Related papers: Stream-K++: Adaptive GPU GEMM Kernel Scheduling an…
Energy system optimization models are increasing in scope and resolution, yielding large and challenging linear programs. For a long time, the standard way to address such problems has relied on shared-memory interior-point methods (IPM),…
Processing-using-DRAM has been proposed for a limited set of basic operations (i.e., logic operations, addition). However, in order to enable the full adoption of processing-using-DRAM, it is necessary to provide support for more complex…
Top-k selection, which identifies the largest or smallest k elements from a data set, is a fundamental operation in data-intensive domains such as databases and deep learning, so its scalability and efficiency are critical for these…
Hardware accelerators such as GPUs are required for real-time, low-latency inference with Deep Neural Networks (DNN). However, due to the inherent limits to the parallelism they can exploit, DNNs often under-utilize the capacity of today's…
Nowadays, the data to be processed by database systems has grown so large that any conventional, centralized technique is inadequate. At the same time, general purpose computation on GPU (GPGPU) recently has successfully drawn attention…
GEMM with the small size of input matrices is becoming widely used in many fields like HPC and machine learning. Although many famous BLAS libraries already supported small GEMM, they cannot achieve near-optimal performance. This is because…
Massive multi-threading in GPU imposes tremendous pressure on memory subsystems. Due to rapid growth in thread-level parallelism of GPU and slowly improved peak memory bandwidth, the memory becomes a bottleneck of GPU's performance and…
The Kernel Polynomial Method (KPM) is a well-established scheme in quantum physics and quantum chemistry to determine the eigenvalue density and spectral properties of large sparse matrices. In this work we demonstrate the high optimization…
Pipeline parallelism has been demonstrated to be a remarkable approach to improve throughput for training deep neural networks with billions of parameters over heterogeneous clusters. The 1F1B scheduling plan is a widely adopted strategy…
The amount of collected information on data repositories has vastly increased with the advent of the internet. It has become increasingly complex to deal with these massive data streams due to their sheer volume and the throughput of…
The scalability of long-context large language models is fundamentally limited by the quadratic memory cost of exact self-attention, which often leads to out-of-memory (OOM) failures on modern hardware. Existing methods improve memory…
General Matrix Multiplication (GEMM) is a critical kernel in high-performance computing and deep learning. While modern architectures like ARM's Scalable Matrix Extension (SME) introduce dedicated hardware for matrix operations, existing…
Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) operations. While digital processing-in-memory (PIM)…
GEneral Matrix Multiply (GEMM) is a central operation in deep learning and corresponds to the largest chunk of the compute footprint. Therefore, improving its efficiency is an active topic of ongoing research. A popular strategy is the use…
Among ML operators today, GEneralMatrix Multiplication (GEMM)-based operators are known to be key operators that build the main backbone of ML models. As their computational overhead dominates the overall execution time (e.g., 42.8% - 96.6%…
Clustering algorithms are a cornerstone of machine learning applications. Recently, a quantum algorithm for clustering based on the k-means algorithm has been proposed by Kerenidis, Landman, Luongo and Prakash. Based on their work, we…
Distributed stream processing systems rely on the dataflow model to define and execute streaming jobs, organizing computations as Directed Acyclic Graphs (DAGs) of operators. Adjusting the parallelism of these operators is crucial to…
Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a…
Scaling laws for Large Language Models (LLMs) establish that model quality improves with computational scale, yet edge deployment imposes strict constraints on compute, memory, and power. Since General Matrix Multiplication (GEMM) accounts…
Asymmetric multicore processors (AMPs) have recently emerged as an appealing technology for severely energy-constrained environments, especially in mobile appliances where heterogeneity in applications is mainstream. In addition, given the…