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, 8 insertions, 8 deletions

diff --git a/src/kernels/level1/xaxpy.opencl b/src/kernels/level1/xaxpy.opencl
index d533041b..ece8476e 100644
--- a/src/kernels/level1/xaxpy.opencl
+++ b/src/kernels/level1/xaxpy.opencl
@@ -22,10 +22,10 @@ R"(
 // =================================================================================================
 
 // Full version of the kernel with offsets and strided accesses
-__attribute__((reqd_work_group_size(WGS, 1, 1)))
-__kernel void Xaxpy(const int n, const real_arg arg_alpha,
-                    const __global real* restrict xgm, const int x_offset, const int x_inc,
-                    __global real* ygm, const int y_offset, const int y_inc) {
+__kernel __attribute__((reqd_work_group_size(WGS, 1, 1)))
+void Xaxpy(const int n, const real_arg arg_alpha,
+           const __global real* restrict xgm, const int x_offset, const int x_inc,
+           __global real* ygm, const int y_offset, const int y_inc) {
   const real alpha = GetRealArg(arg_alpha);
 
   // Loops over the work that needs to be done (allows for an arbitrary number of threads)
@@ -40,10 +40,10 @@ __kernel void Xaxpy(const int n, const real_arg arg_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 XaxpyFast(const int n, const real_arg arg_alpha,
-                        const __global realV* restrict xgm,
-                        __global realV* ygm) {
+__kernel __attribute__((reqd_work_group_size(WGS, 1, 1)))
+void XaxpyFast(const int n, const real_arg arg_alpha,
+               const __global realV* restrict xgm,
+               __global realV* ygm) {
   const real alpha = GetRealArg(arg_alpha);
 
   #pragma unroll