AGENDA

Read Abstract

The presentation starts with highlights of TSMC trinity of strengths: Manufacturing Excellence, Technology Leadership and Customer Trust, then the overview of the Open Innovation Platform (OIP) ecosystem and ANSYS/TSMC collaboration over the years. Latest updates on silicon manufacturing capability and process technologies are also presented. Last but not least, 3DIC stacking and advanced packaging technologies are discussed and the latest ANSYS/TSMC design solutions to enable both Silicon and 3DIC for our mutual customers.

Read Abstract

AI compute is the most important computational workload of our generation. AI has risen from obscurity to top-of-mind, with widespread and growing applications. However, it is profoundly computationally intensive. A report by OpenAI shows that compute required to train the largest models is doubling every 3.5 months, a rate 25,000 times faster than Moore’s Law.

This voracious demand for compute means that AI is constrained not by applications or ideas, but by the availability of compute. Testing a single new hypothesis — training a new model — takes weeks or months and can cost hundreds of thousands of dollars in compute time. This is a significant drag on the pace of innovation. Google, Facebook, and others have noted that long training time is the key impediment to progress in AI - many great ideas are ignored because they take too long to train.

Dhiraj Mallick, VP of Engineering and Business Development at Cerebras Systems, will discuss how AI’s true potential can be realized through eliminating this primary impediment to the advancement of AI — by reducing the time it takes to train models from months to minutes, from weeks to seconds. Cerebras recently introduced CS-1, which is comprised of their Wafer Scale Engine (WSE), the first and only trillion transistor processor for AI applications, the CS-1 system, which delivers power, cooling and data to the WSE, and the Cerebras software platform that enables quick deployment of the full system and allows researchers to use their existing software models without modification.

In this session, Mallick will share perspective on the state of the AI industry and technologies that will enable AI to continue to rapidly grow and evolve.

Read Abstract

Moore’s law may be slowing; however, it is still expected to have life for the next several years primarily enabled by advances in patterning such as EUV. That said, logic performance for the same power is also slowing down. As we enter this fifth wave of computing, we are witnessing massive demands for ever increasing computational power. Edge compute, 5G and beyond, IoT, Data and AI—to name but a few—are changing the way we think of designing IP and systems to solve the workloads of tomorrow. We see more and more examples of systems being built that use the integration techniques that are enabled by 2.5D and 3D connectivity. Heterogenous integration that is unfolding is being accelerated by 2.5D and 3D technology. This creates challenges around systems integrations and chip design that must take into account package analysis and designs. New ways are required for defining systems, and new considerations and tooling for design and analysis when delivering these complex but optimized solutions. We will discuss the challenges ahead.

Read Abstract

This presentation details key industry and market trends for 5G and beyond, and corresponding technology, architecture and research challenges and opportunities.

Read Abstract

As we approach the limitations of Moore's law scaling, quantum computing is gaining traction as an alternate information processing paradigm. This talk will examine the quantum annealing algorithm, discuss D-Wave's implementation of a 2000-qubit processor and introduce a few real-world problems that have been investigated with that processor.

Read Abstract

The world’s appetite for analyzing massive amounts of data is growing dramatically. The computation demands of these abundant-data applications, such as deep learning, far exceed the capabilities of today’s computing systems, and can no longer be met by isolated improvements in transistor technologies, memories or integrated circuit architectures alone. We must create transformative NanoSystems which exploit unique properties of underlying nanotechnologies to implement new architectures. This talk will present the N3XT (Nano-Engineered Computing Systems Technology) approach that enables such NanoSystems through: (i) new computing system architectures leveraging emerging (logic and memory) nanotechnologies and their dense 3D integration with fine-grained connectivity for computation immersed in memory, (ii) new logic devices (such as carbon nanotube field-effect transistors for high-speed and low-energy circuits) as well as high-density non-volatile memory (such as resistive RAM that can store multiple bits inside each memory cell), amenable to (iii) ultra-dense (monolithic) 3D integration of thin layers of logic and memory devices that are fabricated at a low temperature. N3XT is not an academic concept -- N3XT hardware prototypes have been demonstrated in commercial silicon facilities. N3XT NanoSystems target 1,000X system-level energy-delay-product benefits especially for abundant-data applications. Such massive benefits enable coming generations of applications that push new frontiers, from deeply-embedded computing systems all the way to the cloud.

Read Abstract

Over the past 50 years, Ansys has become a leader in engineering simulation software. The world around us is governed by the laws of physics which are captured by equations that model various physics; we solve these equations using numerical methods such as finite element analysis and finite difference methods. In the past 50 years, the world of Artificial Intelligence has progressed from Expert Systems to Machine Learning to Deep Learning. In this talk we will explore the use of AI, Machine Learning and Deep Learning to improve engineering simulation around four use cases: (1) Improving Customer Productivity (2) Augmented Simulation (3) Revolutionizing engineering design and (4) Business Intelligence. We will discuss the use of data-driven and physics informed neural network methods for simulation as well as machine learning based partial differential equation solvers that can speed up engineering simulation by several orders of magnitude. We will show early results of our AI/ML journey in the world of simulation.