Related papers: Preemptive Thread Block Scheduling with Online Str…
The performance of cluster computing depends on how concurrent jobs share multiple data center resource types like CPU, RAM and disk storage. Recent research has discussed efficiency and fairness requirements and identified a number of…
Modern computing workloads are often composed of parallelizable jobs. A parallelizable job can be completed more quickly when run on additional servers. However, each job can only use a limited number of servers, known as its…
Large language model (LLM) inference systems face a fundamental tension between minimizing Time-to-First-Token (TTFT) latency for new requests and maintaining a high, steady token generation rate (low Time-Per-Output-Token, or TPOT) for…
In both mobile and web applications, speeding up user interface response times can often lead to significant improvements in user engagement. A common technique to improve responsiveness is to precompute data ahead of time for specific…
Serving Large Language Models (LLMs) under mixed workloads--short, latency-sensitive interactive queries alongside long, throughput-oriented batch requests--poses a fundamental scheduling challenge. Standard First-Come, First-Served (FCFS)…
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…
Developing CPU scheduling algorithms and understanding their impact in practice can be difficult and time consuming due to the need to modify and test operating system kernel code and measure the resulting performance on a consistent…
In the following, we present example illustrative and experimental results comparing fair schedulers allocating resources from multiple servers to distributed application frameworks. Resources are allocated so that at least one resource is…
While Transformers and other sequence-parallelizable neural network architectures seem like the current state of the art in sequence modeling, they specifically lack state-tracking capabilities. These are important for time-series tasks and…
Current main memory database system architectures are still challenged by high contention workloads and this challenge will continue to grow as the number of cores in processors continues to increase. These systems schedule transactions…
This study introduces GCO-HPIF, a general machine-learning-based framework to predict and explain the computational hardness of combinatorial optimization problems that can be represented on graphs. The framework consists of two stages. In…
Efficiently scaling deep neural networks across GPU clusters requires navigating complex trade-offs between computational throughput, memory utilization, and synchronization overhead. This paper presents a unified empirical evaluation of…
In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to…
Spin-Transfer Torque RAM (STTRAM) is a promising alternative to SRAM in on-chip caches due to several advantages. These advantages include non-volatility, low leakage, high integration density, and CMOS compatibility. Prior studies have…
Motion planning is a fundamental problem in robotics that involves generating feasible trajectories for a robot to follow. Recent advances in parallel computing, particularly through CPU and GPU architectures, have significantly reduced…
Field-Programmable Gate Arrays (FPGAs) have become essential in cloud computing due to their reconfigurability, energy efficiency, and ability to accelerate domain-specific workloads. As FPGA adoption grows, research into task scheduling…
Fourier Neural Operators (FNO) are widely used for learning partial differential equation solution operators. However, FNO lacks architecture-aware optimizations,with its Fourier layers executing FFT, filtering, GEMM, zero padding, and iFFT…
Bundling multiple access technologies increases capacity, resiliency and robustness of network connections. Multi-access is currently being standardized in the ATSSS framework in 3GPP, supporting different access bundling strategies. Within…
With the continuous improvement of on-chip integrated voltage regulators (IVRs) and fast, adaptive frequency control, dynamic voltage-frequency scaling (DVFS) transition times have shrunk from the microsecond to the nanosecond regime,…
In this work, we optimize speculative sampling for parallel hardware accelerators to improve sampling speed. We notice that substantial portions of the intermediate matrices necessary for speculative sampling can be computed concurrently.…