diff options
Diffstat (limited to 'src/routines/level3/xsyrk.cpp')
-rw-r--r-- | src/routines/level3/xsyrk.cpp | 10 |
1 files changed, 2 insertions, 8 deletions
diff --git a/src/routines/level3/xsyrk.cpp b/src/routines/level3/xsyrk.cpp index f56c232b..1992cec1 100644 --- a/src/routines/level3/xsyrk.cpp +++ b/src/routines/level3/xsyrk.cpp @@ -90,12 +90,6 @@ StatusCode Xsyrk<T>::DoSyrk(const Layout layout, const Triangle triangle, const auto a_temp = (a_no_temp) ? a_buffer : Buffer<T>(context_, k_ceiled*n_ceiled); auto c_temp = Buffer<T>(context_, n_ceiled*n_ceiled); - // Upload the scalar arguments as constant buffers to the device (needed for half-precision) - auto alpha_buffer = Buffer<T>(context_, 1); - auto beta_buffer = Buffer<T>(context_, 1); - alpha_buffer.Write(queue_, 1, &alpha); - beta_buffer.Write(queue_, 1, &beta); - // Events of all kernels (including pre/post processing kernels) auto eventWaitList = std::vector<Event>(); auto emptyEventList = std::vector<Event>(); @@ -132,8 +126,8 @@ StatusCode Xsyrk<T>::DoSyrk(const Layout layout, const Triangle triangle, const // Sets the kernel arguments kernel.SetArgument(0, static_cast<int>(n_ceiled)); kernel.SetArgument(1, static_cast<int>(k_ceiled)); - kernel.SetArgument(2, alpha_buffer()); - kernel.SetArgument(3, beta_buffer()); + kernel.SetArgument(2, GetRealArg(alpha)); + kernel.SetArgument(3, GetRealArg(beta)); kernel.SetArgument(4, a_temp()); kernel.SetArgument(5, a_temp()); kernel.SetArgument(6, c_temp()); |