← all workloads

emit_glsl

A single moderately complex shader. Compiled to multiple targets by the harness (same source, varying -target) to isolate generateOutput cost. ``n`` scales the amount of straight-line math the backend must emit. Scaling null: n scales op count and the emitted output is O(n); ideal codegen cost is O(n).

bucket: codegen_source  ·  mode: target  ·  flags: -target glsl -entry computeMain

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.

emit_glsl — phase composition vs N (v2026.5, median ms) emit_glsl 28.2× over N 100→800 0.0 1030 2061 100 200 400 800 N emit_glsl — parseTranslationUnit emit_glsl — SemanticChecking emit_glsl — generateIR emit_glsl — frontEndExecute (self) emit_glsl — specializeModule emit_glsl — simplifyIR emit_glsl — linkIR emit_glsl — unrollLoopsInModule emit_glsl — legalizeResourceTypes emit_glsl — legalizeExistentialTypeLayout emit_glsl — performMandatoryEarlyInlining emit_glsl — performForceInlining emit_glsl — emitEntryPointsSourceFromIR emit_glsl — 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×
100–80091.680.9926819083.92×

Growth attribution (N=100 → N=800)

compileInner grows by 1840 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=100t@N=800Δ msshare× lin∝Nk
emitEntryPointsSourceFromIR18895+87748%4.44×1.89
legalizeExistentialTypeLayout7435+42823%5.15×2.03
legalizeResourceTypes7429+42223%5.21×2.02
SemanticChecking28107+794%0.70×0.71

Near-constant (≤2% of growth each): generateIR (4→17 ms), specializeModule (2→12 ms), simplifyIR (1→9 ms), parseTranslationUnit (0→2 ms), linkIR (1→2 ms), frontEndExecute (self) (0→1 ms), performMandatoryEarlyInlining (0→0 ms), performForceInlining (0→0 ms), unrollLoopsInModule (0→0 ms), compileInner (self) (0→0 ms).

Sweep numbers (median ms)

NcompileInneremitEntryPointsSourceFromIRgenerateOutput
100683535
200153106106
400487413413
800190817821783