Use workspace feature

[luraess]

No description provided.

[github-actions]

AMDGPU.jl Benchmarks

Details

Benchmark suite	Current: 8ef5201	Previous: 77983ff	Ratio
amdgpu/synchronization/context/device	600 ns	590 ns	1.02
amdgpu/synchronization/stream/blocking	250 ns	250 ns	1
amdgpu/synchronization/stream/nonblocking	330 ns	340 ns	0.97
array/accumulate/Float32/1d	87961 ns	87811 ns	1.00
array/accumulate/Float32/dims=1	392066 ns	403115 ns	0.97
array/accumulate/Float32/dims=1L	134902 ns	135562 ns	1.00
array/accumulate/Float32/dims=2	129282 ns	130651 ns	0.99
array/accumulate/Float32/dims=2L	2760200 ns	2830168 ns	0.98
array/accumulate/Int64/1d	97222 ns	95162 ns	1.02
array/accumulate/Int64/dims=1	401686 ns	287554 ns	1.40
array/accumulate/Int64/dims=1L	168272 ns	163062 ns	1.03
array/accumulate/Int64/dims=2	124682 ns	122662 ns	1.02
array/accumulate/Int64/dims=2L	3007974 ns	3009581 ns	1.00
array/broadcast	107222 ns	92571 ns	1.16
array/construct	1680 ns	1650 ns	1.02
array/copy	40760 ns	40541 ns	1.01
array/copyto!/cpu_to_gpu	114801 ns	101241 ns	1.13
array/copyto!/gpu_to_cpu	115572 ns	171042 ns	0.68
array/copyto!/gpu_to_gpu	119402 ns	67061 ns	1.78
array/iteration/findall/bool	186513 ns	186323 ns	1.00
array/iteration/findall/int	172422 ns	193182 ns	0.89
array/iteration/findfirst/bool	117332 ns	116491 ns	1.01
array/iteration/findfirst/int	116572 ns	116172 ns	1.00
array/iteration/findmin/1d	139402 ns	170953 ns	0.82
array/iteration/findmin/2d	156582 ns	157112 ns	1.00
array/iteration/logical	355105 ns	357464 ns	0.99
array/iteration/scalar	297475 ns	297354 ns	1.00
array/permutedims/2d	74751 ns	76211 ns	0.98
array/permutedims/3d	74331 ns	75451 ns	0.99
array/permutedims/4d	76101 ns	77631 ns	0.98
array/random/rand/Float32	52121 ns	52101 ns	1.00
array/random/rand/Int64	56451 ns	57911 ns	0.97
array/random/rand!/Float32	145152 ns	90721 ns	1.60
array/random/rand!/Int64	145742 ns	79251 ns	1.84
array/random/randn/Float32	98541 ns	94361 ns	1.04
array/random/randn!/Float32	160993 ns	111361 ns	1.45
array/reductions/mapreduce/Float32/1d	134392 ns	134212 ns	1.00
array/reductions/mapreduce/Float32/dims=1	95442 ns	95701 ns	1.00
array/reductions/mapreduce/Float32/dims=1L	773621 ns	781590 ns	0.99
array/reductions/mapreduce/Float32/dims=2	97172 ns	97911 ns	0.99
array/reductions/mapreduce/Float32/dims=2L	299114 ns	296814 ns	1.01
array/reductions/mapreduce/Int64/1d	134782 ns	131561 ns	1.02
array/reductions/mapreduce/Int64/dims=1	95642 ns	95531 ns	1.00
array/reductions/mapreduce/Int64/dims=1L	784402 ns	785040 ns	1.00
array/reductions/mapreduce/Int64/dims=2	96612 ns	97011 ns	1.00
array/reductions/mapreduce/Int64/dims=2L	300734 ns	300435 ns	1.00
array/reductions/reduce/Float32/1d	134122 ns	130022 ns	1.03
array/reductions/reduce/Float32/dims=1	95962 ns	95462 ns	1.01
array/reductions/reduce/Float32/dims=1L	773922 ns	776581 ns	1.00
array/reductions/reduce/Float32/dims=2	97692 ns	97971 ns	1.00
array/reductions/reduce/Float32/dims=2L	307585 ns	299134 ns	1.03
array/reductions/reduce/Int64/1d	135042 ns	134991 ns	1.00
array/reductions/reduce/Int64/dims=1	95542 ns	95171 ns	1.00
array/reductions/reduce/Int64/dims=1L	779912 ns	783650 ns	1.00
array/reductions/reduce/Int64/dims=2	97212 ns	97052 ns	1.00
array/reductions/reduce/Int64/dims=2L	298614 ns	298874 ns	1.00
array/reverse/1d	44301 ns	44560 ns	0.99
array/reverse/1dL	76462 ns	76361 ns	1.00
array/reverse/1dL_inplace	169973 ns	119381 ns	1.42
array/reverse/1d_inplace	56611 ns	79391 ns	0.71
array/reverse/2d	52551 ns	52601 ns	1.00
array/reverse/2dL	102452 ns	102402 ns	1.00
array/reverse/2dL_inplace	127852 ns	104651 ns	1.22
array/reverse/2d_inplace	78861 ns	125452 ns	0.63
array/sorting/1d	342565 ns	370525 ns	0.92
integration/byval/reference	39080 ns	39170 ns	1.00
integration/byval/slices=1	40261 ns	40441 ns	1.00
integration/byval/slices=2	159563 ns	147172 ns	1.08
integration/byval/slices=3	237514 ns	240543 ns	0.99
integration/volumerhs	5043492 ns	5026059 ns	1.00
kernel/indexing	54770 ns	65060 ns	0.84
kernel/indexing_checked	131322 ns	50911 ns	2.58
kernel/launch	1280 ns	1280 ns	1
kernel/rand	197823 ns	197633 ns	1.00
latency/import	1492873110 ns	1473646012 ns	1.01
latency/precompile	11959635281 ns	11890085969 ns	1.01
latency/ttfp	10379137050 ns	10356361296 ns	1.00

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