summaryrefslogtreecommitdiff
path: root/src/routines/level3/xsyr2k.cc
diff options
context:
space:
mode:
Diffstat (limited to 'src/routines/level3/xsyr2k.cc')
-rw-r--r--src/routines/level3/xsyr2k.cc13
1 files changed, 10 insertions, 3 deletions
diff --git a/src/routines/level3/xsyr2k.cc b/src/routines/level3/xsyr2k.cc
index 3206c669..c52e1353 100644
--- a/src/routines/level3/xsyr2k.cc
+++ b/src/routines/level3/xsyr2k.cc
@@ -104,6 +104,12 @@ StatusCode Xsyr2k<T>::DoSyr2k(const Layout layout, const Triangle triangle, cons
auto b_temp = (b_no_temp) ? b_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>();
@@ -147,8 +153,8 @@ StatusCode Xsyr2k<T>::DoSyr2k(const Layout layout, const Triangle triangle, cons
// Sets the kernel arguments
kernel.SetArgument(0, static_cast<int>(n_ceiled));
kernel.SetArgument(1, static_cast<int>(k_ceiled));
- kernel.SetArgument(2, alpha);
- kernel.SetArgument(3, beta);
+ kernel.SetArgument(2, alpha_buffer());
+ kernel.SetArgument(3, beta_buffer());
kernel.SetArgument(4, a_temp());
kernel.SetArgument(5, b_temp());
kernel.SetArgument(6, c_temp());
@@ -168,7 +174,8 @@ StatusCode Xsyr2k<T>::DoSyr2k(const Layout layout, const Triangle triangle, cons
// Swaps the arguments for matrices A and B, and sets 'beta' to 1
auto one = static_cast<T>(1);
- kernel.SetArgument(3, one);
+ beta_buffer.Write(queue_, 1, &one);
+ kernel.SetArgument(3, beta_buffer());
kernel.SetArgument(4, b_temp());
kernel.SetArgument(5, a_temp());