Changeset 8b31efa in sasmodels for sasmodels

Timestamp:

Oct 15, 2018 1:27:14 PM (6 years ago)

Author:

pkienzle

Branches:

master, core_shell_microgels, magnetic_model, ticket-1257-vesicle-product, ticket_1156, ticket_1265_superball, ticket_822_more_unit_tests

Children:

508475a, d5ce7fa

Parents:

4de14584

Message:

document cuda device selection; fix cuda speed issue

Location:

sasmodels

Files:

• kernelcl.py (modified) (2 diffs)
• kernelcuda.py (modified) (4 diffs)

sasmodels/kernelcl.py

@@ -227 +227 @@
         self.context = None
         if 'SAS_OPENCL' in os.environ:
-            #Setting PYOPENCL_CTX as a SAS_OPENCL to create cl context
-            os.environ["PYOPENCL_CTX"] = os.environ["SAS_OPENCL"]
+            # Set the PyOpenCL environment variable PYOPENCL_CTX 
+            # from SAS_OPENCL=driver:device.  Ignore the generic
+            # SAS_OPENCL=opencl, which is used to select the default 
+            # OpenCL device.  Don't need to check for "none" or
+            # "cuda" since use_opencl() would return False if they
+            # were defined, and we wouldn't get here.
+            dev_str = os.environ["SAS_OPENCL"]
+            if dev_str and dev_str.lower() != "opencl":
+                os.environ["PYOPENCL_CTX"] = dev_str
+
         if 'PYOPENCL_CTX' in os.environ:
             self._create_some_context()
@@ -568 +576 @@
                 current_time = time.clock()
                 if current_time - last_nap > 0.5:
-                    time.sleep(0.05)
+                    time.sleep(0.001)
                     last_nap = current_time
         cl.enqueue_copy(self.queue, self.result, self.result_b)

sasmodels/kernelcuda.py

@@ -444 +444 @@
         self.q_input = q_input # allocated by GpuInput above
 
-        self._need_release = [self.result_b, self.q_input]
+        self._need_release = [self.result_b]
         self.real = (np.float32 if dtype == generate.F32
                      else np.float64 if dtype == generate.F64
@@ -467 +467 @@
         # Call kernel and retrieve results
         last_nap = time.clock()
-        step = 1000000//self.q_input.nq + 1
+        step = 100000000//self.q_input.nq + 1
         #step = 1000000000
         for start in range(0, call_details.num_eval, step):
@@ -479 +479 @@
                 current_time = time.clock()
                 if current_time - last_nap > 0.5:
-                    time.sleep(0.05)
+                    time.sleep(0.001)
                     last_nap = current_time
         sync()
@@ -500 +500 @@
         Release resources associated with the kernel.
         """
-        if self.result_b is not None:
-            self.result_b.free()
-            self.result_b = None
+        for p in self._need_release:
+            p.free()
+        self._need_release = []
 
     def __del__(self):