View Full Version : nVidia GT300's Fermi architecture unveiled: 512 cores, up to 6GB GDDR5.

09-30-2009, 04:16 PM

"When it comes to boards themselves, you can expect to see configurations with 1.5, 3.0 GB and 6GB of GDDR5 memory, but more on that a little bit later."

"TSMC was in charge of manufacturing the three billion transistor mammoth, but it didn't stop there. Just like the G80 chip, nVidia GT300 packs six 64-bit memory controllers for a grand total of 384-bit"

"Ferni architecture natively supports C [CUDA], C++, DirectCompute, DirectX 11, Fortran, OpenCL, OpenGL 3.1 and OpenGL 3.2. Now, you've read that correctly - Ferni comes with a support for native execution of C++. For the first time in history, a GPU can run C++ code with no major issues or performance penalties and when you add Fortran or C to that, it is easy to see that GPGPU-wise, nVidia did a huge job."

09-30-2009, 04:32 PM
The whitepaper is up: http://www.nvidia.com/content/PDF/fermi_white_papers/NVIDIAFermiArchitectureWhitepaper.pdf

09-30-2009, 05:11 PM

09-30-2009, 06:24 PM
Can't wait to see one of thse with CORE.

09-30-2009, 07:33 PM
OMG! The LW devs really need to consider supporting this nvidia series. It should support LW's renderer natively with very litttle to none engine changes. Also, I hope newtek doesn't buy into an exclusivity contract with Nvidia's Quadro if LW does indeed get support for cGPU rendering, Autodesk really pisses me off when it comes to only using quadro when consumer cards can damn well get the job done.

09-30-2009, 09:36 PM
So I wonder how those CUDA/OpenCL renderers will transfer over? I would love to see the performance on those puppies.

10-01-2009, 03:05 AM
Hello, now this is interesting:

Unified Address Space enables Full C++ Support

Fermi and the PTX 2.0 ISA implement a unified address space that unifies the three separate address spaces (thread private local, block shared, and global) for load and store operations.

In PTX 1.0, load/store instructions were specific to one of the three address spaces; programs could load or store values in a specific target address space known at compile time. It was difficult to fully implement C and C++ pointers since a pointer’s target address space may not be known at compile time, and may only be determined dynamically at run time.
With PTX 2.0, a unified address space unifies all three address spaces into a single, continuous address space. A single set of unified load/store instructions operate on this address space, augmenting the three separate sets of load/store instructions for local, shared and global. The 40-bit unified address space supports a Terabyte of addressable memory, and the load/store ISA supports 64-bit addressing for future growth.

The implementation of a unified address space enables Fermi to support true C++ programs. In C++, all variables and functions reside in objects which are passed via pointers. PTX 2.0 makes it possible to use unified pointers to pass objects in any memory space, and Fermi’s hardware address translation unit automatically maps pointer references to the correct memory space.

Fermi and the PTX 2.0 ISA also add support for C++ virtual functions, function pointers, and ‘new’ and ‘delete’ operators for dynamic object allocation and de-allocation. C++ exception handling operations ‘try’ and ‘catch’ are also supported.

10-01-2009, 03:28 AM
C++ lol, awesome, we will see what developers will do with that... and ATI reaction :D