wifi-densepose/examples/google-cloud/benchmark_results/cuda_sim.json

{
  "gpu_info": {
    "available": false,
    "compute_capability": "N/A",
    "cuda_version": "N/A",
    "driver_version": "N/A",
    "max_threads_per_block": 0,
    "memory_gb": 0.0,
    "name": "N/A",
    "num_sms": 0
  },
  "results": [
    {
      "efficiency_percent": 0.9881420625225114,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 50,
      "max_time_ms": 3.174368,
      "mean_time_ms": 0.16471358,
      "metadata": {
        "bandwidth_gb_s": "5.93",
        "size_mb": "1"
      },
      "min_time_ms": 0.040596,
      "name": "memory_bandwidth_1MB",
      "operation": "memory_transfer",
      "std_time_ms": 0.5062852803394976,
      "throughput": 5.928852375135068
    },
    {
      "efficiency_percent": 0.713928028478,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 50,
      "max_time_ms": 17.299856,
      "mean_time_ms": 2.2797874599999997,
      "metadata": {
        "bandwidth_gb_s": "4.28",
        "size_mb": "10"
      },
      "min_time_ms": 0.37521899999999997,
      "name": "memory_bandwidth_10MB",
      "operation": "memory_transfer",
      "std_time_ms": 3.4558740220220883,
      "throughput": 4.283568170868
    },
    {
      "efficiency_percent": 0.08924861363335496,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 50,
      "max_time_ms": 330.599246,
      "mean_time_ms": 182.36744532,
      "metadata": {
        "bandwidth_gb_s": "0.54",
        "size_mb": "100"
      },
      "min_time_ms": 104.69545500000001,
      "name": "memory_bandwidth_100MB",
      "operation": "memory_transfer",
      "std_time_ms": 55.7021010042311,
      "throughput": 0.5354916818001297
    },
    {
      "efficiency_percent": 0.1439795903913544,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 50,
      "max_time_ms": 1279.9928280000001,
      "mean_time_ms": 565.2204462599999,
      "metadata": {
        "bandwidth_gb_s": "0.86",
        "size_mb": "500"
      },
      "min_time_ms": 199.191355,
      "name": "memory_bandwidth_500MB",
      "operation": "memory_transfer",
      "std_time_ms": 243.53272527540335,
      "throughput": 0.8638775423481264
    },
    {
      "efficiency_percent": null,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 20,
      "max_time_ms": 16.490006,
      "mean_time_ms": 8.214337000000002,
      "metadata": {
        "matrix_size": "128",
        "tflops": "0.001"
      },
      "min_time_ms": 3.316313,
      "name": "gemm_128x128",
      "operation": "gemm",
      "std_time_ms": 4.271369656748477,
      "throughput": 0.0005106077337708447
    },
    {
      "efficiency_percent": null,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 20,
      "max_time_ms": 175.19369,
      "mean_time_ms": 85.41927405,
      "metadata": {
        "matrix_size": "256",
        "tflops": "0.000"
      },
      "min_time_ms": 37.718396,
      "name": "gemm_256x256",
      "operation": "gemm",
      "std_time_ms": 38.2258611390462,
      "throughput": 0.00039282038360989797
    },
    {
      "efficiency_percent": null,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 20,
      "max_time_ms": 1099.584508,
      "mean_time_ms": 720.2384636500001,
      "metadata": {
        "matrix_size": "512",
        "tflops": "0.000"
      },
      "min_time_ms": 416.415041,
      "name": "gemm_512x512",
      "operation": "gemm",
      "std_time_ms": 183.51006806750456,
      "throughput": 0.0003727035829767156
    },
    {
      "efficiency_percent": 0.0,
      "gpu_info": {
        "available": false,
        "compute_capability": "N/A",
        "cuda_version": "N/A",
        "driver_version": "N/A",
        "max_threads_per_block": 0,
        "memory_gb": 0.0,
        "name": "N/A",
        "num_sms": 0
      },
      "iterations": 50,
      "max_time_ms": 383.561285,
      "mean_time_ms": 236.66858410000003,
      "metadata": {
        "batch_size": "64",
        "dims": "128",
        "num_vectors": "10000"
      },
      "min_time_ms": 121.239973,
      "name": "l2_distance_128d_10000v",
      "operation": "l2_distance",
      "std_time_ms": 62.27295731680189,
      "throughput": 2704203.443113428
    }
  ],
  "timestamp": "2025-12-02T00:16:10.163679757+00:00"
}