GPGPU-Sim provides a detailed simulation model of contemporary NVIDIA GPUs running CUDA and/or OpenCL workloads. It includes support for features such as TensorCores and CUDA Dynamic Parallelism as well as a performance visualization tool, AerialVisoin, and an integrated energy model, GPUWattch.
Hi, I ran into deadlock problem when I tried to run several benchmarks with scaling up problem sizes such as matrix multiplication, hotspot3D etc. GPGPU-sim works well on scaled down problem size, but whenever I increased the problem size to some extent, it will crash due to deadlock? Does anyone have any idea on how to fix this? Thanks a lot!
Hi, I ran into deadlock problem when I tried to run several benchmarks with scaling up problem sizes such as matrix multiplication, hotspot3D etc. GPGPU-sim works well on scaled down problem size, but whenever I increased the problem size to some extent, it will crash due to deadlock? Does anyone have any idea on how to fix this? Thanks a lot!