Test GPUArrays reverse

[christiangnrd]

No description provided.

[github-actions]

Your PR requires formatting changes to meet the project's style guidelines.
Please consider running Runic (git runic main) to apply these changes.

Click here to view the suggested changes.

diff --git a/lib/mtl/capture.jl b/lib/mtl/capture.jl
index c2c1a77a..c101c5b7 100644
--- a/lib/mtl/capture.jl
+++ b/lib/mtl/capture.jl
@@ -59,7 +59,8 @@ function MTLCaptureDescriptor()
 end
 
 # TODO: Add capture state
-function MTLCaptureDescriptor(obj::Union{MTLDevice,MTLCommandQueue,MTLCaptureScope},
+function MTLCaptureDescriptor(
+        obj::Union{MTLDevice, MTLCommandQueue, MTLCaptureScope},
                               destination::MTLCaptureDestination;
                               folder::String=nothing)
     desc = MTLCaptureDescriptor()
@@ -110,7 +111,8 @@ end
 
 Start GPU frame capture using the default capture object and specifying capture descriptor parameters directly.
 """
-function startCapture(obj::Union{MTLDevice,MTLCommandQueue,MTLCaptureScope},
+function startCapture(
+        obj::Union{MTLDevice, MTLCommandQueue, MTLCaptureScope},
                       destination::MTLCaptureDestination=MTLCaptureDestinationGPUTraceDocument;
                       folder::String=nothing)
     if destination == MTLCaptureDestinationGPUTraceDocument && folder === nothing
diff --git a/perf/array.jl b/perf/array.jl
index 008ab4d6..b86a675e 100644
--- a/perf/array.jl
+++ b/perf/array.jl
@@ -63,12 +63,12 @@ gpu_vec_ints = reshape(gpu_mat_ints, length(gpu_mat_ints))
 let group = addgroup!(group, "reverse")
     group["1d"] = @benchmarkable Metal.@sync reverse($gpu_vec)
     group["1dL"] = @benchmarkable Metal.@sync reverse($gpu_vec_long)
-    group["2d"] = @benchmarkable Metal.@sync reverse($gpu_mat; dims=1)
-    group["2dL"] = @benchmarkable Metal.@sync reverse($gpu_mat_long; dims=1)
+    group["2d"] = @benchmarkable Metal.@sync reverse($gpu_mat; dims = 1)
+    group["2dL"] = @benchmarkable Metal.@sync reverse($gpu_mat_long; dims = 1)
     group["1d_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_vec)
     group["1dL_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_vec_long)
-    group["2d_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_mat; dims=1)
-    group["2dL_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_mat_long; dims=2)
+    group["2d_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_mat; dims = 1)
+    group["2dL_inplace"] = @benchmarkable Metal.@sync reverse!($gpu_mat_long; dims = 2)
 end
 
 # 'evals=1' added to prevent hang when running benchmarks of CI
diff --git a/perf/runbenchmarks.jl b/perf/runbenchmarks.jl
index 17bf4ea0..98aa3153 100644
--- a/perf/runbenchmarks.jl
+++ b/perf/runbenchmarks.jl
@@ -1,7 +1,7 @@
 # benchmark suite execution and codespeed submission
 
 using Pkg
-Pkg.add(url="https://github.com/christiangnrd/GPUArrays.jl", rev="reverse")
+Pkg.add(url = "https://github.com/christiangnrd/GPUArrays.jl", rev = "reverse")
 
 using Metal
 
diff --git a/test/runtests.jl b/test/runtests.jl
index 081fc280..42f00908 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -1,5 +1,5 @@
 using Pkg
-Pkg.add(url="https://github.com/christiangnrd/GPUArrays.jl", rev="reverse")
+Pkg.add(url = "https://github.com/christiangnrd/GPUArrays.jl", rev = "reverse")
 
 using Distributed
 using Dates

[github-actions]

Metal Benchmarks

Benchmark suite	Current: e3ce3ae	Previous: 18d5d95	Ratio
latency/precompile	10708835208.5 ns	10738355812.5 ns	1.00
latency/ttfp	5088232041.5 ns	5093095000 ns	1.00
latency/import	1309493875 ns	1307420042 ns	1.00
integration/metaldevrt	961416 ns	916521 ns	1.05
integration/byval/slices=1	1650541 ns	1655958 ns	1.00
integration/byval/slices=3	9014521 ns	8745792 ns	1.03
integration/byval/reference	1635625 ns	1624791 ns	1.01
integration/byval/slices=2	2705666 ns	2721500 ns	0.99
kernel/indexing	697500 ns	696291 ns	1.00
kernel/indexing_checked	701625 ns	696584 ns	1.01
kernel/launch	14208 ns	12416 ns	1.14
array/reverse/1d	671833.5 ns
array/reverse/2dL_inplace	3033708.5 ns
array/reverse/1dL	2367708 ns
array/reverse/2d	1462187.5 ns
array/reverse/1d_inplace	728917 ns
array/reverse/2d_inplace	931084 ns
array/reverse/2dL	6684125 ns
array/reverse/1dL_inplace	1072542 ns
array/construct	6167 ns	5792 ns	1.06
array/broadcast	681958 ns	665584 ns	1.02
array/accumulate/Int64/1d	1379520.5 ns	1360750 ns	1.01
array/accumulate/Int64/dims=1	1926125 ns	1916333 ns	1.01
array/accumulate/Int64/dims=2	2291958 ns	2278146 ns	1.01
array/accumulate/Int64/dims=1L	11902291 ns	12001125 ns	0.99
array/accumulate/Int64/dims=2L	9814458 ns	9901666 ns	0.99
array/accumulate/Float32/1d	1268500 ns	1245417 ns	1.02
array/accumulate/Float32/dims=1	1676771 ns	1669792 ns	1.00
array/accumulate/Float32/dims=2	2014833.5 ns	2007458 ns	1.00
array/accumulate/Float32/dims=1L	10007083 ns	9976625 ns	1.00
array/accumulate/Float32/dims=2L	7379750.5 ns	7388583.5 ns	1.00
array/random/randn/Float32	816333 ns	864875 ns	0.94
array/random/randn!/Float32	652459 ns	625250 ns	1.04
array/random/rand!/Int64	578437.5 ns	565916.5 ns	1.02
array/random/rand!/Float32	607375 ns	583083 ns	1.04
array/random/rand/Int64	780084 ns	729917 ns	1.07
array/random/rand/Float32	613833 ns	597917 ns	1.03
array/reductions/reduce/Int64/1d	1383125 ns	1339354 ns	1.03
array/reductions/reduce/Int64/dims=1	1167479.5 ns	1166145.5 ns	1.00
array/reductions/reduce/Int64/dims=2	1331229.5 ns	1307792 ns	1.02
array/reductions/reduce/Int64/dims=1L	2071458 ns	2095291 ns	0.99
array/reductions/reduce/Int64/dims=2L	3649895.5 ns	3597937.5 ns	1.01
array/reductions/reduce/Float32/1d	1093458.5 ns	986792 ns	1.11
array/reductions/reduce/Float32/dims=1	907417 ns	909041.5 ns	1.00
array/reductions/reduce/Float32/dims=2	788458 ns	770916 ns	1.02
array/reductions/reduce/Float32/dims=1L	1415375 ns	1410916.5 ns	1.00
array/reductions/reduce/Float32/dims=2L	1933916 ns	1933084 ns	1.00
array/reductions/mapreduce/Int64/1d	1433562.5 ns	1350250 ns	1.06
array/reductions/mapreduce/Int64/dims=1	1173875 ns	1211709 ns	0.97
array/reductions/mapreduce/Int64/dims=2	1341708 ns	1314292 ns	1.02
array/reductions/mapreduce/Int64/dims=1L	2114542 ns	2102020.5 ns	1.01
array/reductions/mapreduce/Int64/dims=2L	3624312.5 ns	3605750 ns	1.01
array/reductions/mapreduce/Float32/1d	1063146 ns	1059291 ns	1.00
array/reductions/mapreduce/Float32/dims=1	907792 ns	901500 ns	1.01
array/reductions/mapreduce/Float32/dims=2	787604.5 ns	777833 ns	1.01
array/reductions/mapreduce/Float32/dims=1L	1410687.5 ns	1401750 ns	1.01
array/reductions/mapreduce/Float32/dims=2L	1955167 ns	1936959 ns	1.01
array/private/copyto!/gpu_to_gpu	681625 ns	660167 ns	1.03
array/private/copyto!/cpu_to_gpu	827916 ns	805666 ns	1.03
array/private/copyto!/gpu_to_cpu	833833 ns	827000 ns	1.01
array/private/iteration/findall/int	1699916 ns	1676666 ns	1.01
array/private/iteration/findall/bool	1494563 ns	1481375 ns	1.01
array/private/iteration/findfirst/int	2047687.5 ns	2050625 ns	1.00
array/private/iteration/findfirst/bool	1953937.5 ns	1853416.5 ns	1.05
array/private/iteration/scalar	5613812.5 ns	3817291 ns	1.47
array/private/iteration/logical	2852041 ns	2757458 ns	1.03
array/private/iteration/findmin/1d	2056708 ns	2049500 ns	1.00
array/private/iteration/findmin/2d	1638417 ns	1633375 ns	1.00
array/private/copy	560834 ns	561500 ns	1.00
array/shared/copyto!/gpu_to_gpu	83875 ns	84416 ns	0.99
array/shared/copyto!/cpu_to_gpu	83250 ns	82541 ns	1.01
array/shared/copyto!/gpu_to_cpu	89958 ns	83917 ns	1.07
array/shared/iteration/findall/int	1677542 ns	1689292 ns	0.99
array/shared/iteration/findall/bool	1406750 ns	1503229 ns	0.94
array/shared/iteration/findfirst/int	1457917 ns	1457104.5 ns	1.00
array/shared/iteration/findfirst/bool	1439916 ns	1442750 ns	1.00
array/shared/iteration/scalar	161041 ns	155375 ns	1.04
array/shared/iteration/logical	2408104 ns	2449333.5 ns	0.98
array/shared/iteration/findmin/1d	1581708 ns	1513312.5 ns	1.05
array/shared/iteration/findmin/2d	1646458 ns	1636250 ns	1.01
array/shared/copy	243917 ns	257896 ns	0.95
array/permutedims/4d	2558750 ns	2525958 ns	1.01
array/permutedims/2d	1293708 ns	1278583 ns	1.01
array/permutedims/3d	1853417 ns	1824583.5 ns	1.02
metal/synchronization/stream	15084 ns	14541 ns	1.04
metal/synchronization/context	15417 ns	15042 ns	1.02

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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 80.53%. Comparing base (18d5d95) to head (e3ce3ae).

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #648   +/-   ##
=======================================
  Coverage   80.53%   80.53%           
=======================================
  Files          61       61           
  Lines        2779     2779           
=======================================
  Hits         2238     2238           
  Misses        541      541           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[maleadt]

Let's mark this as draft until it pulls from a dev branch on GPUArrays.