Skip to content

Switch to CompilerCaching.jl.#961

Draft
maleadt wants to merge 3 commits into
mainfrom
tb/compilercaching
Draft

Switch to CompilerCaching.jl.#961
maleadt wants to merge 3 commits into
mainfrom
tb/compilercaching

Conversation

@maleadt

@maleadt maleadt commented Jul 6, 2026

Copy link
Copy Markdown
Member

No description provided.

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

AMDGPU.jl Benchmarks

Details
Benchmark suite Current: 7dc36de Previous: c9bb187 Ratio
amdgpu/synchronization/context/device 600 ns 600 ns 1
amdgpu/synchronization/stream/blocking 250 ns 260 ns 0.96
amdgpu/synchronization/stream/nonblocking 340 ns 360 ns 0.94
array/accumulate/Float32/1d 86922 ns 84521 ns 1.03
array/accumulate/Float32/dims=1 384166 ns 249923 ns 1.54
array/accumulate/Float32/dims=1L 136622 ns 135772 ns 1.01
array/accumulate/Float32/dims=2 136002 ns 134282 ns 1.01
array/accumulate/Float32/dims=2L 2812341 ns 2808118 ns 1.00
array/accumulate/Int64/1d 97871 ns 98071 ns 1.00
array/accumulate/Int64/dims=1 396436 ns 242453 ns 1.64
array/accumulate/Int64/dims=1L 167532 ns 167612 ns 1.00
array/accumulate/Int64/dims=2 129122 ns 127572 ns 1.01
array/accumulate/Int64/dims=2L 2983353 ns 2986440 ns 1.00
array/broadcast 95651 ns 60690 ns 1.58
array/construct 1730 ns 1670 ns 1.04
array/copy 40291 ns 39001 ns 1.03
array/copyto!/cpu_to_gpu 183382 ns 115432 ns 1.59
array/copyto!/gpu_to_cpu 122752 ns 183513 ns 0.67
array/copyto!/gpu_to_gpu 47261 ns 42561 ns 1.11
array/iteration/findall/bool 182173 ns 182932 ns 1.00
array/iteration/findall/int 201043 ns 200213 ns 1.00
array/iteration/findfirst/bool 116512 ns 122221 ns 0.95
array/iteration/findfirst/int 116392 ns 118322 ns 0.98
array/iteration/findmin/1d 171483 ns 172192 ns 1.00
array/iteration/findmin/2d 157433 ns 155922 ns 1.01
array/iteration/logical 355665 ns 352985 ns 1.01
array/iteration/scalar 289894 ns 288944 ns 1.00
array/permutedims/2d 75151 ns 72771 ns 1.03
array/permutedims/3d 75751 ns 73321 ns 1.03
array/permutedims/4d 77861 ns 75921 ns 1.03
array/random/rand/Float32 51691 ns 54461 ns 0.95
array/random/rand/Int64 59461 ns 57061 ns 1.04
array/random/rand!/Float32 127422 ns 86631 ns 1.47
array/random/rand!/Int64 91921 ns 92761 ns 0.99
array/random/randn/Float32 85971 ns 87861 ns 0.98
array/random/randn!/Float32 87711 ns 110492 ns 0.79
array/reductions/mapreduce/Float32/1d 134212 ns 133412 ns 1.01
array/reductions/mapreduce/Float32/dims=1 96342 ns 94591 ns 1.02
array/reductions/mapreduce/Float32/dims=1L 777262 ns 773740 ns 1.00
array/reductions/mapreduce/Float32/dims=2 98562 ns 96191 ns 1.02
array/reductions/mapreduce/Float32/dims=2L 298674 ns 294243 ns 1.02
array/reductions/mapreduce/Int64/1d 134922 ns 129821 ns 1.04
array/reductions/mapreduce/Int64/dims=1 96152 ns 94641 ns 1.02
array/reductions/mapreduce/Int64/dims=1L 782412 ns 785310 ns 1.00
array/reductions/mapreduce/Int64/dims=2 97431 ns 98371 ns 0.99
array/reductions/mapreduce/Int64/dims=2L 300895 ns 301204 ns 1.00
array/reductions/reduce/Float32/1d 134222 ns 132981 ns 1.01
array/reductions/reduce/Float32/dims=1 95901 ns 94951 ns 1.01
array/reductions/reduce/Float32/dims=1L 776241 ns 773631 ns 1.00
array/reductions/reduce/Float32/dims=2 97911 ns 97011 ns 1.01
array/reductions/reduce/Float32/dims=2L 299815 ns 296684 ns 1.01
array/reductions/reduce/Int64/1d 135632 ns 133071 ns 1.02
array/reductions/reduce/Int64/dims=1 96182 ns 94911 ns 1.01
array/reductions/reduce/Int64/dims=1L 784052 ns 780131 ns 1.01
array/reductions/reduce/Int64/dims=2 97541 ns 96751 ns 1.01
array/reductions/reduce/Int64/dims=2L 300224 ns 298174 ns 1.01
array/reverse/1d 45341 ns 43060 ns 1.05
array/reverse/1dL 77021 ns 74391 ns 1.04
array/reverse/1dL_inplace 169463 ns 93081 ns 1.82
array/reverse/1d_inplace 77261 ns 141882 ns 0.54
array/reverse/2d 52800 ns 50520 ns 1.05
array/reverse/2dL 102081 ns 101111 ns 1.01
array/reverse/2dL_inplace 115912 ns 119941 ns 0.97
array/reverse/2d_inplace 73052 ns 139582 ns 0.52
array/sorting/1d 342125 ns 342234 ns 1.00
integration/byval/reference 39731 ns 39380 ns 1.01
integration/byval/slices=1 40860 ns 40441 ns 1.01
integration/byval/slices=2 149642 ns 141762 ns 1.06
integration/byval/slices=3 239273 ns 237423 ns 1.01
integration/volumerhs 5030513 ns 5033928 ns 1.00
kernel/indexing 65191 ns 59441 ns 1.10
kernel/indexing_checked 65631 ns 67040 ns 0.98
kernel/launch 1530 ns 1320 ns 1.16
kernel/rand 197773 ns 122232 ns 1.62
latency/import 1599349920 ns 1581839280 ns 1.01
latency/precompile 37149119506 ns 36431611059 ns 1.02
latency/ttfp 5588338761 ns 2156197272 ns 2.59

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

@maleadt maleadt force-pushed the tb/compilercaching branch from 8ce13eb to 57f2026 Compare July 10, 2026 14:00
@maleadt maleadt force-pushed the tb/compilercaching branch from 57f2026 to 0f18147 Compare July 10, 2026 14:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant