Radeon Instinct MI25 Launches + specifications
Click here to post a comment for Radeon Instinct MI25 Launches + specifications on our message forum
SHS
Denial
Kaarme
SHS
Truder
SHS
Denial
CUDA has been able to address a unified memory pool since CUDA 6, which included both Kepler/Maxwell. They improve it's ability/performance each gen and I don't know the performance characteristics compared to AMD's HBCC, but Nvidia definitely offers the functionality.
That being said, the need for higher memory bandwidth on the GV100 is probably due to the tensor cores. Tensor operations are heavily dependent on memory bandwidth:
https://www.extremetech.com/computing/247199-googles-dedicated-tensorflow-processor-tpu-makes-hash-intel-nvidia-inference-workloads
Aura89
Truder
solo16
I'm curious about the double precision figure...isn't that suppose to be half of the single precision?
ChicagoDave