High-performance workloads demand on-package integration of heterogeneous processing units, on-package memory, and communication infrastructure to meet the demands of the emerging compute landscape. Applications such as artificial intelligence, machine learning, data analytics, 5G, automotive, and high-performance computing are driving these demands to meet the needs of cloud computing, intelligent edge, enterprise, and client computing infrastructure. On-package interconnects are a critical component to deliver the power-efficient performance with the right feature set in this evolving landscape. Universal Chiplet Interconnect Express (UCIe), is an open industry standard with a fully specified stack that comprehends plug-and-play interoperability of chiplets on a package; similar to the seamless interoperability on board with well-established and successful off-package interconnect standards such PCI Express®, Universal Serial Bus (USB)®, and Compute Express Link (CXL)®. UCIe enables co-packaged optics that can be used to connect across servers in a Rack and Pod to realize resource sharing and dis-aggregation using CXL protocol. In this talk, we will discuss the usages and key metrics associated with different technology choices in UCIe. We will also delve into the different layers as well as the software model associated with UCIe along with the compliance and interoperability mechanisms. We will also discuss how this open standard could potentially evolve to incorporate additional usage models in the future.
SoC Construction Using Universal Chiplet Interconnect Express (UCIe): A Game Changer
Emerging Deep Learning/ Machine learning and cloud native Applications at data center scale demand terabytes of data flowing across the storage/ memory hierarchy, straining interconnect bandwidth a
- Scott ShadleySolidigm Technology, SNIA
- Mats ObergMarvell Technology
- Pulkit JainAMD (Advanced Micro Devices)
- Heiner LitzUniversity of California, Santa Cruz (UCSC)
- Angelos ArelakisZeroPoint Technologies
Rapidly increasing data sizes, the high cost of data movement, and the advent of fast, NVMe-over-fabric based flash enclosures have led to the exploration of computation near flash for more efficie
Gary Grider will kick off the talk with a brief background of the challenges currently faced in mass storage systems, and why it is so difficult for modern S3 based workloads to utilize them.
- Gary GriderLos Alamos National Laboratory
As the one of the inventors of NVMe at Fusion-io, David has long been a thought leader in the SSD space.
With the growing trend for PCIe and CXL solutions, there is a need to improve the sideband management path as currently defined using SMBus.
- Myron LoewenSolidigm
- Anthony ConstantineSNIA Technical Council
- Juan OrozcoIntel