Hyperscale Datacenters

Hyperscale Datacenters

Tachyum’s Prodigy processor will enable hyperscale data centers, its primary market, to become low cost, energy efficient universal computing centers. Hyperscale data centers with the Prodigy universal processors will reduce their performance per TCO$ (Total Cost of Ownership) by a factor of up to 12x – saving each hyperscale customer billions of dollars per year.

2-socket OCP Tioga-Pass like server

2-socket OCP Tioga-Pass like server

Prodigy’s industry-leading performance, across data center, AI, and High-Performance Computing (HPC) workloads, is a game-changer. With Prodigy chips idle data center servers can be powered up as AI networks that can deliver cutting-edge AI performance without over-provisioning. Alternatively, these same idle Prodigy-powered servers can just as easily run HPC applications that will deliver ExaFLOPS (a billion, billion floating point operations per second) level performance. Prodigy delivers all of this at up to 12x performance per TCO$ and up to 6x performance per watt than the highest performing GPGPU, with a compete software stack for out of the box operation, including common data center applications ported to Prodigy native ISA (Instruction Set Architecture) and a dynamic binary emulator that enables legacy x86 applications to run at Xeon speed.