What are chiplets for software-defined vehicles?

Chiplets for software-defined vehicles are disaggregated semiconductor components designed to create modular computing architectures that can be reconfigured through software to support evolving automotive functions. Unlike traditional monolithic system-on-chips (SoCs), these chiplets enable automotive manufacturers to mix and match specialized processing units – such as AI accelerators, Graphic processing, and sensor interfaces – within a single package.

Chiplet-based SoC platform supports:

Multi-vendor integration via open standards (e.g. UCIe), enabling ecosystem-driven innovation instead of proprietary lock-in [tessolve.com]

Function-driven system partitioning, where hardware architectures are designed around vehicle functions rather than silicon constraints [automotive-chiplets.org]

Scalable and upgradeable compute platforms, allowing reuse across vehicle generations and adaptation to evolving software workloads

Separation of technology nodes and life cycles, enabling optimal cost, performance, and long-term availability

In the context of software-defined vehicles, chiplets are therefore not only a packaging concept, but a system-level architectural principle that enables flexible, upgradable, and sovereign automotive compute platforms across the full vehicle lifecycle.

Where are chiplets used in automotive applications?

Chiplets are increasingly used in automotive applications to power the next generation of highly consolidated, high-performance computing platforms.

As vehicles transition from distributed Electronic Control Units (ECUs) to these centralized, zone-based electrical/electronic (E/E) architectures, monolithic Systems-on-Chip (SoCs) struggle to cost-effectively scale to the massive computing demands of modern software-defined vehicles.

Transition to centralized platforms means introduction of high-performance vehicle computers, where they enable scalable integration of heterogeneous functions such as:

ADAS and automated driving
Vehicle Infotainment & Cockpit Integration
safety-critical control and monitoring
Body & Cabin Control Processing
Vehicle function like OTA updates, gateway functionality, and vehicle availability.

Chiplet-based architectures allow these functions to be partitioned into optimized, reusable semiconductor building blocks, which can be combined within a package or distributed across the vehicle architecture.

For instance, a centralized vehicle computer can integrate leading-edge AI accelerator chiplets (fabricated on advanced 3nm or lower nodes) alongside traditional compute, graphic acceleration safety-critical microcontrollers, power management components, and sensor interfaces manufactured on mature, cost-effective nodes. This modular design facilitates a scalable "building block" approach, enabling OEMs to reuse proven IP, improve manufacturing yields, and optimize thermal dissipation across different vehicle models.

How do chiplets differ from monolithic SoCs in automotive systems?

The fundamental distinction between chiplets and monolithic SoCs lies in their architectural approach to processing distribution and scalability. Monolithic SoCs integrate all processing functions on a single silicon die, creating a fixed hardware configuration that cannot be modified after manufacturing. Chiplets disaggregate these functions into separate dies that communicate through standardized high-efficient low power interfaces, enabling modular system composition.

Attribute	Chiplets	Monolithic SoCs
Attribute Scalability	Chiplets Modular scaling by adding/removing chiplets	Monolithic SoCs Fixed processing capability
Attribute Development effort	Chiplets Higher integration complexity, reusable components	Monolithic SoCs Single-die design, established workflows
Attribute Customization	Chiplets Mix specialized chiplets per application, enable semi-custom SoC’s	Monolithic SoCs Limited to software differentiation
Attribute Time-to-market	Chiplets Faster for derivative platforms, faster Integration of new Innovation from the market	Monolithic SoCs Shorter for initial designs

This architectural difference directly impacts automotive development cycles, where chiplets enable manufacturers to create vehicle variants by selecting appropriate processing modules rather than developing entirely new SoCs for each platform. However, monolithic SoCs maintain advantages in power efficiency and signal integrity for applications with well-defined, stable processing requirements.

How is Bosch positioned in chiplet development for automotive applications?

Bosch sees chiplet technology not only as technical innovation, but also as a potential breakthrough for software-defined mobility.

At Bosch, we’ve recognized that pursuing an open ecosystem for chiplet technology is critical for the advancement of software-defined mobility. This is reflected in our active involvement in several collaborative initiatives with major actors from industry and research. Bosch has taken a leading role in the CHASSIS initiative – which stands for Chiplet-based Architectures for Software-Defined Vehicles.

Bosch aims to become the go-to provider for automotive chiplet systems and shape the future of automotive computing itself through open standards. The company is doing this by:

Coordinating the CHASSIS initiative: taking a leading role in bringing together key industry players and research institutions

Driving standardization: Actively working with partners to create common standards for automotive chiplets

Shaping the future: Influencing key design choices and architectures to ensure chiplet technology meets the evolving needs of software-defined vehicles

Comprehensive expertise: Leveraging its deep understanding of both automotive systems and semiconductor design and integration

Frequently Asked Questions

How can chiplets support software-defined vehicle architectures?

Chiplets enable software-defined vehicles by providing hardware modularity that matches software flexibility. Vehicle manufacturers can deploy different combinations of AI accelerators, graphic processors, andprocessors, and sensor interfaces using a common SoC infrastructure. This approach allows significant reduction of development efforts and time-to-market improvements.

How do chiplets enable modular compute scaling?

Chiplets support compute scaling by allowing manufacturers to add or remove processing units based on specific vehicle requirements. A base vehicle configuration might primarily include essential safety and connectivity chiplets, while premium variants add AI acceleration and advanced sensor processing modules. This modular approach eliminates the need to design separate SoCs for different performance tiers.

How can they improve flexibility and reuse?

Chiplet architectures improve flexibility by enabling component reuse across multiple vehicle platforms and model years. Manufacturers can develop specialized chiplets for functions like battery management or motor control, then deploy these components across different vehicle architectures.

What constraints exist for safety, validation, and supply chain?

Automotive chiplet implementations face functional safety validation challenges since ISO 26262 compliance must be demonstrated across multiple interconnected components rather than within a single SoC. Supply chain complexity increases as manufacturers must coordinate multiple chiplet suppliers and manage interface compatibility. Real-time communication requirements between chiplets also constrain system architectures compared to on-die interconnects.

What are realistic adoption paths?

Realistic automotive chiplet adoption will begin in the first phase with a small, specialized set of interoperable chiplets, likely deployed in medium-volume platforms targeting infotainment or ADAS applications with AI accelerators. As more semiconductor vendors progressively adopt open standards, manufacturers will extend these architectures to domain controllers for body and comfort functions before addressing highly safety-critical systems like autonomous driving and powertrain control. The ultimate goal of this phased approach is to transition from initial proprietary integrations to a fully open marketplace, building upon mature, standardized interfaces to allow seamless "mix-and-match" chiplet customization across multiple vehicle generations.

Chiplets for Software-Defined Vehicles