Abstract: Systems, apparatuses and methods may provide for technology that generates a dependence graph based on a plurality of intermediate representation (IR) code instructions associated with a compiled program code, generates a set of graph embedding vectors based on the plurality of IR code instructions, and determines, via a neural network, one of an analysis of the compiled program code or an enhancement of the program code based on the dependence graph and the set of graph embedding vectors. The technology may provide a graph attention neural network that includes a recurrent block and at least one task-specific neural network layer, the recurrent block including a graph attention layer and a transition function. The technology may also apply dynamic per-position recurrence-halting to determine a number of recurring steps for each position in the recurrent block based on adaptive computation time.

Abstract: Various examples relate to an apparatus, device, method, and computer program for determining a placement of an execution of a computer program, and to an apparatus, device, method, and computer program for training at least one machine-learning model. The apparatus for determining the placement of an execution of a computer program comprises processing circuitry that is configured to generate a graph representation of a computer program, generate, using a first machine-learning model, a vector embedding of the graph representation of the computer program, and to determine, based on an output of a second machine-learning model, a placement of an execution of the computer program on one or more hardware devices of a heterogenous plurality of hardware devices of a computer system, with the vector embedding and information on the load of the hardware devices being provided as input to the second machine-learning model.

Abstract: Systems, apparatuses and methods may provide for technology that generates a dependence graph based on a plurality of intermediate representation (IR) code instructions associated with a compiled program code, generates a set of graph embedding vectors based on the plurality of IR code instructions, and determines, via a neural network, one of an analysis of the compiled program code or an enhancement of the program code based on the dependence graph and the set of graph embedding vectors. The technology may provide a graph attention neural network that includes a recurrent block and at least one task-specific neural network layer, the recurrent block including a graph attention layer and a transition function. The technology may also apply dynamic per-position recurrence-halting to determine a number of recurring steps for each position in the recurrent block based on adaptive computation time.

Abstract: Systems, apparatuses and methods may provide for technology that generates a series of time-stamped object graphs based on object trajectory histories derived from external object data for a plurality of external objects, such as vehicles. The technology may also generate, via a first neural network such as a graph attention network, a series of relational object representations based on the series of time-stamped object graphs, and determine, via a second neural network such as a long short-term memory network, predicted object trajectories for the plurality of external objects based on the series of relational object representations. The technology may also modify behavior of an autonomous vehicle based on the predicted object trajectories and real-time perceptual error information.