Test GPUArrays reverse

[christiangnrd]

Now depends on #688

[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: 36bd61e	Previous: cd8846e	Ratio
latency/precompile	28688656917 ns	25041664500 ns	1.15
latency/ttfp	2291530833 ns	2123110083 ns	1.08
latency/import	1381234520.5 ns	1219920625 ns	1.13
integration/metaldevrt	840667 ns	833750 ns	1.01
integration/byval/slices=1	1555083 ns	1545000 ns	1.01
integration/byval/slices=3	8878646 ns	9534208 ns	0.93
integration/byval/reference	1538083 ns	1538458 ns	1.00
integration/byval/slices=2	2615499.5 ns	2567417 ns	1.02
kernel/indexing	627458 ns	570625 ns	1.10
kernel/indexing_checked	633229 ns	587875 ns	1.08
kernel/launch	12375 ns	12250 ns	1.01
kernel/rand	568167 ns	559417 ns	1.02
array/reverse/1d	632875 ns
array/reverse/2dL_inplace	2500979 ns
array/reverse/1dL	2114333.5 ns
array/reverse/2d	1346708 ns
array/reverse/1d_inplace	577000 ns
array/reverse/2d_inplace	809208 ns
array/reverse/2dL	6548417 ns
array/reverse/1dL_inplace	863000 ns
array/construct	6333 ns	6250 ns	1.01
array/broadcast	595792 ns	568853.5 ns	1.05
array/accumulate/Int64/1d	1321375 ns	1252541.5 ns	1.05
array/accumulate/Int64/dims=1	1916729.5 ns	1812125 ns	1.06
array/accumulate/Int64/dims=2	2272167 ns	2154541.5 ns	1.05
array/accumulate/Int64/dims=1L	11932167 ns	11676250 ns	1.02
array/accumulate/Int64/dims=2L	10049604 ns	9788583 ns	1.03
array/accumulate/Float32/1d	1162333.5 ns	1110125 ns	1.05
array/accumulate/Float32/dims=1	1661541.5 ns	1542584 ns	1.08
array/accumulate/Float32/dims=2	2007729 ns	1844333 ns	1.09
array/accumulate/Float32/dims=1L	10013979.5 ns	9855833 ns	1.02
array/accumulate/Float32/dims=2L	8145167 ns	7549292 ns	1.08
array/random/randn/Float32	810667 ns	806041 ns	1.01
array/random/randn!/Float32	609708 ns	604084 ns	1.01
array/random/rand!/Int64	548125 ns	548625 ns	1.00
array/random/rand!/Float32	582125 ns	569834 ns	1.02
array/random/rand/Int64	768041 ns	813479.5 ns	0.94
array/random/rand/Float32	668062.5 ns	598917 ns	1.12
array/reductions/reduce/Int64/1d	1354396 ns	1246458 ns	1.09
array/reductions/reduce/Int64/dims=1	1113667 ns	1066250 ns	1.04
array/reductions/reduce/Int64/dims=2	1312083 ns	1159375 ns	1.13
array/reductions/reduce/Int64/dims=1L	2023000 ns	2051083 ns	0.99
array/reductions/reduce/Int64/dims=2L	4377083 ns	3424666.5 ns	1.28
array/reductions/reduce/Float32/1d	986750 ns	854125 ns	1.16
array/reductions/reduce/Float32/dims=1	837625 ns	811584 ns	1.03
array/reductions/reduce/Float32/dims=2	881750 ns	743292 ns	1.19
array/reductions/reduce/Float32/dims=1L	1321750.5 ns	1329354.5 ns	0.99
array/reductions/reduce/Float32/dims=2L	1866500 ns	1745667 ns	1.07
array/reductions/mapreduce/Int64/1d	1343500 ns	1416563 ns	0.95
array/reductions/mapreduce/Int64/dims=1	1074125 ns	1069687.5 ns	1.00
array/reductions/mapreduce/Int64/dims=2	1299833 ns	1172437.5 ns	1.11
array/reductions/mapreduce/Int64/dims=1L	2026250 ns	1986541.5 ns	1.02
array/reductions/mapreduce/Int64/dims=2L	4311458.5 ns	3283958 ns	1.31
array/reductions/mapreduce/Float32/1d	1049770.5 ns	992000 ns	1.06
array/reductions/mapreduce/Float32/dims=1	823792 ns	813708 ns	1.01
array/reductions/mapreduce/Float32/dims=2	879292 ns	746375 ns	1.18
array/reductions/mapreduce/Float32/dims=1L	1331417 ns	1326333 ns	1.00
array/reductions/mapreduce/Float32/dims=2L	1853709 ns	1752958 ns	1.06
array/private/copyto!/gpu_to_gpu	634167 ns	618000 ns	1.03
array/private/copyto!/cpu_to_gpu	803604.5 ns	784542 ns	1.02
array/private/copyto!/gpu_to_cpu	782833 ns	785458 ns	1.00
array/private/iteration/findall/int	1718667 ns	1561958 ns	1.10
array/private/iteration/findall/bool	1503666.5 ns	1421958 ns	1.06
array/private/iteration/findfirst/int	2103042 ns	1808166 ns	1.16
array/private/iteration/findfirst/bool	2080229.5 ns	1675041 ns	1.24
array/private/iteration/scalar	5453000 ns	4652479 ns	1.17
array/private/iteration/logical	2645958 ns	2505708.5 ns	1.06
array/private/iteration/findmin/1d	2271250 ns	1902125 ns	1.19
array/private/iteration/findmin/2d	1565500 ns	1510458 ns	1.04
array/private/copy	600250 ns	554729 ns	1.08
array/shared/copyto!/gpu_to_gpu	83875 ns	83750 ns	1.00
array/shared/copyto!/cpu_to_gpu	82875 ns	81542 ns	1.02
array/shared/copyto!/gpu_to_cpu	83000 ns	82459 ns	1.01
array/shared/iteration/findall/int	1669250 ns	1577417 ns	1.06
array/shared/iteration/findall/bool	1515666.5 ns	1437209 ns	1.05
array/shared/iteration/findfirst/int	1708250 ns	1321541.5 ns	1.29
array/shared/iteration/findfirst/bool	1680583.5 ns	1308542 ns	1.28
array/shared/iteration/scalar	208000 ns	199708 ns	1.04
array/shared/iteration/logical	2610854 ns	2227625 ns	1.17
array/shared/iteration/findmin/1d	1887083 ns	1410625 ns	1.34
array/shared/iteration/findmin/2d	1569666 ns	1511604 ns	1.04
array/shared/copy	241541 ns	250333 ns	0.96
array/permutedims/4d	2638959 ns	2361500 ns	1.12
array/permutedims/2d	1135083.5 ns	1143583 ns	0.99
array/permutedims/3d	1660334 ns	1654771 ns	1.00
metal/synchronization/stream	19667 ns	18667 ns	1.05
metal/synchronization/context	19458 ns	20000 ns	0.97

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

[codecov]

Codecov Report

❌ Patch coverage is 97.05882% with 1 line in your changes missing coverage. Please review.
✅ Project coverage is 80.83%. Comparing base (cd8846e) to head (36bd61e).

Files with missing lines	Patch %	Lines
src/indexing.jl	0.00%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #648      +/-   ##
==========================================
- Coverage   80.92%   80.83%   -0.09%     
==========================================
  Files          62       62              
  Lines        2820     2844      +24     
==========================================
+ Hits         2282     2299      +17     
- Misses        538      545       +7     

☔ 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.