[{"data":1,"prerenderedAt":166},["ShallowReactive",2],{"run:lego-w2-chained-12500-rep2":3,"run-findings:lego-w2-chained-12500-rep2":138},{"run":4,"config":20,"metrics":83,"curve":89,"assets":137},{"id":5,"title":5,"subtitle":6,"eyebrow":7,"date":8,"workspace":9,"commit":10,"tags":11,"verdict":19},"lego-w2-chained-12500-rep2","2026-08 1× 工程表 v2 W2 — encoder\u002FCB 統合 chained submission (bit-exact) の 12.5k PSNR guard + wallclock gate (rep2\u002F3 — PSNR guard は n=3 mean 判定)","Run summary · 1x roadmap v2 W2","2026-08-16","splat","671e6b0",[12,13,14,15,16,17,18],"p2-w2","chained-submission","encoder-cb","gpu-gate","lego-12500","brush-compat","premultiplied","partial",[21,24,27,30,33,36,39,42,45,48,51,54,57,60,63,66,69,72,75,78,80],{"key":22,"value":23},"dataset","\u002FUsers\u002Fotkrickey\u002Fdev\u002F3dgs-workspace\u002Fdatasets\u002Fnerf_synthetic\u002Flego",{"key":25,"value":26},"gt_convention","Premultiplied",{"key":28,"value":29},"iterations","12,500",{"key":31,"value":32},"seed","42",{"key":34,"value":35},"capacity","1,000,000 splats",{"key":37,"value":38},"sh_degree","3",{"key":40,"value":41},"loss","L1Ssim",{"key":43,"value":44},"lambda","0.200",{"key":46,"value":47},"ssim","window=7 sigma=1",{"key":49,"value":50},"backend.backward","Simd",{"key":52,"value":53},"backend.loss_path","Gpu",{"key":55,"value":56},"backend.emit_pairs","Original",{"key":58,"value":59},"backend.forward","F32",{"key":61,"value":62},"backend.dispatch","PerStage",{"key":64,"value":65},"backend.radix_scan","Cpu",{"key":67,"value":68},"backend.binning","Resident",{"key":70,"value":71},"backend.tile_sort","GlobalRadix",{"key":73,"value":74},"backend.submission","Chained",{"key":76,"value":77},"backend.target_cache","true",{"key":79,"value":77},"backend.shader_fast_math",{"key":81,"value":82},"os_build","26.5.2 (25F84)",{"psnr":84,"wallclock":85,"wallclock_regress":86,"splats":87,"final_loss":88},36.203433990478516,"3m 44s",false,407135,"5.493475e-3",{"loss":90,"splats":121},{"iters":91,"values":106},[92,93,94,95,96,97,98,99,100,101,102,103,104,105],1,1000,2000,3000,4000,5000,6000,7000,8000,9000,10000,11000,12000,12500,[107,108,109,110,111,112,113,114,115,116,117,118,119,120],0.593845009803772,0.05431508272886276,0.0137704536318779,0.00822716485708952,0.007348175626248121,0.006501145660877228,0.006135345436632633,0.005945616867393255,0.00579548254609108,0.00568044651299715,0.005569683853536844,0.005522825289517641,0.0054590729996562,0.005493475124239922,{"iters":122,"values":123},[92,93,94,95,96,97,98,99,100,101,102,103,104,105],[124,125,126,127,128,129,130,131,132,133,134,135,136,87],5207,8219,182072,297986,349590,374753,388825,396799,401124,403151,404216,405089,406333,{"has_renders":86,"has_splat":86},[139],{"id":140,"title":141,"date":8,"status":142,"polarity":143,"category":144,"axes":145,"tags":147,"task_code":156,"related_runs":157,"delta_psnr":160,"delta_wallclock":161,"rank":162,"verdict":163,"impact_summary":164,"detail_path":165},"p2-w2-chained-submission","W2 encoder\u002FCB 統合 — replay -13.7% \u002F 12.5k -9.1% (bit-exact、default flip)","stable","positive","experiment",[92,146],3,[148,149,13,150,151,152,153,154,155],"1x-roadmap-v2","w2","command-buffer","encoder","set-bytes","bit-exact","lego","unified-memory","2026-08 1× 工程表 v2 W2",[158,5,159],"lego-w2-chained-12500","lego-w2-chained-12500-rep3","12.5k gate n=3: 36.160 \u002F 36.203 \u002F 36.146 dB → mean 36.170 dB = W1 基準 36.201 (n=3 mean) 比 -0.031 dB (guard ±0.1 内、n=3 mean 判定 — n=1 判定なし)","replay bench final regime: 20.869 → 18.005 ms\u002Fiter = **-13.7%** (clean batch 帯 -13.7〜-16.2%、閾値 max(2σ,1%)=1.9%)。iter5000 regime: clean 帯 18.60〜19.76 → 16.56〜16.61 = **-10.7〜-15.9%** (閾値 ≤2.8%)。12.5k full run n=3: 213.42 \u002F 224.83 \u002F 220.27s → mean **219.51s** (W1 基準 241.41s 比 **-9.1%**)","high","w2-adopted-default-flip-chained","1× 工程表 v2 の第 2 波。HW 4 軸調査 #2 の CB\u002Fwait 監査 (本実装 ~21 CB \u002F ~11 wait vs msplat 1 CB \u002F 0 wait) を受け、submission 戦略を BackendConfig の enum variant として実装・gate した。同一 CB 内の連続 encoder は firmware が CPU 介在なしに back-to-back 実行するため、per-kernel の commit + waitUntilCompleted (0.1〜1 ms 級の full round trip) が丸ごと消える。replay 全体で -13.7% (final)、12.5k full run は 241.41 → 219.51s で msplat 同日等価 gap は 1.44× → 1.31× に縮小。累計 (数学的同値の施策のみ) は 766.07 → 219.51s = -71.3%。expected gate 帯 -5〜15% (F.3 overlap 割引済) のほぼ上限で着弾し、F.3 (radix GPU scan) が単独敗北した『wait 除去』が、chain 全体の統合では大きく勝つことを示した — 部分 wait 除去と全 chain 統合の ROI 差は axis 3 (unified memory \u002F submission 論) の narrative 素材。次の律速は forward 30% (radix 18% 内数) \u002F chain GPU 26%。","\u002Ffindings\u002Fp2-w2-chained-submission\u002F",1790227324544]