Merge pull request #1205 from dwf/device_malloc_verbose_flag

theano/sandbox/cuda/cuda_ndarray.cu

@@ -53,7 +53,13 @@ struct table_struct{
 };
 table_struct _alloc_size_table[TABLE_SIZE];
 #endif
+
 void * device_malloc(size_t size)
+{
+    return device_malloc(size, VERBOSE_DEVICE_MALLOC);
+}
+
+void * device_malloc(size_t size, int verbose)
 {
     void * rval=NULL;
     cudaError_t err = cudaMalloc(&rval, size);
@@ -64,11 +70,14 @@ void * device_malloc(size_t size)
         // it returns something else I still don't see why we should ignore
         // it.  All we want to do here is reset the flag.
         cudaGetLastError();
+        if (verbose)
+        {
             #if COMPUTE_GPU_MEM_USED
                 fprintf(stderr, "Error allocating %li bytes of device memory (%s). new total bytes allocated: %d\n", (long)size, cudaGetErrorString(err),_allocated_size);
             #else
                 fprintf(stderr, "Error allocating %li bytes of device memory (%s).\n", (long)size, cudaGetErrorString(err));
             #endif
+        }
         PyErr_Format(PyExc_MemoryError,
                 "Error allocating %li bytes of device memory (%s).", (long)size, cudaGetErrorString(err));
         return NULL;

theano/sandbox/cuda/cuda_ndarray.cuh

@@ -42,6 +42,9 @@ typedef float real;
 #define SHARED_SIZE (16*1024)
 #endif
 
+#define VERBOSE_DEVICE_MALLOC 1
+#define NO_VERBOSE_DEVICE_MALLOC 0
+
 /**
  * Allocation and freeing of device memory should go through these functions so that the lib can track memory usage.
  *
@@ -49,6 +52,7 @@ typedef float real;
  * device_free will return nonzero on failure (after setting the python error message)
  */
 DllExport void * device_malloc(size_t size);
+DllExport void * device_malloc(size_t size, int verbose);
 DllExport int device_free(void * ptr);
 
 template <typename T>