Old Cuda Cards on 1.5
Forum rules
Please add your OS and Hardware Configuration in your signature, it makes it easier for us to help you analyze problems. Example: Win 7 64 | Geforce GTX680 | i7 3770 | 16GB
Please add your OS and Hardware Configuration in your signature, it makes it easier for us to help you analyze problems. Example: Win 7 64 | Geforce GTX680 | i7 3770 | 16GB
As you can see here, the Tesla C1060 has compute capability 1.3 which means it's unfortunately not supported in Octane 1.5.cuda wrote:I know the Quadro cards have been dropped, but will 1.5 run with the old Tesla 1060c's in some configuration?
In theory there is no difference between theory and practice. In practice there is. - Yogi Berra
@abstrax :
Do you think that Compute capability 2.0 will be supported for a long time ? I ask because I am worried : currently I have two GTX 580 3GB and my old Workstation would not support more recent cards.
Do you think that Compute capability 2.0 will be supported for a long time ? I ask because I am worried : currently I have two GTX 580 3GB and my old Workstation would not support more recent cards.
French Blender user - CPU : intel Quad QX9650 at 3GHz - 8GB of RAM - Windows 7 Pro 64 bits. Display GPU : GeForce GTX 480 (2 Samsung 2443BW-1920x1600 monitors). External GPUs : two EVGA GTX 580 3GB in a Cubix GPU-Xpander Pro 2. NVidia Driver : 368.22.
Yes, I think it will be supported for quite some time. The differences between Fermi (2.x), Kepler (3.x) and Maxwell (5.x - when it will work) are not as big as the difference between Tesla (1.x) and Fermi. Fermi was really a big breakthrough in GPU computing.ROUBAL wrote:@abstrax :
Do you think that Compute capability 2.0 will be supported for a long time ? I ask because I am worried : currently I have two GTX 580 3GB and my old Workstation would not support more recent cards.
The biggest problem with Tesla was that the CUDA toolkit uses a completely different compiler suite and that the compilation took more than 3 hours in the end (if it didn't crash before). We then found more and more compiler issues which we couldn't work around, because even a small change requires a full rebuild. Tesla also didn't allow some optimizations we made.
In theory there is no difference between theory and practice. In practice there is. - Yogi Berra
Thanks. By the way, my workstation died just after my last post... Murphy's fault... I don't know yet if it is repairable.
French Blender user - CPU : intel Quad QX9650 at 3GHz - 8GB of RAM - Windows 7 Pro 64 bits. Display GPU : GeForce GTX 480 (2 Samsung 2443BW-1920x1600 monitors). External GPUs : two EVGA GTX 580 3GB in a Cubix GPU-Xpander Pro 2. NVidia Driver : 368.22.