|
@@ -19,7 +19,7 @@ TODO: improve!
|
|
* Task distribution vs Data transfer::
|
|
* Task distribution vs Data transfer::
|
|
* Data prefetch::
|
|
* Data prefetch::
|
|
* Power-based scheduling::
|
|
* Power-based scheduling::
|
|
-* Forcing scheduling::
|
|
|
|
|
|
+* Static scheduling::
|
|
* Profiling::
|
|
* Profiling::
|
|
* CUDA-specific optimizations::
|
|
* CUDA-specific optimizations::
|
|
* Performance debugging::
|
|
* Performance debugging::
|