Power, Area, and Performance Optimization of Standard Cell Memory Arrays Through Controlled Placement

Abstract

Embedded memory remains a major bottleneck in current integrated circuit design in terms of silicon area, power dissipation, and performance; however, static random access memories (SRAMs) are almost exclusively supplied by a small number of vendors through memory generators, targeted at rather generic design specifications. As an alternative, standard cell memories (SCMs) can be defined, synthesized, and placed and routed as an integral part of a given digital system, providing complete design flexibility, good energy efficiency, low-voltage operation, and even area efficiency for small memory blocks. Yet implementing an SCM block with a standard digital flow often fails to exploit the distinct and regular structure of such an array, leaving room for optimization. In this article, we present a design methodology for optimizing the physical implementation of SCM macros as part of the standard design flow. This methodology introduces controlled placement, leading to a structured, noncongested layout with close to 100% placement utilization, resulting in a smaller silicon footprint, reduced wire length, and lower power consumption compared to SCMs without controlled placement. This methodology is demonstrated on SCM macros of various sizes and aspect ratios in a state-of-the-art 28nm fully depleted silicon-on-insulator technology, and compared with equivalent macros designed with the noncontrolled, standard flow, as well as with foundry-supplied SRAM macros. The controlled SCMs provide an average 25% reduction in area as compared to noncontrolled implementations while achieving a smaller size than SRAM macros of up to 1Kbyte. Power and performance comparisons of controlled SCM blocks of a commonly found 256 × 32 (1 Kbyte) memory with foundry-provided SRAMs show greater than 65% and 10% reduction in read and write power, respectively, while providing faster access than their SRAM counterparts, despite being of an aspect ratio that is typically unfavorable for SCMs. In addition, the SCM blocks function correctly with a supply voltage as low as 0.3V, well below the lower limit of even the SRAM macros optimized for low-voltage operation. The controlled placement methodology is applied within a full-chip physical implementation flow of an OpenRISC-based test chip, providing more than 50% power reduction compared to equivalently sized compiled SRAMs under a benchmark application.

An IoT Endpoint System-on-Chip for Secure and Energy-Efficient Near-Sensor Analytics

“…GCC 4.9 and LLVM 3.7 toolchains are available for the cores, while OpenMP 3.0 is supported on top of the bare-metal parallel runtime. The cores share a single instruction cache of 4 kB of Standard Cell Memory (SCM) [55] that can increase energy efficiency by up to 30% compared to an SRAM-based private instruction cache on parallel workloads [56]. The ISA extensions of the core include general-purpose enhancements (automatically inferred by the compiler), such as zero-overhead hardware loops and load and store operations embedding pointer arithmetic, and other DSP extensions that can be explicitly included by means of intrinsic calls.…”

Flexible, Scalable and Energy Efficient Bio-Signals Processing on the PULP Platform: A Case Study on Seizure Detection

“…Instruction caches can also be implemented with SCMs. The usage of SCMs for the implementation of frequently-accessed memory banks significantly improves energy efficiency, since energy/access of SCM is significantly lower than that of SRAMs for the relatively small cuts needed in L1 instruction and data memories [32]. Depending on the availability of low-voltage memories in the targeted implementation technology, different ratios of SCM and SRAM memory can be instantiated at design time.…”

YodaNN: An Architecture for Ultralow Power Binary-Weight CNN Acceleration

“…We demonstrate that this approach improves the energy efficiency of the digital core of the accelerator by 5.1×, and the throughput by 1.3×, with respect to a baseline architecture based on 12-bit MAC units operating at a nominal supply voltage of 1.2 V. To extend the performance scalability of the device, we implement a latch-based standard cell memory (SCM) architecture for on-chip data storage. Although SCMs are more expensive than SRAMs in terms of area, they provide better voltage scalability and energy efficiency [26], extending the operating range of the device in the low-voltage region. This further improves the energy efficiency of the engine by 6× at 0.6 V, with respect to the nominal operating voltage of 1.2 V, and leads to an improvement in energy efficiency by 11.6× with respect to a fixed-point implementation with SRAMs at its best energy point of 0.8 V. To improve the flexibility of the convolutional engine we implement support for several kernel sizes (1×1 -7×7), and support for per-channel scaling and biasing, making it suitable for implementing a large variety of CNNs.…”