Displaying 4 results from an estimated 4 matches for "dqn".
Did you mean:
dan
2020 Apr 08
6
RFC: a practical mechanism for applying Machine Learning for optimization policies in LLVM
...blem (i.e. features); action (inline/not inline), and reward (native
size shrinkage after inline/not inline, using ir2native). To collect the
sequences, we hook the logging infrastructure into LLVM Inliner that is
able to produce logs after the inline optimization pass.
RL - Model training: We use DQN (Deep Q-Network) to train our
inlining-for-size ML policy. On a high level, the DQN algorithm trains a
neural network to predict the value of different actions --- the DQN policy
then chooses to take the action with the highest predicted value. In our
scenario, we have two actions: 1) inline; 2) no...
2020 Apr 08
2
RFC: a practical mechanism for applying Machine Learning for optimization policies in LLVM
...reward (native
> > size shrinkage after inline/not inline, using ir2native). To collect the
> > sequences, we hook the logging infrastructure into LLVM Inliner that is
> > able to produce logs after the inline optimization pass.
> >
> > RL - Model training: We use DQN (Deep Q-Network) to train our
> > inlining-for-size ML policy. On a high level, the DQN algorithm trains a
> > neural network to predict the value of different actions --- the DQN
> policy
> > then chooses to take the action with the highest predicted value. In our
> >...
2020 Apr 09
3
RFC: a practical mechanism for applying Machine Learning for optimization policies in LLVM
...inline, using ir2native). To collect
>>> the
>>> > sequences, we hook the logging infrastructure into LLVM Inliner that
>>> is
>>> > able to produce logs after the inline optimization pass.
>>> >
>>> > RL - Model training: We use DQN (Deep Q-Network) to train our
>>> > inlining-for-size ML policy. On a high level, the DQN algorithm
>>> trains a
>>> > neural network to predict the value of different actions --- the DQN
>>> policy
>>> > then chooses to take the action with...
2020 Apr 09
2
RFC: a practical mechanism for applying Machine Learning for optimization policies in LLVM
...; collect the
>>>>> > sequences, we hook the logging infrastructure into LLVM Inliner
>>>>> that is
>>>>> > able to produce logs after the inline optimization pass.
>>>>> >
>>>>> > RL - Model training: We use DQN (Deep Q-Network) to train our
>>>>> > inlining-for-size ML policy. On a high level, the DQN algorithm
>>>>> trains a
>>>>> > neural network to predict the value of different actions --- the
>>>>> DQN
>>>>> policy
>...