611c491b0f
- scale_mem_bound: FULL PARITY with CCCL (all 11 test cases match) - Extracted all SM100 benchmark annotations from 26 tuning headers - reduce: 7 SM100 tunings + 3 deterministic (SM90/SM86) - scan: 7 SM100 lookback tunings with delay policies - Generated machine-readable JSON with benchmark runner params - Identified 5 pending verification items for BI-V100 hardware
279 lines
5.5 KiB
JSON
279 lines
5.5 KiB
JSON
{
|
|
"source": "cccl_upstream/cub/cub/device/dispatch/tuning/tuning_*.cuh",
|
|
"extracted_by": "automated audit from CCCL source code",
|
|
"reduce": {
|
|
"sm100_float32_plus_o4": {
|
|
"items": 16,
|
|
"threads": 512,
|
|
"vec": 2,
|
|
"benchmark": "ipt_16.tpb_512.ipv_2",
|
|
"speedup": [
|
|
1.061295,
|
|
1.0,
|
|
1.065478,
|
|
1.167139
|
|
]
|
|
},
|
|
"sm100_float64_plus_o4": {
|
|
"items": 16,
|
|
"threads": 640,
|
|
"vec": 1,
|
|
"benchmark": "ipt_16.tpb_640.ipv_1",
|
|
"speedup": [
|
|
1.017834,
|
|
1.0,
|
|
1.015835,
|
|
1.057092
|
|
]
|
|
},
|
|
"sm100_accum8_plus_o4": {
|
|
"items": 15,
|
|
"threads": 512,
|
|
"vec": 2,
|
|
"benchmark": "ipt_15.tpb_512.ipv_2",
|
|
"speedup": [
|
|
1.019887,
|
|
1.0,
|
|
1.017636,
|
|
1.058036
|
|
]
|
|
},
|
|
"sm100_accum8_plus_o8": {
|
|
"items": 15,
|
|
"threads": 512,
|
|
"vec": 1,
|
|
"benchmark": "ipt_15.tpb_512.ipv_1",
|
|
"speedup": [
|
|
1.019414,
|
|
1.0,
|
|
1.017218,
|
|
1.057143
|
|
]
|
|
},
|
|
"sm90_det_float32": {
|
|
"items": 13,
|
|
"threads": 224,
|
|
"benchmark": "ipt_13.tpb_224",
|
|
"speedup": [
|
|
1.107188,
|
|
1.009709,
|
|
1.097114,
|
|
1.31682
|
|
]
|
|
},
|
|
"sm86_det_float32": {
|
|
"items": 6,
|
|
"threads": 224,
|
|
"benchmark": "ipt_6.tpb_224",
|
|
"speedup": [
|
|
1.034383,
|
|
1.0,
|
|
1.032097,
|
|
1.090909
|
|
]
|
|
},
|
|
"sm86_det_float64": {
|
|
"items": 11,
|
|
"threads": 128,
|
|
"benchmark": "ipt_11.tpb_128",
|
|
"speedup": [
|
|
1.232089,
|
|
1.002124,
|
|
1.245336,
|
|
1.582279
|
|
]
|
|
}
|
|
},
|
|
"scan": {
|
|
"sm100_lookback_1B_o4": {
|
|
"items": 18,
|
|
"threads": 512,
|
|
"delay": {
|
|
"ns": 768,
|
|
"dcid": 7,
|
|
"l2w": 820
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 0
|
|
},
|
|
"benchmark": "ipt_18.tpb_512.ns_768.dcid_7.l2w_820.trp_1.ld_0",
|
|
"speedup": [
|
|
1.188818,
|
|
1.005682,
|
|
1.173041,
|
|
1.305288
|
|
]
|
|
},
|
|
"sm100_lookback_2B_o4": {
|
|
"items": 13,
|
|
"threads": 512,
|
|
"delay": {
|
|
"ns": 1384,
|
|
"dcid": 7,
|
|
"l2w": 720
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 0
|
|
},
|
|
"benchmark": "ipt_13.tpb_512.ns_1384.dcid_7.l2w_720.trp_1.ld_0",
|
|
"speedup": [
|
|
1.128443,
|
|
1.002841,
|
|
1.119688,
|
|
1.307692
|
|
]
|
|
},
|
|
"sm100_lookback_4B_o4": {
|
|
"items": 22,
|
|
"threads": 384,
|
|
"delay": {
|
|
"ns": 1904,
|
|
"dcid": 6,
|
|
"l2w": 830
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 0
|
|
},
|
|
"benchmark": "ipt_22.tpb_384.ns_1904.dcid_6.l2w_830.trp_1.ld_0",
|
|
"speedup": [
|
|
1.148442,
|
|
0.997167,
|
|
1.139902,
|
|
1.462651
|
|
]
|
|
},
|
|
"sm100_lookback_8B_o4": {
|
|
"items": 23,
|
|
"threads": 416,
|
|
"delay": {
|
|
"ns": 772,
|
|
"dcid": 5,
|
|
"l2w": 710
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 0
|
|
},
|
|
"benchmark": "ipt_23.tpb_416.ns_772.dcid_5.l2w_710.trp_1.ld_0",
|
|
"speedup": [
|
|
1.089468,
|
|
1.015581,
|
|
1.08563,
|
|
1.264583
|
|
]
|
|
},
|
|
"sm100_lookback_1B_o8": {
|
|
"items": 14,
|
|
"threads": 384,
|
|
"delay": {
|
|
"ns": 228,
|
|
"dcid": 7,
|
|
"l2w": 775
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 1
|
|
},
|
|
"benchmark": "ipt_14.tpb_384.ns_228.dcid_7.l2w_775.trp_1.ld_1",
|
|
"speedup": [
|
|
1.10721,
|
|
1.0,
|
|
1.100637,
|
|
1.307692
|
|
]
|
|
},
|
|
"sm100_lookback_4B_o8": {
|
|
"items": 19,
|
|
"threads": 416,
|
|
"delay": {
|
|
"ns": 956,
|
|
"dcid": 7,
|
|
"l2w": 550
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 1
|
|
},
|
|
"benchmark": "ipt_19.tpb_416.ns_956.dcid_7.l2w_550.trp_1.ld_1",
|
|
"speedup": [
|
|
1.146142,
|
|
0.99435,
|
|
1.137459,
|
|
1.455636
|
|
]
|
|
},
|
|
"sm100_lookback_8B_o8": {
|
|
"items": 22,
|
|
"threads": 320,
|
|
"delay": {
|
|
"ns": 328,
|
|
"dcid": 2,
|
|
"l2w": 965
|
|
},
|
|
"load": {
|
|
"transpose": 1,
|
|
"modifier": 0
|
|
},
|
|
"benchmark": "ipt_22.tpb_320.ns_328.dcid_2.l2w_965.trp_1.ld_0",
|
|
"speedup": [
|
|
1.080133,
|
|
1.0,
|
|
1.075577,
|
|
1.248963
|
|
]
|
|
}
|
|
},
|
|
"benchmark_runner_params": {
|
|
"reduce": {
|
|
"items_range": "7:24:1",
|
|
"threads_range": "128:1024:32",
|
|
"vec_pow2_range": "1:2:1",
|
|
"problem_sizes": [
|
|
"2^16",
|
|
"2^20",
|
|
"2^24",
|
|
"2^28"
|
|
]
|
|
},
|
|
"scan_lookback": {
|
|
"items_range": "7:24:1",
|
|
"threads_range": "128:1024:32",
|
|
"delay_ns_range": "0:2048:4",
|
|
"delay_algo_range": "0:7:1",
|
|
"l2w_range": "0:1200:5",
|
|
"transpose_range": "0:1:1",
|
|
"load_range": "0:1:1",
|
|
"problem_sizes": [
|
|
"2^16",
|
|
"2^20",
|
|
"2^24",
|
|
"2^28",
|
|
"2^32"
|
|
]
|
|
},
|
|
"topk": {
|
|
"items_range": "7:24:1",
|
|
"threads_range": "128:1024:32",
|
|
"load_algo_range": "0:2:1"
|
|
},
|
|
"radix_sort": {
|
|
"items_range": "7:24:1",
|
|
"threads_range": "128:1024:32",
|
|
"radix_bits": 8
|
|
}
|
|
},
|
|
"dcid_mapping": {
|
|
"0": "no_delay",
|
|
"1": "fixed_delay",
|
|
"2": "exponential_backoff",
|
|
"3": "exponential_backoff_jitter",
|
|
"4": "exponential_backoff_jitter_window",
|
|
"5": "exponential_backon_jitter_window",
|
|
"6": "exponential_backon_jitter",
|
|
"7": "exponential_backon"
|
|
}
|
|
}
|