56 lines
2.1 KiB
JSON
56 lines
2.1 KiB
JSON
{
|
|
"status": "rejected",
|
|
"reason": "The exact temporal two-pair QK/PV schedule improved the isolated mainloop by only 0.10% and missed the absolute 220 ms gate.",
|
|
"device": "NVIDIA GB10",
|
|
"compute_capability": "SM121",
|
|
"source_commit": "d1a57a546c3d395b1ffcbeecc66d81db76f3b4b5",
|
|
"candidate": {
|
|
"name": "temporal-pair",
|
|
"description": "Two warp pairs alternate QK/online-softmax and prior-tile PV while preserving private per-warp scores, softmax state, and output accumulators.",
|
|
"production_dispatch": "unchanged"
|
|
},
|
|
"correctness": {
|
|
"compute_sanitizer_errors": 0,
|
|
"short_shape_cases": 13,
|
|
"short_shape_result": "byte-exact",
|
|
"real_block": 24,
|
|
"real_tokens": 37810,
|
|
"real_heads": 56,
|
|
"reference_output_sha256": "4c666c20f5f8f651158a2ced33ccff08f3bada07665c595b99008d171db30574",
|
|
"candidate_output_sha256": "4c666c20f5f8f651158a2ced33ccff08f3bada07665c595b99008d171db30574"
|
|
},
|
|
"ptxas": {
|
|
"baseline": {
|
|
"registers_per_thread": 255,
|
|
"static_spill_stores_bytes": 24,
|
|
"static_spill_loads_bytes": 24
|
|
},
|
|
"candidate": {
|
|
"registers_per_thread": 254,
|
|
"static_spill_stores_bytes": 32,
|
|
"static_spill_loads_bytes": 24
|
|
},
|
|
"dynamic_shared_memory_bytes": 32768
|
|
},
|
|
"timing": {
|
|
"rounds": 5,
|
|
"iterations_per_round": 10,
|
|
"baseline_p50_ms": 245.437279,
|
|
"candidate_p50_ms": 245.198769,
|
|
"speedup_percent": 0.097272,
|
|
"candidate_gate_ms": 220.0,
|
|
"gate_result": "fail"
|
|
},
|
|
"decision": {
|
|
"ncu_followup": "skipped because the latency gate failed",
|
|
"block_integration": "skipped",
|
|
"trajectory_validation": "skipped",
|
|
"runtime_integration": "not attempted",
|
|
"conclusion": "Temporal separation alone does not unlock material INT-QK/FP8-PV overlap in the existing SM89 instruction stream on SM121. Further exact work requires a substantially different mainloop or native Blackwell numerical contract."
|
|
},
|
|
"source_artifacts": [
|
|
"research/sage2_temporal_pair/patches/0001-sm89-temporal-two-pair-qk-pv.patch",
|
|
"benchmarks/gb10-sage2-temporal-pair-short-20260825-p0.json",
|
|
"benchmarks/gb10-sage2-temporal-pair-timing-20260825-p0.json"
|
|
]
|
|
}
|