← all workloads

ir_builder

One enormous straight-line function: `n` trivial integer SSA ops, almost no semantic work. Stresses IR instruction construction / dedup / hash-cons and the SSA simplifier (the shared IRBuilder layer the v2026.7 release regressed). Scaling null: n scales straight-line op count; ideal cost is O(n) with amortized-constant hash-consing, so super-linear sweep growth means IR dedup/use-list structures scale worse than the code.

bucket: ir_infra  ·  mode: target  ·  flags: -target spirv -emit-spirv-directly

Phase composition vs N (stacked sub-counters)

compileInner split into phase buckets (named leaves + (self) residuals) stacked across the sweep sizes — the top edge is compileInner, so you can see which phase drives the scaling.

ir_builder — phase composition vs N (v2026.13.1, median ms) ir_builder 3.5× over N 500→4000 0.0 35 70 500 1000 2000 4000 N ir_builder — parseTranslationUnit ir_builder — SemanticChecking ir_builder — generateIR ir_builder — frontEndExecute (self) ir_builder — specializeModule ir_builder — simplifyIR ir_builder — linkIR ir_builder — legalizeResourceTypes ir_builder — legalizeExistentialTypeLayout ir_builder — performMandatoryEarlyInlining ir_builder — performForceInlining ir_builder — linkAndOptimizeIR (self) ir_builder — generateOutput (self) ir_builder — compileInner (self) phase buckets parseTranslationUnit SemanticChecking generateIR frontEndExecute (self) specializeModule simplifyIR linkIR unrollLoopsInModule legalizeResourceTypes legalizeExistentialTypeLayout performMandatoryEarlyInlining performForceInlining linkAndOptimizeIR (self) emitEntryPointsSourceFromIR generateOutput (self) compileInner (self)

Scaling analysis

floor-subtracted power-law fit (t − floor) = a·Nk; floor = the minimal workload (fixed per-compile cost), k the global exponent, top-2× the local high-end doubling ratio.

N rangefloor (ms)k (work)fit R²t(Nmin)t(Nmax)top-2×
500–4000110.930.99319651.71×

Growth attribution (N=500 → N=4000)

compileInner grows by 46 ms across the sweep; the mutually-exclusive phase buckets below partition that growth exactly (no nested-timer double counting). × lin is the same metric as the top-level panels, per bucket: the end point vs a linear expectation anchored to the bucket's share of the minimal floor and fitted on the low-N half — 1.0 = grew exactly linearly, >1 bends up. The super-linearity lives where × lin (and k) are red.

buckett@N=500t@N=4000Δ msshare× lin∝Nk
generateOutput (self)416+1226%0.97×0.91
linkAndOptimizeIR (self)29+716%1.14×1.09
SemanticChecking714+714%0.86×0.77
simplifyIR18+714%1.07×1.02
generateIR28+613%1.07×1.02

Also growing (below top-5): specializeModule (+3 ms, 6%), parseTranslationUnit (+2 ms, 4%), linkIR (+1 ms, 3%), legalizeExistentialTypeLayout (+1 ms, 3%), legalizeResourceTypes (+1 ms, 2%).

Near-constant (≤2% of growth each): frontEndExecute (self) (1→0 ms), compileInner (self) (0→0 ms), performForceInlining (0→0 ms), performMandatoryEarlyInlining (0→0 ms).

Sweep numbers (median ms)

NcompileInnergenerateIRsimplifyIR
5001921
10002432
20003844
40006588