inswapper_128.onnx more slow in GPU mode than CPU Mode

I tested inswapper_128.onnx in GPU mode (nvidia V100, cuda: 11.8, cudnn:8.9.1, onnxruntime-gpu:1.15.1) and CPU mode respectively, and found it ran faster in CPU mode, did you test in GPU mode ?

Start by reproducing the reported inswapper_128.onnx comparison with the stated NVIDIA V100, CUDA 11.8, cuDNN 8.9.1, and onnxruntime-gpu 1.15.1 setup, measuring CPU and GPU execution consistently. No source files or tests are named; done means identifying a reproducible reason for the GPU slowdown or documenting that the behavior cannot be reproduced.

Written by the indexing model from the issue text.