Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update wrapping readme #525

Merged
merged 1 commit into from
Jan 23, 2025
Merged

Update wrapping readme #525

merged 1 commit into from
Jan 23, 2025

Conversation

christiangnrd
Copy link
Contributor

No description provided.

@christiangnrd christiangnrd merged commit e85bf52 into main Jan 23, 2025
5 of 6 checks passed
@christiangnrd christiangnrd deleted the tweak branch January 23, 2025 21:25
Copy link
Contributor

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

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

Metal Benchmarks

Benchmark suite Current: 3e69cd3 Previous: ebf223f Ratio
private array/construct 25472.25 ns 24000 ns 1.06
private array/broadcast 461750 ns 461833 ns 1.00
private array/random/randn/Float32 865000 ns 803937.5 ns 1.08
private array/random/randn!/Float32 633000 ns 633167 ns 1.00
private array/random/rand!/Int64 555292 ns 570209 ns 0.97
private array/random/rand!/Float32 594791 ns 596292 ns 1.00
private array/random/rand/Int64 755209 ns 780395.5 ns 0.97
private array/random/rand/Float32 603500 ns 629104 ns 0.96
private array/copyto!/gpu_to_gpu 656833 ns 654875 ns 1.00
private array/copyto!/cpu_to_gpu 807896 ns 606000 ns 1.33
private array/copyto!/gpu_to_cpu 821208.5 ns 719750 ns 1.14
private array/accumulate/1d 1329333 ns 1343417 ns 0.99
private array/accumulate/2d 1392750 ns 1391771 ns 1.00
private array/iteration/findall/int 2078021 ns 2086417 ns 1.00
private array/iteration/findall/bool 1823792 ns 1827187.5 ns 1.00
private array/iteration/findfirst/int 1702979 ns 1691000 ns 1.01
private array/iteration/findfirst/bool 1658250 ns 1656687 ns 1.00
private array/iteration/scalar 3931458 ns 3828063 ns 1.03
private array/iteration/logical 3172166.5 ns 3206792 ns 0.99
private array/iteration/findmin/1d 1762000 ns 1773250 ns 0.99
private array/iteration/findmin/2d 1349875 ns 1361792 ns 0.99
private array/reductions/reduce/1d 1041896 ns 1034250 ns 1.01
private array/reductions/reduce/2d 657083 ns 663937.5 ns 0.99
private array/reductions/mapreduce/1d 1044458 ns 1042125 ns 1.00
private array/reductions/mapreduce/2d 662062.5 ns 655458 ns 1.01
private array/permutedims/4d 2512750 ns 2508375 ns 1.00
private array/permutedims/2d 1023354.5 ns 1030500 ns 0.99
private array/permutedims/3d 1571312.5 ns 1594042 ns 0.99
private array/copy 588541.5 ns 595041 ns 0.99
latency/precompile 5904319542 ns 5777750625 ns 1.02
latency/ttfp 3461550771 ns 3042774604 ns 1.14
latency/import 1124615541 ns 1143862583 ns 0.98
integration/metaldevrt 700500 ns 714708.5 ns 0.98
integration/byval/slices=1 1641020.5 ns 1633333 ns 1.00
integration/byval/slices=3 11626521 ns 11174041 ns 1.04
integration/byval/reference 1635708 ns 1586104 ns 1.03
integration/byval/slices=2 2648250 ns 2623021 ns 1.01
kernel/indexing 474375 ns 453208 ns 1.05
kernel/indexing_checked 472270.5 ns 449750 ns 1.05
kernel/launch 7959 ns 7833 ns 1.02
metal/synchronization/stream 14833 ns 14917 ns 0.99
metal/synchronization/context 14917 ns 15333 ns 0.97
shared array/construct 23951.333333333332 ns 25300 ns 0.95
shared array/broadcast 457750 ns 454667 ns 1.01
shared array/random/randn/Float32 744583.5 ns 791354 ns 0.94
shared array/random/randn!/Float32 635208 ns 642542 ns 0.99
shared array/random/rand!/Int64 560333 ns 563917 ns 0.99
shared array/random/rand!/Float32 592500 ns 594792 ns 1.00
shared array/random/rand/Int64 781166.5 ns 777042 ns 1.01
shared array/random/rand/Float32 611958 ns 605500 ns 1.01
shared array/copyto!/gpu_to_gpu 83416 ns 82750 ns 1.01
shared array/copyto!/cpu_to_gpu 83042 ns 83625 ns 0.99
shared array/copyto!/gpu_to_cpu 83667 ns 82625 ns 1.01
shared array/accumulate/1d 1355229 ns 1349792 ns 1.00
shared array/accumulate/2d 1390875 ns 1394042 ns 1.00
shared array/iteration/findall/int 1833521 ns 1839167 ns 1.00
shared array/iteration/findall/bool 1582500 ns 1608125 ns 0.98
shared array/iteration/findfirst/int 1396625 ns 1411500 ns 0.99
shared array/iteration/findfirst/bool 1357666.5 ns 1372250 ns 0.99
shared array/iteration/scalar 159833 ns 160250 ns 1.00
shared array/iteration/logical 2971208 ns 2997125 ns 0.99
shared array/iteration/findmin/1d 1471708 ns 1473292 ns 1.00
shared array/iteration/findmin/2d 1371521 ns 1370000 ns 1.00
shared array/reductions/reduce/1d 729625 ns 725167 ns 1.01
shared array/reductions/reduce/2d 665500 ns 665270.5 ns 1.00
shared array/reductions/mapreduce/1d 743229 ns 739000 ns 1.01
shared array/reductions/mapreduce/2d 668959 ns 666125 ns 1.00
shared array/permutedims/4d 2501250 ns 2534959 ns 0.99
shared array/permutedims/2d 1018583 ns 1043500 ns 0.98
shared array/permutedims/3d 1573292 ns 1595999.5 ns 0.99
shared array/copy 244291.5 ns 238666 ns 1.02

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

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