llmda newsletter ad (2)

A Different Angle on Co-Simulation for Systems

A Different Angle on Co-Simulation for Systems
by Bernard Murphy on 05-06-2026 at 6:00 am

FMI use cases

Co-simulation, two or more simulations running concurrently in some manner, is not a new idea. I have written before about multiphysics systems able to model thermal, stress, CFD and other factors simultaneously. I just read a white paper from Siemens based on a different method, using an open standard called the Functional Mockup Interface (FMI) to connect simulators/models to co-analyze mechatronic and other systems across a range of multidiscipline analyses, going beyond what I have seen in multiphysics systems. My take is that looks like a more total systems-centric view to multi-domain simulation than chip-centric approaches.

About FMI

FMI is a standard created within the Modelica Association, an organization founded in 2000 in Sweden, with the intention to simplify the creation, storage, exchange and (re-) use of dynamic system models of different simulation systems for abstract model (e.g. MatLab)/software/hardware-in-the-loop simulation, for cyber physical systems, and other applications. The list of FMI members is impressive: Bosch, Dassault, Siemens, Synopsys/Ansys, Ampere, Saab, Airbus, Caterpillar, Hyundai, GM, Boeing, NVIDIA, VW, Volvo, MathWorks, Maplesoft and many more.

There are two use-cases: standalone FMUs and tool-coupling FMUs.  The standalone approach allows a component provider to build an abstracted model of an IP based on simulations within a specific domain. A system builder can then use such a model in their system analysis without revealing implementation details and without need for licenses used in building that abstracted model. A tool-coupling model provides more flexibility through FMI defined API interfacing between simultaneously running simulators. Both methods depend on a user-defined time-step to determine communication frequency.

Which approach will be most effective will depend on the application. The Siemens white paper provides examples for both use-cases.

A mechatronic application

The paper illustrates with three applications. The first of these is a mechatronic example for which the electrical side is a circuit to control a stepper motor. This circuitry is modeled in HyperLynx AMS which is FMI compatible. The mechanical part connects the motor output to a gear reducer, then a winch, raising or lowering a weight suspended on a rope. I’m guessing this is not a typical application, more likely an artificial use case to illustrate a capability without revealing customer proprietary details in real designs. The mechanical part is modeled in Siemens Simcenter Amesim. Sensors feedback winch RPMs and the airgap between the weight and the ground.

This method uses a tool-coupling FMU, here by generating an FMU model for the circuitry which can be inserted into the Amesim mechanical model. Remember in tool-coupling cases this model is an interface between the mechanical simulation and the electrical simulation, both of which will be running.

The paper illustrates the point of running this joint simulation in first observing that the rotational velocity of the gear shift is noisy and the weight hits the ground after a few cycles. They replace the stepper motor with a stronger model and reduce the weight, following which simulations show much cleaner behavior and the weight doesn’t hit the ground. Here and in the standalone methods users will need to experiment with time-step choices to find an optimum balance between accuracy and analysis throughput.

A control system application

The white paper illustrates a standalone FMU example with a power convertor example. The controller is designed through Altair Twin-Activate and MathWorks and exported as a standalone FMU. This is then imported into HyperLynx AMS to model the power convertor electronics around the controller. HyperLynx can run simulations with this FMU model without need for co-simulation. Again, a user may need to fine-tune a time-step choice for optimum results.

Very interesting to see a method for handling multi-domain simulations outside conventional multiphysics applications. I can see why this would be popular with system builders who have preferred simulator choices in each domain yet need to be able to stitch them together for full-system analysis. You can download the whitepaper HERE.

Also Read:

Siemens U2U 3D IC Design and Verification Panel

Solving the EDA tool fragmentation crisis

Complex PCB signoff challenges


Synopsys and TSMC Deepen AI Design Alliance: What It Means

Synopsys and TSMC Deepen AI Design Alliance: What It Means
by Kalar Rajendiran on 05-05-2026 at 10:00 am

Synopsys Powering the next generation of AI

A recent announcement from Synopsys signals a meaningful escalation in the race to build next-generation AI hardware. The expanded collaboration between Synopsys and TSMC brings together silicon-proven IP, AI-driven design tools, and cutting-edge manufacturing processes in a tightly integrated effort to accelerate high-performance computing (HPC) and AI system development. More than a routine partnership update, the move reflects a broader industry transition toward ecosystem-level innovation, where success depends on how well design, IP, and fabrication technologies align from the outset.

What Was Announced

At the core of the announcement is a three-part expansion of capabilities spanning IP, design flows, and system-level enablement.

Synopsys is advancing silicon-proven interface IP validated on TSMC’s most advanced nodes, including 3nm and emerging 2nm-class processes. These include next-generation standards such as M-PHY v6.0 which is now achieving industry-first low-power silicon bring-up on N2P, alongside tapeouts of 64G UCIe IP and 224G high-speed interconnect IP. Together, these technologies form the backbone of AI chips that must move massive volumes of data with minimal latency and power overhead, particularly in bandwidth-constrained environments.

The companies are also extending certified electronic design automation (EDA) flows with a sharper emphasis on increasingly agentic AI-driven optimization. Collaboration on run assistance within Synopsys Fusion Compiler, leveraging TSMC’s A14 process and NanoFlex Pro architecture, is aimed at improving power, performance, and area (PPA) while boosting design productivity. This signals a shift from passive AI assistance toward more active, decision-guiding systems that can materially impact how chips are designed at advanced nodes.

Beyond individual dies, the partnership continues to push into advanced packaging and system-level integration. Synopsys’ 3DIC Compiler platform is now enabling productivity improvements for TSMC’s CoWoS technology at interposer sizes reaching up to 5.5 times the reticle limit, underscoring the scale of modern multi-die designs. This is complemented by multiphysics simulation capabilities that address thermal, electrical, and optical interactions. These requirements are becoming essential as chips evolve into tightly integrated systems.

The announcement also highlights expansion into new application domains. In automotive, Synopsys is offering a UCIe IP solution compliant with ASIL B functional safety requirements on TSMC’s N5A process, marking a significant step toward enabling chiplet-based architectures in safety-critical environments. Meanwhile, advancements in M-PHY IP are targeted at next-generation mobile and storage applications, including smartphones that demand both high performance and power efficiency.

Finally, the collaboration advances AI infrastructure through co-packaged optics. Multiphysics design enablement for co-packaged optical systems, including TSMC’s COUPE design flow, spans optical path simulation, electromagnetic extraction, and system-level analysis, and is paired with 224G IP designed to support optical Ethernet and emerging interconnect standards such as UALink. Together, these capabilities directly address the growing bandwidth and energy challenges facing large-scale AI systems.

Why This Matters for AI Hardware

The significance of this partnership lies in how it tackles the core constraints of modern AI workloads. As compute performance scales, the bottlenecks have shifted toward data movement, power efficiency, and system integration. By combining high-speed IP, agentic AI-driven design tools, and advanced packaging technologies, Synopsys and TSMC are reducing the gap between design complexity and manufacturable silicon.

The introduction of agentic run assistance in EDA tools marks a particularly important inflection point. Rather than simply accelerating existing workflows, these capabilities begin to reshape them, enabling engineers to delegate increasingly complex optimization tasks to AI systems. This has the potential to significantly compress development cycles while improving overall design quality.

Equally critical is the focus on bandwidth. Technologies such as 224G interconnects and co-packaged optics are emerging as key enablers for scaling AI infrastructure, where moving data efficiently is often more challenging than processing it. By integrating these capabilities into both IP and design flows, the partnership addresses one of the most pressing limitations in next-generation AI systems.

The expansion into automotive and mobile markets further underscores the breadth of this strategy. It signals that advanced-node, multi-die, and chiplet-based designs are no longer confined to hyperscale data centers but are beginning to permeate safety-critical and consumer applications as well.

Market And Industry Implications

The expanded alliance reinforces Synopsys’s position as a central player in AI silicon enablement while strengthening TSMC’s ecosystem around its most advanced process nodes. For chip designers, tighter integration between EDA tools and foundry technologies can translate into faster time-to-market and reduced development risk, particularly when targeting cutting-edge nodes.

At the same time, the partnership reflects a broader industry dynamic in which design tools and manufacturing processes are becoming increasingly interdependent. As flows become more deeply optimized and certified for specific nodes, the cost and complexity of switching ecosystems rise. This creates a form of strategic lock-in that benefits tightly aligned partners while raising barriers for competitors.

The Bigger Picture

Taken together, the announcement illustrates a shift in how semiconductor innovation is defined in the AI era. Progress is no longer driven solely by transistor scaling but by the ability to coordinate across multiple layers of the technology stack, from design software and reusable IP to packaging and system integration.

The Synopsys–TSMC collaboration points to a future where chips are conceived not as isolated components but as parts of larger, highly integrated systems spanning data centers, vehicles, and mobile devices. In this landscape, competitive advantage will increasingly depend on how effectively companies can bring together tools, technologies, and partners to deliver complete, optimized solutions.

As AI continues to push the limits of performance and complexity, partnerships like this are likely to define the pace of innovation. The companies that succeed will be those that can bridge the gap between design intent and real-world deployment, turning increasingly sophisticated ideas into scalable, manufacturable systems.

You can access the entire press announcement here.

Also Read:

How to Overcome the Advanced Node Physical Verification Bottleneck

Podcast EP342: The Evolution and Impact of Physical AI with Hezi Saar

WEBINAR: Beyond Moore’s Law and The Future of Semiconductor Manufacturing Intelligence


Siemens U2U 3D IC Design and Verification Panel

Siemens U2U 3D IC Design and Verification Panel
by Daniel Nenni on 05-05-2026 at 6:00 am

IMG 1201
Kalar Rajenderan, Javier dela Cruz, Subi Kengeri, Satish Surana, Jeff Cain

Given the success of the event in Silicon Valley last week, I would expect the Siemens U2U event in Munich to be even bigger. In my experience this has been the best user driven event in 2026 with the deepest customer content. EDA has always been a customer driven industry and it is good to see us recognize that from time to time. Kalar was the moderator on this panel so I was in the front row taking notes.

The semiconductor industry is entering a pivotal phase as it transitions from traditional 2D ICs to 3D ICs and chiplet-based architectures. This shift represents a fundamental evolution in how chips are designed, manufactured, and deployed. Rather than relying solely on shrinking transistors, engineers are now stacking and integrating multiple dies into a single package, enabling higher performance, better power efficiency, and greater system flexibility. While this approach unlocks significant advantages, it also introduces a new set of challenges that must be addressed for widespread adoption.

At its core, 3D integration allows different functional components, such as logic, memory, and accelerators, to be combined in a modular fashion. This enables scalable architectures and significantly improves bandwidth by reducing the distance data must travel between components. It also allows designers to mix and match technologies from different process nodes, optimizing each function independently. As a result, 3D ICs are becoming essential for applications like artificial intelligence, high-performance computing, and data centers, where performance and efficiency are critical.

However, the move to 3D scaling is far from straightforward. One of the most significant challenges is the increased complexity across the entire development lifecycle. In traditional chip design, many issues could be addressed at the component level. In contrast, 3D ICs require a system-level perspective, where interactions between dies, packaging, and the overall system must be carefully managed. Thermal and power considerations, in particular, have become major concerns. As power density increases, heat dissipation becomes more difficult, and inefficient power delivery can lead to both performance limitations and reliability issues.

Another critical challenge is supply chain and manufacturing capacity. The semiconductor industry has experienced rapid growth, with demand accelerating at an unprecedented rate. While this growth is positive, it has also exposed limitations in infrastructure. Building new fabrication facilities and expanding cleanroom capacity takes years, and advanced packaging processes are becoming increasingly complex. Technologies such as hybrid bonding, high-bandwidth memory integration, and large interposers require sophisticated equipment and processes that are not yet widely available. These constraints can create bottlenecks, particularly for smaller companies trying to enter the market.

To navigate these challenges, industry experts emphasize the importance of early architectural planning. In the past, packaging was often treated as a secondary consideration, addressed after the core chip design was complete. This approach is no longer viable. Advanced packaging must now be considered at the very beginning of the design process, alongside system architecture and functionality. Decisions about packaging technology, supply chain partners, and manufacturing processes must be made early to avoid costly redesigns and delays. Designing for manufacturability and yield is especially important, as even small inefficiencies can significantly impact production capacity and cost.

Interoperability and standardization are also key factors in enabling the growth of the 3D IC ecosystem. Efforts to develop open standards for die-to-die communication aim to make it easier to integrate components from different vendors. While these standards can reduce barriers to entry and promote innovation, they are not a complete solution. In practice, achieving seamless interoperability is challenging due to differences in design choices, protocols, and performance requirements. As a result, many high-performance systems still rely on customized interfaces to achieve optimal results, while standards play a more prominent role in mid-range and emerging applications.

Looking ahead, innovation in materials, cooling, and power delivery will be essential to overcoming current limitations. New substrate materials, such as glass, offer improved mechanical stability and finer feature resolution compared to traditional organic substrates. Advanced cooling techniques, including near-chip cooling and novel heat dissipation methods, are being explored to manage increasing thermal loads. Similarly, improvements in power delivery, such as backside power distribution and integrated voltage regulation, are critical for supporting the high current densities required by modern systems.

Another promising area of development is the use of advanced modeling and simulation tools. Multiphysics simulation, which accounts for electrical, thermal, and mechanical interactions, is becoming increasingly important in 3D IC design. By incorporating these analyses early in the design process, engineers can identify potential issues and optimize system performance before manufacturing. Digital twin technology, which creates a virtual representation of the entire system and manufacturing process, is expected to play a major role in improving design accuracy and reducing time to market.

Bottom line: The transition to 3D ICs and chiplet architectures marks a significant turning point in semiconductor innovation. While the benefits in performance, efficiency, and flexibility are substantial, the challenges are equally complex. Success in this new era requires a holistic approach that integrates design, manufacturing, and system considerations from the outset. By investing in early planning, embracing new technologies, and fostering collaboration across the ecosystem, the industry can overcome these challenges and unlock the full potential of 3D integration.

MUNICH, GERMANY | MAY 12, 2026 User2User Europe

Also Read:

Solving the EDA tool fragmentation crisis

Exploring the Hidden Complexity of Modern Power Electronics Design – A Siemens White Paper

Siemens Wins Best in Show Award at Chiplet Summit and Targets Broad 3D IC Design Enablement


Connecting the Dots: Why RISC-V System Design Is Entering a New Era

Connecting the Dots: Why RISC-V System Design Is Entering a New Era
by Kalar Rajendiran on 05-04-2026 at 10:00 am

Andes x Arteris Pre Verified and Silicon Proven SoC Integration

At the recent RISC-V Now event hosted by Andes, the discussion underscored the fact that RISC-V is no longer just about instruction set architecture advantages or customizable cores. The real focus has moved up the stack to system-level design. This is where connectivity, integration, and security define whether an innovation can scale.

This shift reflects a broader reality: modern SoCs are no longer simple, monolithic designs. They are complex, heterogeneous systems that must seamlessly integrate multiple compute domains, memory hierarchies, and specialized accelerators. In this environment, the success of RISC-V depends not only on openness, but on how effectively that openness can be orchestrated into a cohesive and efficient system.

Guillaume Boillet, Vice President of Strategic Marketing at Arteris framed his talk around a central thesis: that RISC-V’s long-term success will hinge not just on open architectures, but on mastering integration, embedding security at the hardware level, adopting true systems thinking, and leveraging deep ecosystem collaboration.

The Hidden Bottleneck: Data Movement and System Complexity

One of the most compelling insights from the presentation is that compute is no longer the dominant constraint in system performance. Instead, data movement has emerged as the primary bottleneck. A significant portion of system energy is consumed simply moving and storing data, especially in GPU-class SoCs

This has profound implications. As workloads like artificial intelligence (AI) and real-time analytics continue to grow, the efficiency of the interconnect fabric becomes just as important as the performance of the compute engines themselves. The architecture must be designed to minimize latency, optimize bandwidth, and reduce power consumption associated with moving data across increasingly complex systems.

At the same time, the rise of chiplets and multi-die architectures introduces new layers of design complexity. What was once contained within a single piece of silicon must now operate across multiple interconnected dies, each potentially optimized for different functions. This transforms connectivity from a supporting role into a central architectural pillar.

RISC-V’s Promise Meets Integration Reality

RISC-V’s flexibility is one of its greatest strengths, but it also introduces a unique challenge: integration. The ability to mix and match IP from different sources creates enormous opportunity, yet it also leads to fragmentation if not managed carefully.

Modern SoCs often incorporate a wide array of IP blocks, each using different communication protocols. Bringing these together into a unified system requires a robust and adaptable interconnect strategy. Without it, the very modularity that makes RISC-V attractive can become a source of inefficiency and risk.

This is where Network-on-Chip (NoC) technologies play a crucial role. By providing a scalable and configurable communication backbone, they enable designers to integrate diverse components while maintaining performance and efficiency. The interconnect effectively becomes the glue that holds the system together, ensuring that all parts can communicate reliably despite their differences.

Automotive and AI: Stress Testing the Architecture

The growing demands of automotive and AI applications highlight just how critical system-level design has become. In automotive systems, especially those supporting advanced driver assistance and autonomous capabilities, architectures must handle a mix of workloads with different safety and performance requirements. Some functions demand strict determinism and compliance with safety standards, while others require high-throughput data processing.

These systems are also evolving toward chiplet-based implementations, further increasing the importance of reliable and scalable interconnects . The ability to manage both coherent and non-coherent data flows across such architectures is essential for ensuring system integrity and performance.

AI workloads present a different but equally demanding challenge. As AI becomes more pervasive, the need for specialized accelerators continues to grow. Integrating these accelerators efficiently into the broader system requires careful orchestration of data movement and memory access. Without a well-designed interconnect, the benefits of these accelerators can be significantly diminished.

The Overlooked Risk: Hardware Security

Another critical theme is the increasing importance of hardware security. Historically, security efforts have focused on software and network layers, but recent vulnerabilities have demonstrated that hardware itself can be a significant point of exposure.

The number of reported hardware vulnerabilities has been rising, reflecting a growing awareness of this issue . As systems become more complex and interconnected, the potential attack surface expands, making it essential to address security at the hardware level from the outset.

This requires new approaches to design and verification, including the ability to identify and mitigate vulnerabilities early in the development process. Hardware security is a foundational requirement for modern SoCs, not an afterthought.

Ecosystem Collaboration as a Force Multiplier

The collaboration between Andes and Arteris illustrates the importance of ecosystem-level solutions in addressing these challenges. By pre-validating the interoperability between processor cores and interconnect technologies, they reduce integration risk and accelerate development timelines.

This kind of partnership reflects a broader trend in the industry toward platform-based design. Instead of building systems from scratch, companies are increasingly relying on pre-validated components that can be assembled into complete solutions. This approach not only improves efficiency but also increases confidence in achieving first-pass silicon success.

From Components to Systems Thinking

The overarching message: the industry must move from a component-centric mindset to a system-centric one. Designing a successful RISC-V-based SoC today requires a holistic understanding of how all parts of the system interact.

It is no longer sufficient to optimize individual components in isolation. Designers must consider how data flows across the system, how different subsystems communicate, and how security is enforced at every level. This shift in perspective is essential for managing the complexity of modern designs.

Summary

RISC-V is well positioned to thrive in this new environment, but its success will depend on more than just its open architecture. It will require robust solutions for connectivity, integration, and security as these aspects are becoming increasingly critical as systems grow in complexity.

The future of RISC-V will be defined not just by its flexibility, but by its ability to deliver complete, scalable, and secure systems. Those who embrace this systems-level approach will be best equipped to lead the next wave of semiconductor innovation.

To learn more, visit Arteris.com

Also Read:

Scalable Network-on-Chip Enables a Modular Chiplet Platform

Renesas Scalable Automotive SoC Design Using Arteris NoC

NXP Expands Arteris NoC Deployment to Scale Edge AI Architectures


Rethinking ECAD IT Infrastructure: From Fragmentation to an Engineering Platform

Rethinking ECAD IT Infrastructure: From Fragmentation to an Engineering Platform
by Kalar Rajendiran on 05-04-2026 at 6:00 am

The semiconductor industry is entering a new phase of complexity. Advanced nodes, heterogeneous integration, and AI-driven design workflows are placing unprecedented demands on engineering teams. While much of the focus remains on tools and methodologies, an equally critical constraint is emerging beneath the surface: infrastructure.

Every IC design company today must make a foundational decision:

How to design, build, and operate the increasingly AI-driven ECAD IT infrastructure required to deliver chips efficiently. Historically, the answer has been to build and manage it internally. But that model is becoming increasingly difficult to sustain.

The Growing Infrastructure Burden

Modern semiconductor workflows depend on a combination of:

  • Distributed compute environments
  • Multiple EDA toolchains from different vendors
  • GPU-intensive AI/ML workloads
  • Strict data security and compliance requirements

Yet the infrastructure supporting these workflows is often fragmented. Teams must stitch together cloud resources, on-prem systems, license servers, and workflow orchestration tools without compromising on uptime and performance.

Cloud providers offer scalable compute, storage, and networking. And EDA vendors provide powerful design tools. But a unified, production-ready vendor agnostic environment is hard to come by for semiconductor engineering. This results in a gap that engineering teams must fill themselves.

The Limits of the Build-It-Yourself Model

To bridge this gap, companies invest heavily in:

  • CAD engineering teams
  • DevOps and cloud specialists
  • Custom scripts and automation frameworks

While this approach provides flexibility, it introduces significant overhead. Infrastructure must be continuously maintained, updated, and debugged. Misconfigurations, workflow failures, and resource inefficiencies are common.

More importantly, this effort does not directly contribute to product differentiation. Engineering teams end up spending time maintaining infrastructure rather than advancing design. As AI-driven workflows accelerate the increase in design complexity, the above burden grows even more.

A Shift Toward Engineering Infrastructure Platforms

An alternative approach is beginning to gain traction: the engineering infrastructure platform.

Rather than assembling infrastructure components manually, teams can deploy a platform that provides:

  • Pre-integrated environments
  • Vendor-neutral tool support
  • Automated orchestration
  • Built-in observability and security

This model abstracts the complexity of infrastructure while preserving flexibility. Tuple Technologies’ Stratos platform is one example of this approach, designed specifically for semiconductor workflows.

Below is a quote from Vamshi Kothur, CEO of Tuple Technologies.

“The Stratos Platform was built to solve the most critical bottleneck in semiconductor innovation: the infrastructure gap. By enabling rapid environment provisioning in minutes rather than weeks and offering a truly vendor-neutral architecture, we empower design teams to scale AI and HPC workloads seamlessly across any self-hosted, cloud or hybrid environment. Our mission at Tuple Tech is to provide a continuous, AI-driven automation layer that eliminates vendor lock-in and manual remediation, allowing engineers to focus on what matters most—accelerating the path to tapeout.”

What Changes with a Platform Approach

Stratos is built on Infrastructure-as-Code (IaC) principles and enables teams to deploy and operate environments across on-premises, hybrid, and cloud configurations.

Key capabilities include:

  • Rapid environment provisioning — in minutes rather than weeks
  • Support for multiple EDA vendors without lock-in
  • Integration of AI and HPC workloads into existing flows
  • Continuous monitoring, alerting, and automated remediation

The impact changes how teams work. Engineers shift from managing infrastructure to focusing on design execution.

CAD teams no longer need to manually manage licenses, debug workflows, or coordinate across fragmented environments. Instead, they operate within a unified platform where infrastructure is automated and observable.

Quantifiable Impact

The benefits of this approach are measurable: (as reported by Tuple Technologies)

  • Up to 70% reduction in infrastructure development time
  • Provisioning in minutes instead of weeks
  • Average 38% reduction in GPU and compute costs through multi-cloud optimization
  • 43% reduction in cloud computing costs in Pegasus sign-off workloads (customer case study)

In addition:

  • License utilization improves through real-time analytics
  • Downtime is minimized through proactive incident management
  • Disaster recovery is accelerated using IaC-based reconstruction

These improvements directly translate into faster design cycles and lower operational costs.

Key Differentiators

Several characteristics distinguish an engineering infrastructure platform from traditional approaches:

Vendor Neutrality: Teams can combine tools from multiple vendors without workflow fragmentation.

Multi-Cloud Optimization: Workloads are dynamically executed where compute resources are most efficient.

Operational Intelligence: Failures are detected and resolved automatically through integrated monitoring and escalation.

Built-In Security: Continuous compliance and threat detection are embedded into the platform.

Domain-Specific Support: Real-time support from engineers familiar with semiconductor workflows ensures rapid resolution of issues.

Why This Matters Now

As semiconductor design becomes increasingly data- and compute-intensive, infrastructure is no longer a secondary concern. It is a critical enabler of engineering productivity.

Companies that continue to rely on fragmented, manually managed environments risk:

  • Slower time-to-market
  • Higher compute and operational costs
  • Reduced engineering efficiency

By contrast, those adopting a platform approach gain:

  • Faster iteration cycles
  • Greater flexibility across tools and environments
  • Improved reliability and scalability

Summary

The semiconductor industry has long focused on advancing tools and methodologies. The next frontier is infrastructure. Moving from fragmented systems to unified engineering platforms represents a fundamental shift. A unified engineering platform can significantly impact productivity, cost, and competitiveness.

Learn more at https://www.tupletechnologies.net/

Also Read:

Tuple Technologies at the 2025 Design Automation Conference #62DAC

CEO Interview with Geoffrey Rodgers of Chameleon Semiconductor

Bronco AI Webinar: Full-Chip SoC Debug in 15 Minutes


CEO Interview with Geoffrey Rodgers of Chameleon Semiconductor

CEO Interview with Geoffrey Rodgers of Chameleon Semiconductor
by Daniel Nenni on 05-03-2026 at 2:00 pm

image (9)

Geoffrey Rodgers spent most of his career at the intersection of semiconductor technology and go-to-market execution, with a focus on scaling businesses and bringing complex solutions to market. He previously led the Analog Go-To-Market motion at Synopsys following the acquisition of Analog Design Automation and held leadership roles at PDF Solutions.

In addition to his semiconductor background, Geoff spent time in enterprise B2B SaaS, where he developed a strong foundation in modern go-to-market models, including segmentation, pipeline development, and building repeatable growth frameworks.

At Chameleon, he is focused on translating technical innovation into scalable, real-world impact in an industry undergoing a fundamental shift toward more flexible, secure, and adaptive silicon architectures.

Tell us about your company.

Modern silicon is still designed as if the future can be fully predicted at tapeout. In reality, standards, threats, and system requirements continue to evolve long after deployment.

Chameleon Semiconductor is focused on solving that gap. We provide embedded FPGA (eFPGA) via user-defined soft IP that brings post-silicon hardware-based programmability into ASICs and SoCs, allowing customers to modify, extend, and future-proof their designs without a respin.

We believe the industry is moving toward a design-for-change model, where flexibility is architected into the system from the start.

Our fabric is delivered as synthesizable RTL, not a hard macro, enabling customers to define exact requirements for their application while maintaining portability across foundries and process nodes. This provides both technical flexibility and supply chain freedom, while also allowing customers to retain tighter control over their IP and where it is manufactured.

Chameleon was founded by a team with deep experience across semiconductor IP, EDA, and system design.

Co-founder, Ken Mai, is a Professor of Electrical and Computer Engineering at Carnegie Mellon University and a recognized leader in digital system design. He has built a prominent research program focused on high-performance and energy-efficient architectures and maintains deep ties into the aerospace, defense, and intelligence communities.

Additionally, Robert Bielby, a recognized authority in FPGA architecture and programmable logic has joined. He has spent decades advancing reconfigurable computing, contributed to high-performance FPGA architectures, holds numerous patents, and has brought complex programmable fabrics from concept through production deployment.

What problems are you solving?

The semiconductor industry is facing a mismatch between design rigidity and real-world change.

Design cycles are long and expensive, but standards, security threats, and system requirements continue to evolve after deployment. Once silicon is taped out, adapting is costly and often requires a respin.

At the same time, customers are facing increasing pressure around IP security and trusted manufacturing. Protecting critical functionality while maintaining flexibility in where and how chips are built has become a growing concern.

We address three core issues.

First, lack of post-silicon flexibility. We enable customers to modify functionality at speed after deployment, versus more traditional software or microprocessor-based approaches, extending product life while maintaining performance.

Second, the cost of getting it wrong. A respin can cost millions and delay programs by months. Our fabric acts as an architectural safety net against that uncertainty.

Third, system fragmentation. As chiplet-based and heterogeneous architectures scale, integrating mismatched protocols and evolving interfaces becomes more complex. We provide a programmable layer that can adapt at those boundaries.

We are enabling a shift from fixed-function silicon to systems that can evolve over time while maintaining control over critical IP.

What application areas are your strongest?

We focus on markets where change is constant and the cost of inflexibility is high.

Aerospace and defense was our initial focus and remains a core market. These systems have long lifecycles, operate in harsh environments, and must respond to evolving threats. They also require strict control over IP, supply chain integrity, and trusted manufacturing environments. Our approach enables customers to maintain control of sensitive functionality while supporting deployment in trusted or onshore fabrication flows.

Our support for radiation-hardened design approaches, combined with the ability to update functionality in the field, aligns well with these requirements.

At the same time, we are expanding into commercial markets where architectural flexibility is becoming critical. Chiplet-based designs are a prime example. As systems are assembled from heterogeneous die, interoperability challenges increase. Our fabric enables protocol adaptation and long-term flexibility at chiplet interfaces.

Security-driven applications are another major driver, particularly around post-quantum cryptography. As standards evolve, maintaining compliance requires hardware-based programmability to support changes without sacrificing performance.

We are also seeing interest in AI-related applications, where rapidly evolving neural network architectures can outpace fixed-function silicon approaches.

Any system where the future cannot be fully predicted at design time, or where control of IP and manufacturing is critical, is a strong fit for our technology.

What keeps your customers up at night?

The common theme is uncertainty.

Customers are being asked to make long-term design decisions in an environment that is changing rapidly. They worry about locking into standards, security algorithms, and architectures that may not hold.

At the same time, supply chain, IP security, and geopolitical concerns are increasing pressure around foundry choice and IP sourcing.

The cost of being wrong is rising, while predictability is declining.

We give customers a way to manage that uncertainty by building flexibility and control directly into their silicon.

We also enable them to respond to new market opportunities that may emerge after tapeout or deployment.

What does the competitive landscape look like and how do you differentiate?

There are several established players in the eFPGA space, each providing variations on embedded programmable fabric.

Our view is that the competitive dynamic is less about the fabric itself and more about how customers address change over the life of a system.

The fabric must meet the power, performance, and area requirements of modern SoCs. That is table stakes.

Traditional approaches, particularly hard macro implementations, are optimized for integration efficiency at design time but remain fixed once deployed. As system requirements evolve, that rigidity becomes a limitation.

We take a different approach. Our soft IP architecture is designed around portability and adaptability, allowing customers to deploy across multiple foundries and process nodes while retaining the ability to update functionality over time. This is increasingly important in a world where both requirements and supply chains are in flux.

We are also the only US-based provider of soft embedded FPGA IP, which is highly relevant in security-sensitive domains such as aerospace, defense, and cryptography. In these environments, control over IP, provenance, and access to trusted manufacturing flows are critical considerations.

Beyond the fabric itself, we focus on system-level challenges such as chiplet interoperability, cryptographic agility, and long lifecycle adaptability.

Our view is that the value lies in enabling customers to build systems that can evolve without sacrificing performance, security, or control.

Our tool flow is based on open-source technologies, which helps avoid the long-term risks associated with proprietary tool lock-in.

What new features or technology are you working on?

Our roadmap is focused on making embedded programmability more practical and impactful at the system level.

We are advancing integration with emerging chiplet standards to enable seamless protocol adaptation across heterogeneous die.

We are also investing in tooling and flows that simplify deployment and make it easier for customers to update functionality over time.

On the security side, we are expanding support for cryptographic agility, with a focus on enabling migration to post-quantum algorithms without requiring new silicon.

We continue to improve performance and density to broaden the range of applications where embedded programmability is viable.

How do customers normally engage with your company?

Engagement typically starts when customers recognize a gap between what they can confidently design today and what they may need to support over the life of the product.

In many cases, this is driven by uncertainty around evolving standards, security requirements, or system architectures. We help them reframe the problem from committing to a fixed design to architecting for change.

From there, we work closely with system and SoC teams to identify where programmability provides the most leverage, often at control points, interfaces, or security functions.

We provide evaluation IP and support integration using standard RTL-based methodologies, with a focus on minimizing disruption to existing design flows while enabling long-term flexibility.

As programs progress, we support optimization, deployment, and ongoing updates, particularly in areas such as cryptographic agility and protocol adaptation.

Over time, the relationship tends to expand. Once customers adopt a design-for-change mindset, they begin to apply it more broadly across their portfolio.

Contact Chameleon Semiconductor

Also Read:

CEO Interview with Xianxin Guo of Lumai

CEO Interview with Johan Wadenholt Vrethem of Voxo

CEO Interview with Dr. Hardik Kabaria of Vinci


Podcast EP344: An Overview of the Upcoming Sensors Converge Event with David Drain

Podcast EP344: An Overview of the Upcoming Sensors Converge Event with David Drain
by Daniel Nenni on 05-01-2026 at 6:00 am

Daniel is joined by David Drain, show director for Questex’s Sensors Converge and Broadband Nation Expo, where he leads strategy, content, and industry engagement for two of the company’s flagship technology events. Prior to joining Questex, David spent more than 15 years with Networld Media Group, most recently as senior vice president of events and managing director of the Interactive Customer Experience Association.

Dan explores the details of the upcoming Sensors Converge conference with David, who explains how AI is bringing sensors, connectivity and compute together to form a new ecosystem. The upcoming conference provides a venue for this integrated focus to grow. Beyond a specific engineering focus, David explains that there is now a wider participation from system developers that reflects the convergence of multiple technologies to address the needs of the market.

The conference will host about 5,000 attendees, 200 exhibitors and about 100 speakers, making it a significant event. If you need to run AI on new applications and balance items such as power, latency, and cost, this event could be quite beneficial. It will be held May 5-7, 2026 at the Santa Clara Convention Center in Santa Clara, CA. You can learn more about the show and register to attend here.


Dr. L.C. Lu on TSMC Advanced Technology Design Solutions

Dr. L.C. Lu on TSMC Advanced Technology Design Solutions
by Daniel Nenni on 05-01-2026 at 6:00 am

L.C. Lu TSMC Senior Fellow and Vice President, Research and Development Design & Technology Platform (1)
Dr. L.C. Lu is Vice President of Research & Development / Design & Technology Platform at Taiwan Semiconductor Manufacturing Co. Ltd. (TSMC) and a TSMC Senior Fellow.

L.C. leads efforts in design enablement, ensuring that the company can meet the diverse and evolving requirements of its global customer base. Prior to this, he headed the Design and Technology Platform organization starting in 2018.

Since joining TSMC in 2000, Dr. Lu has held multiple leadership positions in design services. He has worked closely with process R&D teams to pioneer Design and Technology Co-Optimization (DTCO), improving speed, power efficiency, and density in advanced process technologies. He has also collaborated extensively with ecosystem partners through the TSMC Open Innovation Platform (OIP), helping deliver comprehensive design solutions and intellectual property for a wide range of applications, including high-performance computing, automotive, RF, and advanced 2.5D and 3D designs.

Dr. Lu’s contributions have earned him significant recognition. He received Taiwan’s National Outstanding Manager Award in 2012 and was named a TSMC Senior Fellow in 2025. He is also one of the company’s most prolific inventors, holding more than 100 patents worldwide.

He earned his bachelor’s degree in electrical engineering from National Taiwan University, a master’s degree in computer science from National Tsing Hua University, and a Ph.D. in computer science from Yale University.

L.C.’s presentation focuses on advanced design-technology co-optimization (DTCO), packaging innovations, and AI-driven methodologies that enable continued scaling in performance, power, and area (PPA) for next-generation semiconductor systems. The discussion highlights how tightly coupled design and process innovations, along with system-level integration, are critical to sustaining Moore’s Law in the era of AI and HPC.

At the device and design level, TSMC emphasizes DTCO and design-driven cell (DDCL) innovations to achieve node-to-node scaling from N5 through N2 and into A14. The introduction of NanoFlex and NanoFlex Pro architectures enables flexible standard cell design with significant gains in efficiency. N2 NanoFlex achieves up to 50% speed improvement at constant voltage or 50% power reduction at constant performance compared to traditional cells. Building on this, A14 NanoFlex Pro introduces a 1.5× cell height merged oxide diffusion (OD) architecture, significantly improving OD utilization and enabling tighter placement of high-speed and low-power cells. This results in 10–15% speed gains and ~20% area reduction relative to N2, effectively delivering multi-node scaling benefits within a single generation.

https://x.com/SemiAnalysis_/status/2047888356701306916

Further enhancements in N2P and N2U nodes incorporate advanced DTCO and power delivery optimizations. Hybrid dual-rail architectures reduce minimum operating voltage (Vmin) by over 200 mV compared to single-rail designs, achieving approximately 40% energy savings. N2U extends N2P with incremental improvements—3–4% higher performance or 8–10% lower power—while maintaining full compatibility with existing design rules and IP, ensuring smooth adoption for customers.

EDA readiness and AI integration are key enablers of these advanced nodes. TSMC collaborates closely with electronic design automation (EDA) partners to ensure tool readiness and to incorporate AI-enhanced workflows. Agentic AI systems are being deployed across design cycles to optimize block placement, routing, and performance, improving both productivity and design quality. These AI techniques are also applied to analog and RF design, enabling efficient migration across process nodes and accelerating time-to-market.

At the system level, TSMC’s advanced packaging technologies—particularly CoWoS, SoIC, and 3D Fabric—play a central role in enabling AI scaling. CoWoS technology continues to scale reticle size and integration capacity, allowing significant increases in compute density. From 2024 to 2029, the number of transistors in a single CoWoS system is projected to increase by 48×, driven by larger package sizes, increased system-on-chip (SoC) counts, and transition to advanced nodes such as TSMC A14.

Memory bandwidth scaling is similarly aggressive, with high-bandwidth memory (HBM) integration increasing both capacity and throughput. HBM stacks are expected to grow from 8 to 24, while I/O bandwidth per stack doubles and data rates increase significantly, resulting in an overall 34× bandwidth improvement. This scaling is supported by advancements in both DRAM technology and logic-based base dies fabricated on advanced nodes.

Interconnect performance is improved through finer pitch scaling in both 2.5D and 3D integration. In CoWoS, micro-bump pitch reduction enhances bandwidth density and energy efficiency, while in SoIC, scaling to ~4.5 µm bump pitch delivers up to 4× bandwidth density and substantial energy savings. Additionally, silicon photonics integration via CUPE optical engines provides high-speed, low-latency interconnects, achieving 5–10× power efficiency improvements and 10–20× latency reduction compared to traditional electrical links.

Power delivery and thermal management are identified as critical challenges in AI systems due to increasing compute density. TSMC addresses these through advanced capacitance solutions such as metal-insulator-metal (MIM) capacitors and embedded deep trench capacitors (eDDC), achieving over 10× improvements in capacitance density and reducing voltage droop significantly. Thermal optimization techniques—including improved packaging materials, hotspot spreading, and structural enhancements—reduce thermal resistance by up to 40%, ensuring reliable operation under high power conditions.

Bottom line: TSMC is advancing design methodologies through 3D IC design standardization and AI-driven automation. The introduction of “3D Blocks” as a modular design language aims to streamline 3D IC workflows and enhance collaboration across the ecosystem, with ongoing efforts toward IEEE standardization. Combined with generative AI and agent-based design optimization, these innovations promise substantial improvements in productivity and scalability for complex chip-package co-design.

Also Read:

Dr. Cliff Hou and the TSMC N2 Process Technology

TSMC Technology Symposium 2026 Overview


Solving the EDA tool fragmentation crisis

Solving the EDA tool fragmentation crisis
by Admin on 04-30-2026 at 10:00 am

fig1 cci flow (1)

By Samar Abd El-Hady and Wael ElManhawy

Design teams today face an uncomfortable truth: the specialized tools they need to verify modern ICs can’t reliably share the same design data. As geometries shrink below five nanometers and designs incorporate billions of transistors across multiple dies, no single Electronic Design Automation (EDA) tool can address every verification, analysis and modeling challenge.

Design teams routinely use specialized tools for parasitic extraction, power integrity analysis, electromagnetic simulation and soft error rate prediction. Each tool excels in its domain, but this creates a fundamental problem: how do you make sure that all these tools work from the same verified design data without manual translation, reformatting or error-prone data transfers?

This interoperability crisis demands a solution that can bridge the gap between verification and analysis tools. The Calibre Connectivity Interface (CCI) does this by transforming Layout vs. Schematic (LVS) verification data into a universal data source that downstream tools can query with precision and confidence.

Mining the SVDB: How CCI extracts verified design data

At its core, CCI operates on the Standard Verification Database (SVDB) generated during a Calibre nmLVS verification run. This database contains far more than simple pass or fail verification results. The SVDB captures the complete connectivity graph of the design, including layout geometry coordinates, net topology, device parameters, hierarchical relationships and the critical mapping between layout elements and their corresponding schematic or source names.

CCI provides a structured query interface to this rich dataset. Through the Query Server Tcl shell and Calibre YieldServer implementations, downstream tools can extract precisely the information they need. A typical CCI workflow begins with a completed LVS run that generates the SVDB. The CCI command file then specifies what data to extract and in what format. The interface processes these commands against the SVDB and outputs files tailored to the requirements of specific third-party tools.

Figure 1 illustrates this flow, showing how layout, source and rules feed into Calibre nmLVS, which generates the SVDB. CCI then acts as the bridge between this verified database and the diverse ecosystem of analysis tools.

Figure 1. The Calibre Connectivity Interface flow. The interface connects verification, analysis and design tools through a common protocol.
Feeding parasitic extraction tools with accurate connectivity data

Third-party parasitic extraction tools represent one of the most demanding integration scenarios. These tools need comprehensive access to geometric layouts, detailed connectivity information, net and instance names, device characteristics and port definitions. The accuracy of parasitic RC models depends entirely on the fidelity of this input data.

CCI is specifically engineered to provide all this essential data through flexible application programming interfaces (APIs). Each parasitic extraction tool can precisely query and retrieve the specific data it needs. Here’s how different tools leverage CCI:

Empyrean’s PEX tool uses CCI data to generate layout analysis with parasitic RC extraction and critical path netlists with RC annotation.

Phlexing’s GloryEX extraction tool leverages CCI to support advanced 3D modeling for planar gate, FinFET, gate-all-around and other complex device structures. GloryEX also handles sophisticated process modeling including chemical mechanical planarization, etch effects and multi-patterning, while providing high-speed capacitance table generation and pattern matching for 2.5D flows at both gate and transistor levels.

Synopsys StarRC and Cadence QRC demonstrate CCI’s ability to interface with industry-standard sign-off tools. Both tools benefit from dedicated APIs that provide real-time access to device-level layout data, robust SPICE model correlation, geometry-to-schematic mapping, automated net hierarchy tracing and seamless integration into full-chip sign-off flows.

Correlating electromagnetic analysis for high-frequency designs

For high-speed designs operating at multi-gigahertz frequencies, electromagnetic effects in critical signal paths can determine whether a design meets timing and signal integrity requirements. Siemens collaborated with Lorentz Solution, Inc. to integrate Calibre nmLVS with Lorentz PeakView products using CCI.

Together, the tools create a high-frequency design flow that delivers ease of use while enabling IC and 3D IC designers to develop post-layout solutions correlated with source and schematic names, devices and hierarchy. This correlation throughout the electromagnetic analysis workflow means you can trace results back to specific design elements for debugging and optimization.

Streamlining power integrity analysis with comprehensive grid data

Power delivery network analysis has become critical as voltage margins shrink and current densities increase. CCI integrates with mPower, the Siemens power integrity solution that provides comprehensive analysis for digital, analog and complex 3D IC architectures across all design flows.

This integration enables high-resolution voltage drop (IR) and electromigration (EM) analysis, full-chip power grid modeling and accurate power pin annotation with connectivity tracing. The key enabler is CCI’s ability to seamlessly provide all essential input data to the mPower flow—Annotated Geometry Files (AGF), detailed device data and cross-reference files. Figure 2 illustrates how CCI feeds this critical data into the mPower design import flow, ensuring accurate and efficient execution of power integrity analyses.

Figure 2. CCI provides all essential input data to the mPower flow.

Automating soft error analysis for radiation-hardened designs
Many semiconductor devices operate in harsh environments, from automotive applications to aerospace systems, making soft error analysis essential. CCI successfully interfaces with IROC Technologies, a leader in enhancing electronic system reliability through specialized EDA solutions.
IROC’s cell-level soft error detector, TFIT (Transistor Failure in Time), needs precise transistor drain and source diffusion coordinates from GDS files to perform its analysis. The output consists of detailed sensitivity maps identifying vulnerable zones within the design. Before integrating with CCI, IROC relied on a custom LVS module with limited technology support and error-prone workflows.

By integrating with Calibre nmLVS through CCI, a new reliable and automated flow emerged. Figure 3 compares the previous TFIT design import flow with the new automated flow using Calibre nmLVS and CCI. The new flow extracts accurate drain and source locations, executes the TFIT flow with precise input data, eliminates previous technical limitations and streamlines the entire analysis process.

Figure 3. Comparison of the previous flow for TFIT design import (left) and the new flow that uses Calibre nmLVS and CCI.
Deploying CCI across multi-tool verification workflows

To understand the practical value of CCI, consider these real-world applications across multi-tool workflows: In automotive IC sign-off, design teams combine parasitic extraction using StarRC with soft error rate analysis using TFIT. CCI makes sure both tools get consistent, verified design data so you can count on functional correctness and reliability over extended temperature and voltage ranges.

For 2.5D and 3D IC integration, a single design stack benefits from CCI feeding both mPower and GloryEX simultaneously. This lets you run comprehensive interposer parasitic analysis and package power analysis from a common verified database, eliminating potential inconsistencies from using different data sources.

Analog and mixed-signal designers leverage CCI for electromagnetic validation, parasitic-aware simulation and noise coupling prediction with various third-party tools. The ability to maintain correlation between layout and schematic throughout these analyses proves crucial for sensitive analog circuits where small parasitic differences can affect performance.

Building a foundation for seamless multi-tool integration

In today’s complex IC design landscape, seamless collaboration between EDA tools has evolved from a convenience to an absolute necessity. The Calibre Connectivity Interface serves as a critical integration hub, enabling efficient data exchange and communication across diverse design and verification workflows.

By transforming LVS verification data from a simple pass or fail check into a comprehensive, queryable design database, CCI provides a robust foundation for the specialized tool ecosystem that modern IC design requires. As design complexity continues to increase and new analysis requirements emerge, this foundational integration technology proves indispensable for enhancing design accuracy, streamlining verification cycles and accelerating time-to-market for cutting-edge semiconductor innovation.

Samar Abd El-Hady is a Advanced Product Engineer, Calibre Design to Silicon Division, at Siemens EDA, a part of Siemens Digital Industries Software. She is supporting Calibre LVS, layers promotion, CCI, V2LVS and ML activities . Samar has been working in Siemens EDA for over 6 years. Before, she received her BS in electronics & communication engineering in 2019 from Ain Shams University in Cairo, Egypt. After graduation, Samar joined Siemens EDA as a PE supporting Calibre LVS.

Wael ElManhawy is a Director in Calibre Management at Siemens EDA, responsible for leading the Calibre LVS product line. He brings 29 years of experience in VLSI and EDA, specializing in physical and circuit verification, including 26 years at Siemens EDA and 21 years working on Calibre, where he has played a key role in shaping different Calibre products strategy, technology, and customer adoption at the most advanced nodes.

Also Read:

Exploring the Hidden Complexity of Modern Power Electronics Design – A Siemens White Paper

Siemens Wins Best in Show Award at Chiplet Summit and Targets Broad 3D IC Design Enablement

Siemens Fuse EDA AI Agent Releases to Orchestrate Agentic Semiconductor and PCB Design


Dr. Y.J. Mii on TSMC Technology Leadership in 2026

Dr. Y.J. Mii on TSMC Technology Leadership in 2026
by Daniel Nenni on 04-30-2026 at 8:00 am

Y.J. Mii Executive Vice President and Co Chief Operating Officer, TSMC (1)
Dr. Y.J. Mii is Executive Vice President and Co-Chief Operating Officer at Taiwan Semiconductor Manufacturing Co. Ltd. (TSMC).

Dr. Y.J. Mii joined TSMC in 1994 as a manager at Fab 3 before moving into the company’s research and development organization in 2001. He was appointed Vice President of R&D in 2011 and later advanced to Senior Vice President in November 2016.

Over more than 20 years at TSMC, Dr. Mii has played a central role in advancing and manufacturing cutting-edge CMOS technologies across both fab operations and R&D. He led the successful development of key process nodes, including 90nm, 40nm, and 28nm. In addition, he has driven innovation in more advanced technologies—such as 16nm, 7nm, 5nm, and 3nm—helping sustain TSMC’s leadership position in the global semiconductor foundry industry.

In recognition of his leadership in research and development, Dr. Mii received the IEEE Frederik Philips Award in 2022. Prior to joining TSMC, he worked as a research staff member at the IBM Research Center.

Dr. Mii holds 34 patents worldwide, including 25 granted in the United States. He earned his bachelor’s degree in electrical engineering from National Taiwan University, and both his master’s and Ph.D. in electrical engineering from University of California, Los Angeles.

Dr. Y.J. Mii’s presentation outlines the company’s continued leadership in semiconductor technology and its roadmap for future innovation across advanced logic, system integration, and specialty platforms. The talk emphasizes TSMC’s commitment to delivering cutting-edge technologies that support next-generation applications such as AI, high-performance computing (HPC), and mobile devices.

TSMC is introducing several new advanced nodes, including A14, A13, and A12, which extend its leadership into what is described as the “Armstrong era.” The A14 node represents a second-generation nanosheet transistor technology and incorporates NanoFlex Pro, achieving significant improvements in performance, power, and area (PPA). Compared to the 2nm (N2) node, A14 delivers 10–15% speed improvement or 25–30% power reduction, along with notable density gains. Production is expected by 2028. Building on this, A13 offers further optimization, including a 6% die size reduction through optical shrink and improved efficiency, while maintaining backward compatibility with A14 designs.

TSMC’s 2nm family is also expanding, including N2, N2P, N2X, and N2U. These technologies are already seeing strong customer adoption, particularly driven by AI and HPC demands. N2 entered production recently, with N2P and A16 progressing toward volume production. The N2U variant further enhances performance and efficiency while maintaining compatibility with N2P, offering incremental speed and power improvements. The rapid increase in customer tapeouts highlights the strong industry demand for these advanced nodes.

Beyond nanosheet transistors, TSMC is investing in future innovations such as complementary field-effect transistors (CFET), which stack nFET and pFET vertically to enable continued scaling. The company has already demonstrated early CFET implementations and advanced SRAM designs with reduced footprint. Additionally, research into two-dimensional materials shows significant improvements in transistor performance, suggesting further opportunities for scaling and energy efficiency.

Interconnect technology is another key focus area. TSMC is improving copper-based interconnects by reducing resistance and capacitance through new materials and structures. It is also exploring alternative materials and air-gap techniques to further enhance performance. Long-term research includes novel 2D conductors that could dramatically reduce contact resistance compared to existing solutions.

In system integration, TSMC is advancing its HPC platform through technologies such as CoWoS, SoIC, and SoW. CoWoS remains a central platform for scaling, with increasing reticle sizes and high-bandwidth memory (HBM) integration planned through 2030. SoW technology aims to integrate entire systems on a wafer, enabling massive computing capabilities for AI workloads. Meanwhile, SoIC 3D stacking continues to evolve, improving interconnect density and power efficiency.

The company is also developing photonic integration technologies like the Compact Universal Photonic Engine (COUPE), which enables high-speed, low-power optical data transmission. These solutions significantly outperform traditional copper interconnects in both power efficiency and latency, and future advancements aim to further increase bandwidth and scalability.

In the specialty technology segment, TSMC highlights advancements in automotive, RF, memory, and display technologies. The N3A node is now fully automotive-qualified, while future nodes like N2A are in development. RF technologies such as N4C RF deliver improved power efficiency and performance for edge AI applications. In memory, embedded flash is being replaced by alternatives like resistive RAM (RRAM) and MRAM, which offer better scalability and performance. Display innovations, including high-voltage platforms, enable more efficient and compact designs for smartphones and smart glasses.

Bottom line: TSMC’s roadmap demonstrates a comprehensive approach to semiconductor innovation, spanning advanced nodes, new transistor architectures, system integration, and specialized technologies. The company aims to empower customers with industry-leading solutions that drive future computing advancements and enable emerging applications across multiple industries.

Also Read: 

Enabling Next-Generation AI Through Advanced Packaging and 3D Fabric Integration

Dr. Cliff Hou and the TSMC N2 Process Technology

The Shift to System-Level AI Drives Next-Generation Silicon

TSMC Technology Symposium 2026 Overview