The 1st International workshop on the High Performance Chiplet and Interconnect Architectures (code named “HipChips”), organized by the OCP Open Domain Specific Architecture Project Community, is a new workshop targeting research between academia and industry. This workshop helps researchers share the latest progress on chiplet-powered architectures for data-intensive applications and ML/HPC-motivated chiplet designs and helps promote the open chiplet standards to foster collaborations on further development of the chiplet ecosystem. The call for papers to present at the workshop is officially open.
The International Symposium on Computer Architecture (ISCA) is the premier forum for new ideas and research results in computer architecture. In June of 2022, the 49th edition of ISCA will be held in New York City, New York, USA. Conference dates are June 11-15, 2022.
The Open Compute Project Foundation (OCP) was initiated in 2011 with a mission to apply the benefits of open source and open collaboration to hardware and rapidly increase the pace of innovation in, near and around the data center’s networking equipment, general purpose and GPU servers, storage devices and appliances, and scalable rack designs. OCP’s collaboration model is being applied beyond the data center, helping to advance the telecom industry & EDGE infrastructure. Learn more at www.opencompute.org. OCP’s ODSA Project Community’s mission is to offer a new design option to heterogeneous integrated systems. ODSA Community is proposing a low-cost, high performance open-accelerator architecture to address the full stack of requirements to develop a DSA.
Schedule
Call for workshop papers: Feb 15th
Website page goes live: Feb 15th
Submission deadline: March 31st
Submission acceptance: April 15th
Agenda Publication: May 1st
Final Papers presentations due by: May 13th
Content review and final feedback: May 26th
Workshop date: June 11th or 12
Background
Machine learning (ML), high performance computing (HPC), and the convergence of both are becoming the major driving force to define future computer architectures in both data center and edge. As performance requirements of workloads have catapulted, heterogeneous computing with domain-specific accelerators (DSA) is deemed as a new computing paradigm to meet the computation demand in the post-Moore era.
While an accelerator architecture is still evolving to continuously integrate more components to boost its computing horsepower, the increasing cost of silicon results in the rise of chiplet architectures.
As a promising alternative to advance a chip design, chiplets take advantages of the recent development of packaging technologies to reduce the complexity of traditional monolithic system-on-a-chip (SoC) design by improving system-level interconnection density and reducing power consumption via mix-and-matching existing or new components and integrating them into a single package. The modularized approach presumably can shorten the development time and improve yield to lower the manufacturing costs. However, one of the biggest challenges industry currently faces is lack of standards and tools to allow different pieces of silicon across vendors to be tied together and work seamlessly through a common interface.
At the same time, as individual devices continue to shrink and more heterogeneous chiplets are integrated, innovations on chiplet-based computing architectures will be required. Though communication between chiplets is typically slower than on-chip communication, distances are shorter and there might be more conduits for inter-chip signals. Thus, collectively inter-chiplet communication may be faster with less energy consumption. So how to distribute data among chiplets and optimize data movement for efficient spatial parallel processing is another key to success.
ODSA’s goal is to create an open chiplet marketplace that allows systems in packages to be built from building blocks from multiple vendors with speed and simplicity to enable shipping new solutions faster. To achieve this, the ODSA strategy is centered on following three core areas:
· Area 1: Enable open die to die interfaces to reduce barrier for interoperation
· Area 2: Create reference designs as starting points for allowing technology development
· Area 3: Define business reference workflows for enabling reusable, open practices
Submission Format
We request all submitters to use the following format for their workshop talk submissions:
– Title of Talk
– Presenters and affiliations (name, company name, title, email, phone, location)
– Category:
· Chiplet-based accelerator level parallelism (ALP)
· Chiplet architecture for large scale system design
· Physical and logical inter-die interface design for heterogeneous architectures
· Coherent and non-coherent data sharing protocols via fast chiplet interconnection
· Chiplet architectures for in-memory computing and other emerging technologies
· ODSA-based 3D architecture for efficient ML acceleration
· Chiplet-based secure computing
· Power evaluation and performance modeling of chiplet architecture
· Software optimization framework with fast inter-chiplet network
· Chiplet topology aware ML optimizations
· Scheduling for massive heterogeneous chiplet-based processors
· Electro-optical Chiplet Interconnects
· Bootstrapping Chiplet ecosystems
· Other
– Abstract summary (1-2 pages):
· Include relevance to HipChips focus
· Brief abstract or the summary of the talk. What is the talk about?
· No proprietary information or confidential info
· Technology centric – not a marketing/product pitch
Learn more about the workshop and learn how to submit your paper for a speaking spot here: https://www.opencompute.org/events/upcoming-events/ocp-at-the-isca-conference
Submit your paper by email to: ISCAchiplets@opencompute.org by March 31st.