haraldwolff
/
CLBlast
mirror of https://github.com/CNugteren/CLBlast.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixed number of threads launched for AXPY

pull/2/head
CNugteren 2015-06-14 10:08:23 +02:00
parent 4b3e3dcfe0
commit 9aa2989447
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/routines/xaxpy.cc
View File

@ -88,8 +88,8 @@ StatusCode Xaxpy<T>::DoAxpy(const size_t n, const T alpha,
status = RunKernel(kernel, global, local);
}
else {
auto n_ceiled = Ceil(n, db_["WGS"]);
auto global = std::vector<size_t>{CeilDiv(n_ceiled, db_["WPT"])};
auto n_ceiled = Ceil(n, db_["WGS"]*db_["WPT"]);
auto global = std::vector<size_t>{n_ceiled/db_["WPT"]};
auto local = std::vector<size_t>{db_["WGS"]};
status = RunKernel(kernel, global, local);
}