LAS VEGAS–(BUSINESS WIRE)–Tachyum™ Inc. today announced that it is nearing design completion of its Prodigy Universal Processor, further ensuring that hyperscale data centers, supercomputer and next generation AI system designers, will finally have the disruptive universal computing fabric to deliver beyond state-of-the-art performance.
Tachyum’s ability to achieve Prodigy’s 99 percent completion with a stable netlist layout and Clock Tree Synthesis (CTS) implemented is a last netlist milestone before final netlist and its tape-out. Tachyum has successfully compiled its Prodigy design to an FPGA emulation, moving it one step closer to meeting its goal of achieving production later this year.
Prodigy has the ability to correctly execute instructions directly from DDR5 memory through coherent mesh with the Prodigy core producing correct results, as well as the creation of an in-house CTS that provides better latency and skew. The company also confirmed that Prodigy maintains netlist clock speed targets with no die size growth from its targets to ensure chip stability. With the Prodigy Software Emulation Systems currently available, a FPGA-based hardware emulation will be announced shortly.
“There are a number of industries and sectors that are anxiously awaiting the deployment of hyperscale-ready chips to overcome the limitations that today’s processing solutions simply cannot overcome,” said Dr. Radoslav Danilak, Tachyum founder and CEO. “The march to 99 percent completion has been reached in leaps and bounds rather than small steps. What was once projected to be years away is now only months away, as Prodigy continues to surpass milestone after milestone. We look forward to doing DFT scan chain insertion and reaching 100 percent completion next quarter and the move to production of Prodigy in the 2nd half of this year.”
Tachyum’s Prodigy can run HPC applications, convolutional AI, explainable AI, general AI, bio-AI, and spiking neural networks, plus normal data center workloads, on a single homogeneous processor platform, using existing standard programming models.
Without Prodigy, hyperscale data centers must use a heterogeneous hardware fabric, consisting of CPU, GPU, TPU processors, to address these different workloads, creating inefficiency, expense, and increasing the complexity of supply and maintenance challenges. Using specific hardware dedicated to each type of workload (e.g. data center, AI, HPC), results in underutilization of hardware resources, more challenging programming, software integration & maintenance, as well as increased hardware maintenance challenges. Prodigy’s ability to seamlessly switch among these various workloads dramatically changes the competitive landscape and the economics of data centers.
In hyperscale data centers, Prodigy significantly improves computational performance, energy consumption, hardware (server) utilization and space requirements compared to existing processor chips currently provisioned. As the world’s first universal processor, it also runs legacy x86, ARM and RISC-V binaries in addition to its native Prodigy code. With a single, highly efficient processor architecture, Prodigy delivers industry-leading performance across data center, AI, and HPC workloads, outperforming the fastest Xeon processors while consuming 10x lower power (core vs. core), as well as outperforming NVIDIA’s fastest GPU in HPC, as well as AI training and inference. A mere 125 HPC Prodigy racks can deliver 32 tensor EXAFLOPS.
Prodigy’s 3X lower cost per MIPS and its 10X lower core power translate to a 4X lower data center Total Cost of Ownership (TCO), delivering billions of dollars in annual savings to hyperscalers. Since Prodigy is the world’s only processor that can switch between data center, AI and HPC workloads, unused servers can be used as CAPEX- free AI or HPC cloud resources, because the servers have already been amortized. Prodigy will also allow Edge developers for IoT to exploit its low power/high performance, along with its simple programming model, to deliver efficient high- performance AI to the edge.
Parties interested in evaluating Prodigy software emulation systems can visit https://www.tachyum.com/webhosting for more information.
Tachyum is building the world’s fastest AI supercomputer to enable data centers that are more powerful than the human brain. Its soon-to-be-launched Prodigy Universal Processor delivers industry-leading performance, cost and power benefits to a $50B market that is expected to grow at 20 percent a year. Early adopter customers and partners can use Prodigy software emulation systems today that will enable them to transition their existing applications that demand high performance and low power to run optimally on Prodigy processors, which ship in volume later this year, with fully functional FPGA emulation system boards also available for pre-order. To enroll in these programs or to sign up for the company’s quarterly newsletter, visit https://tachyum.com.