NVIDIA GF100 & Friends speculation

Only 4 partners will launch Fermi (this might be for Europe only) and XFX won't be one.
Cards won't ship until 1 or 2 weeks after launch. though partner availability in May will be quite bigger.

NV Hopes to get the speeds from the B1 chip that everyone is expecting from the launch chips. So we're a couple of months away from seeing the true GF100 performance.

Glad to see others are now posting what I did around or a little bit more than a month ago in this thread concering B1 stepping Fermi's.
 
Availability for May should be about 6 to 7 times that of Rv770/Rv870 at launch

Oh, you haven't heard? the chip is going back to TSMC after the "launch" for it's first full re-spin!

Hence the no-to-limited availability etc. until June/July. It also is the basis for Charlies "handful" of chips for partners, A3 will be here for launch and B1 will be the "shipping" product.

We will see B1 in may? Nice. :LOL:
 
Glad to see others are now posting what I did around or a little bit more than a month ago in this thread concering B1 stepping Fermi's.

Well for what it's worth he said a couple months. Timeframes are colliding with your past data and I personally prefer neliz' version of it :LOL:
 
If B1 is even production silicon. While it's not unlikely cases where NV went into production with A1/B1 silicon should be extremely rare.

It had better, other wise a B2 in August will leave it precariously close to NI. And subsequently push back future roadmaps.
 
GTX480 power usage is "well" below 300W.

What is your definition of well ?

What is your definition of definition ?

What do you think of my poor spelling.

Will batman and robin escape ?

Tune in next post at the same bat-channel and bat-time ! :LOL:
 
What is your definition of well ?

What is your definition of definition ?

What do you think of my poor spelling.

Will batman and robin escape ?

Tune in next post at the same bat-channel and bat-time ! :LOL:

let's say it's performance is in-line with it's power usage.
So, no it won't use as much power as a 5970 and no, it won't challenge a 5970 as "graphics king."
 
let's say it's performance is in-line with it's power usage.
So, no it won't use as much power as a 5970 and no, it won't challenge a 5970 as "graphics king."

I don't care about it challing the 5970 . That was silly to think a single gpu on the same process will defeat a dual gpu .

I just hope its fast enough to cause ati to drop prices.
 
I don't care about it challing the 5970 . That was silly to think a single gpu on the same process will defeat a dual gpu .

I just hope its fast enough to cause ati to drop prices.

If the B1 comes out of teh oven as good as they hope it does, OC'd versions(factory and user) might challenge the stock 5970 in some cases.
 
If the B1 comes out of teh oven as good as they hope it does, OC'd versions(factory and user) might challenge the stock 5970 in some cases.

Problem is that when B1 arrives in Q3 (1) it may not fix the issues (2) it will spend it's life up against Northern Islands products.

And B1 is still only a high end product with nothing in sight for the mainstream.
 
Problem is that when B1 arrives in Q3 (1) it may not fix the issues (2) it will spend it's life up against Northern Islands products.

And B1 is still only a high end product with nothing in sight for the mainstream.

We will see B1 in may, guys. Neliz said it:

Availability for May should be about 6 to 7 times that of Rv770/Rv870 at launch

Hence the no-to-limited availability etc. until June/July. It also is the basis for Charlies "handful" of chips for partners, A3 will be here for launch and B1 will be the "shipping" product.
 
If the B1 comes out of teh oven as good as they hope it does, OC'd versions(factory and user) might challenge the stock 5970 in some cases.

By then the 5870 will be 9 months old and the 5970 would be what 6 months old ? 7 ?

We are already seeing faster 5970s coming.
 
I think you're just seeing the effect of tessellation increasing the GPU bottleneck and thus driving up frame times (and relatively driving down the amount of work the CPU is doing to generate frames for the GPU to process). If you modified the resolutions or similar so that the two runs were running at similar frame rates I imagine you would see the lines close together regardless of the tessellation setting.

Right, but it also proves to some extent that my system's not necessarily the limit for Heaven in tessellated mode (which was one of the possibilities where the discussion was coming from).
 
640x400 -> 2.19/0.45 :oops:
1280x800 -> 1.98/0.50 :???:
2560x1600 40,4 -> 1.48/0.67

I think it's a serious subpixel polygon size issue caused by tesselation. I don't know which hardware units correspond to that though.
It's not perfectly related to sub-pixel polys/high overdraw induced by tessellation.

If it were an efficiency loss, framerate would drop as you lower resolution substantially, which I checked is not the case all the way down to 320x200, framerate increases even if it's minimal (when using a GPU capable of 200fps and making it stall for 30ms, halving effective rendering time won't have much of an impact, basically 35ms -> 32.5ms total frame time).

There's an enormous overhead on Evergreen GPUs when tessellation is On, but apparently entirely due to poor dispatch... which could explain why GF100 has no less than 1 tessellation unit per SM and why LDS conflicts appear on Cypress.

I think a workaround for this behaviour could be to dedicate some of the SIMDs to tessellation as that should avoid conflicts.

Hopefully, AlexV or someone else will be able to dig more into it.
 
Last edited by a moderator:
We will see B1 in may, guys. Neliz said it:

Did you even read the what you quoted? How can there be "little to no" product until July even after the launch, but B1 will somehow be available in massive quantities in May?

Same way I called the GF100 launch as being six months later back in October despite other claims to the contrary, I'm calling B1 in Q3, with no guarantee that it's going to fix all their problems.
 
Back
Top