大規模最適化問題、グラフ探索、機械学習やデジタルツインなど

旧名:最適化問題に対する超高速&安定計算

NVIDIA A100 2枚 と bandwidthTest

# ./bandwidthTest --device=all
[CUDA Bandwidth Test] - Starting...

!!!!!Cumulative Bandwidth to be computed from all the devices !!!!!!

Running on...

Device 0: NVIDIA A100 80GB PCIe
Device 1: NVIDIA A100 80GB PCIe
Quick Mode

Host to Device Bandwidth, 2 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(GB/s)
32000000 24.7

Device to Host Bandwidth, 2 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(GB/s)
32000000 26.4

Device to Device Bandwidth, 2 Device(s)
PINNED Memory Transfers
Transfer Size (Bytes) Bandwidth(GB/s)
32000000 2629.9