Age | Commit message (Collapse) | Author |
|
|
|
|
|
(#461)
|
|
|
|
* Fixed a bug in XAMAX/XMIN routines that caused the increment and offset to be included in the result
* Perform proper integer-output testing in XAMAX tests
* A few changes towards getting it ready for a PR
* Also fix compilation for clBLAS and cuBLAS references
* Fix a bug that would only use the real part of complex numbers in the amax/amin routines
* A few small fixes related to the AMAX tests
|
|
|
|
|
|
|
|
|
|
for opencl.hpp
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
numbering
|
|
the tuners
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
First im2col+GEMM implementation of convolution
|
|
|
|
|
|
|
|
|
|
|
|
|
|
transposing
|
|
invalid ones completely, saving compilation time
|
|
|
|
|
|
|
|
|
|
|
|
OpenCL driver unloads first
|
|
|
|
comparisons
|