← all workloads

codegen_spirv

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  ·  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.

codegen_spirv — phase composition vs N (v2026.13.1, median ms) codegen_spirv 24.5× over N 100→800 0.0 699 1399 100 200 400 800 N codegen_spirv — parseTranslationUnit codegen_spirv — SemanticChecking codegen_spirv — generateIR codegen_spirv — frontEndExecute (self) codegen_spirv — specializeModule codegen_spirv — simplifyIR codegen_spirv — linkIR codegen_spirv — unrollLoopsInModule codegen_spirv — legalizeResourceTypes codegen_spirv — legalizeExistentialTypeLayout codegen_spirv — performMandatoryEarlyInlining codegen_spirv — performForceInlining codegen_spirv — linkAndOptimizeIR (self) codegen_spirv — generateOutput (self) codegen_spirv — 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×
100–800111.650.9915312953.76×

Growth attribution (N=100 → N=800)

compileInner grows by 1242 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
linkAndOptimizeIR (self)8498+49039%5.50×2.03
legalizeExistentialTypeLayout4309+30525%5.84×2.12
legalizeResourceTypes4304+30124%5.77×2.11
SemanticChecking1561+464%0.86×0.86
generateOutput (self)744+363%1.04×1.02

Near-constant (≤2% of growth each): specializeModule (4→28 ms), simplifyIR (3→28 ms), generateIR (5→16 ms), linkIR (1→2 ms), parseTranslationUnit (0→2 ms), compileInner (self) (1→1 ms), performForceInlining (0→1 ms), performMandatoryEarlyInlining (0→1 ms), frontEndExecute (self) (0→0 ms), unrollLoopsInModule (0→0 ms).

Sweep numbers (median ms)

NcompileInnergenerateOutput
1005332
20011182
400344299
80012951215