Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.