To completely utilize the advantages of dynamic voltage and frequency scaling (DVFS) techniques, a quantized decoder (QNT-D) was developed. The QNT-D generates a quantized signal processing quantity (Q) using a predicted signal processing quantity (M). Q is used to produce the optimum frequency (opt.fc) and the optimum supply voltage (opt.VD) that are proportional to Q. To develop a DVFS controlled motion estimation (ME) processor, we used both the QNT-D and a fast ME algorithm called A2BC (Adaptively Assigned Breaking-off Condition) to predict M for each macro-block (MB). A DVFS controlled ME processor was fabricated using 90-nm CMOS technology. The total power dissipation (PT) of the processor was significantly reduced and varied from 38.65 to 99.5 µW, only 3.27 to 8.41 % of PT of a conventional ME processor, depending on the test video picture.

In this paper, we propose the novel low voltage CMOS current mode reference circuit. It reduces the minimum supply voltage by consisting the subthreshold two stage operational amplifier (OPAMP) which is regarded as the combination of the proportional to absolute temperature (PTAT) and the complementary to absolute temperature (CTAT) current generators. It makes possible to implement without extra OPAMP. This proposed circuit has been designed and evaluated by SPICE simulation using TSMC 65nm CMOS process with 3.3V (2.5V over-drive) transistor option. From simulation results, the line sensitivity is as good as 0.196%/V under the condition that the range of supply voltage (VDD) is wide as 0.6V to 3.0V. The temperature coefficient is 71ppm/ under the condition that the temperature range is from -40 to 125 and VDD=0.6V. The power supply rejection ratio (PSRR) is -47.7dB when VDD=0.6V and the noise frequency is 100Hz. According to comparing the proposed circuit with prior current mode circuits, we could confirm the performance of the proposed circuit is better than that of prior circuits.

In the past decade, real-time systems (RTSs), which must maintain time constraints to avoid catastrophic consequences, have been widely introduced into various embedded systems and Internet of Things (IoTs). The RTSs are required to be energy efficient as they are used in embedded devices in which battery life is important. In this study, we investigated the RTS energy efficiency by analyzing the ability of body bias (BB) in providing a satisfying tradeoff between performance and energy. We propose a practical and realistic model that includes the BB energy and timing overhead in addition to idle region analysis. This study was conducted using accurate parameters extracted from a real chip using silicon on thin box (SOTB) technology. By using the BB control based on the proposed model, about 34% energy reduction was achieved.

In at-speed scan testing, capture power is a serious problem because the high power dissipation that can occur when the response for a test vector is captured by flip-flops results in excessive voltage drops, known as IR-drops, which may cause significant capture-induced yield loss. In low capture power test generation, the test vectors that violate capture power constraints in an initial test set are defined as capture-unsafe test vectors, while faults that are detected solely by capture-unsafe test vectors are defined as unsafe faults. It is necessary to regenerate the test vectors used to detect unsafe faults in order to prevent unnecessary yield losses. In this paper, we propose a new low capture power test generation method based on fault simulation that uses capture-safe test vectors in an initial test set. Experimental results show that the use of this method reduces the number of unsafe faults by 94% while requiring just 18% more additional test vectors on average, and while requiring less test generation time compared with the conventional low capture power test generation method.

An energy-efficient nonvolatile FPGA with assuring highly-reliable backup operation using a self-terminated power-gating scheme is proposed. Since the write current is automatically cut off just after the temporal data in the flip-flop is successfully backed up in the nonvolatile device, the amount of write energy can be minimized with no write failure. Moreover, when the backup operation in a particular cluster is completed, power supply of the cluster is immediately turned off, which minimizes standby energy due to leakage current. In fact, the total amount of energy consumption during the backup operation is reduced by 66% in comparison with that of a conventional worst-case-based approach where the long time write current pulse is used for the reliable write.

This paper presents an ultra-low power and temperature-independent voltage detector with a post-fabrication programming method, and presents a theoretical analysis and measurement results. The voltage detector is composed of a programmable voltage detector and a glitch-free voltage detector to realize both programmable and glitch-free operation. The programmable voltage detector enables the programmable detection voltages in the range from 0.52V to 0.85V in steps of less than 49mV. The glitch-free voltage detector enables glitch-free operation when the supply voltage is near 0V. A multiple voltage copier (MVC) in the programmable voltage detector is newly proposed to eliminate the tradeoff between the temperature dependence and power consumption. The design consideration and a theoretical analysis of the MVC are introduced to clarify the relationship between the current in the MVC and the accuracy of the duplication. From the analysis, the tradeoff between the duplication error and the current of MVC is introduced. The proposed voltage detector is fabricated in a 250nm CMOS process. The measurement results show that the power consumption is 248pW and the temperature coefficient is 0.11mV/°C.

This paper presents a design optimization method for a Gm-C active filter via geometric programming (GP). We first describe a GP-compatible model of a cascaded Gm-C filter that forms a biquadratic output transfer function. The bias, gain, bandwidth, and signal-to-noise ratio (SNR) of the Gm-C filter are described in a GP-compatible way. To further enhance the accuracy of the model, two modeling techniques are introduced. The first, a two-step selection method, chooses whether a saturation or subthreshold model should be used for each transistor in the filter to enhance the modeling accuracy. The second, a bisection method, is applied to include non-posynomial inequalities in the filter modeling. The presented filter model is optimized via a GP solver along with proposed modeling techniques. The numerical experiments over wide ranges of design specifications show good agreement between model and simulation results, with the average error for gain, bandwidth, and SNR being less than 9.9%, 4.4%, and 14.6%, respectively.

This paper presents a low power millimeter-wave oscillator consisting of a current-reused topology and buffer-feedback. By connecting a buffer-feedback topology between the core LC-tank of the oscillator and the output buffer stage, the simulated oscillation frequency of the proposed oscillator is increased by 17%, compared to that of the conventional current-reused oscillator. In addition, to obtain the same output power, the proposed oscillator reduces the power dissipation by 47%, compared to that of the conventional buffer-feedback oscillator. The prototype of the proposed oscillator is fabricated in a 65nm CMOS technology with a size of 700µm×480µm including pad. Measurement results indicate an oscillation frequency of 71.3GHz, while dissipating 10mA from a 1.6V supply.

Linear feedback shift register (LFSR) reseeding is an effective method for test data reduction. However, the test patterns generated by LFSR reseeding generally have high toggle rate and thus cause high test power. Therefore, it is feasible to fill X bits in deterministic test cubes with 0 or 1 properly before encoding the seed to reduce toggle rate. However, X-filling will increase the number of specified bits, thus increase the difficulty of seed encoding, what's more, the size of LFSR will increase as well. This paper presents a test frame which takes into consideration both compression ratio and power consumption simultaneously. In the first stage, the proposed reseeding-oriented X-filling proceeds for shift power (shift filling) and capture power (capture filling) reduction. Then, encode the filled test cubes using the proposed Compatible Block Code (CBC). The CBC can X-ize specified bits, namely turning specified bits into X bits, and can resolve the conflict between low-power filling and seed encoding. Experiments performed on ISCAS'89 benchmark circuits show that our scheme attains a compression ratio of 94.1% and reduces capture power by at least 15% and scan-in power by more than 79.5%.

In this paper, the Multi-voltage (multi-Vdd) variable pipeline router is proposed to reduce the power consumption of Network-on-Chips (NoCs) designed for Chip Multi-processors (CMPs). The multi-Vdd variable pipeline router adjusts its pipeline depth (i.e., communication latency) and supply voltage level in response to the applied workload. Unlike Dynamic Voltage and Frequency Scaling (DVFS) routers, the operating frequency remains the same for all routers throughout the CMP; thus, omitting the need to synchronize neighboring routers working at different frequencies. Two types of router architectures are presented: a Coarse-Grained Variable Pipeline (CG-VP) router that changes the voltage supplied to the entire router, and a Fine-Grained Variable Pipeline (FG-VP) router that uses a finer power partition. The evaluation results showed that the CG-VP and FG-VP routers achieve a 22.9% and 35.3% power reduction on average with 14% and 23% area overhead in comparison with a baseline router without variable pipelines, respectively. Thanks to the adopted look-ahead mechanism to switch the supply voltage, the performance overhead is only 4.4%.

In the most recent processor designs, memory access latency is shortened by adopting a memory hierarchy. In this configuration, the memory consists of a main memory, which comprises dynamic random-access memory (DRAM), and a cache memory, which consists of static random-access memory (SRAM). A cache memory, which is now used in increasingly large volumes, accounts for a vast proportion of the energy consumption of the overall processor. There are two ways to reduce the energy consumption of the cache memory: by decreasing the number of accesses, and by minimizing the energy consumed per access. In this study, we reduce the size of the L1 cache by compressing frequent bit sequences, thus cutting the energy consumed per access. A “frequent bit sequence” is a specific bit pattern that often appears in high-order bits of data retained in the cache memory. Our proposed mechanism, which is based on measurements using a software simulator, cuts energy consumption by 41.0% on average as compared with conventional mechanisms.

A 62ps timing resolution pulse generator (PG) is presented. The PG adopts the multi-phase ring oscillator and the pulse combiner circuit (PCC) to achieve the low timing error. The PCC can decide an arbitrary waveform via 16 phase outputs. PCC adopts the coarse-tuning stage (CTS) and the fine-tuning (FTS) to define the operational frequency range and the timing resolution, respectively. Hence, PCC uses edge combiner (EC) to combine the period window of CTS. The latency of PG is only 3 cycle times. The operational frequency range of PG is from 15MHz to 245MHz. The timing resolution and average accuracy of PG are 62.5ps and ±0.5 LSB, respectively. The RMS jitter and peak-to-peak jitter of PG are 6.55ps and 66.67ps, respectively, at 245MHz.

Two-port SRAMs are frequently installed in gate-array VLSIs to implement smart functions. This paper presents a new high-density 10T CMOS base cell for gate-array-based two-port SRAM applications. Using the single base cell alone, we can implement a two-port memory cell whose bitline contacts are shared with the memory cell adjacent to one of two dedicated sides, resulting in greatly reduced parasitic capacitance in bitlines. To throw light on the total performance derived from the base cell, a plain two-port SRAM macro was designed and fabricated with a 0.35-µm low cost, logic process. Each of two 10-bit power-saved address decoders was formed with 36% fewer base cells by employing complex gates and a subdecoder. The new sense amplifier with a complementary sensing scheme had a fine sensitivity of 35 mVpp, and so we successfully reduced the required read bitline signal from 250 to 70 mVpp. With the macro with 1024 memory cells per bitline, the address access time under typical conditions of a 2.5-V power supply and 25°C was 4.0 ns (equal to that obtained with full-custom style design) and the power consumption at 200-MHz simultaneous operations of two ports was 6.7 mW for an I/O-data width of 1 bit.

In order to further optimize the power consumption of Pseudo-CMOS inverter, this paper proposes a Re-Pull-Down transistor scheme. Two additional transistors are used to build another pull-down network. With this design, the quiescent current of the inverter can be reduced while the ratioless nature is preserved. Based on the reduced input gate area, two output transistors are set wider to compensate for the pull-up speed. The simulation result shows that, compared with Pseudo-CMOS inverter, the maximum quiescent current of the Re-Pull-Down transistor scheme inverter is reduced by 37.6% in the static analysis. Besides, the average power consumption is reduced by 30.8% in the 5-stage ring oscillator test.

Analog and digital collaborative design techniques for wireless SoCs are reviewed in this paper. In wireless SoCs, delicate analog performance such as sensitivity of the receiver is easily degraded due to interferences from digital circuit blocks. On the other hand, an analog performance such as distortion is strongly compensated by digital assist techniques with low power consumption. In this paper, a sensitivity recovery technique using the analog and digital collaborative design, and digital assist techniques to achieve low-power and high-performance analog circuits are presented. Such analog and digital collaborative design is indispensable for wireless SoCs.

Liquid crystal displays (LCDs) are suitable as elements underlying wearable and ubiquitous computing thanks to their low power consumption. A technique that uses less power to drive 1-pixel LCDs is proposed. It harvests the charges on the LCD and stores them in an external capacitor for reuse when the polarity changes. A simulation shows that the charge reduction depends on the ratio of the capacitance of the external capacitor to that of the LCD and can reach 50%. An experiment on a prototype demonstrates an almost 30% reduction with large 1-pixel LCDs. With a small 10 × 10mm2 LCD, the overhead of the micro-controller matches the reduction so no improvement could be measured. Though the technique requires longer time for polarity reversal, we confirm that it does not significantly degrade visual quality.

This paper presents a cell-based all-digital phase-locked loop (ADPLL) with hierarchical gated digitally controlled oscillator (G-DCO) for low voltage operation, wide frequency range as well as low-power consumption. In addition, a new time-domain hierarchical frequency estimation algorithm (HFEA) for frequency acquisition is proposed to estimate the output frequency in 1.5MF (MF = 3 in this paper) cycles and this fast lock-in time is suitable to the dynamic voltage frequency scaling (DVFS) systems. A hierarchical G-DCO is proposed to work at low supply voltage to reduce the power consumption and at the same time to achieve wide frequency range and precise frequency resolution. The core area of the proposed ADPLL is 0.02635 mm2. In near-threshold region (VDD = 0.36 V), the proposed ADPLL only dissipates 68.2 µW and has a rms period jitter of 1.25% UI at 60 MHz output clock frequency. Under 0.5 V VDD operation, the proposed ADPLL dissipates 404.2 µW at 400 MHz. The fast lock-in time of 4.489 µs and the low jitter performance below 0.5% UI at 400 MHz output clock frequency in the proposed ADPLL are suitable in event-driven or DVFS applications.

In emerging wearable sensor systems, it is crucial to save energy because these systems are severely energy-constrained. For making the sensors in these systems energy efficient, transmission power control (TPC) is widely used, and thus far, many TPC algorithms have been proposed in the literature. However, these TPC algorithms do not always work well in all wireless body channel conditions, which are capriciously varied due to diverse sensor environments such as sensor placements, body movements, and body locations. In this paper, we propose a simple TPC algorithm that quickly and stably approaches the optimal transmission power level and works well in all wearable sensor environments. We experimentally evaluated the proposed TPC algorithm and proved that it works well under all wireless body channel conditions.

Motion estimation (ME) is a key encoding component of almost all modern video coding standards. ME contributes significantly to video coding efficiency, but, it also consumes the most power of any component in a video encoder. In this paper, an ME processor with 3D stacked memory architecture is proposed to reduce memory and core power consumption. First, a memory die is designed and stacked with ME die. By adding face-to-face (F2F) pads and through-silicon-via (TSV) definitions, 2D electronic design automation (EDA) tools can be extended to support the proposed 3D stacking architecture. Moreover, a special memory controller is applied to control data transmission and timing between the memory die and the ME processor die. Finally, a 3D physical design is completed for the entire system. This design includes TSV/F2F placement, floor plan optimization, and power network generation. Compared to 2D technology, the number of input/output (IO) pins is reduced by 77%. After optimizing the floor plan of the processor die and memory die, the routing wire lengths are reduced by 13.4% and 50%, respectively. The stacking static random access memory contributes the most power reduction in this work. The simulation results show that the design can support real-time 720p @ 60fps encoding at 8MHz using less than 65mW in power, which is much better compared to the state-of-the-art ME processor.

A 32bit CPU, which can operate more than 15 years with 220mAH Li battery, or eternally operate with an energy harvester of in-door light is presented. The CPU was fabricated by using 65nm SOTB CMOS technology (Silicon on Thin Buried oxide) where gate length is 60nm and BOX layer thickness is 10nm. The threshold voltage was designed to be as low as 0.19V so that the CPU operates at over threshold region, even at lower supply voltages down to 0.22V. Large reverse body bias up to -2.5V can be applied to bodies of SOTB devices without increasing gate induced drain leak current to reduce the sleep current of the CPU. It operated at 14MHz and 0.35V with the lowest energy of 13.4 pJ/cycle. The sleep current of 0.14µA at 0.35V with the body bias voltage of -2.5V was obtained. These characteristics are suitable for such new applications as energy harvesting sensor network systems, and long lasting wearable computers.