Robin Wilson

A 3 GHz Dual Core Processor ARM Cortex TM -A9 in 28 nm UTBB FD-SOI CMOS With Ultra-Wide Voltage Range and Energy Efficiency Optimization

This paper presents the implementation details and silicon results of a 3 GHz dual-core ARM Cortex TM -A9 (A9) manufactured in the 28 nm planar Ultra-Thin Box and Body Fully-Depleted CMOS (UTBB FD-SOI) technology. The implementation is based on a fully synthesizable standard design flow. The design exploits the important flexibility provided by the FD-SOI technology, notably a wide Dynamic Voltage and Frequency Scaling (DVFS) range, from 0.52 V to 1.37 V, and Forward Body Bias (FBB) techniques up to 1.3 V. Detailed explanations of the body-biasing techniques specific to this technology are largely presented, in the context of a multi- VT co-integration, which enable this energy efficient silicon implementation. The system integrates all the advanced IPs for energy efficiency as well as the body bias generator and a fast (μs range) dynamic body bias management capability. The measured dual core CPU maximum operation frequency is 3 GHz (for 1.37 V) and it can be operated down to 300 MHz (for 0.52 V) in full continuous DVFS. The obtained relative performance, with respect to an equivalent planar 28 nm bulk CMOS chip, shows an improvement of +237% at 0.6 V, or +544% at 0.61 V with 1.3 V FBB.

Temperature- and Voltage-Aware Timing Analysis

In the nanometer era, the physical verification of a CMOS digital circuit becomes a long, tedious, and complex task. Designers must indeed account for numerous new factors that impose a drastic change in validation and physical-verification methods. One of these major changes in timing verification to handle process variation lies in the progressive development of statistical static-timing engines. However, the statistical approach cannot capture accurately the deterministic variations of both the voltage and temperature variations. Therefore, we define a novel method, based on nonlinear-derating coefficients, to account for these environmental variations. Based on temperature- and voltage-drop computer-aided-design tool reports, this method allows computing the propagation delay of logical paths considering the operating conditions of each cell. As the statistical timing analysis does, the proposed approach reduces design margins compared to worst/best case corner analysis with fixed voltage and temperature values, a gain of 10% on the delay has been observed for critical paths

A single chip videophone video encoder/decoder

This paper describes the realization of a single chip CODEC for a video telephone terminal. Several image compression architectures have already been reported. This chip allows implementation of the video sub-system of a consumer video telephone with only 4 chips including this CODEC, a dedicated display controller chip, a standard low-end ST9 microprocessor, and a standard video RAM component. The chip encodes and decodes simultaneously 15 QCIF (144/spl times/176 pixels) images per second, according to the H.261 norm. It is optimized for bit streams in the 48 kb/s to 128 kb/s range, but lower bit rates can be accommodated. The chip also encodes or decodes still CIF (288/spl times/352) images. A flow diagram of the embedded algorithm is presented.

Ultra-wide body-bias range LDPC decoder in 28nm UTBB FDSOI technology

This paper presents an IEEE 802.11n Low-Density Parity-Check (LDPC) decoder implemented in 28nm Ultra-Thin Body and BOX Fully Depleted SOI (UTBB FDSOI), and demonstrates the performance gains of this circuit vs. 28nm LP high-κ metal-gate CMOS bulk technology. It also introduces extended body bias (BB) design techniques to take advantage of specific features of the UTBB technology to overcome the +/-300mV BB range limitation of conventional bulk technologies [1].

A 460 MHz at 397 mV, 2.6 GHz at 1.3 V, 32 bits VLIW DSP Embedding F MAX Tracking

Wide voltage range operation for DSPs brings more versatility to achieve high energy efficiency in mobile applications. This paper describes a 32 bits DSP fabricated in 28 nm Ultra Thin Body and Box FDSOI technology. Body Biasing Voltage (VBB) scaling from 0 V up to ±2 V decreases the core VDDMIN to 397 mV and increases clock frequency by +400%@500 mV and +114%@1.3 V. The DSP frequency measurements show 2.6 GHz@1.3 V(VDD)@2 V(VBB) and 460 MHz@397 mV(VDD)@2 V(VBB). The lowest peak energy efficiency is measured at 62 pJ/op at 0.53 V. In addition to technological gains, maximum frequency tracking design techniques are proposed for wide voltage range operation. On silicon, at 0.6 V, those techniques allow high energy gain of 40.6% w.r.t. a worst case corner approach.

Logical effort model extension to propagation delay representation

The logical effort method is widely recognized as a pedagogical way allowing designers to quickly estimate and optimize single paths by modeling equivalently propagation delay and transition time. However, this method necessitates a calibration of all the gates of the library and appears suboptimal in real combinatorial paths for satisfying tight timing constraints. This is due to the inability of the logical effort model in capturing I/O coupling and input ramp effects that distinguish the transition time from the propagation delay. Using an analytical modeling of the supply current that flows in simple gates during their switching process, this paper introduces an extension of the logical effort model that considers the I/O coupling capacitance and the input ramp effect. Validation of this model is performed on 130-nm STMicroelectronics technology. A compact representation of CMOS library timing performance is given as a possible application of the proposed model. The choice of sampling points to be used in look-up tables as representative steps of the design range is also discussed

A Fine-Grain Variation-Aware Dynamic

In order to optimize global energy efficiency in the context of dynamic process, voltage and temperature variations in advanced nodes, a fine-grain adaptive voltage and frequency scaling architecture is proposed for multiprocessor systems-on-chip (MPSoC), where each processing element is an independent voltage-frequency island. This architecture has been implemented on a 32 nm globally asynchronous locally-synchronous MPSoC. It shows up to 18.2% energy gains thanks to local adaptability compared with a global dynamic voltage and frequency scaling approach using 25% timing margins between slow and nominal process, by reducing margins to 60 ps of the real process. These gains are obtained for a total area overhead of 10% including local frequency/voltage actuators, sensors, and digital controller.

{\rm Vdd}

The increase of within-die variations and design margins is creating a need for statistical design methods. This paper proposes a simple statistical timing analysis method considering the lot to lot process shifts occurring during production. This method is first validated for 90nm and 65nm processes. Finally, this statistical timing analysis is applied on basic ring oscillators to evaluate the timing margins introduced at the design level by the traditional corner based approach.

-Hopping AVFS Architecture on a 32 nm GALS MPSoC

Wide-voltage-range-operation DSPs bring more versatility to achieve high energy efficiency in mobile applications to increase signal processing complexity and handle a large range of performance specifications. This paper describes a 32b DSP fabricated in 28nm UTBB FDSOI technology [1]. Body-bias-voltage (VBB) scaling from 0V up to ±2V (Pwell/Nwell) decreases the DSP core VDDMIN to 397mV and increases clock frequency by +400% at 500mV and +114% at 1.3V. In addition to technology gains, dedicated design features are included to increase frequency over the full VDD range, considering parameter variations. As depicted in Fig. 27.1.1, the 32b datapath VLIW DSP is organized around a MAC dedicated to complex arithmetic and two dedicated operators: a cordic/divider and a compare/select. Data enters the circuit through a serial interface and code is run from a 64×32b register file. It has been shown in [1] that a given operating frequency can be achieved at a lower VDD in UTBB FDSOI compared to bulk by applying a forward-body bias. An additional design step is achieved in this work by (1) increasing the frequency at low VDD thanks to a specific selection and design of standard cells with respect to power vs. performance and (2) dynamically tracking the maximum frequency to cope with variations.

A simple statistical timing analysis flow and its application to timing margin evaluation

This work presents a method for the design and characterization of a scalable ultra-wide voltage range static random access memory using an optimized 10 transistor bitcell, targeting minimum operating voltage, high yield and a Silicon-CAD correlation within 5%. The method is based on both static and dynamic metrics. The experimental validation was first performed in BULK CMOS 65 nm on a 32 kb memory array, then applied in 28 nm FDSOI on a 64 kb memory array. Over 10× energy reduction is achieved across a wide voltage range, i.e., from 1.2 V to 0.35 V while achieving high speed at the nominal voltage, i.e., 485 MHz in 65 nm BULK and 1 GHz in 28 nm FDSOI.