Conversation
Merged
simeonschaub
approved these changes
Aug 13, 2026
Contributor
There was a problem hiding this comment.
AMDGPU.jl Benchmarks
Details
| Benchmark suite | Current: 10f974c | Previous: c72c1be | Ratio |
|---|---|---|---|
amdgpu/synchronization/context/device |
552.5 ns |
575 ns |
0.96 |
amdgpu/synchronization/stream/blocking |
232.5 ns |
237.5 ns |
0.98 |
amdgpu/synchronization/stream/nonblocking |
312.5 ns |
320 ns |
0.98 |
array/accumulate/Float32/1d |
78658.5 ns |
73123.5 ns |
1.08 |
array/accumulate/Float32/dims=1 |
267881.25 ns |
273991.5 ns |
0.98 |
array/accumulate/Float32/dims=1L |
89401.25 ns |
79548.75 ns |
1.12 |
array/accumulate/Float32/dims=2 |
85768.75 ns |
71198.5 ns |
1.20 |
array/accumulate/Float32/dims=2L |
2751522 ns |
2617322.75 ns |
1.05 |
array/accumulate/Int64/1d |
82211.25 ns |
77823.5 ns |
1.06 |
array/accumulate/Int64/dims=1 |
244303.5 ns |
243748.5 ns |
1.00 |
array/accumulate/Int64/dims=1L |
84353.5 ns |
84018.75 ns |
1.00 |
array/accumulate/Int64/dims=2 |
89621.25 ns |
84761.25 ns |
1.06 |
array/accumulate/Int64/dims=2L |
2896871.75 ns |
2888798.75 ns |
1.00 |
array/broadcast |
74271.25 ns |
73361 ns |
1.01 |
array/construct |
2125 ns |
2392.75 ns |
0.89 |
array/copy |
37463 ns |
36770.75 ns |
1.02 |
array/copyto!/cpu_to_gpu |
111714.25 ns |
111709.25 ns |
1.00 |
array/copyto!/gpu_to_cpu |
111879.25 ns |
120241.75 ns |
0.93 |
array/copyto!/gpu_to_gpu |
59591 ns |
59065.75 ns |
1.01 |
array/iteration/findall/bool |
140502.25 ns |
136584.5 ns |
1.03 |
array/iteration/findall/int |
152192.25 ns |
150607.25 ns |
1.01 |
array/iteration/findfirst/bool |
147554.75 ns |
144959.5 ns |
1.02 |
array/iteration/findfirst/int |
147734.5 ns |
146344.5 ns |
1.01 |
array/iteration/findmin/1d |
123236.75 ns |
110519.25 ns |
1.12 |
array/iteration/findmin/2d |
114769 ns |
108191.75 ns |
1.06 |
array/iteration/logical |
250471.25 ns |
249886.25 ns |
1.00 |
array/iteration/scalar |
309307 ns |
295226.75 ns |
1.05 |
array/permutedims/2d |
72801.25 ns |
71816 ns |
1.01 |
array/permutedims/3d |
72361 ns |
71356.25 ns |
1.01 |
array/permutedims/4d |
75071 ns |
73651 ns |
1.02 |
array/random/rand/Float32 |
46415.75 ns |
45315.75 ns |
1.02 |
array/random/rand/Int64 |
55368.5 ns |
54385.75 ns |
1.02 |
array/random/rand!/Float32 |
66248.25 ns |
65446 ns |
1.01 |
array/random/rand!/Int64 |
69086 ns |
72981 ns |
0.95 |
array/random/randn/Float32 |
81686.25 ns |
80736.25 ns |
1.01 |
array/random/randn!/Float32 |
79056 ns |
69953.5 ns |
1.13 |
array/reductions/mapreduce/Float32/1d |
109024 ns |
97681.5 ns |
1.12 |
array/reductions/mapreduce/Float32/dims=1 |
95259 ns |
84113.5 ns |
1.13 |
array/reductions/mapreduce/Float32/dims=1L |
831739.5 ns |
826296.75 ns |
1.01 |
array/reductions/mapreduce/Float32/dims=2 |
96954 ns |
84213.75 ns |
1.15 |
array/reductions/mapreduce/Float32/dims=2L |
145334.5 ns |
144304.5 ns |
1.01 |
array/reductions/mapreduce/Int64/1d |
92798.75 ns |
86961.25 ns |
1.07 |
array/reductions/mapreduce/Int64/dims=1 |
95301.5 ns |
84591.25 ns |
1.13 |
array/reductions/mapreduce/Int64/dims=1L |
835034.5 ns |
831914.5 ns |
1.00 |
array/reductions/mapreduce/Int64/dims=2 |
98646.5 ns |
84978.75 ns |
1.16 |
array/reductions/mapreduce/Int64/dims=2L |
145464.75 ns |
144542 ns |
1.01 |
array/reductions/reduce/Float32/1d |
109071.5 ns |
95551.5 ns |
1.14 |
array/reductions/reduce/Float32/dims=1 |
95158.75 ns |
84178.75 ns |
1.13 |
array/reductions/reduce/Float32/dims=1L |
829942.25 ns |
832961.75 ns |
1.00 |
array/reductions/reduce/Float32/dims=2 |
99666.25 ns |
84558.5 ns |
1.18 |
array/reductions/reduce/Float32/dims=2L |
145007 ns |
144109.5 ns |
1.01 |
array/reductions/reduce/Int64/1d |
92266.5 ns |
87298.75 ns |
1.06 |
array/reductions/reduce/Int64/dims=1 |
95453.75 ns |
84841.25 ns |
1.13 |
array/reductions/reduce/Int64/dims=1L |
836097.25 ns |
833982 ns |
1.00 |
array/reductions/reduce/Int64/dims=2 |
98646.5 ns |
84928.75 ns |
1.16 |
array/reductions/reduce/Int64/dims=2L |
144114.5 ns |
144862.25 ns |
0.99 |
array/reverse/1d |
46545.75 ns |
45665.75 ns |
1.02 |
array/reverse/1dL |
76683.75 ns |
75713.5 ns |
1.01 |
array/reverse/1dL_inplace |
81298.75 ns |
80391.25 ns |
1.01 |
array/reverse/1d_inplace |
43998.25 ns |
61033.5 ns |
0.72 |
array/reverse/2d |
51530.75 ns |
50165.75 ns |
1.03 |
array/reverse/2dL |
86926.25 ns |
82746 ns |
1.05 |
array/reverse/2dL_inplace |
92953.75 ns |
91868.75 ns |
1.01 |
array/reverse/2d_inplace |
64318.5 ns |
57983.25 ns |
1.11 |
array/sorting/1d |
335037.5 ns |
334465 ns |
1.00 |
integration/byval/reference |
40130 ns |
39820 ns |
1.01 |
integration/byval/slices=1 |
40641 ns |
40850 ns |
0.99 |
integration/byval/slices=2 |
151923 ns |
135422 ns |
1.12 |
integration/byval/slices=3 |
237263 ns |
238763 ns |
0.99 |
integration/volumerhs |
5001022 ns |
5002821 ns |
1.00 |
kernel/indexing |
58663.25 ns |
57225.75 ns |
1.03 |
kernel/indexing_checked |
60028.25 ns |
59125.75 ns |
1.02 |
kernel/launch |
1407.5 ns |
1387.5 ns |
1.01 |
kernel/rand |
104326.25 ns |
99286.5 ns |
1.05 |
latency/import |
1897309357 ns |
1891983250 ns |
1.00 |
latency/precompile |
38374092930 ns |
38268995266 ns |
1.00 |
latency/ttfp |
5937313941 ns |
5932734415 ns |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Was needed in 2022 to run LLVM_jll.lld() which we do no longer do.