[christiangnrd]

Rationals: JuliaGPU/OpenCL.jl#567
Show fix: JuliaGPU/OpenCL.jl@ac06098

[github-actions]

Benchmark results

Compared with 7d2ea0f46, the latest measured ancestor of the merge base (2 commits before it).
The environment differs from the baseline's: JSON 1.13.0 → 1.13.4, Parsers 3.0.3 → 3.0.5, SPIRVIntrinsics 1.5.1 → 1.6.0, StructUtils 2.11.2 → 2.12.0, StructUtilsStaticArraysCoreExt 2.11.2 → 2.12.0.

Times are the minimum time of every benchmark. A change is unusual when it exceeds both three times the benchmark's typical change between consecutive runs on the default branch and a minimum per category (performance 3%, latency 5%, applications 3%, other 3%). A benchmark that starts or stops allocating is listed however few the allocations. A single run can still be a fluke, so rerun before drawing conclusions.

	Geometric mean	Unusual: slower	Unusual: faster	Compared
Performance	+0.5%	0	0	32
Latency	−2.6%	0	0	13
Applications	−0.7%	0	0	5

No unusual changes.

All benchmarks

Benchmark	Baseline	This PR	Change
Performance
julia/serial/arithmetic/muladd-reference	655 µs	655 µs	−0.0%	noise unknown
julia/serial/math/exp-f64-reference	290 µs	291 µs	+0.6%	noise unknown
julia/serial/narrow/masked-reference	711 µs	714 µs	+0.5%	noise unknown
pocl/parallel/atomics/histogram	5.16 ms	5.14 ms	−0.4%	noise unknown
pocl/parallel/groupreduce/add-f64	1.66 ms	1.65 ms	−0.1%	noise unknown
pocl/parallel/groupreduce/fallback	18.1 ms	18.1 ms	−0.0%	noise unknown
pocl/parallel/groupscan/add-i32	2.53 ms	2.52 ms	−0.4%	noise unknown
pocl/parallel/indexing/cartesian3d	77.8 µs	78.6 µs	+0.9%	noise unknown
pocl/parallel/indexing/linear3d	78.4 µs	78.8 µs	+0.5%	noise unknown
pocl/parallel/indexing/ntuple3d	79.5 µs	79.2 µs	−0.3%	noise unknown
pocl/parallel/indexing/ntuple4d	165 µs	162 µs	−1.5%	noise unknown
pocl/parallel/localmem/transpose-naive	457 µs	456 µs	−0.2%	noise unknown
pocl/parallel/localmem/transpose-tiled	104 µs	114 µs	+9.3%	noise unknown
pocl/parallel/private/across-barrier	165 µs	165 µs	−0.2%	noise unknown
pocl/parallel/scheduling/default	182 µs	181 µs	−0.3%	noise unknown
pocl/parallel/scheduling/explicit	181 µs	181 µs	+0.0%	noise unknown
pocl/parallel/stream/copy/cache	784 ns	687 ns	−12.4%	noise unknown
pocl/parallel/stream/copy/dram	6.25 ms	6.29 ms	+0.6%	noise unknown
pocl/parallel/stream/triad/cache	7.54 µs	7.05 µs	−6.5%	noise unknown
pocl/parallel/stream/triad/dram	8.73 ms	9.46 ms	+8.4%	noise unknown
pocl/parallel/util/copyto-small	24.0 ns	27.0 ns	+12.5%	noise unknown
pocl/parallel/util/zeros-large	999 µs	1.01 ms	+1.3%	noise unknown
pocl/parallel/util/zeros-small	632 ns	628 ns	−0.6%	noise unknown
pocl/serial/arithmetic/contract	1.91 ms	1.90 ms	−0.2%	noise unknown
pocl/serial/arithmetic/muladd	765 µs	764 µs	−0.2%	noise unknown
pocl/serial/const/marked	727 µs	738 µs	+1.5%	noise unknown
pocl/serial/const/unmarked	914 µs	919 µs	+0.5%	noise unknown
pocl/serial/math/exp-f64	146 µs	146 µs	+0.3%	noise unknown
pocl/serial/math/sin-f64	191 µs	191 µs	+0.1%	noise unknown
pocl/serial/narrow/masked	815 µs	835 µs	+2.4%	noise unknown
pocl/serial/narrow/unmasked	788 µs	794 µs	+0.8%	noise unknown
pocl/serial/stream/triad/dram	8.61 ms	8.61 ms	+0.1%	noise unknown
Latency
host/import/ka	509 ms	508 ms	−0.1%	noise unknown
host/precompile/ka	44.8 s	44.4 s	−1.0%	noise unknown
host/startup	131 ms	129 ms	−1.2%	noise unknown
pocl/parallel/launch/dynamic-default	4.36 µs	4.55 µs	+4.4%	noise unknown
pocl/parallel/launch/groupreduce-f64	6.59 µs	5.39 µs	−18.2%	noise unknown
pocl/parallel/launch/many-args	12.1 µs	10.1 µs	−16.9%	noise unknown
pocl/parallel/launch/partial-workgroup	4.25 µs	4.31 µs	+1.4%	noise unknown
pocl/serial/compile/groupreduce	1.86 s	1.88 s	+1.2%	noise unknown
pocl/serial/compile/localmem-barrier	718 ms	711 ms	−0.9%	noise unknown
pocl/serial/compile/new-kernel	109 ms	110 ms	+0.3%	noise unknown
pocl/serial/compile/new-workgroupsize	13.6 ms	13.7 ms	+1.0%	noise unknown
pocl/serial/first-kernel/cold-cache	2.05 s	2.05 s	+0.2%	noise unknown
pocl/serial/first-kernel/warm-cache	386 ms	385 ms	−0.3%	noise unknown
Applications
pocl/parallel/dgsem/fluxdiff-node	295 µs	292 µs	−0.8%	noise unknown
pocl/parallel/dgsem/weak-element	160 µs	159 µs	−0.7%	noise unknown
pocl/parallel/dgsem/weak-node-localmem	119 µs	117 µs	−1.2%	noise unknown
pocl/parallel/stencil/timestep	7.65 ms	7.77 ms	+1.6%	noise unknown
pocl/serial/stencil/timestep	11.5 ms	11.2 ms	−2.5%	noise unknown

History: https://juliagpu.org/perf/?pkg=kernelabstractions

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 83.93%. Comparing base (81aca7d) to head (3491a89).

Additional details and impacted files

@@            Coverage Diff             @@
##           isbits     #944      +/-   ##
==========================================
+ Coverage   83.85%   83.93%   +0.07%     
==========================================
  Files          31       31              
  Lines        2533     2533              
==========================================
+ Hits         2124     2126       +2     
+ Misses        409      407       -2     

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

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