vortex-data
vortex
Blog
Docs
Changelog
Blog
Docs
Changelog
Overview
Branches
Benchmarks
Runs
Performance History
Latest Results
Merge remote-tracking branch 'origin/develop' into ngates/arithmetic Signed-off-by: Nicholas Gates <nick@nickgates.com>
ngates/arithmetic
4 hours ago
More arithmetic benchmarks (#8402) Signed-off-by: Nicholas Gates <nick@nickgates.com>
develop
4 hours ago
Keep integer multiply benchmark inputs in range Signed-off-by: Nicholas Gates <nick@nickgates.com>
ngates/arith-bench
4 hours ago
Rename integer multiply benchmarks Signed-off-by: Nicholas Gates <nick@nickgates.com>
ngates/arith-bench
5 hours ago
Merge remote-tracking branch 'origin/develop' into lukim/exec-kernel-snapshot-develop
spiceai:lukim/exec-kernel-snapshot-develop
5 hours ago
Refactor binary arithmetic lifting Signed-off-by: Nicholas Gates <nick@nickgates.com>
ngates/arithmetic
5 hours ago
Merge branch 'develop' into lukim/scan-split-large-chunks-develop
spiceai:lukim/scan-split-large-chunks-develop
7 hours ago
perf(executor): cache ArrayKernels as a per-ExecutionCtx snapshot Resolve ArrayKernels once at ExecutionCtx construction into a KernelSnapshot (an ArcSwapMap::load_full of the execute-parent kernel map) instead of cloning the session and probing the sharded session-variable DashMap on every array node in the execute_until / single-step paths. This also stops holding the session-variable read guard across kernel invocation. The registry is session-scoped and mutable via its public register_* methods: an ExecutionCtx sees a point-in-time snapshot taken at construction, and later registrations are picked up by the next context (contexts are created per evaluation). Adds a pub(crate) ArcSwapMap::load_full accessor; the KernelSnapshot type and ArrayKernels::snapshot() are pub(crate), so no new public API is added. Signed-off-by: Luke Kim <80174+lukekim@users.noreply.github.com>
spiceai:lukim/exec-kernel-snapshot-develop
7 hours ago
Latest Branches
CodSpeed Performance Gauge
+22%
Arithmetic Operations
#8398
4 hours ago
74343cf
ngates/arithmetic
CodSpeed Performance Gauge
-19%
More arithmetic benchmarks
#8402
4 hours ago
8b3ccf2
ngates/arith-bench
CodSpeed Performance Gauge
0%
perf(executor): per-ExecutionCtx ArrayKernels snapshot
#8401
7 hours ago
2820b17
spiceai:lukim/exec-kernel-snapshot-develop
© 2026 CodSpeed Technology
Home
Terms
Privacy
Docs