Harden intrinsic compile-time validation

[maleadt]

No description provided.

[github-actions]

CUDA.jl Benchmarks

Details

Benchmark suite	Current: cab8e53	Previous: afa2910	Ratio
array/accumulate/Float32/1d	97341 ns	97747 ns	1.00
array/accumulate/Float32/dims=1	70947 ns	71976 ns	0.99
array/accumulate/Float32/dims=1L	1598936 ns	1599967 ns	1.00
array/accumulate/Float32/dims=2	136437 ns	137440 ns	0.99
array/accumulate/Float32/dims=2L	659270 ns	660596 ns	1.00
array/accumulate/Int64/1d	117336 ns	117891 ns	1.00
array/accumulate/Int64/dims=1	75525 ns	76054 ns	0.99
array/accumulate/Int64/dims=1L	1715577 ns	1715738 ns	1.00
array/accumulate/Int64/dims=2	148561 ns	148322 ns	1.00
array/accumulate/Int64/dims=2L	986422 ns	987261 ns	1.00
array/broadcast	17914 ns	17989 ns	1.00
array/broadcast launch	8903 ns	9147 ns	0.97
array/construct	866.8888888888889 ns	875.4736842105264 ns	0.99
array/copy	16370 ns	16155 ns	1.01
array/copyto!/cpu_to_gpu	206266 ns	208486 ns	0.99
array/copyto!/gpu_to_cpu	240006 ns	240770 ns	1.00
array/copyto!/gpu_to_gpu	8709 ns	10136.333333333334 ns	0.86
array/iteration/findall/bool	132335 ns	132973 ns	1.00
array/iteration/findall/int	146478 ns	147213 ns	1.00
array/iteration/findfirst/bool	68390 ns	68985 ns	0.99
array/iteration/findfirst/int	69677 ns	70264 ns	0.99
array/iteration/findmin/1d	64206 ns	65866 ns	0.97
array/iteration/findmin/2d	99452 ns	99890 ns	1.00
array/iteration/logical	186807 ns	190437 ns	0.98
array/iteration/scalar	61912 ns	62891 ns	0.98
array/permutedims/2d	48427 ns	48712 ns	0.99
array/permutedims/3d	49649 ns	49818 ns	1.00
array/permutedims/4d	49467 ns	50140 ns	0.99
array/random/rand/Float32	10635 ns	11148 ns	0.95
array/random/rand/Int64	22840 ns	20832 ns	1.10
array/random/rand!/Float32	7769.75 ns	7712.75 ns	1.01
array/random/rand!/Int64	17815 ns	20257 ns	0.88
array/random/randn/Float32	32689 ns	33642 ns	0.97
array/random/randn!/Float32	24030 ns	23327 ns	1.03
array/reductions/mapreduce/Float32/1d	32396 ns	32777 ns	0.99
array/reductions/mapreduce/Float32/dims=1	37705 ns	37483 ns	1.01
array/reductions/mapreduce/Float32/dims=1L	50319 ns	50527 ns	1.00
array/reductions/mapreduce/Float32/dims=2	54804 ns	54952 ns	1.00
array/reductions/mapreduce/Float32/dims=2L	66959 ns	66867 ns	1.00
array/reductions/mapreduce/Int64/1d	39346 ns	40408 ns	0.97
array/reductions/mapreduce/Int64/dims=1	40678 ns	40598 ns	1.00
array/reductions/mapreduce/Int64/dims=1L	88483 ns	88591 ns	1.00
array/reductions/mapreduce/Int64/dims=2	57072 ns	57456 ns	0.99
array/reductions/mapreduce/Int64/dims=2L	83310 ns	83174 ns	1.00
array/reductions/reduce/Float32/1d	32596 ns	32826 ns	0.99
array/reductions/reduce/Float32/dims=1	37873 ns	38089 ns	0.99
array/reductions/reduce/Float32/dims=1L	50428 ns	50431 ns	1.00
array/reductions/reduce/Float32/dims=2	55101 ns	55201 ns	1.00
array/reductions/reduce/Float32/dims=2L	68538 ns	68585 ns	1.00
array/reductions/reduce/Int64/1d	39196 ns	40169 ns	0.98
array/reductions/reduce/Int64/dims=1	40334 ns	40395 ns	1.00
array/reductions/reduce/Int64/dims=1L	88359 ns	88535 ns	1.00
array/reductions/reduce/Int64/dims=2	57181 ns	57292 ns	1.00
array/reductions/reduce/Int64/dims=2L	82789 ns	82961 ns	1.00
array/reverse/1d	16948 ns	16982 ns	1.00
array/reverse/1dL	69638 ns	69764 ns	1.00
array/reverse/1dL_inplace	67336 ns	67354 ns	1.00
array/reverse/1d_inplace	8612 ns	8438 ns	1.02
array/reverse/2d	19872 ns	20209 ns	0.98
array/reverse/2dL	73133 ns	73660 ns	0.99
array/reverse/2dL_inplace	67190 ns	67230 ns	1.00
array/reverse/2d_inplace	9768 ns	12124 ns	0.81
array/sorting/1d	2638894 ns	2648896 ns	1.00
array/sorting/2d	1028658 ns	1028886 ns	1.00
array/sorting/by	3183213 ns	3183595 ns	1.00
cuda/synchronization/context/auto	1071.7 ns	1021.9 ns	1.05
cuda/synchronization/context/blocking	823.6625 ns	796.009900990099 ns	1.03
cuda/synchronization/context/nonblocking	5870.666666666667 ns	5942.4 ns	0.99
cuda/synchronization/stream/auto	871.6666666666666 ns	889.9791666666666 ns	0.98
cuda/synchronization/stream/blocking	664.5949367088608 ns	675.4285714285714 ns	0.98
cuda/synchronization/stream/nonblocking	5608.166666666667 ns	5698.571428571428 ns	0.98
integration/byval/reference	147850 ns	148004 ns	1.00
integration/byval/slices=1	148751 ns	149038 ns	1.00
integration/byval/slices=2	291706 ns	291758 ns	1.00
integration/byval/slices=3	434924 ns	434808 ns	1.00
integration/cudadevrt	105085 ns	105235 ns	1.00
integration/volumerhs	9150828 ns	9146301 ns	1.00
kernel/indexing	12923 ns	12981 ns	1.00
kernel/indexing_checked	13597 ns	13640 ns	1.00
kernel/launch	2155.4444444444443 ns	2330.777777777778 ns	0.92
kernel/occupancy	840.6 ns	791.2549019607843 ns	1.06
kernel/rand	14714 ns	16700 ns	0.88
latency/import	4093128115 ns	4072981641 ns	1.00
latency/precompile	4849615660 ns	4839233008 ns	1.00
latency/ttfp	4572739980 ns	4570871244 ns	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[kshyatt]

(Rebased to run this on top of the Crayons fix)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 92.70%. Comparing base (4fa9999) to head (cab8e53).
⚠️ Report is 3 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #3213      +/-   ##
==========================================
+ Coverage   92.66%   92.70%   +0.04%     
==========================================
  Files         184      185       +1     
  Lines       16170    16238      +68     
==========================================
+ Hits        14984    15054      +70     
+ Misses       1186     1184       -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.