A member of the audience asked Gelsinger if he agreed with the fact that a quarter of servers could be shipped around the low-power ARM architecture.
It is the sort of question Gelsinger does not like much. For those with long memories, in 2008, IBM PowerPC chips powered EMC’s storage arrays. But after Gelsinger arrived he kicked them all out and all four of EMC’s product lines, Symmetrix, Clariion, Celerra and Centera, shifted to the Intel Xeon processor.
Gelsinger said that the situation is unlikely to change, even if ARM could deliver workloads at a fraction of the power of an X86 chip.
He said that that even if the power of the core was zero, there was still the server workload, I/O memory to worry about.
“The X86 core—take a low power core, you’re only talking two or three watts to a core, at the lowest end is close to a watt. Take that to zero, it doesn’t matter—you’ve still got memory power, I/O power, et cetera associated with that. So fundamentally I don’t think the math makes sense when you go look at it,” he said.
He said that EMC’s arrays are homogeneous, running on the same architecture and if you changed that you added unnecessary complexity.
It means that IT staff can’t schedule across the whole pool, can’t pick up workloads and move them and can’t power them down. Failing servers over to other data centres is tricky and it adds costs to a cloud computing model.
Gelsinger said that software could support any emerging model that actually met the math requirements.