Some cudadrv tests

[kshyatt]

Also added some more @testset blocks instead of let

[github-actions]

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

Click here to view the suggested changes.

diff --git a/src/texture.jl b/src/texture.jl
index fc1590423..bbdca57db 100644
--- a/src/texture.jl
+++ b/src/texture.jl
@@ -97,7 +97,7 @@ end
 
 # idempotency
 CuTextureArray{T,N}(xs::CuTextureArray{T,N}) where {T,N} = xs
-CuTextureArray(xs::CuTextureArray{T,N}) where {T,N} = xs
+CuTextureArray(xs::CuTextureArray{T, N}) where {T, N} = xs
 
 CuTextureArray(A::AbstractArray{T,N}) where {T,N} = CuTextureArray{T,N}(A)
 
diff --git a/test/core/cudadrv.jl b/test/core/cudadrv.jl
index 2372cb568..7772cf9cb 100644
--- a/test/core/cudadrv.jl
+++ b/test/core/cudadrv.jl
@@ -435,15 +435,15 @@ nb = sizeof(data)
 typed_pointer(buf::Union{CUDA.DeviceMemory, CUDA.UnifiedMemory}, T) = convert(CuPtr{T}, buf)
 typed_pointer(buf::CUDA.HostMemory, T)                              = convert(Ptr{T},   buf)
 
-@testset "showing" begin
-    for (Ty, str) in zip([CUDA.DeviceMemory, CUDA.HostMemory, CUDA.UnifiedMemory], ("DeviceMemory", "HostMemory", "UnifiedMemory"))
-        dummy = CUDA.alloc(Ty, 0)
-        @test startswith(sprint(show, dummy), str)
-        CUDA.free(dummy)
+    @testset "showing" begin
+        for (Ty, str) in zip([CUDA.DeviceMemory, CUDA.HostMemory, CUDA.UnifiedMemory], ("DeviceMemory", "HostMemory", "UnifiedMemory"))
+            dummy = CUDA.alloc(Ty, 0)
+            @test startswith(sprint(show, dummy), str)
+            CUDA.free(dummy)
+        end
     end
-end
 
-@testset "allocations and copies, src $srcTy dst $dstTy" for srcTy in [CUDA.DeviceMemory, CUDA.HostMemory, CUDA.UnifiedMemory],
+    @testset "allocations and copies, src $srcTy dst $dstTy" for srcTy in [CUDA.DeviceMemory, CUDA.HostMemory, CUDA.UnifiedMemory],
     dstTy in [CUDA.DeviceMemory, CUDA.HostMemory, CUDA.UnifiedMemory]
 
     dummy = CUDA.alloc(srcTy, 0)
@@ -479,7 +479,7 @@ end
 
     # test device with context in which pointer was allocated.
     @test device(typed_pointer(src, T)) == device()
-    @test context(typed_pointer(src, T)) == context()
+        @test context(typed_pointer(src, T)) == context()
     if !memory_pools_supported(device())
         # NVIDIA bug #3319609
         @test context(typed_pointer(src, T)) == context()
@@ -503,7 +503,7 @@ end
     CUDA.free(dst)
 end
 
-@testset "pointer attributes" begin
+    @testset "pointer attributes" begin
     src = CUDA.alloc(CUDA.DeviceMemory, nb)
 
     attribute!(typed_pointer(src, T), CUDA.POINTER_ATTRIBUTE_SYNC_MEMOPS, 0)
@@ -511,7 +511,7 @@ end
     CUDA.free(src)
 end
 
-@testset "asynchronous operations" begin
+    @testset "asynchronous operations" begin
     src = CUDA.alloc(CUDA.DeviceMemory, nb)
 
     unsafe_copyto!(typed_pointer(src, T), pointer(data), N; async=true)
@@ -521,7 +521,7 @@ end
     CUDA.free(src)
 end
 
-@testset "pinned memory" begin
+    @testset "pinned memory" begin
     # create a pinned and mapped buffer
     src = CUDA.alloc(CUDA.HostMemory, nb, CUDA.MEMHOSTALLOC_DEVICEMAP)
 
@@ -553,16 +553,16 @@ if attribute(device(), CUDA.DEVICE_ATTRIBUTE_HOST_REGISTER_SUPPORTED) != 0
 
     CUDA.unregister(src)
 
-    # with a RefValue
-    src = Ref{T}(T(42))
-    CUDA.pin(src)
-    cpu_ptr = Base.unsafe_convert(Ptr{T}, src)
-    ref = Array{T}(undef, 1)
-    unsafe_copyto!(pointer(ref), cpu_ptr, 1)
-    @test ref == [T(42)]
+        # with a RefValue
+        src = Ref{T}(T(42))
+        CUDA.pin(src)
+        cpu_ptr = Base.unsafe_convert(Ptr{T}, src)
+        ref = Array{T}(undef, 1)
+        unsafe_copyto!(pointer(ref), cpu_ptr, 1)
+        @test ref == [T(42)]
 end
 
-@testset "unified memory" begin
+    @testset "unified memory" begin
     src = CUDA.alloc(CUDA.UnifiedMemory, nb)
 
     @test_throws BoundsError CUDA.prefetch(src, 2*nb; device=CUDA.DEVICE_CPU)
@@ -583,7 +583,7 @@ end
     CUDA.free(src)
 end
 
-@testset "3d memcpy" begin
+    @testset "3d memcpy" begin
     # TODO: use cuMemAllocPitch (and put pitch in buffer?) to actually get benefit from this
 
     data = collect(reshape(1:27, 3, 3, 3))

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 82.86%. Comparing base (6bf72dd) to head (dbb2215).

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #2684      +/-   ##
==========================================
+ Coverage   82.57%   82.86%   +0.28%     
==========================================
  Files         153      153              
  Lines       13606    13606              
==========================================
+ Hits        11235    11274      +39     
+ Misses       2371     2332      -39     

☔ 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.

[github-actions]

CUDA.jl Benchmarks

Details

Benchmark suite	Current: dbb2215	Previous: 6bf72dd	Ratio
latency/precompile	46183641505 ns	46450283323 ns	0.99
latency/ttfp	7001382825 ns	7028014177 ns	1.00
latency/import	3651822156 ns	3667348189 ns	1.00
integration/volumerhs	9616637.5 ns	9625836 ns	1.00
integration/byval/slices=1	146680.5 ns	146875 ns	1.00
integration/byval/slices=3	425045 ns	424860 ns	1.00
integration/byval/reference	144900 ns	144959 ns	1.00
integration/byval/slices=2	285974 ns	285961 ns	1.00
integration/cudadevrt	103233 ns	103332 ns	1.00
kernel/indexing	13949 ns	14061 ns	0.99
kernel/indexing_checked	14499 ns	14775 ns	0.98
kernel/occupancy	637.1046511627907 ns	656.859649122807 ns	0.97
kernel/launch	2004.2 ns	2090.2 ns	0.96
kernel/rand	14598 ns	16643 ns	0.88
array/reverse/1d	19363 ns	19602 ns	0.99
array/reverse/2d	24535 ns	24553 ns	1.00
array/reverse/1d_inplace	10719 ns	11159 ns	0.96
array/reverse/2d_inplace	12480 ns	13010 ns	0.96
array/copy	21175 ns	20672 ns	1.02
array/iteration/findall/int	157906 ns	157732 ns	1.00
array/iteration/findall/bool	138756 ns	138853.5 ns	1.00
array/iteration/findfirst/int	152794 ns	153651.5 ns	0.99
array/iteration/findfirst/bool	154428 ns	153926 ns	1.00
array/iteration/scalar	70496 ns	72447 ns	0.97
array/iteration/logical	213423 ns	206640.5 ns	1.03
array/iteration/findmin/1d	41018 ns	40619 ns	1.01
array/iteration/findmin/2d	93431 ns	93219 ns	1.00
array/reductions/reduce/1d	35842 ns	34826 ns	1.03
array/reductions/reduce/2d	40715 ns	50621 ns	0.80
array/reductions/mapreduce/1d	32909 ns	32476 ns	1.01
array/reductions/mapreduce/2d	41241 ns	50769 ns	0.81
array/broadcast	20512 ns	20427 ns	1.00
array/copyto!/gpu_to_gpu	13698 ns	11886 ns	1.15
array/copyto!/cpu_to_gpu	208479.5 ns	207751.5 ns	1.00
array/copyto!/gpu_to_cpu	243344 ns	245794 ns	0.99
array/accumulate/1d	108244 ns	109015 ns	0.99
array/accumulate/2d	80382 ns	79626 ns	1.01
array/construct	1302.7 ns	1306 ns	1.00
array/random/randn/Float32	43238 ns	43298.5 ns	1.00
array/random/randn!/Float32	26422 ns	26052 ns	1.01
array/random/rand!/Int64	26958 ns	26998 ns	1.00
array/random/rand!/Float32	8688.5 ns	8602.333333333334 ns	1.01
array/random/rand/Int64	29725 ns	29780 ns	1.00
array/random/rand/Float32	13025 ns	12942 ns	1.01
array/permutedims/4d	61583 ns	60894 ns	1.01
array/permutedims/2d	55519.5 ns	55115 ns	1.01
array/permutedims/3d	55841.5 ns	55898 ns	1.00
array/sorting/1d	2775794 ns	2776458 ns	1.00
array/sorting/by	3367253 ns	3369147.5 ns	1.00
array/sorting/2d	1084250 ns	1084406 ns	1.00
cuda/synchronization/stream/auto	1004 ns	1025.7 ns	0.98
cuda/synchronization/stream/nonblocking	6261.8 ns	6461.2 ns	0.97
cuda/synchronization/stream/blocking	776.5849056603773 ns	789.3663366336634 ns	0.98
cuda/synchronization/context/auto	1160.1 ns	1164 ns	1.00
cuda/synchronization/context/nonblocking	6588 ns	6604.6 ns	1.00
cuda/synchronization/context/blocking	903.7234042553191 ns	889.4285714285714 ns	1.02

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