Related papers: Old is Gold: Optimizing Single-threaded Applicatio…
We present a number of novel algorithms, based on mathematical optimization formulations, in order to solve a homogeneous multiprocessor scheduling problem, while minimizing the total energy consumption. In particular, for a system with a…
The quadratic complexity and weak length extrapolation of Transformers limits their ability to scale to long sequences, and while sub-quadratic solutions like linear attention and state space models exist, they empirically underperform…
High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…
Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is essential for robust collocation, and GPU utilization…
At the allocation and deallocation of small objects with fixed size, the standard allocator of the runtime system has commonly a worse time performance compared to allocators adapted for a special application field. We propose a memory…
The introduction of cloud data centres has opened new possibilities for the storage and processing of data, augmenting the limited capabilities of peripheral devices. Large data centres tend to be located away from the end users which…
GPU clusters in multi-tenant settings often suffer from underutilization, making GPU-sharing technologies essential for efficient resource use. Among them, NVIDIA Multi-Instance GPU (MIG) has gained traction for providing hardware-level…
Optimizing resource allocation for analytical workloads is vital for reducing costs of cloud-data services. At the same time, it is incredibly hard for users to allocate resources per query in serverless processing systems, and they…
There is a lot of interest today in building autonomous (or, self-driving) data processing systems. An emerging school of thought is to leverage AI-driven "black box" algorithms for this purpose. In this paper, we present a contrarian view.…
Mobile edge computing (MEC) is an emerging paradigm that mobile devices can offload the computation-intensive or latency-critical tasks to the nearby MEC servers, so as to save energy and extend battery life. Unlike the cloud server, MEC…
When multiple processor cores (CPUs) and a GPU integrated together on the same chip share the off-chip DRAM, requests from the GPU can heavily interfere with requests from the CPUs, leading to low system performance and starvation of cores.…
This paper presents a programmable in-memory-computing processor, demonstrated in a 65nm CMOS technology. For data-centric workloads, such as deep neural networks, data movement often dominates when implemented with today's computing…
The demand for MEC has increased with the rise of data-intensive applications and 5G networks, while conventional cloud models struggle to satisfy low-latency requirements. While task offloading is crucial for minimizing latency on…
Current Multimodal Large Language Model (MLLM) architectures face a critical tradeoff between performance and efficiency: decoder-only architectures achieve higher performance but lower efficiency, while cross-attention-based architectures…
The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of…
Optimizer states occupy massive GPU memory in large-scale model training. However, gradients in different network blocks exhibit distinct behaviors, such as varying directional stability and scale anisotropy, implying that expensive…
In this paper, the problem of joint user scheduling and computing resource allocation in asynchronous mobile edge computing (MEC) networks is studied. In such networks, edge devices will offload their computational tasks to an MEC server,…
In our exploration of Composable Memory systems utilizing CXL, we focus on overcoming adoption barriers at Hyperscale, underscored by economic models demonstrating Total Cost of Ownership (TCO). While CXL addresses the pressing memory…
The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…
While multi-GPU (MGPU) systems are extremely popular for compute-intensive workloads, several inefficiencies in the memory hierarchy and data movement result in a waste of GPU resources and difficulties in programming MGPU systems. First,…