diff options
author | Cedric Nugteren <web@cedricnugteren.nl> | 2016-06-28 22:32:25 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2016-06-28 22:32:25 +0200 |
commit | 7c13bacf129291e3e295ecb6e833788477085fa0 (patch) | |
tree | d114eeca418444d0b1c70cc9cce983de041235c9 /src/kernels/level2/xgemv_fast.opencl | |
parent | 181eb20bbf15cf11baaf6112b6965050c49dd543 (diff) | |
parent | 577f0ee1179014ece853af39d6f0ff0c87316eb3 (diff) |
Merge pull request #70 from CNugteren/development
Update to version 0.8.0
Diffstat (limited to 'src/kernels/level2/xgemv_fast.opencl')
-rw-r--r-- | src/kernels/level2/xgemv_fast.opencl | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/src/kernels/level2/xgemv_fast.opencl b/src/kernels/level2/xgemv_fast.opencl index 61fdffa3..6a494e84 100644 --- a/src/kernels/level2/xgemv_fast.opencl +++ b/src/kernels/level2/xgemv_fast.opencl @@ -95,13 +95,18 @@ inline realVFR LoadMatrixAVFR(const __global realVFR* restrict agm, const int x, // --> 'a_rotated' is 0 // --> 'do_conjugate' is 0 __attribute__((reqd_work_group_size(WGS2, 1, 1))) -__kernel void XgemvFast(const int m, const int n, const real alpha, const real beta, +__kernel void XgemvFast(const int m, const int n, + const __constant real* restrict arg_alpha, + const __constant real* restrict arg_beta, const int a_rotated, const __global realVF* restrict agm, const int a_offset, const int a_ld, 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 int do_conjugate, const int parameter, const int kl, const int ku) { + const real alpha = arg_alpha[0]; + const real beta = arg_beta[0]; + // Local memory for the vector X __local real xlm[WGS2]; @@ -192,13 +197,18 @@ __kernel void XgemvFast(const int m, const int n, const real alpha, const real b // --> 'a_rotated' is 1 // --> 'do_conjugate' is 0 __attribute__((reqd_work_group_size(WGS3, 1, 1))) -__kernel void XgemvFastRot(const int m, const int n, const real alpha, const real beta, +__kernel void XgemvFastRot(const int m, const int n, + const __constant real* restrict arg_alpha, + const __constant real* restrict arg_beta, const int a_rotated, const __global realVFR* restrict agm, const int a_offset, const int a_ld, 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 int do_conjugate, const int parameter, const int kl, const int ku) { + const real alpha = arg_alpha[0]; + const real beta = arg_beta[0]; + // Local memory for the vector X __local real xlm[WGS3]; |