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 cuda
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.
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 range | floor (ms) | k (work) | fit R² | t(Nmin) | t(Nmax) | top-2× |
|---|---|---|---|---|---|---|
| 100–800 | 11 | 1.57 | 0.992 | 45 | 922 | 3.56× |
compileInner grows by 877 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.
| bucket | t@N=100 | t@N=800 | Δ ms | share | × lin | ∝Nk |
|---|---|---|---|---|---|---|
| emitEntryPointsSourceFromIR | 13 | 447 | +433 | 49% | 3.46× | 1.70 |
| linkAndOptimizeIR (self) | 3 | 337 | +335 | 38% | 7.22× | 2.40 |
| SemanticChecking | 15 | 61 | +46 | 5% | 0.85× | 0.86 |
| simplifyIR | 3 | 28 | +25 | 3% | 1.05× | 1.02 |
| specializeModule | 4 | 26 | +22 | 3% | 0.91× | 0.92 |
Near-constant (≤2% of growth each): generateIR (5→16 ms), linkIR (1→2 ms), parseTranslationUnit (0→2 ms), compileInner (self) (0→2 ms), performMandatoryEarlyInlining (0→1 ms), performForceInlining (0→1 ms), frontEndExecute (self) (0→0 ms), unrollLoopsInModule (0→0 ms).
| N | compileInner | emitEntryPointsSourceFromIR | generateOutput |
|---|---|---|---|
| 100 | 45 | 24 | 25 |
| 200 | 92 | 63 | 63 |
| 400 | 259 | 212 | 213 |
| 800 | 922 | 841 | 842 |