[connortsui20]

Tracking Issue: #10701

Stacked on #11003. #11005 builds on it. No release gate.

Summary

Decimal widening preserves order, equality and validity, so ordered aggregates can use the child instead of copying it first. Sum also needs the logical result precision: using the child's sum dtype could overflow a result that should fit.

Changes

Ordered aggregates widen their child partials, and MinMax reuses exact cached child extrema before scanning. Decimal Sum runs in the logical sum dtype only when the legacy Stat::Sum path combines independent batch totals. SumV2 and Sum without skip_nans keep the fallback because their running sum can cancel a batch total that would overflow on its own. Tests compare running partials against fresh canonical batches so cached statistics cannot hide kernel work.

Historical local benchmark results

These retained measurements predate this style pass and rebase. They do not measure the current head.

cargo bench -p vortex-array --bench widen_decimal, Apple M4, medians. The numbers were measured at the top of this stack before the split, so they cover the whole stack, not this layer alone. The baseline is the canonical input, and the candidate is the same values as a Widen (child precision 5 under precision 10, 9 under 18, and 18 under 38). CodSpeed on this PR measures the layer itself.

bench	p10 canonical	p10 Widen	p18 canonical	p18 Widen	p38 canonical	p38 Widen
min_max	14.93 µs	15.12 µs	14.62 µs	15.12 µs	21.58 µs	14.95 µs

sum medians are within 8% of the canonical input at every precision.

API Changes

None.

[codspeed]

Merging this PR will regress 3 benchmarks

1 warning

⚠️ Walltime results may be unreliable

Some benchmarks used the Walltime instrument outside CodSpeed Macro Runners, which can make the results inconsistent.

Learn more about Macro Runners

See affected benchmarks

⚡ 9 improved benchmarks
❌ 3 regressed benchmarks
✅ 2348 untouched benchmarks

Warning

Please fix the performance issues or acknowledge them on CodSpeed.

Performance Changes

	Mode	Benchmark	BASE	HEAD	Efficiency
❌	Walltime	threshold_neon[80]	4.5 µs	5.7 µs	-21.94%
❌	CPU Simulation	encode_primitives[u8, (2000, 4)]	134.3 µs	163 µs	-17.6%
❌	CPU Simulation	take_filter_primitive_small_uncached_random_mask_random_indices[4096, 10]	20.5 µs	23.8 µs	-14.09%
⚡	CPU Simulation	min_max[p38_childp18_widen]	1,393.8 µs	436.9 µs	×3.2
⚡	CPU Simulation	filter_powerlaw_by_random[10000]	1,013.5 ns	348.4 ns	×2.9
⚡	CPU Simulation	sum[p38_childp18_widen]	1,221.6 µs	426.4 µs	×2.9
⚡	CPU Simulation	sum[p10_childp5_widen]	563.5 µs	236.3 µs	×2.4
⚡	CPU Simulation	sum[p18_childp9_widen]	563.5 µs	237.8 µs	×2.4
⚡	Walltime	mul_u64_nonnull_neon	39 µs	20.5 µs	+90.42%
⚡	CPU Simulation	min_max[p18_childp9_widen]	614.5 µs	324 µs	+89.65%
⚡	CPU Simulation	min_max[p10_childp5_widen]	614.6 µs	326 µs	+88.5%
⚡	Walltime	lt_i64_nullable_avx512	8.2 µs	7.4 µs	+11.96%

Tip

Investigate this regression by commenting @codspeedbot fix this regression on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing ct/decimal-widen-aggregates (5d992ff) with ct/decimal-widen-compare (e4a453e)}