The reference hub for the chiplet ecosystem
Where the chiplet marketplace starts with trust.
New Chiplets
Integrated voltage regulator (IVR) chiplet
- In-package voltage regulation for improved efficiency and performance.
- Reduced board-level complexity and external power components.
- Real-time control and feedback for dynamic system optimization.
High-performance connectivity chiplets
- PCIe and CXL-based connectivity for chiplet and system-level communications.
- High-bandwidth, low-latency data movement across compute, memory, and IO domains.
- Reusable IO architecture that reduces engineering effort across AI designs.
IMDD Tx PICs
- Reliable & qualified
- Supports single or dual input laser to drive all 8-channels
- CMOS-level drive voltage, featuring our patented ultra-low drive voltage design
- > 110 GHz electro-optic bandwidth
Near-Packaged Optics (NPO) Chiplet Solution
- CPO/NPO connectivity for GPU/Switch/ASIC with integrated OSPic™ all-optical signal processor
- High capacity, low latency up to 10Tbps for scale out CPO
- From 1.6Tbps to 6.4Tbps NPO in-field serviceability with heterogeneous laser integration
New Chiplet-Ready IP
Ncore Multi-Die Interconnect IP
- Scale Performance with Multi-Die Coherency
- Increase Bandwidth and Reduce Latency
- Tune Systems for Flexibility and Design Requirements
eFPGA Chiplet
- Optimized Performance for Advanced Computing
- Reduced Development Risk and Faster Time-to-Market
- MOSAICS-Ready Chiplet Architecture
High Performance Droplet
- High-Performance Analog Front-Ends (AFEs): Essential for data acquisition and signal processing in various applications.
- High-Speed Interfaces: Facilitating seamless communication between solutions. Omni Design supports various standards, including JESD204 and PCIe.
- Custom Solutions: Omni Design can tailor SoC solutions to meet specific customer requirements.
12nm EURYTION RFK1 - UCIe SP based Ka-Ku Band Chiplet Transceiver
- UCIe based Ka/Ku band transceiver
- Wide Bandwidth
- Scalable solution for dense mm-wave radio into single multi-chip modules
UCIe AP based 8-bit 170-Gsps Chiplet Transceiver
- 2T2R chiplet configuration
- 160/175-GSa/s sample rate
- 7-bit resolution
100G optical I/O chiplets
- RANOVUS®’ Odin® optical I/O cores set industry benchmarks for high bandwidth, low power consumption and small size for AI, cloud, metaverse, and communications applications
Insights
Ecosystem Highlights
PFN and SEMIFIVE Collaborate to Develop the MN-Core L2000 Series of Next-Generation AI Inference Chips
2026-11-17T06:34:00+00:00
Silicon Box semiconductor manufacturing facility in Italy enters Basic Design phase
2026-11-16T08:41:28+00:00
Axelera AI Unveils Titania Dual-Chiplet Architecture for AI Inference
2026-11-16T07:45:00+00:00
Expert Perspectives
The Economics of a Failed Chiplet Package
Silicon Motherboard Enables Double-Sided Integration of ICs and Passive Components
The Step-by-Step Process of STCO
The chip beneath the chips: Why silicon interposers matter more than ever
Recent Updates
Manufacturing & Supply Chain
Ecosystem & Strategy
HTSI & ficonTEC Strengthen Strategic Partnership to Expand Silicon Photonics Testing Capabilities
2026-11-17T14:32:00+00:00
Chiplet-Based Chips
PFN and SEMIFIVE Collaborate to Develop the MN-Core L2000 Series of Next-Generation AI Inference Chips
2026-11-17T06:34:00+00:00
Manufacturing & Supply Chain
Silicon Box semiconductor manufacturing facility in Italy enters Basic Design phase
2026-11-16T08:41:28+00:00
Chiplet-Based Chips
Axelera AI Unveils Titania Dual-Chiplet Architecture for AI Inference
2026-11-16T07:45:00+00:00
Ecosystem & Strategy
Technical Library
Whitepapers & Technical Articles
Technical Challenges for Ultra Fine Pitch Hybrid Bonding
DT-MATCH: Defect- and Topology-Aware Chiplet Matching for Yield Optimization in Heterogeneous Integration
Starscream: Reimagining LLM Sharding on AMD Instinct GPUs with GPU Partitioning
Tri-Stack-PIM: A Heterogeneous Multi-Die 3D-Integrated Processing-in-Memory Architecture for Efficient LLM Inference