Speed up Classify using GPU

I am interested in classify binary data using a Random Forest method. My data is numeric tensor and label of each class represented by 1.0 or 0.0. The size of the training data is ~16 million examples, and the size of the test data is around 500 million examples.

rfST = Classify[traningData,
Method -> {"RandomForest", "TreeNumber" -> 500},
TrainingProgressReporting -> "Print", TargetDevice -> {"GPU", 1}]

predictionRes =
Transpose[
Values[rfST[testData, "Probabilities", TargetDevice -> {"GPU", 1}]]][[
2]];


To speed up the training and test, I am using TargetDevice -> "GPU." When I am run the prediction I "feel" that a GPU doesn't take part in computation, however, the CPU is a computation engine. Please see the attached figures.

Any suggestion on what to check to speed up the calculation Note: I am using Win 10, and WL 11.3 and the GPU is GTX 1080 (I update the driver)

• try to install CUDA drivers manually – Fortsaint Jan 11 at 16:40
• I did it, but I don't see improvement. – Kiril Danilchenko Jan 11 at 16:49
• TargetDevice -> {"GPU", 2} ? – Fortsaint Jan 11 at 17:05
• similar performance, also I try 'TargetDevice -> {"GPU",{1,2}}' – Kiril Danilchenko Jan 11 at 17:52
• @KirilDanilchenko You cannot use GPU because RandomForest method uses Intel DAAL library under the hood. To speed up training, use option PerformanceGoal -> "DirectTraining". – Alexey Golyshev Jan 12 at 12:17