ucTrace: A Multi-Layer Profiling Tool for UCX-driven Communication
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914342325190656 |
|---|---|
| author | Gencer, Emir Issa, Mohammad Kefah Taha Turimbetov, Ilyas Trotter, James D. Unat, Didem |
| author_facet | Gencer, Emir Issa, Mohammad Kefah Taha Turimbetov, Ilyas Trotter, James D. Unat, Didem |
| contents | UCX is a communication framework that enables low-latency, high-bandwidth communication in HPC systems. With its unified API, UCX facilitates efficient data transfers across multi-node CPU-GPU clusters. UCX is widely used as the transport layer for MPI, particularly in GPU-aware implementations. However, existing profiling tools lack fine-grained communication traces at the UCX level, do not capture transport-layer behavior, or are limited to specific MPI implementations.
To address these gaps, we introduce ucTrace, a novel profiler that exposes and visualizes UCX-driven communication in HPC environments. ucTrace provides insights into MPI workflows by profiling message passing at the UCX level, linking operations between hosts and devices (e.g., GPUs and NICs) directly to their originating MPI functions. Through interactive visualizations of process- and device-specific interactions, ucTrace helps system administrators, library and application developers optimize performance and debug communication patterns in large-scale workloads. We demonstrate ucTrace's features through a wide range of experiments including MPI point-to-point behavior under different UCX settings, Allreduce comparisons across MPI libraries, communication analysis of a linear solver, NUMA binding effects, and profiling of GROMACS MD simulations with GPU acceleration at scale. ucTrace is publicly available at https://github.com/ParCoreLab/ucTrace. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19084 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ucTrace: A Multi-Layer Profiling Tool for UCX-driven Communication Gencer, Emir Issa, Mohammad Kefah Taha Turimbetov, Ilyas Trotter, James D. Unat, Didem Distributed, Parallel, and Cluster Computing UCX is a communication framework that enables low-latency, high-bandwidth communication in HPC systems. With its unified API, UCX facilitates efficient data transfers across multi-node CPU-GPU clusters. UCX is widely used as the transport layer for MPI, particularly in GPU-aware implementations. However, existing profiling tools lack fine-grained communication traces at the UCX level, do not capture transport-layer behavior, or are limited to specific MPI implementations. To address these gaps, we introduce ucTrace, a novel profiler that exposes and visualizes UCX-driven communication in HPC environments. ucTrace provides insights into MPI workflows by profiling message passing at the UCX level, linking operations between hosts and devices (e.g., GPUs and NICs) directly to their originating MPI functions. Through interactive visualizations of process- and device-specific interactions, ucTrace helps system administrators, library and application developers optimize performance and debug communication patterns in large-scale workloads. We demonstrate ucTrace's features through a wide range of experiments including MPI point-to-point behavior under different UCX settings, Allreduce comparisons across MPI libraries, communication analysis of a linear solver, NUMA binding effects, and profiling of GROMACS MD simulations with GPU acceleration at scale. ucTrace is publicly available at https://github.com/ParCoreLab/ucTrace. |
| title | ucTrace: A Multi-Layer Profiling Tool for UCX-driven Communication |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2602.19084 |