changes, and improvements in process. But from the above I can clearly see why we didn't get a Fermi desktop part this year.

I may be mistaken but I think the 933gflop number was the theoretical max for the GTX280 (while real world flops in real apps being much lower) while the 600gflop number for fermi was projected real performance with the theoretical max gflops being much higher

 

[Voo]

I may be mistaken but I think the 933gflop number was the theoretical max for the GTX280 (while real world flops in real apps being much lower) while the 600gflop number for fermi was projected real performance with the theoretical max gflops being much higher

Correct.. which means that that's so far from being an apple to apple comparison that it already comes back from the other side of the spectrum.

Theoretical max. gflops are always MUCH higher than the real performance you'll get and as long as we don't know exactly how they measured the 933gflops, these numbers are rather useless.. depending on the benchmark these numbers vary quite a lot..

 

[Keysplayr]

Keys whats the point of this Post . YOU know dam well that I recieved a warning . Deny That. Also I stll waiting on that Link were as you said I said The 300 series was just a refresh . Were is that Link Keys. Rules only apply to US and not you. Holy Moly .

Everthing you posted here was befor the warning . What was that warning for . Seems to me you have done the exact same thing . So drop stay on topic Please.

I did a search, Nemesis. But I cannot find it. It may very well be due to my search criteria and spelling things correctly. Who knows how you spelled those words. So, if in my travels I come across it, I will post it. It was one of your insane rants where you said, that G300 would just be a die shrunk GT200. And said something to the effect of "Mark my werds".

 

[Nemesis 1]

Keys there is one thing wrong , I know what I said . Ihave a very good memory almost photo. You really wouldn't want to know my I.Q. I never said anything about Fermi being a Redo. WE were discussing the 310/320 redos . I could easily find it . But it matters not about whois right or wrong its kicking this stuff around that counts . It makes everbodythink . That way better than watching TV . The only reason I really like Tech forums is because it stimulates the brain cells . and it keeps your mind out of the gutter.

 

[PingviN]

Wow... this "discussion" is actually pretty pathetic. It's interesting how something as trivial as graphics cards can result in this kind of troll-fest.

 

[SlowSpyder]

Wow... this "discussion" is actually pretty pathetic. It's interesting how something as trivial as graphics cards can result in this kind of troll-fest.

I see you are new here...


We don't have much data from Nvidia, we can only guesstimate on what we do have at this point... it's not like Nvidia is bombarding us with benches exactly. But going by what we do have at this point, it looks to me that Nvidia is really focusing on the HPC market. Obviously that's just my guess based on what we have available now and certainly could change. But the changes they've made and shared with us thus far don't point to a gaming monster to me. I guess we'll see in a few months.

 

[cbn]

With LCDs becoming much more affordable I just hope Nvidia Fermi comes with Mult-monitor support.

Then reviewers can do some memory bandwidth/VRAM comparisons at higher resolutions than 2560x1600.