Moved the RunKernel and PadCopyTransposeMatrix functions out of the Routine class

8 files changed, 16 insertions, 16 deletions

diff --git a/src/routines/level1/xamax.cc b/src/routines/level1/xamax.cc
index 9a7d2173..6028d953 100644
--- a/src/routines/level1/xamax.cc
+++ b/src/routines/level1/xamax.cc
@@ -80,7 +80,7 @@ StatusCode Xamax<T>::DoAmax(const size_t n,
     auto global1 = std::vector<size_t>{db_["WGS1"]*temp_size};
     auto local1 = std::vector<size_t>{db_["WGS1"]};
     auto kernelEvent = Event();
-    status = RunKernel(kernel1, global1, local1, kernelEvent.pointer());
+    status = RunKernel(kernel1, queue_, device_, global1, local1, kernelEvent.pointer());
     if (ErrorIn(status)) { return status; }
     eventWaitList.push_back(kernelEvent);
 
@@ -93,7 +93,7 @@ StatusCode Xamax<T>::DoAmax(const size_t n,
     // Launches the epilogue kernel
     auto global2 = std::vector<size_t>{db_["WGS2"]};
     auto local2 = std::vector<size_t>{db_["WGS2"]};
-    status = RunKernel(kernel2, global2, local2, event_, eventWaitList);
+    status = RunKernel(kernel2, queue_, device_, global2, local2, event_, eventWaitList);
     if (ErrorIn(status)) { return status; }
 
     // Succesfully finished the computation
diff --git a/src/routines/level1/xasum.cc b/src/routines/level1/xasum.cc
index 3dcaa80a..6046a467 100644
--- a/src/routines/level1/xasum.cc
+++ b/src/routines/level1/xasum.cc
@@ -78,7 +78,7 @@ StatusCode Xasum<T>::DoAsum(const size_t n,
     auto global1 = std::vector<size_t>{db_["WGS1"]*temp_size};
     auto local1 = std::vector<size_t>{db_["WGS1"]};
     auto kernelEvent = Event();
-    status = RunKernel(kernel1, global1, local1, kernelEvent.pointer());
+    status = RunKernel(kernel1, queue_, device_, global1, local1, kernelEvent.pointer());
     if (ErrorIn(status)) { return status; }
     eventWaitList.push_back(kernelEvent);
 
@@ -90,7 +90,7 @@ StatusCode Xasum<T>::DoAsum(const size_t n,
     // Launches the epilogue kernel
     auto global2 = std::vector<size_t>{db_["WGS2"]};
     auto local2 = std::vector<size_t>{db_["WGS2"]};
-    status = RunKernel(kernel2, global2, local2, event_, eventWaitList);
+    status = RunKernel(kernel2, queue_, device_, global2, local2, event_, eventWaitList);
     if (ErrorIn(status)) { return status; }
 
     // Succesfully finished the computation
diff --git a/src/routines/level1/xaxpy.cc b/src/routines/level1/xaxpy.cc
index b57001f9..dbc05cf7 100644
--- a/src/routines/level1/xaxpy.cc
+++ b/src/routines/level1/xaxpy.cc
@@ -94,13 +94,13 @@ StatusCode Xaxpy<T>::DoAxpy(const size_t n, const T alpha,
     if (use_fast_kernel) {
       auto global = std::vector<size_t>{CeilDiv(n, db_["WPT"]*db_["VW"])};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     else {
       auto n_ceiled = Ceil(n, db_["WGS"]*db_["WPT"]);
       auto global = std::vector<size_t>{n_ceiled/db_["WPT"]};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     if (ErrorIn(status)) { return status; }
 
diff --git a/src/routines/level1/xcopy.cc b/src/routines/level1/xcopy.cc
index 273e87a6..8848201c 100644
--- a/src/routines/level1/xcopy.cc
+++ b/src/routines/level1/xcopy.cc
@@ -88,13 +88,13 @@ StatusCode Xcopy<T>::DoCopy(const size_t n,
     if (use_fast_kernel) {
       auto global = std::vector<size_t>{CeilDiv(n, db_["WPT"]*db_["VW"])};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     else {
       auto n_ceiled = Ceil(n, db_["WGS"]*db_["WPT"]);
       auto global = std::vector<size_t>{n_ceiled/db_["WPT"]};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     if (ErrorIn(status)) { return status; }
 
diff --git a/src/routines/level1/xdot.cc b/src/routines/level1/xdot.cc
index 25eccadf..a819564a 100644
--- a/src/routines/level1/xdot.cc
+++ b/src/routines/level1/xdot.cc
@@ -86,7 +86,7 @@ StatusCode Xdot<T>::DoDot(const size_t n,
     auto global1 = std::vector<size_t>{db_["WGS1"]*temp_size};
     auto local1 = std::vector<size_t>{db_["WGS1"]};
     auto kernelEvent = Event();
-    status = RunKernel(kernel1, global1, local1, kernelEvent.pointer());
+    status = RunKernel(kernel1, queue_, device_, global1, local1, kernelEvent.pointer());
     if (ErrorIn(status)) { return status; }
     eventWaitList.push_back(kernelEvent);
 
@@ -98,7 +98,7 @@ StatusCode Xdot<T>::DoDot(const size_t n,
     // Launches the epilogue kernel
     auto global2 = std::vector<size_t>{db_["WGS2"]};
     auto local2 = std::vector<size_t>{db_["WGS2"]};
-    status = RunKernel(kernel2, global2, local2, event_, eventWaitList);
+    status = RunKernel(kernel2, queue_, device_, global2, local2, event_, eventWaitList);
     if (ErrorIn(status)) { return status; }
 
     // Succesfully finished the computation
diff --git a/src/routines/level1/xnrm2.cc b/src/routines/level1/xnrm2.cc
index eca283f8..8904c369 100644
--- a/src/routines/level1/xnrm2.cc
+++ b/src/routines/level1/xnrm2.cc
@@ -78,7 +78,7 @@ StatusCode Xnrm2<T>::DoNrm2(const size_t n,
     auto global1 = std::vector<size_t>{db_["WGS1"]*temp_size};
     auto local1 = std::vector<size_t>{db_["WGS1"]};
     auto kernelEvent = Event();
-    status = RunKernel(kernel1, global1, local1, kernelEvent.pointer());
+    status = RunKernel(kernel1, queue_, device_, global1, local1, kernelEvent.pointer());
     if (ErrorIn(status)) { return status; }
     eventWaitList.push_back(kernelEvent);
 
@@ -90,7 +90,7 @@ StatusCode Xnrm2<T>::DoNrm2(const size_t n,
     // Launches the epilogue kernel
     auto global2 = std::vector<size_t>{db_["WGS2"]};
     auto local2 = std::vector<size_t>{db_["WGS2"]};
-    status = RunKernel(kernel2, global2, local2, event_, eventWaitList);
+    status = RunKernel(kernel2, queue_, device_, global2, local2, event_, eventWaitList);
     if (ErrorIn(status)) { return status; }
 
     // Succesfully finished the computation
diff --git a/src/routines/level1/xscal.cc b/src/routines/level1/xscal.cc
index 0ce211b6..8078c076 100644
--- a/src/routines/level1/xscal.cc
+++ b/src/routines/level1/xscal.cc
@@ -82,13 +82,13 @@ StatusCode Xscal<T>::DoScal(const size_t n, const T alpha,
     if (use_fast_kernel) {
       auto global = std::vector<size_t>{CeilDiv(n, db_["WPT"]*db_["VW"])};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     else {
       auto n_ceiled = Ceil(n, db_["WGS"]*db_["WPT"]);
       auto global = std::vector<size_t>{n_ceiled/db_["WPT"]};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     if (ErrorIn(status)) { return status; }
 
diff --git a/src/routines/level1/xswap.cc b/src/routines/level1/xswap.cc
index 773d78b5..01184db5 100644
--- a/src/routines/level1/xswap.cc
+++ b/src/routines/level1/xswap.cc
@@ -88,13 +88,13 @@ StatusCode Xswap<T>::DoSwap(const size_t n,
     if (use_fast_kernel) {
       auto global = std::vector<size_t>{CeilDiv(n, db_["WPT"]*db_["VW"])};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     else {
       auto n_ceiled = Ceil(n, db_["WGS"]*db_["WPT"]);
       auto global = std::vector<size_t>{n_ceiled/db_["WPT"]};
       auto local = std::vector<size_t>{db_["WGS"]};
-      status = RunKernel(kernel, global, local, event_);
+      status = RunKernel(kernel, queue_, device_, global, local, event_);
     }
     if (ErrorIn(status)) { return status; }