06-02-2015, 10:59 AM
decent read
thanks
this part
People dont seem to realize that nvidia sells 3 GPUs to every 1 AMD sales. He straight up says there is a capacity issue with HBM, he is probably not making that up. AMD seems to be struggling with something when it comes to fiji. I had real high hopes for it but there seems to be some pretty serious issue(s).
Capacity may be one of them.
thanks
this part
Quote:When asked about high bandwidth, or stacked memory for Pascal, Huang quickly touted the Maxwell memory architecture and then said that what matters is performance and efficiency. The future will likely hold stacked memories, but for now the cost of that memory is high and the availability is low. "It's a little too early to use it," he said.
People dont seem to realize that nvidia sells 3 GPUs to every 1 AMD sales. He straight up says there is a capacity issue with HBM, he is probably not making that up. AMD seems to be struggling with something when it comes to fiji. I had real high hopes for it but there seems to be some pretty serious issue(s).
Capacity may be one of them.