[{"data":1,"prerenderedAt":179},["ShallowReactive",2],{"run:c1v3-12500-off-prof":3,"run-findings:c1v3-12500-off-prof":153},{"run":4,"config":18,"metrics":98,"curve":104,"assets":152},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":17},"c1v3-12500-off-prof","M7: per-kernel gpu_ms 再々計測 v2 (submission=per_kernel \u002F forward_submission=per_stage \u002F pipelining=off、M4 radix simd_ballot + A7 refine 3-pass 後の kernel)","Run summary · 2026-09-seminar05-milestones M7 (最終スタック確定 + msplat 等価再比較 + Pareto v3)","2026-08-30","splat","a556b78",[12,13,14,15,16],"p3-kernel-share-post-s3","m7","gpu-gate","lego","v2","partial",[19,22,25,28,31,34,37,40,43,46,49,52,55,58,61,64,67,70,73,76,79,81,84,87,89,92,95],{"key":20,"value":21},"dataset","\u002FUsers\u002Fotkrickey\u002Fdev\u002F3dgs-workspace\u002Fdatasets\u002Fnerf_synthetic\u002Flego",{"key":23,"value":24},"gt_convention","Premultiplied",{"key":26,"value":27},"iterations","12,500",{"key":29,"value":30},"seed","42",{"key":32,"value":33},"capacity","1,000,000 splats",{"key":35,"value":36},"sh_degree","3",{"key":38,"value":39},"loss","L1Ssim",{"key":41,"value":42},"lambda","0.200",{"key":44,"value":45},"ssim","window=7 sigma=1",{"key":47,"value":48},"backend.backward","Simd",{"key":50,"value":51},"backend.loss_path","Gpu",{"key":53,"value":54},"backend.emit_pairs","Original",{"key":56,"value":57},"backend.forward","F32",{"key":59,"value":60},"backend.dispatch","PerStage",{"key":62,"value":63},"backend.radix_scan","GpuHierarchical",{"key":65,"value":66},"backend.radix_scatter","SimdBallot",{"key":68,"value":69},"backend.binning","Resident",{"key":71,"value":72},"backend.tile_sort","GlobalRadix",{"key":74,"value":75},"backend.submission","PerKernel",{"key":77,"value":78},"backend.target_cache","true",{"key":80,"value":78},"backend.shader_fast_math",{"key":82,"value":83},"os_build","26.6.2 (25G83)",{"key":85,"value":86},"backend.ssim_clear","HostMemset",{"key":88,"value":86},"backend.raster_grad_clear",{"key":90,"value":91},"backend.backward_uniform","HostBuffer",{"key":93,"value":94},"backend.lazy_c3_scratch","false",{"key":96,"value":97},"backend.ssim_walk","PerChannel",{"psnr":99,"wallclock":100,"wallclock_regress":101,"splats":102,"final_loss":103},36.18955612182617,"2m 54s",false,409702,"5.481522e-3",{"loss":105,"splats":136},{"iters":106,"values":121},[107,108,109,110,111,112,113,114,115,116,117,118,119,120],1,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000,11000,12000,12500,[122,123,124,125,126,127,128,129,130,131,132,133,134,135],0.5938452482223511,0.05510123446583748,0.01383999828249216,0.008196663111448288,0.007204122841358185,0.006497407332062721,0.006075368262827396,0.005909476429224014,0.00576668418943882,0.005665606819093227,0.0056185354478657246,0.005523084197193384,0.0054887328296899796,0.005481521598994732,{"iters":137,"values":138},[107,108,109,110,111,112,113,114,115,116,117,118,119,120],[139,140,141,142,143,144,145,146,147,148,149,150,151,102],5207,8208,183008,297681,350476,376489,391352,399286,403461,405746,406820,407646,408944,{"has_renders":101,"has_splat":101},[154],{"id":155,"title":156,"date":157,"status":158,"polarity":159,"category":160,"axes":161,"tags":163,"task_code":169,"related_runs":170,"delta_psnr":173,"delta_wallclock":174,"rank":175,"verdict":176,"impact_summary":177,"detail_path":178},"p3-kernel-share-drums","drums (998k splats @30k, in-window 749k @12.5k) per-kernel share 実測 — share 構造は Lego とほぼ不変 (backward_raster 40.09% vs 40.07%)、絶対 ms\u002Fiter 差は binary vintage (S4b+C2) で汚染","2026-08-31","stable","mixed","measurement",[107,162],3,[155,164,165,166,167,14,168],"multi-scene","drums","per-kernel-gpu-ms","kernel-share","binary-vintage-caveat","次フェーズ タスクリスト — 多 scene 検証 (drums per-kernel share)",[171,172,5],"c1-drums-12500-off-prof","c1v2-12500-off-prof","n\u002Fa (drums self-eval mean val PSNR 24.518 dB @12.5k — non-converged 途中経過、多 scene 退行チェックの正式値ではない。参照: multiscene-drums-30k baseline は 30k 収束時 27.217 dB)","drums: train elapsed 249.77s (n=1) \u002F Lego v2: 174.57s (n=1)。**両方とも production baseline とは比較しない** — submission=per_kernel\u002Fforward_submission=per_stage\u002Fpipelining=off の 3 重に非 production な測定専用 regime (busy% drums 68.3%、Lego v2 65.6%)。意味があるのは kernel 単体の gpu_ms とその share のみ","medium","share-structure-invariant-under-1.85x-splat-scale \u002F absolute-ms-comparison-contaminated-by-binary-vintage","Lego で判断された今日の最適化候補が drums (998k splats @30k、Lego の 2.5倍) でも同じ share 構造で有効かを判定した。drums 12.5k を Lego v2 と同一 regime (submission=per_kernel\u002Fforward_submission=per_stage\u002Fpipelining=off) で 1 run 実測した結果、\u003Cstrong>per-kernel share は Lego v2 とほぼ同一\u003C\u002Fstrong> (backward_raster 40.09% vs 40.07%、adam 15.52% vs 15.28%、rasterize 14.94% vs 14.13%、ssim 12.75% vs 13.12%、radix 11.37% vs 12.01% — 全 kernel で Δ≤1.5pt)。\u003Cstrong>splat 数が 1.85倍 (in-window 748,708 vs 404,652) 違っても share 順位・構造がほぼ動かない\u003C\u002Fstrong>という結果は、Lego で優先度付けした施策 (M3 系 backward・M4 radix・S4b ssim 等) の相対重要度が drums でも維持されることを示唆する。\u003Cstrong>ただし絶対 ms\u002Fiter の比較は binary vintage 差で汚染されている\u003C\u002Fstrong> — 比較対象の Lego v2 は commit a446f2c、drums は HEAD 3db33a8 で、間に S4b (ssim_reduce=gpu default flip) と C2 計装 (全 CB へ kernel timestamp 収集追加) が入っている。splat 数と無関係なはずの ssim_fwd_grad が 1.446倍 (1.202→1.738 ms\u002Fiter) 増えている一方、全 9 leaf kernel が揃って 1.17〜1.93倍という比較的均一な増加を示しており、これは\u003Cstrong>純粋な splat-count scaling では説明しにくく、binary vintage (S4b\u002FC2) 由来の系統的な底上げが乗っている可能性が高い\u003C\u002Fstrong>。よって「share の相対構造」は信頼できるが「ms\u002Fiter の絶対値・scaling 係数」は次ラウンドで Lego 側も HEAD で撮り直すまで確定できない。","\u002Ffindings\u002Fp3-kernel-share-drums\u002F",1790227323336]