{ "benchmark": { "memory": { "source": "nvbandwidth", "h2d_bandwidth_gbps": 55.5, "d2h_bandwidth_gbps": 55.0, "d2d_bandwidth_gbps": 0.0, "h2d_peak_gbps": 64, "d2h_peak_gbps": 64, "d2d_peak_gbps": 450.0, "h2d_efficiency_pct": 86.7, "d2h_efficiency_pct": 85.9, "d2d_efficiency_pct": null, "peak_bandwidth_gbps": 3400, "efficiency_pct": null, "results_by_test": { "h2d": 55.5, "d2h": 55.0, "d2d_write": 0.0, "d2d_read": 0.0, "d2d_bidir": 0.0 }, "per_gpu": [] }, "compute": { "per_dtype_tflops": { "fp32": 52.2, "tf32": 357.5, "fp16": 665.3, "bf16": 697.1, "fp8": 1138.8 }, "peak_tflops": { "fp32": 67, "tf32": 495, "fp16": 990, "bf16": 990, "fp8": 1979 }, "efficiency_pct": { "fp32": 77.9, "tf32": 72.2, "fp16": 67.2, "bf16": 70.4, "fp8": 57.5 }, "pass_thresholds_tflops": { "fp32": 54, "tf32": 444, "fp16": 734, "bf16": 745, "fp8": 1400 }, "per_gpu": [ { "index": 0, "fp32": 52.2, "tf32": 357.5, "fp16": 665.3, "bf16": 697.1, "fp8": 1138.8 } ], "matrix_size": 8192, "warmup": 50, "iterations": 500 } }, "timestamp": "2026-05-22T15:35:19.219299" }