Version 2.0.0

API Changes:

• deviceType, gpuInfo, cpuInfo not longer accepts 'platform_idx' parameter as OpenCL contexts cannot contain more than one platform.

New Features:

• Added functionality to create custom OpenCL functions from user provided kernels

• Added 'synchronize' function to assure completion of device calls (necessary for benchmarking)

• Added determinant function (det)

• Allow for gpuR object - base object interaction (e.g. vclMatrix * matrix)

• Added ‘inplace' function for ’inplace' operations. These operations include '+', '-', '*', '/', 'sin', 'asin', 'sinh', 'cos', 'acos', 'cosh', 'tan', 'atan', 'tanh'.

• Added 'sqrt', 'sum', 'sign','pmin', and 'pmax' functions

• Methods to pass two gpuR matrix objects to 'cov'

• Added 'norm' method

• Added gpuRmatrix/gpuRvector Arith '+','-' methods

Bug Fixes:

• Fixed incorrect device info when using different contexts

• Fixed Integer Matrix Multiplication

• All OpenCL devices will be initialized on startup (previous version occasionally would omit some devices)

Most recent release of gpuR.

There are several new enhancements to the package including:

1. Automatically detect available SDK on install if available
2. Simplified installation to build OpenCL ICD when have OpenCL driver but no SDK installed (thanks Yixuan Qui)
3. Control over individual OpenCL contexts to allow user to choose device to use
4. Added as.* methods for vclMatrix/Vector and gpuMatrix/Vector objects
5. Added str method for matrix objects
6. Added length method for matrix objects
7. Added solve method for square vclMatrix objects
8. Added QR-decompsition, SVD, Cholesky for square gpuMatrix/vclMatrix objects
9. Added diag and diag<- method for matix objects

This is the initial release for the CRAN repository.