Fermi gets cut back

[Trotter]

IT LOOKS LIKE we were right about Fermi being too big, too hot, and too late, Nvidia just castrated it to 448SPs. Even at that, it is a 225 Watt part, slipping into the future.

Source

Doesn't sound good. Cutting Fermi from 512 stream processors to 448. Confirmed 225W. Read the whole article and draw your own conclusions.

 

[zedman3d]

Source

Doesn't sound good. Cutting Fermi from 512 stream processors to 448. Confirmed 225W. Read the whole article and draw your own conclusions.

Conclusion? Suicide.

 

[philbar71]

Source

Doesn't sound good. Cutting Fermi from 512 stream processors to 448. Confirmed 225W. Read the whole article and draw your own conclusions.

This is for the TESLAS's only!!! The Geforce version WILL have 512SP

have a read over this,

Nvidia Reveals Specifications of Next-Gen Tesla Computing Processors - X-bit labs

Charlie must have forgotten the fact that this is for the teslas only

 

[Puddle Jumper]

If the 448sp version consumes 225w that pretty much guarantees there will be no fermi based dual gpu cards.

 

[Ste]

Not necessarily, they could do what ATI did with the 5970 and clock back memory and Core clocks a bit.

 

[kmote]

Even so the heat output... well it'll certainly be one way of keeping the house warm.

 

[zmatt]

This is for the TESLAS's only!!! The Geforce version WILL have 512SP

have a read over this,

Nvidia Reveals Specifications of Next-Gen Tesla Computing Processors - X-bit labs

Charlie must have forgotten the fact that this is for the teslas only

Actually he didn't say it was for teslas only. He said it was for teslas, he didn't say anything about the state of the desktop card. the dedicated gpgpu cards have always simply been the desktop cards with the video outputs removed. I see no reason to think that the desktop release will be any different.

Even so the heat output... well it'll certainly be one way of keeping the house warm.

Yeah, looks liek i found a replacement for my pentium 4 space heater.

 

[philbar71]

Actually he didn't say it was for teslas only. He said it was for teslas, he didn't say anything about the state of the desktop card. the dedicated gpgpu cards have always simply been the desktop cards with the video outputs removed. I see no reason to think that the desktop release will be any different.





Yeah, looks liek i found a replacement for my pentium 4 space heater.

Carlie just said "fermi" but X-bit says for teslas only.

Nvidia Reveals Specifications of Next-Gen Tesla Computing Processors - X-bit labs

The flagship Nvidia Fermi “GF100” graphics processor will feature 512 stream processing engines (which are organized as 16 streaming multi-processors with 32 cores in each) that support a type of multi-threading technology to maximize utilization of cores and deliver extreme computing power. Each stream processor has a fully pipelined integer arithmetic logic unit (ALU) and floating point unit (FPU). The top-of-the-range chip contains 3 billion of transistors, features 384-bit memory GDDR5 memory controller with ECC and features rather unprecedented (for GPUs) 768KB unified level-two cache as well as rather complex cache hierarchy in general. Naturally, the Fermi family is compatible with DirectX 11, OpenGL 3.x and OpenCL 1.x application programming interfaces (APIs). The new chips will be made using 40nm process technology at TSMC.

Also, on the NVIDIA website it says Geforce Fermi will have 512 SP.

And also think about how much stress these tesla cards will be put through, they have to be run maxed out 24/7 and be 100% stable.

 

[Fat.Clown]

I just want to see what it can do already......

Nvidia sure does know how to keep us interested and guessing and wanting more

 

[Fat.Clown]

If the 448sp version consumes 225w that pretty much guarantees there will be no fermi based dual gpu cards.

The Turkish website Donanimhaber has recently published a new video interview with Luciano Alibrandi, the Director of PR at NVIDIA.

Here are some highlights from the video:
According to Alibrandi,
- Fermi based GPUs will be the fastest solutions in the market;
- We are very happy to see internal test results of Fermi;
- Fermi architecture developing for every single segment, and dual GPU is also possible;
- We are very happy to work with TSMC but always looking for another opportunities;
- ION 2 and Tegra 2 are very near to launch.
You may click here for the video.

src= "Expreview"