add debug option

src/orisys/HHD.py

@@ -51,7 +51,8 @@ class nHHD(object):
             backend = 'cpu'
         elif backend == 'opencl' and not OPENCL_AVAILABLE:
             backend = 'cpu'
-        
+
+        self.debug = kwargs.get('debug', False)
         self.poisson_backend = backend
         
         # Initialize CUDA streams for cupy backend
@@ -103,7 +104,7 @@ class nHHD(object):
         Dispatch Poisson solve using the selected backend.
         """
         if self.poisson_backend == 'opencl':
-            return self.psolver.solve_opencl(field, verbose, profile=True)
+            return self.psolver.solve_opencl(field, verbose, profile=self.debug)
 
         if self.poisson_backend == 'cupy':
             return self.psolver.solve_gpu(field, verbose)
@@ -136,7 +137,7 @@ class nHHD(object):
 
             # compute potentials
             if self.poisson_backend == 'opencl' and ('OPENCL_AVAILABLE' in globals() and OPENCL_AVAILABLE):
-                self.nD, self.nRu = self.psolver.solve_opencl_batch2(self.div, self.curlw, verbose > 0, profile=True)
+                self.nD, self.nRu = self.psolver.solve_opencl_batch2(self.div, self.curlw, verbose > 0, profile=self.debug)
             else:
                 self.nD = self._solve_poisson_backend(self.div, verbose > 0)
                 self.nRu = self._solve_poisson_backend(self.curlw, verbose > 0)
@@ -1655,7 +1656,7 @@ class PoissonSolver(object):
         return full_conv[slices]
 
 
-    def solve_opencl_batch2(self, f1, f2, verbose=False, profile=True):
+    def solve_opencl_batch2(self, f1, f2, verbose=False, profile=False):
         """
         Batched OpenCL Poisson solver for two 2D fields.
         Optimized: scatter H2D (~4x smaller transfer), fused multiply