They include Alphawave, an expert in high-speed connectivity and a developer of IP solutions that meet the needs of customers in data centres, compute, networking, AI, 5G, autonomous vehicles and storage, and Rambus, a SIP provider specialising in high-speed interconnects supporting multi-gigabit rates (2.5G, 5G, 8G, 16G, 25G, 32G, 64G), and protocols such as PCI Express (PCIe), CXL and CCIX.
Tachyum will leverage Alphawave’s AlphaCORE Long-Reach (LR) Multi-Standard-Serdes (MSS) IP, which is high-performance, low-power, DSP-based PHY with speeds up to 112Gbps. Alphawave will also deliver complete Ethernet and PCIe IP subsystems.
According to Dr. Radoslav Danilak, founder and CEO of Tachyum, “Working with partners like Alphawave and Rambus we are able to access industry-proven solutions, deliver smooth IP integration and the ability to execute on schedule and target in a much shorter time. By leveraging their IP as part of our Prodigy solution, we will be able to deliver the world’s first universal processor to market faster so that we can best address the growing needs of AI, HPC and hyperscale data centres.”
The Prodigy processor can run HPC applications, convolutional AI, explainable AI, general AI, bio AI, and spiking neural networks, as well as normal data centre workloads, on a single homogeneous processor platform, using existing standard programming models.
According to Tachyun, without Prodigy, hyperscale data centres will have to use a combination of disparate CPU, GPU and TPU hardware, for different workloads, creating inefficiency, expense, and the complexity of separate supply and maintenance infrastructures.
Using specific hardware dedicated to each type of workload results in underutilisation of hardware resources, and more challenging programming, support, and maintenance.
Prodigy will have the ability to seamlessly switch between these various workloads and will help to dramatically change the competitive landscape and the economics of data centres.