diff options
Diffstat (limited to 'src/kernels/level2')
| -rw-r--r-- | src/kernels/level2/xgemv.opencl | 4 | ||||
| -rw-r--r-- | src/kernels/level2/xgemv_fast.opencl | 8 | ||||
| -rw-r--r-- | src/kernels/level2/xger.opencl | 4 | ||||
| -rw-r--r-- | src/kernels/level2/xher.opencl | 4 | ||||
| -rw-r--r-- | src/kernels/level2/xher2.opencl | 4 |
5 files changed, 12 insertions, 12 deletions
diff --git a/src/kernels/level2/xgemv.opencl b/src/kernels/level2/xgemv.opencl index 65b4291f..41d44dab 100644 --- a/src/kernels/level2/xgemv.opencl +++ b/src/kernels/level2/xgemv.opencl @@ -210,8 +210,8 @@ inline real LoadMatrixA(const __global real* restrict agm, const int x, const in // ================================================================================================= // Full version of the kernel -__attribute__((reqd_work_group_size(WGS1, 1, 1))) -__kernel void Xgemv(const int m, const int n, +__kernel __attribute__((reqd_work_group_size(WGS1, 1, 1))) +void Xgemv(const int m, const int n, const __constant real* restrict arg_alpha, const __constant real* restrict arg_beta, const int a_rotated, diff --git a/src/kernels/level2/xgemv_fast.opencl b/src/kernels/level2/xgemv_fast.opencl index 6a494e84..dae31a2b 100644 --- a/src/kernels/level2/xgemv_fast.opencl +++ b/src/kernels/level2/xgemv_fast.opencl @@ -94,8 +94,8 @@ inline realVFR LoadMatrixAVFR(const __global realVFR* restrict agm, const int x, // --> 'a_ld' is a multiple of VW2 // --> '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, +__kernel __attribute__((reqd_work_group_size(WGS2, 1, 1))) +void XgemvFast(const int m, const int n, const __constant real* restrict arg_alpha, const __constant real* restrict arg_beta, const int a_rotated, @@ -196,8 +196,8 @@ __kernel void XgemvFast(const int m, const int n, // --> 'a_ld' is a multiple of VW3 // --> '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, +__kernel __attribute__((reqd_work_group_size(WGS3, 1, 1))) +void XgemvFastRot(const int m, const int n, const __constant real* restrict arg_alpha, const __constant real* restrict arg_beta, const int a_rotated, diff --git a/src/kernels/level2/xger.opencl b/src/kernels/level2/xger.opencl index 63817afb..21744799 100644 --- a/src/kernels/level2/xger.opencl +++ b/src/kernels/level2/xger.opencl @@ -18,8 +18,8 @@ R"( // ================================================================================================= // Regular version of the rank-1 matrix update kernel (GER, GERU, GERC) -__attribute__((reqd_work_group_size(WGS1, WGS2, 1))) -__kernel void Xger(const int max1, const int max2, +__kernel __attribute__((reqd_work_group_size(WGS1, WGS2, 1))) +void Xger(const int max1, const int max2, const __constant real* restrict arg_alpha, const __global real* restrict xgm, const int x_offset, const int x_inc, const __global real* ygm, const int y_offset, const int y_inc, diff --git a/src/kernels/level2/xher.opencl b/src/kernels/level2/xher.opencl index fc635f2e..4b304a9f 100644 --- a/src/kernels/level2/xher.opencl +++ b/src/kernels/level2/xher.opencl @@ -18,8 +18,8 @@ R"( // ================================================================================================= // Symmetric version of the rank-1 matrix update kernel (HER, HPR, SYR, SPR) -__attribute__((reqd_work_group_size(WGS1, WGS2, 1))) -__kernel void Xher(const int n, +__kernel __attribute__((reqd_work_group_size(WGS1, WGS2, 1))) +void Xher(const int n, const __constant real* restrict arg_alpha, const __global real* restrict xgm, const int x_offset, const int x_inc, __global real* restrict agm, const int a_offset, const int a_ld, diff --git a/src/kernels/level2/xher2.opencl b/src/kernels/level2/xher2.opencl index a66f255f..8d05f020 100644 --- a/src/kernels/level2/xher2.opencl +++ b/src/kernels/level2/xher2.opencl @@ -18,8 +18,8 @@ R"( // ================================================================================================= // Symmetric version of the rank-2 matrix update kernel (HER2, HPR2, SYR2, SPR2) -__attribute__((reqd_work_group_size(WGS1, WGS2, 1))) -__kernel void Xher2(const int n, +__kernel __attribute__((reqd_work_group_size(WGS1, WGS2, 1))) +void Xher2(const int n, const __constant real* restrict arg_alpha, const __global real* restrict xgm, const int x_offset, const int x_inc, const __global real* restrict ygm, const int y_offset, const int y_inc, |