Update Buildkite pipeline for the new JuliaGPU cluster

[maleadt]

The JuliaGPU Buildkite agents have moved to a dedicated cluster, where the single juliagpu queue has been split into per-backend queues. Steps now select agents using queue: "cuda", queue: "rocm" or queue: "oneapi" instead of queue: "juliagpu" combined with a cuda/rocm/intel tag.

This change only affects agent selection; the steps themselves are unchanged.

🤖 Generated with Claude Code

[github-actions]

AMDGPU.jl Benchmarks

Details

Benchmark suite	Current: 756cd0f	Previous: f49923a	Ratio
amdgpu/synchronization/context/device	610 ns	620 ns	0.98
amdgpu/synchronization/stream/blocking	240 ns	250 ns	0.96
amdgpu/synchronization/stream/nonblocking	340 ns	340 ns	1
array/accumulate/Float32/1d	87781 ns	86721 ns	1.01
array/accumulate/Float32/dims=1	391616 ns	283534 ns	1.38
array/accumulate/Float32/dims=1L	133732 ns	132701 ns	1.01
array/accumulate/Float32/dims=2	129161 ns	128622 ns	1.00
array/accumulate/Float32/dims=2L	2828591 ns	2830679 ns	1.00
array/accumulate/Int64/1d	93961 ns	96522 ns	0.97
array/accumulate/Int64/dims=1	403466 ns	398946 ns	1.01
array/accumulate/Int64/dims=1L	162593 ns	161462 ns	1.01
array/accumulate/Int64/dims=2	100701 ns	125241 ns	0.80
array/accumulate/Int64/dims=2L	3011653 ns	3010532 ns	1.00
array/broadcast	119141 ns	87271 ns	1.37
array/construct	1710 ns	1610 ns	1.06
array/copy	39580 ns	39990 ns	0.99
array/copyto!/cpu_to_gpu	183353 ns	183233 ns	1.00
array/copyto!/gpu_to_cpu	183392 ns	119621 ns	1.53
array/copyto!/gpu_to_gpu	88691 ns	66311 ns	1.34
array/iteration/findall/bool	184762 ns	186173 ns	0.99
array/iteration/findall/int	192903 ns	195203 ns	0.99
array/iteration/findfirst/bool	116462 ns	120502 ns	0.97
array/iteration/findfirst/int	116272 ns	115651 ns	1.01
array/iteration/findmin/1d	170783 ns	169593 ns	1.01
array/iteration/findmin/2d	155862 ns	155303 ns	1.00
array/iteration/logical	355266 ns	355134 ns	1.00
array/iteration/scalar	290064 ns	289534 ns	1.00
array/permutedims/2d	75531 ns	74191 ns	1.02
array/permutedims/3d	75021 ns	73501 ns	1.02
array/permutedims/4d	77781 ns	77031 ns	1.01
array/random/rand/Float32	49131 ns	51380 ns	0.96
array/random/rand/Int64	58101 ns	57211 ns	1.02
array/random/rand!/Float32	142572 ns	90061 ns	1.58
array/random/rand!/Int64	58430 ns	93842 ns	0.62
array/random/randn/Float32	83561 ns	88552 ns	0.94
array/random/randn!/Float32	160572 ns	112572 ns	1.43
array/reductions/mapreduce/Float32/1d	133952 ns	132972 ns	1.01
array/reductions/mapreduce/Float32/dims=1	78751 ns	94771 ns	0.83
array/reductions/mapreduce/Float32/dims=1L	774462 ns	774400 ns	1.00
array/reductions/mapreduce/Float32/dims=2	98042 ns	96822 ns	1.01
array/reductions/mapreduce/Float32/dims=2L	308084 ns	298774 ns	1.03
array/reductions/mapreduce/Int64/1d	134992 ns	133662 ns	1.01
array/reductions/mapreduce/Int64/dims=1	96212 ns	95181 ns	1.01
array/reductions/mapreduce/Int64/dims=1L	788952 ns	784161 ns	1.01
array/reductions/mapreduce/Int64/dims=2	96792 ns	96381 ns	1.00
array/reductions/mapreduce/Int64/dims=2L	302454 ns	304945 ns	0.99
array/reductions/reduce/Float32/1d	133842 ns	132751 ns	1.01
array/reductions/reduce/Float32/dims=1	79001 ns	94801 ns	0.83
array/reductions/reduce/Float32/dims=1L	774932 ns	772081 ns	1.00
array/reductions/reduce/Float32/dims=2	97411 ns	94952 ns	1.03
array/reductions/reduce/Float32/dims=2L	307564 ns	305064 ns	1.01
array/reductions/reduce/Int64/1d	134862 ns	133482 ns	1.01
array/reductions/reduce/Int64/dims=1	95551 ns	94961 ns	1.01
array/reductions/reduce/Int64/dims=1L	781592 ns	782411 ns	1.00
array/reductions/reduce/Int64/dims=2	96742 ns	94081 ns	1.03
array/reductions/reduce/Int64/dims=2L	308104 ns	298415 ns	1.03
array/reverse/1d	44680 ns	44041 ns	1.01
array/reverse/1dL	59641 ns	75781 ns	0.79
array/reverse/1dL_inplace	94771 ns	169563 ns	0.56
array/reverse/1d_inplace	136302 ns	60091 ns	2.27
array/reverse/2d	51101 ns	52051 ns	0.98
array/reverse/2dL	101012 ns	101912 ns	0.99
array/reverse/2dL_inplace	116772 ns	176962 ns	0.66
array/reverse/2d_inplace	100882 ns	123882 ns	0.81
array/sorting/1d	344115 ns	339895 ns	1.01
integration/byval/reference	39240 ns	39110 ns	1.00
integration/byval/slices=1	41231 ns	39650 ns	1.04
integration/byval/slices=2	122902 ns	147182 ns	0.84
integration/byval/slices=3	240504 ns	237883 ns	1.01
integration/volumerhs	4930820 ns	5038970 ns	0.98
kernel/indexing	126362 ns	64551 ns	1.96
kernel/indexing_checked	118872 ns	59681 ns	1.99
kernel/launch	1290 ns	1290 ns	1
kernel/rand	98592 ns	122581 ns	0.80
latency/import	1499239223 ns	1490559052 ns	1.01
latency/precompile	12026324165 ns	11957081563 ns	1.01
latency/ttfp	10487340929 ns	10414604626 ns	1.01

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