DEVoT: Dynamic Delay Modeling of Functional Units Under Voltage and Temperature Variations

Timing errors of microelectronic circuits occur when the circuit timing specification is violated, i.e., the dynamic delay of circuits exceeds the circuit clock period. With the continuous scaling of CMOS technology, microelectronic circuits are increasingly susceptible to microelectronic variations such as variations in operating conditions. Such variations can cause delay uncertainty in microelectronic circuits, leading to
timing errors
. Circuit designers typically combat these errors using conservative guardbands in the circuit and architectural design, which can, however, cause significant loss of operational efficiency. In this article, we propose
DEVoT
, a supervised learning model that can predict the dynamic delay of functional units (FUs) under different operating conditions, clock speeds, and input workload. The main contribution of
DEVoT
is to jointly consider the impact of voltage, temperature, and input workload in path sensitization, hence predicting the dynamic delay. We measure the dynamic delay using switching activity generated through gate-level simulation of post place-and-route design in the TSMC 45-nm process. We characterize the delay of FUs under different operating conditions and input workload. We then extract useful features in the input workload that influences dynamic path sensitization. Using these features, we apply supervised learning methods to build
DEVoT
. Across 100 different operating conditions, four widely used FUs, and three datasets,
DEVoT
achieves, on average, less than 2% relative deviation from the ground truth and is
$100\times $
faster than the gate-level simulation. We present two case studies using
DEVoT
. First, we use
DEVoT
to predict timing errors of FUs, and
DEVoT
achieves an average prediction accuracy at 98.04%. We further use
DEVoT
to estimate application output quality under different operating conditions, and
DEVoT
achieves an average estimation accuracy at 97% for two image processing applications. Second, we present a fuzzing-based method to identify “critical” patterns that can cause longer delay for a given circuit. Built on top of
DEVoT
, the generated input patterns can improve the sensitized delay by up to 8.3% compared to random patterns.
DEVoT
also outperforms automatic test pattern generation (ATPG) in sensitizing circuit delay. We will opensource
DEVoT
, which can assist circuit designers to perform early design space exploration and can also help software developers in approximate computing community to assess their program resilience to hardware approximation without performing circuit simulation.