End-to-end DPU design expertise. From specification to silicon
Kalray Design Services accelerate the development of custom DPU chips by combining deep design expertise with production-ready technologies. From architecture up to tape-out and board production, we help customers de-risk projects and significantly shorten time-to-market.
Architecture to silicon to system, one team
The same engineering team that designs Kalray's own DPUs is available to support your custom silicon program with proven methodologies, leading-edge process node experience, and the full Kalray IP portfolio at the ready.
1. Define The Acceleration Needs Of Your Use Case
- Jointly assess performance, power, and integration requirements.
- Identify bottlenecks and opportunities for hardware offload.
- Tailor architectural options to your business and technical goals.
2. Translate insights into a modular architecture plan
- Leverage the modular MPPA reference platform to combine compute, memory, and I/O blocks into a domain-specific design.
- Ensure alignment with scalability, flexibility, and efficiency goals.
3. Create And Validate Your Customized DPU
- Reuse proven IP to reduce cost and accelerate development.
- Validate performance and interoperability through Kalray’s co-design and testing framework.
- Choose the delivery format that fits your system — chip, chiplet, or card.
4. Deploy You DPU At Speed And Scale
- Our expert team delivers your DPU faster — from prototype to production in months, not years.
- Supported by Kalray’s software ecosystem, we provide integration guidance and long-term lifecycle support.
From spec to silicon
Kalray Design Services accelerate the development of custom DPU chips by combining deep design expertise with production-ready technologies. From architecture up to tape-out and board production, we help customers de-risk projects and significantly shorten time-to-market.
- 01 Specification & Architecture
- 02 Front-End Design & Verification
- 03 Design for Test (DFT)
- 04 Physical Design
- 05 Emulation, Prototyping, Validation
- 06 Software Development
- Build customized dPUs for any workload
Silicon-proven specification and architecture expertise to define optimal system foundations. Requirements analysis, architecture definition, hardware and software partitioning, aligned with target workloads.
- System-level analysis and modeling
- Early design exploration for PPA optimization
- Front-End Design & Verification
Robust front-end design and verification expertise transforming architecture into high-quality, silicon-ready RTL. Subsystem specification, RTL development, IP integration, top-level assembly.
- UVM-based verification, formal methods, coverage-driven flow
- Proven IP integration with AXI/AMBA standards
- Design for Test (DFT)
Comprehensive DFT expertise ensuring testability, quality, and yield of complex SoCs. Scalable test strategies including scan, BIST, and advanced compression techniques.
- DFT architecture, implementation, and tools
- Efficient fault coverage and optimized test patterns
- Physical Design
Advanced physical design expertise transforming RTL into high-performance, manufacturable silicon ready for tape-out. Synthesis, floorplanning, place-and-route, CTS, sign-off, optimized for advanced process nodes.
- Experience down to leading-edge 3nm nodes
- PPA optimization, timing closure, power integrity
- Emulation, Prototyping, Validation
Emulation, prototyping, and system validation to secure early software bring-up and de-risk SoC development. Hardware emulation and FPGA prototyping enable full-system execution before silicon.
- Hardware emulation platforms, FPGA prototyping
- End-to-end HW/SW integration testing
- Software Development
Comprehensive software development for seamless HW/SW co-design and full system bring-up, from low-level firmware and boot code through drivers, OS integration, middleware, and SDKs.
- Proven toolchains, frameworks, and validation flows
- Tailored to target workloads and architectures
From spec to silicon
Kalray Design Services accelerate the development of custom DPU chips by combining deep design expertise with production-ready technologies. From architecture up to tape-out and board production, we help customers de-risk projects and significantly shorten time-to-market.
- 01 Specification & Architecture
- 02 Front-End Design & Verification
- 03 Design for Test (DFT)
- 04 Physical Design
- 05 Emulation, Prototyping, Validation
- 06 Software Development
- Build customized dPUs for any workload
Silicon-proven specification and architecture expertise to define optimal system foundations. Requirements analysis, architecture definition, hardware and software partitioning, aligned with target workloads.
- System-level analysis and modeling
- Early design exploration for PPA optimization
- Front-End Design & Verification
Robust front-end design and verification expertise transforming architecture into high-quality, silicon-ready RTL. Subsystem specification, RTL development, IP integration, top-level assembly.
- UVM-based verification, formal methods, coverage-driven flow
- Proven IP integration with AXI/AMBA standards
- Design for Test (DFT)
Comprehensive DFT expertise ensuring testability, quality, and yield of complex SoCs. Scalable test strategies including scan, BIST, and advanced compression techniques.
- DFT architecture, implementation, and tools
- Efficient fault coverage and optimized test patterns
- Physical Design
Advanced physical design expertise transforming RTL into high-performance, manufacturable silicon ready for tape-out. Synthesis, floorplanning, place-and-route, CTS, sign-off, optimized for advanced process nodes.
- Experience down to leading-edge 3nm nodes
- PPA optimization, timing closure, power integrity
- Emulation, Prototyping, Validation
Emulation, prototyping, and system validation to secure early software bring-up and de-risk SoC development. Hardware emulation and FPGA prototyping enable full-system execution before silicon.
- Hardware emulation platforms, FPGA prototyping
- End-to-end HW/SW integration testing
- Software Development
Comprehensive software development for seamless HW/SW co-design and full system bring-up, from low-level firmware and boot code through drivers, OS integration, middleware, and SDKs.
- Proven toolchains, frameworks, and validation flows
- Tailored to target workloads and architectures
1. Define The Acceleration Needs Of Your Use Case
- Jointly assess performance, power, and integration requirements.
- Identify bottlenecks and opportunities for hardware offload.
- Tailor architectural options to your business and technical goals.
2. Translate insights into a modular architecture plan
- Leverage the modular MPPA reference platform to combine compute, memory, and I/O blocks into a domain-specific design.
- Ensure alignment with scalability, flexibility, and efficiency goals.
3. Create And Validate Your Customized DPU
- Reuse proven IP to reduce cost and accelerate development.
- Validate performance and interoperability through Kalray’s co-design and testing framework.
- Choose the delivery format that fits your system — chip, chiplet, or card.
4. Deploy You DPU At Speed And Scale
- Our expert team delivers your DPU faster — from prototype to production in months, not years.
- Supported by Kalray’s software ecosystem, we provide integration guidance and long-term lifecycle support.
1. Define The Acceleration Needs Of Your Use Case
- Jointly assess performance, power, and integration requirements.
- Identify bottlenecks and opportunities for hardware offload.
- Tailor architectural options to your business and technical goals.
2. Translate insights into a modular architecture plan
- Leverage the modular MPPA reference platform to combine compute, memory, and I/O blocks into a domain-specific design.
- Ensure alignment with scalability, flexibility, and efficiency goals.
3. Create And Validate Your Customized DPU
- Reuse proven IP to reduce cost and accelerate development.
- Validate performance and interoperability through Kalray’s co-design and testing framework.
- Choose the delivery format that fits your system — chip, chiplet, or card.
4. Deploy You DPU At Speed And Scale
- Our expert team delivers your DPU faster — from prototype to production in months, not years.
- Supported by Kalray’s software ecosystem, we provide integration guidance and long-term lifecycle support.
Benefits of building DPUs with MPPA
A Ready-Made Architecture For Building DPU Accelerators
No need to start from scratch
A shorter path to deployment
Reusable IP, pre-integrated subsystems, and standard toolchains
A flexible foundation that adapts to rapidly evolving workloads
Without sacrificing efficiency or control.
Kalray brings unmatched expertise in designing and delivering specialized DPU accelerators
- 500+ engineering-years invested in MPPA development, covering silicon, boards, and software
- Modular design approach, enabling rapid adaptation to new workloads and form factors
- Shorter time-to-market than FPGAs or ASICs, with lower development risk
- Flexible delivery options: standalone chips, chiplets, or fully integrated PCIe acceleration cards
- Proven architecture deployed in AI, networking, security, and storage environments
- End-to-end co-design support, from architectural definition to hardware, firmware, and SDKs
- Developer-friendly programmability, with no RTL expertise required
- Trusted by leading innovators across cloud, telecom, defense, and embedded systems
From Architecture to Real-World Impact
Discover how Kalray’s MPPA®-based DPUs power domain-specific acceleration for today’s most demanding workloads
AI & Compute
Storage Acceleration
5G Radio Access Networks (RAN)
Security Acceleration
GigaOm DPU Sonar Report
Recognized as a Leader and Fast Mover for innovative architecture and strong performance across AI and data workloads.
ISO 9001 certified
Interoperability validations across the storage, AI, and networking ecosystem.
Deployed at 50+ customers
