Sub-Threshold Design - A Revolutionary Approach to Eliminating Power
Mike Salas, VP Marketing, Ambiq Micro
EDN (December 22, 2014)
Low energy consumption has replaced performance as the foremost challenge in electronic design. Performance is important, but it must now accede to the energy capacity of batteries and even the minimal output of energy harvesters. Performance at all costs no longer works; energy consumption is now the dominant requirement. While reducing energy consumption is critically important throughout the electronics industry, the question is: how should that goal be achieved? Ambiq Micro’s approach moves beyond the incremental improvements that other semiconductor companies have taken and makes revolutionary advances through a unique approach to the problem: sub-threshold circuit design.
Energy is consumed in two fundamental ways: as leakage, when a circuit’s state isn’t changing, and dynamically as internal nodes are charged up and down. For realistic circuits in operation, dynamic power dominates – especially for the higher power supply voltages used in most designs today.
To read the full article, click here
Related Semiconductor IP
- Ultra-Low-Power LPDDR3/LPDDR2/DDR3L Combo Subsystem
- 1G BASE-T Ethernet Verification IP
- Network-on-Chip (NoC)
- Microsecond Channel (MSC/MSC-Plus) Controller
- 12-bit, 400 MSPS SAR ADC - TSMC 12nm FFC
Related Articles
- PCI Express 3.0 needs reliable timing design
- PCI Express 3.0 needs reliable timing design
- Design patterns in SystemVerilog OOP for UVM verification
- A Heuristic Approach to Fix Design Rule Check (DRC) Violations in ASIC Designs @7nm FinFET Technology
Latest Articles
- Extending and Accelerating Inner Product Masking with Fault Detection via Instruction Set Extension
- ioPUF+: A PUF Based on I/O Pull-Up/Down Resistors for Secret Key Generation in IoT Nodes
- In-Situ Encryption of Single-Transistor Nonvolatile Memories without Density Loss
- David vs. Goliath: Can Small Models Win Big with Agentic AI in Hardware Design?
- RoMe: Row Granularity Access Memory System for Large Language Models