[diskann-wide] Add sumtree for 64-bit types

[hildebrandmw]

Add SIMDSumTree requirement/impls for u64x2 and u64x4 types (and for the currently one-off i64x2 in Neon).

This is part of a series of PRs for better AVX-512 1-bit kernels.

AI Disclaimer: the author cannot currently type well, a directed agent did most of the changes. Fortunately, most are mechanical.

[Copilot]

Pull request overview

This PR extends diskann-wide’s reduction support by adding SIMDSumTree as a requirement and providing implementations/tests for 64-bit integer SIMD vectors (u64x2, u64x4, plus i64x2 on Neon). This supports upcoming AVX-512 1-bit kernel work by making horizontal lane-sum reductions uniformly available for these types.

Changes:

• Add Emulated<i64, {2,4}> and Emulated<u64, {2,4}> SIMDSumTree implementations and corresponding tests.
• Implement SIMDSumTree for x86_64 u64x2/u64x4 for both V3 (direct intrinsics) and V4 (retargeting to V3).
• Add Neon SIMDSumTree implementations for u64x2 and i64x2, and require SIMDSumTree for u64x2/u64x4 in the Architecture trait.

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
diskann-wide/src/emulated.rs	Adds sum-tree reductions + tests for emulated i64/u64 vectors (2/4 lanes).
diskann-wide/src/arch/x86_64/v4/u64x4_.rs	Adds SIMDSumTree for u64x4 (V4), plus a reduction test.
diskann-wide/src/arch/x86_64/v4/u64x2_.rs	Adds SIMDSumTree for u64x2 (V4), plus a reduction test.
diskann-wide/src/arch/x86_64/v3/u64x4_.rs	Adds an intrinsic-based SIMDSumTree implementation for u64x4 (V3), plus a test.
diskann-wide/src/arch/x86_64/v3/u64x2_.rs	Adds an intrinsic-based SIMDSumTree implementation for u64x2 (V3), plus a test.
diskann-wide/src/arch/mod.rs	Requires SIMDSumTree on the Architecture trait’s u64x2 and u64x4 vectors.
diskann-wide/src/arch/aarch64/u64x2_.rs	Adds Neon SIMDSumTree for u64x2 (with Miri fallback) + test.
diskann-wide/src/arch/aarch64/i64x2_.rs	Adds Neon SIMDSumTree for i64x2 (with Miri fallback) + test.
diskann-wide/src/arch/aarch64/double.rs	Adds a sum-tree test for u64x4 (implemented via Doubled<T>’s SIMDSumTree).

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[codecov-commenter]

Codecov Report

❌ Patch coverage is 71.42857% with 6 lines in your changes missing coverage. Please review.
✅ Project coverage is 91.47%. Comparing base (2ee97ff) to head (14ee85b).

Files with missing lines	Patch %	Lines
diskann-wide/src/arch/x86_64/v4/u64x2_.rs	0.00%	3 Missing ⚠️
diskann-wide/src/arch/x86_64/v4/u64x4_.rs	0.00%	3 Missing ⚠️

❌ Your patch status has failed because the patch coverage (71.42%) is below the target coverage (90.00%). You can increase the patch coverage or adjust the target coverage.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1311   +/-   ##
=======================================
  Coverage   91.46%   91.47%           
=======================================
  Files         516      516           
  Lines       98276    98297   +21     
=======================================
+ Hits        89891    89914   +23     
+ Misses       8385     8383    -2     

Flag	Coverage Δ
miri	91.47% <71.42%> (+<0.01%)	⬆️
unittests	91.14% <71.42%> (+<0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
diskann-wide/src/arch/mod.rs	83.79% <ø> (ø)
diskann-wide/src/arch/x86_64/v3/u64x2_.rs	100.00% <100.00%> (ø)
diskann-wide/src/arch/x86_64/v3/u64x4_.rs	100.00% <100.00%> (ø)
diskann-wide/src/emulated.rs	98.29% <ø> (ø)
diskann-wide/src/arch/x86_64/v4/u64x2_.rs	50.00% <0.00%> (-7.15%)	⬇️
diskann-wide/src/arch/x86_64/v4/u64x4_.rs	50.00% <0.00%> (-7.15%)	⬇️

... and 5 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.