Insup Shin

Register allocation for high-level synthesis using dual supply voltages

Reducing the power consumption of memory elements is known to be the most influential in minimizing total power consumption, since designs tend to use more memories these days. In this paper, we address a problem of high-level synthesis with the objective of minimizing power consumption of storage using dual-Vdd. Specifically, we propose a complete design framework that starts from dual-Vdd scheduling, dual-Vdd allocation, and controller synthesis down to the final layout. Its main feature is dual-Vdd register allocation, which exploits timing slacks left in the data-path after operation scheduling. In experiments on benchmark designs implemented in 1.08 V (with Vddl of 0.8 V), 65-nm CMOS technology, both switching and leakage power were reduced by 20% on average, respectively, compared to data-path with dual-Vdd applied to functional units alone. Detailed analysis of slack histogram, area, wirelength, and congestion were performed to assess feasibility of the design framework.

A pipeline architecture with 1-cycle timing error correction for low voltage operations

We present a new timing error correction scheme which allows each pipeline stage to halt for one cycle only. The small timing penalty for the error correction operation in the proposed scheme makes it possible to eliminate the extra timing guardband that was needed to accommodate timing uncertainty due to process variations. As a result, lower supply voltage can be used with the proposed scheme for low power operations. Compared to the previous 1-cycle error correction scheme which uses two-phase transparent latch based pipeline [1], the proposed scheme can be applied to the pipeline based on more popular clocking elements such as flip-flop or pulsed latch.

HLS-l: A High-Level Synthesis Framework for Latch-Based Architectures

Level-sensitive latches are widely used in high-performance custom designs while edge-triggered flip-flops are predominantly used in application-specific integrated circuits. We consider a latch as a basis for storage and address each step of high-level synthesis (HLS), including scheduling, allocation, and control synthesis. While the use of latches provides an opportunity to reduce the latency during the scheduling, the register allocation has to take extra conflicts caused by latch into account, and the control synthesis has to be tailored to support the latch-based data-path. Optimization potentials specific to this HLS are identified and solutions are proposed. Specifically, the register allocation can be improved by refining the operation schedule in a way to reduce the number of edges in a register conflict graph; the latency can be reduced by adjusting the clock duty cycle in a way to generate a tighter schedule. All the steps of HLS and optimization procedures were integrated into a framework called HLS-l. It was tested on benchmark designs implemented in 1.1-V, 45 nm complementary metal-oxide-semiconductor technology. Compared to the conventional HLS, HLS-l was able to reduce the latency by 18.2% on average with 9.2% less area and 16.0% less power consumption. The application of HLS-l to an industrial example is demonstrated through the design of a module extracted from H.264/advanced video coding.

Synthesis of Active-Mode Power-Gating Circuits

Active leakage is transient, which can be suppressed by design techniques such as dual-Vt. Active-mode power-gating (AMPG) can further reduce active leakage by power-gating groups of gates that perform computations with results that are not loaded due to clock-gating. AMPG involves several challenges; the grouping of gates must take circuit timing into account, and current switches need to be sized to preserve power network integrity as well as circuit timing. We propose solutions to these problems in the content of the entire process of synthesizing AMPG circuits. The physical design of AMPG circuits is also difficult due to the large number of virtual ground rails that must be mutually isolated. We address these issues by integrating placement with power network synthesis. Experiments on several test circuits implemented in 45-nm technology demonstrate the effectiveness of AMPG in the circuits that we synthesized, in terms of power consumption, area, wirelength, and timing.

Synthesis and implementation of active mode power gating circuits

Active leakage current is much larger (~10×) than standby leakage current, and takes a large proportion (30% to 40%) of active power consumption. Active mode power gating (AMPG) has been proposed to extend the application of basic power gating to reducing active leakage; it relies on clock-gating signals to cut the power off a part of combinational gates. The problem to select those gates while integrity of circuit behavior remains intact has not been solved yet. We identify three constraints to solve this problem, namely functional, timing, and current constraints. The problem of synthesizing AMPG circuits is then laid out, and synthesis algorithm is proposed; a group of gates that can be power-gated by each clock-gating signal and the size of footer that is attached to the group constitute a synthesis output. The layout methodology for standard cell designs is proposed to assess AMPG circuits in area and wirelength. Experiments in 1.1 V, 45-nm technology demonstrate that active leakage is reduced by 16% on average compared to clock-gated circuits.

Selectively patterned masks: structured ASIC with asymptotically ASIC performance

Structured ASIC, which consists of a homogeneous array of tiles, suffers from large delay and area due to its inherent regularity. A new lithography method called selectively patterned masks (SPM) is proposed. It exploits special masks called masking masks and double exposure technique to allow more than one types of tiles to be patterned on the same wafer. The result is a heterogeneous array of tiles, which relaxes regularity in structured ASIC. A new structured ASIC based on SPM is proposed; tile and routing architectures, design flow, and tile packing and routing algorithm are all addressed. Experiments in 45-nm technology show that, compared to ASIC, the proposed structured ASIC exhibits 2.0 times of area when circuits are optimized for area and 1.2 times of delay when they are optimized for delay. Both figures represent substantial improvement over conventional structured ASIC.

Aggressive Voltage Scaling Through Fast Correction of Multiple Errors With Seamless Pipeline Operation

Aggressive reduction of timing margins, called timing speculation, is an effective way of reducing the supply voltage for a pipeline circuit and thereby its power consumption. However, probability of timing error increases with the voltage scaling and hence, the errors must be corrected with small cycle penalty. We introduce an improved Razor flip-flop which makes more effective use of its shadow latch, so that a pipeline stage can correct an error while continuing to receive data. This avoids the need for repeated clock gating when timing errors happen simultaneously at different stages, or when an error persists. The new flip-flop also facilitates time-borrowing. Our technique uses less energy than the state-of-the art technique, and the energy saving increases with pipeline length: with 10 stages, 4-9% smaller energy is used.

HLS-dv: A High-Level Synthesis Framework for Dual-Vdd Architectures

Dual supply voltage design is widely accepted as an effective way to reduce the power consumption of CMOS circuits. In this paper, we propose a comprehensive design framework that includes dual- scheduling, dual- allocation, controller synthesis as well as layout generation. In particular, we address a problem of high-level synthesis with objective of minimizing power consumption of storage units and multiplexers using dual- ; this is made possible by utilizing timing slack that is left in the data-path after operation scheduling. We use integer linear programming (ILP) and also provide heuristic algorithms to solve the dual- register and connection allocation. The physical layout of dual-circuits has to separate power rails of and cells from each other. We propose a voltage island based placement algorithm to relieve this restriction and allow more flexibility of placement. In experiments on benchmark designs implemented in 1.08 V (with Vddl of 0.8 V) 65-nm CMOS technology, both switching and leakage power are reduced by 20% on average, respectively, compared to data-path with dual-Vdd applied to functional units alone. Detailed analysis of area and wirelength is performed to assess feasibility of the proposed method.

One-Cycle Correction of Timing Errors in Pipelines With Standard Clocked Elements

One of the most aggressive uses of dynamic voltage scaling is timing speculation, which in turn requires fast correction of timing errors. The fastest existing error correction technique imposes a one-cycle time penalty only, but it is restricted to two-phase transparent latch-based pipelines. We perform one-cycle error correction by gating only the main latch in each stage of the pipeline that precedes a failed stage. This new method is applicable to widely used clocking elements, such as flip-flops and pulsed latches. Because it prevents inputs arriving at a stage, which is stalled, it can also be used in pipelines with multiple fan-in, fan-out, and looping. Simulations show an energy saving of 8%-12% with a target throughput of 0.9 instructions per cycle, and 15%-18% when the target is 0.8.

Power minimization of pipeline architecture through 1-cycle error correction and voltage scaling

We present a new 1-cycle timing error correction method, which enables aggressive voltage scaling in a pipelined architecture. The proposed method differs from the state-of-the-art in that the pipeline stage where the timing error occurs can continue to receive input data without halting to avoid data collision. The feature allows the pipeline to avoid recurring clock gating when timing errors happen at multiple stages or timing errors continue to occur at a certain stage. Compared to a state-of-the-art method, the proposed method shows 2-6% energy reduction for a 5-stage pipeline and 7-11% reduction for a 10-stage pipeline. In addition, the proposed logic to propagate clock gating signal is much simpler than that of the previous method [1] by eliminating reverse propagation path of clock gating signal.