skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on March 1, 2026

Title: Modeling Utilization to Identify Shared-Memory Atomic Bottlenecks
Performance analysis is critical for GPU programs with data-dependent behavior, but models like Roofline are not very useful for them and interpreting raw performance counters is tedious. In this work, we present an analytical model for shared memory atomics (fetch-and-op and compare-and-swap instructions on NVIDIA Volta and Ampere GPU) that allows users to immediately determine if shared memory atomic operations are a bottleneck for a program’s execution. Our model is based on modeling the architecture as a single-server queuing model whose inputs are performance counters. It captures load-dependent behavior such as pipelining, parallelism, and different access patterns. We embody this model in a tool that uses CUDA hardware counters as parameters to predict the utilization of the shared-memory atomic unit. To the best of our knowledge, no existing profiling tool or model provides this capability for shared-memory atomic operations. We used the model to compare two histogram kernels that use shared-memory atomics. Although nearly identical, their performance can be different by up to 30%. Our tool correctly identifies a bottleneck shift from shared-memory atomic unit as the cause of this discrepancy  more » « less
Award ID(s):
2144384
PAR ID:
10589843
Author(s) / Creator(s):
;
Publisher / Repository:
ACM
Date Published:
ISBN:
9798400714917
Page Range / eLocation ID:
14 to 20
Subject(s) / Keyword(s):
GPU Performance Modeling Shared Memory Atomic Instructions Queuing Theory
Format(s):
Medium: X
Location:
Las Vegas NV USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems)
    null (Ed.)
    Writing correct concurrent code that uses atomics under the C/C++ memory model is extremely difficult. We present C11Tester, a race detector for the C/C++ memory model that can explore executions in a larger fragment of the C/C++ memory model than previous race detector tools. Relative to previous work, C11Tester's larger fragment includes behaviors that are exhibited by ARM processors. C11Tester uses a new constraint-based algorithm to implement modification order that is optimized to allow C11Tester to make decisions in terms of application-visible behaviors. We evaluate C11Tester on several benchmark applications, and compare C11Tester's performance to both tsan11rec, the state of the art tool that controls scheduling for C/C++; and tsan11, the state of the art tool that does not control scheduling. 
    more » « less
  2. ; ; (, ACM Transactions on Architecture and Code Optimization)
    The abstraction of a shared memory space over separate CPU and GPU memory domains has eased the burden of portability for many HPC codebases. However, users pay for ease of use provided by system-managed memory with a moderate-to-high performance overhead. NVIDIA Unified Virtual Memory (UVM) is currently the primary real-world implementation of such abstraction and offers a functionally equivalent testbed for in-depth performance study for both UVM and future Linux Heterogeneous Memory Management (HMM) compatible systems. The continued advocacy for UVM and HMM motivates improvement of the underlying system. We focus on UVM-based systems and investigate the root causes of UVM overhead, a non-trivial task due to complex interactions of multiple hardware and software constituents and the desired cost granularity. In our prior work, we delved deeply into UVM system architecture and showed internal behaviors of page fault servicing in batches. We provided quantitative evaluation of batch handling for various applications under different scenarios, including prefetching and oversubscription. We revealed that the driver workload depends on the interactions among application access patterns, GPU hardware constraints, and host OS components. Host OS components have significant overhead present across implementations, warranting close attention. This extension furthers our prior study in three aspects: fine-grain cost analysis and breakdown, extension to multiple GPUs, and investigation of platforms with different GPU-GPU interconnects. We take a top-down approach to quantitative batch analysis and uncover how constituent component costs accumulate and overlap, governed by synchronous and asynchronous operations. Our multi-GPU analysis shows reduced cost of GPU-GPU batch workloads compared to CPU-GPU workloads. We further demonstrate that while specialized interconnects, NVLink, can improve batch cost, their benefits are limited by host OS software overhead and GPU oversubscription. This study serves as a proxy for future shared memory systems, such as those that interface with HMM, and the development of interconnects. 
    more » « less
  3. ; ; ; ; ; ; ; (, 2020 53rd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO))
    null (Ed.)
    Deterministic execution for GPUs is a desirable property as it helps with debuggability and reproducibility. It is also important for safety regulations, as safety critical workloads are starting to be deployed onto GPUs. Prior deterministic architectures, such as GPUDet, attempt to provide strong determinism for all types of workloads, incurring significant performance overheads due to the many restrictions that are required to satisfy determinism. We observe that a class of reduction workloads, such as graph applications and neural architecture search for machine learning, do not require such severe restrictions to preserve determinism. This motivates the design of our system, Deterministic Atomic Buffering (DAB), which provides deterministic execution with low area and performance overheads by focusing solely on ordering atomic instructions instead of all memory instructions. By scheduling atomic instructions deterministically with atomic buffering, the results of atomic operations are isolated initially and made visible in the future in a deterministic order. This allows the GPU to execute deterministically in parallel without having to serialize its threads for atomic operations as opposed to GPUDet. Our simulation results show that, for atomic-intensive applications, DAB performs 4× better than GPUDet and incurs only a 23% slowdown on average compared to a non-deterministic GPU architecture. We also characterize the bottlenecks and provide insights for future optimizations. 
    more » « less
  4. ; (, 10.1109/NANOARCH47378.2019.181297)
    Latest algorithmic development has brought competitive classification accuracy for neural networks despite constraining the network parameters to ternary or binary representations. These findings show significant optimization opportunities to replace computationally-intensive convolution operations (based on multiplication) with more efficient and less complex operations such as addition. In hardware implementation domain, processing-in-memory architecture is becoming a promising solution to alleviate enormous energy-hungry data communication between memory and processing units, bringing considerable improvement for system performance and energy efficiency while running such large networks. In this paper, we review several of our recent works regarding Processing-in-Memory (PIM) accelerator based on Magnetic Random Access Memory computational sub-arrays to accelerate the inference mode of quantized neural networks using digital non-volatile memory rather than using analog crossbar operation. In this way, we investigate the performance of two distinct in-memory addition schemes compared to other digital methods based on processing-in-DRAM/GPU/ASIC design to tackle DNN power and memory wall bottleneck. 
    more » « less
  5. ; ; ; ; (, Proceedings of the 31st IEEE International Parallel and Distributed Processing Symposium)
    We present a single-node, multi-GPU programmable graph processing library that allows programmers to easily extend single-GPU graph algorithms to achieve scalable performance on large graphs with billions of edges. Directly using the single-GPU implementations, our design only requires programmers to specify a few algorithm-dependent concerns, hiding most multi-GPU related implementation details. We analyze the theoretical and practical limits to scalability in the context of varying graph primitives and datasets. We describe several optimizations, such as direction optimizing traversal, and a just-enough memory allocation scheme, for better performance and smaller memory consumption. Compared to previous work, we achieve best-of-class performance across operations and datasets, including excellent strong and weak scalability on most primitives as we increase the number of GPUs in the system. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email