Platform-Based Design: What is Required for Viable SoC Design?
by Bob Altizer, Larry Cooke and Grant Martin
SoC Paradigm Change
When the Virtual Socket Interface Alliance (VSIA) began promoting IP block reuse in 1996 (or as VSIA calls it, Virtual Component (VC) reuse), state of the art chips were about 1 million gates. If each VC were 50,000 gates in size, there would be 20 blocks to integrate together. Today the state of the art is about 40 million gates and by the same measure there would be 800 blocks to integrate. But that is only a small part of the problem. Six years ago the chip was still a component in the system, but next generation chips are the system, with complex communication sub-systems, multiple processors, and their embedded software, all on a single piece of silicon.
SoC Paradigm Change
When the Virtual Socket Interface Alliance (VSIA) began promoting IP block reuse in 1996 (or as VSIA calls it, Virtual Component (VC) reuse), state of the art chips were about 1 million gates. If each VC were 50,000 gates in size, there would be 20 blocks to integrate together. Today the state of the art is about 40 million gates and by the same measure there would be 800 blocks to integrate. But that is only a small part of the problem. Six years ago the chip was still a component in the system, but next generation chips are the system, with complex communication sub-systems, multiple processors, and their embedded software, all on a single piece of silicon.
Related Semiconductor IP
- HBM4 PHY IP
- Ultra-Low-Power LPDDR3/LPDDR2/DDR3L Combo Subsystem
- MIPI D-PHY and FPD-Link (LVDS) Combinational Transmitter for TSMC 22nm ULP
- HBM4 Controller IP
- IPSEC AES-256-GCM (Standalone IPsec)
Related Articles
- The SoC design: What’s next for NoCs?
- Agile Analog's Approach to Analog IP Design and Quality --- Why "Silicon Proven" is NOT What You Think
- SoC design: When is a network-on-chip (NoC) not enough?
- System-on-chip (SoC) design is all about IP management
Latest Articles
- ElfCore: A 28nm Neural Processor Enabling Dynamic Structured Sparse Training and Online Self-Supervised Learning with Activity-Dependent Weight Update
- A 14ns-Latency 9Gb/s 0.44mm² 62pJ/b Short-Blocklength LDPC Decoder ASIC in 22FDX
- Pipeline Stage Resolved Timing Characterization of FPGA and ASIC Implementations of a RISC V Processor
- Lyra: A Hardware-Accelerated RISC-V Verification Framework with Generative Model-Based Processor Fuzzing
- Leveraging FPGAs for Homomorphic Matrix-Vector Multiplication in Oblivious Message Retrieval