rand and friends default to Float64

[Sleort]

Describe the bug
The random number generator in CuArrays seems to default to Float64, although
https://github.com/JuliaGPU/CuArrays.jl/blob/7f7e72c1152c25855bbaea0cabdc6d5857c50c21/src/rand/random.jl#L134-L138
specifies that it should be Float32. I'm not sure why, though...

To Reproduce

julia> using CuArrays

julia> rng = CURAND.RNG()
CuArrays.CURAND.RNG(Ptr{Nothing} @0x00000000025b6be0, 100)

julia> rand(rng, 1)
1-element CuArray{Float64,1,Nothing}:
 0.4384508447184235

julia> randn(rng, 1)
1-element CuArray{Float64,1,Nothing}:
 0.8943739751223734

Expected behavior
The default element type should be Float32 for CuArrays

Environment details (please complete this section)
Details on Julia:

Julia Version 1.2.0
Commit c6da87ff4b (2019-08-20 00:03 UTC)
Platform Info:
  OS: Linux (x86_64-pc-linux-gnu)
  CPU: Intel(R) Core(TM) i7-8750H CPU @ 2.20GHz
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-6.0.1 (ORCJIT, skylake)

Julia packages:

• CuArrays.jl: v1.4.7
• CUDAnative.jl: v2.5.5
• CUDAdrv: v4.0.4
• CUDAapi: v2.0.0

CUDA: toolkit and driver version

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Fri_Feb__8_19:08:17_PST_2019
Cuda compilation tools, release 10.1, V10.1.105

[maleadt]

julia> rng = CUDA.RNG()
CUDA.RNG(0xd4039d1b, 0x00000000)

julia> rand(rng, 1)
1-element CuArray{Float32, 1, CUDA.DeviceMemory}:
 0.9444126

Defaults to Float32 now.