This paper introduces BigPower, a hierarchical source-level surrogate model for fine-grained module-level power estimation during CPU design using large language models and architectural hierarchy.

The paper presents ExaGEMM, a framework for designing and exploring CPU-native low-bit GEMM via register-resident LUT execution.

This paper investigates a network side-channel vulnerability in multi-tenant datacenter fabrics caused by shared congestion behavior, achieving up to 97.3% run-level accuracy in workload inference.

This paper presents DOPS, a hardware-aware framework for optimizing operator scheduling and weight layouts in Large Language Models, achieving significant speedups over prefill-decode disaggregation.

This paper presents two loop cache architectures for RISC-V processors to reduce instruction fetches and energy consumption during AI inference.

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, ou…

This paper introduces campaign diagrams, a visualization technique for analyzing resource utilization and identifying bottlenecks in modern workloads.

The paper proposes a dynamic queueing framework that estimates an organization's cyber resources and attack surface dynamics by analyzing the timestamps of vulnerabilities and fixes, achieving high ac…

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model se…

This paper presents a simulation framework to optimize workflow composition in high-throughput computing environments, demonstrating up to 3.8x throughput increase and a 14.9x reduction in network ove…

This paper proposes Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference in Large Language Models (LLMs) using budget-conditioned and input-aware gating networks.

This paper presents a comprehensive measurement study on the performance and energy consumption of large language models on mobile devices, using five frameworks and three hardware backends, and intro…

This paper introduces Ichnos+, a system to estimate the environmental footprint of Nextflow scientific workflows using post-hoc analysis and node-specific power models.

Proposed EnerInfer framework manages energy efficiency, throughput, and thermal comfort for on-device LLM inference, improving energy efficiency up to 65% without QoE violation.

This paper proposes a proactive fair scheduling framework to prevent fabric oversubscription and eliminate incast in Mixture of Experts (MoE) architectures, demonstrating consistent link utilization a…

This paper introduces CW-Ghost, a method for estimating cache line fill volume and determining helper-thread prefetching granularity based on cache capacity constraints.

The paper introduces GRIEF, a greybox fuzzer that discovers critical, concurrency-related vulnerabilities in LLM serving systems by treating timed multi-request traces as inputs, finding issues like c…