Routing density analysis of ASICs, Structured ASICs, and FPGAs
Programmable Logic DesignLine
(10/19/2005 11:14 AM EDT)
This article uses well-known routing estimation techniques to analyze the trends of routing area requirements for standard cell ASICs, coarse-grained standard metal Structured ASICs, and field programmable gate arrays FPGAs. The cell granularity and the metal interconnect structure of these diametrically different architectures is analyzed and compared.
Standard cell ASICs typically feature fine-grained cell architectures. These devices have functions created out of standard single gate primitives, which are combined with custom metal interconnect, metal segments, and vias fabricated with custom masks. At the other end of the spectrum we find FPGAs, which are standard products with programmable elements that are used to connect predefined metal segments together with coarse-grained programmable cells.
Structured ASICs have regular arrays of coarse-grained programmable cells. Early Structured ASIC fabrics required multiple unique metal and via photomasks to fully implement a design. More recently, standard metal Structured ASICs have evolved. These devices comprise a sea of basic logic and memory building blocks coupled with a pre-configured, pre-characterized routing superhighway system. In the case of these standard metal fabrics, a single via layer - implemented using a single photomask or ebeam - is used to turn different routing paths on and off.
To read the full article, click here
Related Semiconductor IP
- USB 20Gbps Device Controller
- 25MHz to 4.0GHz Fractional-N RC PLL Synthesizer on TSMC 3nm N3P
- AGILEX 7 R-Tile Gen5 NVMe Host IP
- 100G PAM4 Serdes PHY - 14nm
- Bluetooth Low Energy Subsystem IP
Related White Papers
- Improving ASIC Design Verification using FPGAs and Structured ASICs
- Single event effects (SEEs) in FPGAs, ASICs, and processors, part I: impact and analysis
- Structured ASICs rescue endangered species
- Structured ASICs allow improved design flow
Latest White Papers
- Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
- Hardware Acceleration of Kolmogorov-Arnold Network (KAN) in Large-Scale Systems
- CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
- On the Thermal Vulnerability of 3D-Stacked High-Bandwidth Memory Architectures
- OmniSim: Simulating Hardware with C Speed and RTL Accuracy for High-Level Synthesis Designs