Timezone: »

Live Q&A session: MAPLE: Microprocessor A Priori for Latency Estimation
Saad Abbasi · Alexander Wong · Mohammad Javad Shafiee

Tue Dec 07 12:40 PM -- 12:45 PM (PST) @

Modern deep neural networks must demonstrate state-of-the-art accuracy while exhibiting low latency and energy consumption. As such, neural architecture search (NAS) algorithms take these two constraints into account when generating a new architecture. However, efficiency metrics such as latency are typically hardware dependent requiring the NAS algorithm to either measure or predict the architecture latency.Measuring the latency of every evaluated architecture adds a significant amount of time to the NAS process. Here we propose Microprocessor A Priori for Latency Estimation MAPLE that does not rely on transfer learning or domain adaptation but instead generalizes to new hardware by incorporating a prior hardware characteristics during training. MAPLE takes advantage of a novel quantitative strategy to characterize the underlying microprocessor by measuring relevant hardware performance metrics, yielding a fine-grained and expressive hardware descriptor. Moreover, the proposed MAPLE benefits from the tightly coupled I/O between the CPU and GPU and their dependency to predict DNN latency on GPUs while measuring microprocessor performance hardware counters from the CPU feeding the GPU hardware. Through this quantitative strategy as the hardware descriptor, MAPLE can generalize to new hardware via a few shot adaptation strategy where with as few as 3 samples it exhibits a 3% improvement over state-of-the-art methods requiring as much as 10 samples. Experimental results showed that, increasing the few shot adaptation samples to 10 improves the accuracy significantly over the state-of-the-art methods by 12%. Furthermore, it was demonstrated that MAPLE exhibiting 8-10% better accuracy, on average, compared to relevant baselines at any number of adaptation samples. The proposed method provides a versatile and practical latency prediction methodology inferring DNN run-time on multiple hardware devices while not imposing any significant overhead for sample collection.

Author Information

Saad Abbasi (University of Waterloo)
Alexander Wong (University of Waterloo)
Mohammad Javad Shafiee (University of Waterloo)

More from the Same Authors