9 papers
Closer in the Gap: Towards Portable Performance on RISC-V Vector Processors
Ruimin Shi, Maya Gokhale, Pei-Hung Lin +2
The RISC-V Vector Extension~(RVV) is a cornerstone for supporting compute throughout in scientific and machine learning workloads. Yet compiler support and performance monitoring o…
Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference
Lingchao Zheng, Yuwei Fan, Jun Li +5
Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplicatio…
Taming GPU Underutilization via Static Partitioning and Fine-grained CPU Offloading
Gabin Schieffer, Ruimin Shi, Jie Ren +1
Advances in GPU compute throughput and memory capacity brings significant opportunities to a wide range of workloads. However, efficiently utilizing these resources remains challen…
High-performance Vector-length Agnostic Quantum Circuit Simulations on ARM Processors
Ruimin Shi, Gabin Schieffer, Pei-Hung Lin +3
ARM SVE and RISC-V RVV are emerging vector architectures in high-end processors that support vectorization of flexible vector length. In this work, we leverage an important workloa…
Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs
Jacob Wahlgren, Gabin Schieffer, Ruimin Shi +4
Discrete GPUs are a cornerstone of HPC and data center systems, requiring management of separate CPU and GPU memory spaces. Unified Virtual Memory (UVM) has been proposed to ease t…
Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: a Deep Dive
Gabin Schieffer, Jacob Wahlgren, Ruimin Shi +4
The ever-increasing compute performance of GPU accelerators drives up the need for efficient data movements within HPC applications to sustain performance. Proposed as a solution t…