diff options
Diffstat (limited to 'src/kernels/level1/xaxpy.opencl')
| -rw-r--r-- | src/kernels/level1/xaxpy.opencl | 7 |
1 files changed, 5 insertions, 2 deletions
diff --git a/src/kernels/level1/xaxpy.opencl b/src/kernels/level1/xaxpy.opencl index 574beb43..e0efadc1 100644 --- a/src/kernels/level1/xaxpy.opencl +++ b/src/kernels/level1/xaxpy.opencl @@ -23,9 +23,10 @@ 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 alpha, +__kernel void Xaxpy(const int n, const __constant real* restrict 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 = arg_alpha[0]; // Loops over the work that needs to be done (allows for an arbitrary number of threads) #pragma unroll @@ -40,9 +41,11 @@ __kernel void Xaxpy(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 XaxpyFast(const int n, const real alpha, +__kernel void XaxpyFast(const int n, const __constant real* restrict arg_alpha, const __global realV* restrict xgm, __global realV* ygm) { + const real alpha = arg_alpha[0]; + #pragma unroll for (int w=0; w<WPT; ++w) { const int id = w*get_global_size(0) + get_global_id(0); |