# Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures

arXiv: https://arxiv.org/abs/2606.19365 · HTML: https://mlsanity.com/paper/2606.19365/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 0 of its 65 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Abstract (arXiv)

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.