Alias WMMA_RDNA3 to WMMA

[vchuravy]

To make #929 not require a major release.

[github-actions]

AMDGPU.jl Benchmarks

Details

Benchmark suite	Current: ec1b8f3	Previous: 4e50cae	Ratio
amdgpu/synchronization/context/device	620 ns	610 ns	1.02
amdgpu/synchronization/stream/blocking	250 ns	260 ns	0.96
amdgpu/synchronization/stream/nonblocking	350 ns	350 ns	1
array/accumulate/Float32/1d	88271 ns	86981 ns	1.01
array/accumulate/Float32/dims=1	326355 ns	378846 ns	0.86
array/accumulate/Float32/dims=1L	136661 ns	132282 ns	1.03
array/accumulate/Float32/dims=2	137912 ns	133772 ns	1.03
array/accumulate/Float32/dims=2L	2810127 ns	2810689 ns	1.00
array/accumulate/Int64/1d	101231 ns	97481 ns	1.04
array/accumulate/Int64/dims=1	241863 ns	291384 ns	0.83
array/accumulate/Int64/dims=1L	168602 ns	167053 ns	1.01
array/accumulate/Int64/dims=2	128441 ns	129182 ns	0.99
array/accumulate/Int64/dims=2L	2987880 ns	2985353 ns	1.00
array/broadcast	63271 ns	123931 ns	0.51
array/construct	1760 ns	1710 ns	1.03
array/copy	39800 ns	39851 ns	1.00
array/copyto!/cpu_to_gpu	111751 ns	184052 ns	0.61
array/copyto!/gpu_to_cpu	182552 ns	184212 ns	0.99
array/copyto!/gpu_to_gpu	131802 ns	105661 ns	1.25
array/iteration/findall/bool	184252 ns	181272 ns	1.02
array/iteration/findall/int	191783 ns	189313 ns	1.01
array/iteration/findfirst/bool	124572 ns	119871 ns	1.04
array/iteration/findfirst/int	118251 ns	115941 ns	1.02
array/iteration/findmin/1d	172033 ns	170673 ns	1.01
array/iteration/findmin/2d	153942 ns	156922 ns	0.98
array/iteration/logical	352814 ns	352605 ns	1.00
array/iteration/scalar	296355 ns	290394 ns	1.02
array/permutedims/2d	75801 ns	74821 ns	1.01
array/permutedims/3d	74380 ns	74791 ns	0.99
array/permutedims/4d	76721 ns	76911 ns	1.00
array/random/rand/Float32	54871 ns	52791 ns	1.04
array/random/rand/Int64	57161 ns	58121 ns	0.98
array/random/rand!/Float32	86451 ns	128531 ns	0.67
array/random/rand!/Int64	148342 ns	140842 ns	1.05
array/random/randn/Float32	90982 ns	100101 ns	0.91
array/random/randn!/Float32	162362 ns	138282 ns	1.17
array/reductions/mapreduce/Float32/1d	135821 ns	134052 ns	1.01
array/reductions/mapreduce/Float32/dims=1	96911 ns	95721 ns	1.01
array/reductions/mapreduce/Float32/dims=1L	779970 ns	774771 ns	1.01
array/reductions/mapreduce/Float32/dims=2	97871 ns	97462 ns	1.00
array/reductions/mapreduce/Float32/dims=2L	297784 ns	297195 ns	1.00
array/reductions/mapreduce/Int64/1d	137852 ns	134082 ns	1.03
array/reductions/mapreduce/Int64/dims=1	96382 ns	95861 ns	1.01
array/reductions/mapreduce/Int64/dims=1L	782920 ns	782441 ns	1.00
array/reductions/mapreduce/Int64/dims=2	97601 ns	97161 ns	1.00
array/reductions/mapreduce/Int64/dims=2L	299634 ns	309335 ns	0.97
array/reductions/reduce/Float32/1d	135102 ns	134082 ns	1.01
array/reductions/reduce/Float32/dims=1	95931 ns	95671 ns	1.00
array/reductions/reduce/Float32/dims=1L	773190 ns	775341 ns	1.00
array/reductions/reduce/Float32/dims=2	96371 ns	97581 ns	0.99
array/reductions/reduce/Float32/dims=2L	297824 ns	298904 ns	1.00
array/reductions/reduce/Int64/1d	136222 ns	134082 ns	1.02
array/reductions/reduce/Int64/dims=1	95821 ns	95511 ns	1.00
array/reductions/reduce/Int64/dims=1L	782630 ns	782481 ns	1.00
array/reductions/reduce/Int64/dims=2	97471 ns	97042 ns	1.00
array/reductions/reduce/Int64/dims=2L	299434 ns	305295 ns	0.98
array/reverse/1d	44171 ns	43960 ns	1.00
array/reverse/1dL	75761 ns	76071 ns	1.00
array/reverse/1dL_inplace	166002 ns	91651 ns	1.81
array/reverse/1d_inplace	141442 ns	85681 ns	1.65
array/reverse/2d	52481 ns	52560 ns	1.00
array/reverse/2dL	103351 ns	101932 ns	1.01
array/reverse/2dL_inplace	174482 ns	123241 ns	1.42
array/reverse/2d_inplace	143902 ns	118402 ns	1.22
array/sorting/1d	349515 ns	342315 ns	1.02
integration/byval/reference	39520 ns	38960 ns	1.01
integration/byval/slices=1	40571 ns	40171 ns	1.01
integration/byval/slices=2	152442 ns	130801 ns	1.17
integration/byval/slices=3	237803 ns	238734 ns	1.00
integration/volumerhs	5024707 ns	5033812 ns	1.00
kernel/indexing	130472 ns	130172 ns	1.00
kernel/indexing_checked	60981 ns	67421 ns	0.90
kernel/launch	1490 ns	1310 ns	1.14
kernel/rand	111762 ns	197503 ns	0.57
latency/import	1590347862 ns	1587944525 ns	1.00
latency/precompile	36228942939 ns	36355885132 ns	1.00
latency/ttfp	2161304777 ns	2161069761 ns	1.00

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