This paper presents a charge-domain in-memory computing (IMC) macro for precision-scalable deep neural network accelerators. The proposed Dual-SRAM cell structure with coupling capacitors enables charge-domain multiply and accumulate (MAC) operation with variable-precision signed weights. Unlike prior charge-domain IMC macros that only support binary neural networks or digitally compute weighted sums for MAC operation with multi-bit weights, the proposed macro implements analog weighted sums for energy-efficient bit-scalable MAC operations with a novel series-coupled merging scheme. A test chip with a 16-kb SRAM macro is fabricated in 28-nm FDSOI process, and the measured macro throughput is 125.2-876.5 GOPS for weight bit-precision varying from 2 to 8. The macro also achieves energy efficiency ranging from 18.4 TOPS/W for 8-b weight to 119.2 TOPS/W for 2-b weight.
28 June 2023 in IEEE Journal of Solid-State Circuits
A pressure-sensing system with a half-Wheatstone-bridge-to-digital converter (HBDC) is proposed for implantable intraocular pressure (IOP) monitoring systems. The half-Wheatstone-bridge (H-WhB) sensor uses an RC-delay comparison instead of direct bias of the pressure transducer, allowing it to self-limit the current for efficient operation. To overcome the limited sensitivity of the H-WhB, energy-efficient bit-level oversampling (OS) is introduced. The system achieves 0.24-mmHg (1 $\sigma )$ resolution with an 8.58-nJ $\cdot$ mmHg $^{2}$ FOM and 12.79- $\mu $ W power consumption with a 11.52-ms conversion time. This marks a 2.8 $\times$ improvement in measured system power, 56.24 $\times$ improvement in energy consumption, and 2.8 $\times$ improvement in resolution compared to the prior H-WhB-based pressure sensor. In addition, the HBDC overcomes the low sensitivity limitations of the H-WhB and achieves a resolution FOM comparable to that of Wheatstone-bridge (WhB) sensor-based pressure sensors.
28 March 2024 in IEEE Solid-State Circuits Letters
This letter proposes a low-power high-precision capacitance-to-digital converter (CDC) utilizing a dynamic current mirror (DCM) to transform a sensor input capacitance (CIN) into an output current. The resulting current is directly proportional to the ratio of CIN to an internal reference capacitor (CREF) and subsequently converted into a period-modulated output, facilitating simple digitization by a digital counter. The CDC achieves an extensive CIN range of 1 to 68 pF without the need for a power-hungry reference buffer. Fabricated in a 65-nm CMOS process, the prototype IC occupies a small area of 0.05-mm2 and consumes only 23.9 μW even with a CIN of 47 pF. It achieves a capacitance resolution of 1.65 fF for a CIN of 1 pF with a conversion time of 4 ms, corresponding to a 13.6-bit ENOB.
A charge-domain SRAM-based CIM macro is proposed to implement efficient neural accelerator with variable input/weight/output precisions. A versatile All-Around-Wire-Capacitor (AAWC) is introduced to enable accurate charge-domain MAV operation with 1–5 bit variable-precision weight capability with 10T SRAM cell structure. The AAWC also allows variable-precision array-embedded 1–5 bit digital-to-analog (DA) conversion for input, and 1–6 bit analog-to-digital (AD) conversion for output without additional passive devices. Such array-embedded DA/AD conversion scheme significantly reduces area overhead and simplifies peripheral circuits to achieve high array efficiency while achieving high energy efficiency of 24–330 TOPS/W.
31 December 2025 in IEEE Transactions on Power Electronics
A novel energy-harvesting interface (EHI) circuit that employs a continuously scalable-conversion-ratio (CSCR) switched-capacitor dc–dc converter is introduced in this article. CSCR converters inherently sustain high power conversion efficiency across a wide voltage conversion ratio, making them well-suited for EHI applications. Realizing wide-range maximum-power-point tracking (MPPT) with a hill-climbing algorithm, however, demands accurate on-chip power estimation. Recent EHI works failed to provide such an estimation, neglecting the unit step voltages in the internal flying-capacitor network, hence constraining the attainable MPPT range. To overcome this limitation, a compact power monitor that explicitly accounts for the unit step voltages in the internal flying-capacitor network is introduced. The monitor employs a capacitive divider and is tightly coupled to an exponential digitally controlled oscillator, yielding precise power measurements over a broad frequency span. Fabricated in a 180 nm CMOS process, the prototype delivers up to 6.05 mW while achieving 90.4% end-to-end efficiency. It sustains ≥97% MPPT efficiency over a 14.6× dynamic-power range (130 µW–1.9 mW), 3.4× wider than previously reported CSCR-based harvesters. The proposed architecture thus offers an efficient and scalable solution for next-generation energy-harvesting systems.
A charge-domain SRAM-based CIM macro is proposed to implement efficient neural accelerator with variable input/weight/output precisions. A versatile All-Around-Wire-Capacitor (AAWC) is introduced to enable accurate charge-domain MAV operation with 1-5 bit variable-precision weight capability with 10T SRAM cell structure. The AAWC also allows variable-precision array-embedded 1-5 bit digital-to-analog (DA) conversion for input, and 1-6 bit analog-to-digital (AD) conversion for output without additional passive devices. Such array-embedded DA/AD conversion scheme significantly reduces area overhead and simplifies peripheral circuits to achieve high array efficiency while achieving high energy efficiency of 24-330 TOPS/W.