Add gemmex wrapper and test

[kshyatt]

Porting JuliaGPU/CuArrays.jl#653

[codecov]

Codecov Report

Merging #196 into master will increase coverage by 0.19%.
The diff coverage is 93.75%.

@@            Coverage Diff             @@
##           master     #196      +/-   ##
==========================================
+ Coverage   81.47%   81.66%   +0.19%     
==========================================
  Files         142      142              
  Lines        9229     9245      +16     
==========================================
+ Hits         7519     7550      +31     
+ Misses       1710     1695      -15     

Impacted Files	Coverage Δ
test/cublas.jl	91.66% <ø> (ø)
lib/cublas/wrappers.jl	92.52% <93.75%> (+0.02%)	⬆️
test/runtests.jl	61.53% <0.00%> (+11.18%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 8ee1a6f...fb1c34b. Read the comment docs.