Fix compat in profile

[vchuravy]

No description provided.

[maleadt]

Doesn't it need an additional empty line too?

[github-actions]

CUDA.jl Benchmarks

Details

Benchmark suite	Current: 3151c6c	Previous: 0b05451	Ratio
latency/precompile	44931145637 ns	4612556023 ns	9.74
latency/ttfp	12943499837 ns	4408562143 ns	2.94
latency/import	3563511009 ns	3821839641 ns	0.93
integration/volumerhs	9440699.5 ns	9448669.5 ns	1.00
integration/byval/slices=1	146095 ns	145839 ns	1.00
integration/byval/slices=3	423324 ns	423425 ns	1.00
integration/byval/reference	144115 ns	144031 ns	1.00
integration/byval/slices=2	285137 ns	284559 ns	1.00
integration/cudadevrt	102657.5 ns	102661 ns	1.00
kernel/indexing	13221 ns	13693 ns	0.97
kernel/indexing_checked	13979 ns	14309 ns	0.98
kernel/occupancy	668.2151898734177 ns	663.8086419753087 ns	1.01
kernel/launch	2156.3333333333335 ns	2210.6666666666665 ns	0.98
kernel/rand	14582 ns	16005 ns	0.91
array/reverse/1d	18785 ns	18568 ns	1.01
array/reverse/2dL_inplace	66191 ns	66179 ns	1.00
array/reverse/1dL	69282 ns	69124 ns	1.00
array/reverse/2d	21586 ns	21081 ns	1.02
array/reverse/1d_inplace	10600.666666666666 ns	8671.333333333334 ns	1.22
array/reverse/2d_inplace	10583 ns	10405 ns	1.02
array/reverse/2dL	73490 ns	73273 ns	1.00
array/reverse/1dL_inplace	66213 ns	66158 ns	1.00
array/copy	18706 ns	18801 ns	0.99
array/iteration/findall/int	149764 ns	149677 ns	1.00
array/iteration/findall/bool	132247 ns	132815 ns	1.00
array/iteration/findfirst/int	84317 ns	84077 ns	1.00
array/iteration/findfirst/bool	82632 ns	81834 ns	1.01
array/iteration/scalar	67579 ns	67842 ns	1.00
array/iteration/logical	201911 ns	205668 ns	0.98
array/iteration/findmin/1d	89632 ns	88143.5 ns	1.02
array/iteration/findmin/2d	117317 ns	117602 ns	1.00
array/reductions/reduce/Int64/1d	43074 ns	43879 ns	0.98
array/reductions/reduce/Int64/dims=1	42319 ns	42363.5 ns	1.00
array/reductions/reduce/Int64/dims=2	59769 ns	59729 ns	1.00
array/reductions/reduce/Int64/dims=1L	87694 ns	87783 ns	1.00
array/reductions/reduce/Int64/dims=2L	84746 ns	84600.5 ns	1.00
array/reductions/reduce/Float32/1d	34775.5 ns	35554 ns	0.98
array/reductions/reduce/Float32/dims=1	39790 ns	40471.5 ns	0.98
array/reductions/reduce/Float32/dims=2	57018 ns	57348 ns	0.99
array/reductions/reduce/Float32/dims=1L	51911 ns	52155 ns	1.00
array/reductions/reduce/Float32/dims=2L	69921 ns	70051 ns	1.00
array/reductions/mapreduce/Int64/1d	42828 ns	43658 ns	0.98
array/reductions/mapreduce/Int64/dims=1	42715 ns	42850 ns	1.00
array/reductions/mapreduce/Int64/dims=2	59449 ns	60283 ns	0.99
array/reductions/mapreduce/Int64/dims=1L	87721 ns	87856 ns	1.00
array/reductions/mapreduce/Int64/dims=2L	84538 ns	84886 ns	1.00
array/reductions/mapreduce/Float32/1d	34528 ns	35439 ns	0.97
array/reductions/mapreduce/Float32/dims=1	40228 ns	49602 ns	0.81
array/reductions/mapreduce/Float32/dims=2	56891 ns	57112 ns	1.00
array/reductions/mapreduce/Float32/dims=1L	51793 ns	52066 ns	0.99
array/reductions/mapreduce/Float32/dims=2L	69287 ns	70220.5 ns	0.99
array/broadcast	20728 ns	20835 ns	0.99
array/copyto!/gpu_to_gpu	11282 ns	11409 ns	0.99
array/copyto!/cpu_to_gpu	215496.5 ns	217482 ns	0.99
array/copyto!/gpu_to_cpu	283460.5 ns	284547 ns	1.00
array/accumulate/Int64/1d	118849 ns	119536 ns	0.99
array/accumulate/Int64/dims=1	79803 ns	80581.5 ns	0.99
array/accumulate/Int64/dims=2	155916 ns	156671 ns	1.00
array/accumulate/Int64/dims=1L	1694625.5 ns	1706437 ns	0.99
array/accumulate/Int64/dims=2L	961590 ns	962104 ns	1.00
array/accumulate/Float32/1d	101671 ns	102057 ns	1.00
array/accumulate/Float32/dims=1	76866 ns	77830 ns	0.99
array/accumulate/Float32/dims=2	143826 ns	144868 ns	0.99
array/accumulate/Float32/dims=1L	1585623 ns	1586085 ns	1.00
array/accumulate/Float32/dims=2L	657591 ns	661758 ns	0.99
array/construct	1291.55 ns	1349.1 ns	0.96
array/random/randn/Float32	38465 ns	42622 ns	0.90
array/random/randn!/Float32	31529 ns	31841 ns	0.99
array/random/rand!/Int64	34185 ns	34412 ns	0.99
array/random/rand!/Float32	8498.666666666666 ns	8601 ns	0.99
array/random/rand/Int64	37008.5 ns	37538 ns	0.99
array/random/rand/Float32	13002.5 ns	13018 ns	1.00
array/permutedims/4d	52636.5 ns	52619.5 ns	1.00
array/permutedims/2d	52787 ns	52940 ns	1.00
array/permutedims/3d	52988 ns	53310 ns	0.99
array/sorting/1d	2735841 ns	2735465.5 ns	1.00
array/sorting/by	3304400 ns	3315555 ns	1.00
array/sorting/2d	1069201 ns	1072718 ns	1.00
cuda/synchronization/stream/auto	1036.6470588235295 ns	1042.1 ns	0.99
cuda/synchronization/stream/nonblocking	7682 ns	7867.299999999999 ns	0.98
cuda/synchronization/stream/blocking	836.8019801980198 ns	828.4299065420561 ns	1.01
cuda/synchronization/context/auto	1203 ns	1198.8 ns	1.00
cuda/synchronization/context/nonblocking	7482.1 ns	7295 ns	1.03
cuda/synchronization/context/blocking	954.5142857142857 ns	929.6410256410256 ns	1.03

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