Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
This paper analyzes Med-DDPM's performance across three NVIDIA GPU generations, identifies inefficiencies, and demonstrates TF32 Tensor Core and channels-last optimizations achieving up to 100x improvement without quality loss.
[2606.19365] Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
[Submitted on 11 Jun 2026]
Title:Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
View a PDF of the paper titled Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures, by Jeeho Ryoo and 5 other authors
View PDF HTML (experimental)
Abstract:Diffusion models have become essential for high-fidelity 3D MRI synthesis, yet their deployment remains constrained by substantial GPU resource demands arising from hundreds of U-Net evaluations per sample and a highly heterogeneous kernel behavior. This paper performs a comprehensive performance analysis of the state-of-the-art medical diffusion model, Med-DDPM, across three generations of NVIDIA architectures to study kernel-level runtime breakdowns, instruction-mix characteristics, memory system utilization, warp-level activities, and profiler priority-score estimates. We show that training is overwhelmingly dominated by cuDNN convolution and implicit-GEMM kernels, with inefficiencies arising from memory-access patterns, tensor-layout conversions, and limited Tensor Core utilization. Guided by these insights, we evaluate two architecture-aware optimizations TF32 Tensor Core activation and a 3D channels-last layout and demonstrate that they reduce SM cycles by up to 100x, cut dynamic instructions by 100x, raise Tensor Core utilization from 1.45 to 9.98x, and increase IPC by 7% on A100, all without degrading synthesis quality.
Subjects:
Machine Learning (cs.LG)
Cite as: arXiv:2606.19365 [cs.LG]
(or arXiv:2606.19365v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.19365
arXiv-issued DOI via DataCite
Related DOI:
https://doi.org/10.1145/3777884.3797012
DOI(s) linking to related resources
Submission history
From: Jeeho Ryoo [view email] [v1] Thu, 11 Jun 2026 02:12:10 UTC (438 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures, by Jeeho Ryoo and 5 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)