Related papers: Triangel: A High-Performance, Accurate, Timely On-…

Processing large-scale graph datasets is computationally intensive and time-consuming. Processor-centric CPU and GPU architectures, commonly used for graph applications, often face bottlenecks caused by extensive data movement between the…

Recursive query processing has experienced a recent resurgence, as a result of its use in many modern application domains, including data integration, graph analytics, security, program analysis, networking and decision making. Due to the…

Speculative decoding accelerates generation by drafting candidates and verifying them in parallel, yet state-of-the-art drafters (e.g., EAGLE) still require N sequential passes to propose N tokens. We present FastEagle, a non-autoregressive…

Performance evaluation of caching systems is an old and widely investigated research topic. The research community is once again actively working on this topic because the Internet is evolving towards new transfer modes, which envisage to…

Pairwise sequence alignment is a very time-consuming step in common bioinformatics pipelines. Speeding up this step requires heuristics, efficient implementations, and/or hardware acceleration. A promising candidate for all of the above is…

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not…

Large language models (LLMs) are increasingly used for complex tasks that require multiple generation calls, advanced prompting techniques, control flow, and structured inputs/outputs. However, efficient systems are lacking for programming…

Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…

Modern industrial Deep Learning Recommendation Models typically extract user preferences through the analysis of sequential interaction histories, subsequently generating predictions based on these derived interests. The inherent…

Large-scale distributed graph-parallel computing is challenging. On one hand, due to the irregular computation pattern and lack of locality, it is hard to express parallelism efficiently. On the other hand, due to the scale-free nature,…

DRAM-based memory is a critical factor that creates a bottleneck on the system performance since the processor speed largely outperforms the DRAM latency. In this thesis, we develop a low-cost mechanism, called ChargeCache, which enables…

Data and pipeline parallelism are key strategies for scaling neural network training across distributed devices, but their high communication cost necessitates co-located computing clusters with fast interconnects, limiting their…

The rapid growth of AI applications has driven increased demand for specialized AI hardware, highlighting critical opportunities within the memory subsystem, which often serves as a performance bottleneck in high-demand workloads such as…

It is a challenging task to train large DNN models on sophisticated GPU platforms with diversified interconnect capabilities. Recently, pipelined training has been proposed as an effective approach for improving device utilization. However,…

The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formidable memory challenge for edge deployment. Prior works to…

Even with generational improvements in DRAM technology, memory access latency still remains the major bottleneck for application accelerators, primarily due to limitations in memory interface IPs which cannot fully account for variations in…

Deep learning (DL) frameworks take advantage of GPUs to improve the speed of DL inference and training. Ideally, DL frameworks should be able to fully utilize the computation power of GPUs such that the running time depends on the amount of…

Genome sequence alignment is the core of many biological applications. The advancement of sequencing technologies produces a tremendous amount of data, making sequence alignment a critical bottleneck in bioinformatics analysis. The existing…

To improve efficiency, nearly all parallel processing units (CPUs and GPUs) implement relaxed memory models in which memory operations may be re-ordered, i.e., executed out-of-order. Prior testing work in this area found that memory…

Fine-tuning pre-trained language models (PLMs) achieves impressive performance on a range of downstream tasks, and their sizes have consequently been getting bigger. Since a different copy of the model is required for each task, this…