Merge branch 'master' of https://github.com/dvasschemacq/CLBlast into dvasschemacq-master

Conflicts:
	src/kernels/level1/xaxpy.opencl
	src/kernels/level2/xgemv.opencl
	src/kernels/level2/xgemv_fast.opencl
	src/kernels/level2/xger.opencl
	src/kernels/level2/xher.opencl
	src/kernels/level2/xher2.opencl
	src/kernels/level3/xgemm_part2.opencl

1 files changed, 9 insertions, 6 deletions

diff --git a/src/kernels/level1/xscal.opencl b/src/kernels/level1/xscal.opencl
index 59936776..3da9c2fd 100644
--- a/src/kernels/level1/xscal.opencl
+++ b/src/kernels/level1/xscal.opencl
@@ -22,9 +22,10 @@ R"(
 // =================================================================================================
 
 // Full version of the kernel with offsets and strided accesses
-__attribute__((reqd_work_group_size(WGS, 1, 1)))
-__kernel void Xscal(const int n, const real alpha,
-                    __global real* xgm, const int x_offset, const int x_inc) {
+__kernel __attribute__((reqd_work_group_size(WGS, 1, 1)))
+void Xscal(const int n, const real_arg arg_alpha,
+           __global real* xgm, const int x_offset, const int x_inc) {
+  const real alpha = GetRealArg(arg_alpha);
 
   // Loops over the work that needs to be done (allows for an arbitrary number of threads)
   #pragma unroll
@@ -40,9 +41,11 @@ __kernel void Xscal(const int n, const real alpha,
 
 // Faster version of the kernel without offsets and strided accesses. Also assumes that 'n' is
 // dividable by 'VW', 'WGS' and 'WPT'.
-__attribute__((reqd_work_group_size(WGS, 1, 1)))
-__kernel void XscalFast(const int n, const real alpha,
-                        __global realV* xgm) {
+__kernel __attribute__((reqd_work_group_size(WGS, 1, 1)))
+void XscalFast(const int n, const real_arg arg_alpha,
+               __global realV* xgm) {
+  const real alpha = GetRealArg(arg_alpha);
+
   #pragma unroll
   for (int w=0; w<WPT; ++w) {
     const int id = w*get_global_size(0) + get_global_id(0);