PT × CT matrix multiplication
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionNVIDIA GeForce RTX 4060 TiNVIDIA RTX A6000 · 300 WNVIDIA H100 NVL · 400 WAMD Ryzen Threadripper PRO 7975WX 32-Cores
N = 65,536 · Scale 250
Linux · PyTorch 2.13.0+cu130
3740 cases in original runLinux · PyTorch 2.13.0+cu130
920 cases in original runLinux · PyTorch 2.13.0+cu130
920 cases in original runLinux · PyTorch 2.13.0+cu130
920 cases in original runLinux · PyTorch 2.13.0+cu130
920 cases in original run