SparseMatricesCSR Dispatch

[Abdelrahman912]

This PR adds a new extension module SparseMatricesCSRExt that enables dispatching SparseMatrixCSR from SparseMatricesCSR.jl to CuSparseMatrixCSR.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 89.00%. Comparing base (af58f61) to head (627c794).

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #2720      +/-   ##
==========================================
+ Coverage   88.87%   89.00%   +0.12%     
==========================================
  Files         153      153              
  Lines       13154    13154              
==========================================
+ Hits        11691    11708      +17     
+ Misses       1463     1446      -17     

☔ 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]

Your PR no longer requires formatting changes. Thank you for your contribution!

[github-actions]

CUDA.jl Benchmarks

Benchmark suite	Current: 627c794	Previous: af58f61	Ratio
latency/precompile	47219964749 ns	47364047578 ns	1.00
latency/ttfp	6800010126 ns	6821264934 ns	1.00
latency/import	3212836642.5 ns	3225196597.5 ns	1.00
integration/volumerhs	9610171.5 ns	9614354 ns	1.00
integration/byval/slices=1	146882 ns	146613 ns	1.00
integration/byval/slices=3	425144 ns	425074 ns	1.00
integration/byval/reference	144782 ns	144823 ns	1.00
integration/byval/slices=2	286155 ns	286027 ns	1.00
integration/cudadevrt	103242 ns	103297 ns	1.00
kernel/indexing	14023 ns	14019 ns	1.00
kernel/indexing_checked	14532 ns	14585 ns	1.00
kernel/occupancy	687.8533333333334 ns	721.3333333333334 ns	0.95
kernel/launch	2110 ns	2085.8 ns	1.01
kernel/rand	17528 ns	18047 ns	0.97
array/reverse/1d	19719 ns	19477 ns	1.01
array/reverse/2d	25105 ns	24090.5 ns	1.04
array/reverse/1d_inplace	11120 ns	10504 ns	1.06
array/reverse/2d_inplace	13011 ns	12197 ns	1.07
array/copy	21291 ns	21209 ns	1.00
array/iteration/findall/int	157272 ns	158069.5 ns	0.99
array/iteration/findall/bool	138618.5 ns	139342 ns	0.99
array/iteration/findfirst/int	153006.5 ns	153958 ns	0.99
array/iteration/findfirst/bool	154403 ns	154465 ns	1.00
array/iteration/scalar	70522 ns	72075 ns	0.98
array/iteration/logical	213281.5 ns	215491 ns	0.99
array/iteration/findmin/1d	41124 ns	41679 ns	0.99
array/iteration/findmin/2d	94274 ns	94340 ns	1.00
array/reductions/reduce/1d	35396 ns	35947 ns	0.98
array/reductions/reduce/2d	41051 ns	41316 ns	0.99
array/reductions/mapreduce/1d	33102 ns	33483 ns	0.99
array/reductions/mapreduce/2d	40882.5 ns	40997 ns	1.00
array/broadcast	20761.5 ns	20733 ns	1.00
array/copyto!/gpu_to_gpu	13749 ns	13434 ns	1.02
array/copyto!/cpu_to_gpu	207750 ns	208335 ns	1.00
array/copyto!/gpu_to_cpu	243108.5 ns	243244 ns	1.00
array/accumulate/1d	109745.5 ns	109403 ns	1.00
array/accumulate/2d	80219 ns	80261 ns	1.00
array/construct	1247.5 ns	1244.9 ns	1.00
array/random/randn/Float32	44314 ns	43677.5 ns	1.01
array/random/randn!/Float32	26326 ns	26376 ns	1.00
array/random/rand!/Int64	27062 ns	27073 ns	1.00
array/random/rand!/Float32	8598.333333333334 ns	8572 ns	1.00
array/random/rand/Int64	33597 ns	29918 ns	1.12
array/random/rand/Float32	12971 ns	12871 ns	1.01
array/permutedims/4d	61325 ns	61023 ns	1.00
array/permutedims/2d	55343 ns	55334 ns	1.00
array/permutedims/3d	55951 ns	55987.5 ns	1.00
array/sorting/1d	2775342.5 ns	2774813 ns	1.00
array/sorting/by	3367068 ns	3365701 ns	1.00
array/sorting/2d	1084272 ns	1084786 ns	1.00
cuda/synchronization/stream/auto	1043.1 ns	1038.1 ns	1.00
cuda/synchronization/stream/nonblocking	6521.2 ns	6575 ns	0.99
cuda/synchronization/stream/blocking	833.1764705882352 ns	798.2788461538462 ns	1.04
cuda/synchronization/context/auto	1189.9 ns	1153 ns	1.03
cuda/synchronization/context/nonblocking	6686.2 ns	6748.6 ns	0.99
cuda/synchronization/context/blocking	932.2051282051282 ns	888.7142857142857 ns	1.05

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

[Abdelrahman912]

This PR should be ready by now