A graph placement methodology for fast chip design.

Chip floorplanning is the engineering task of designing the physical layout of a computer chip. Despite five decades of research1, chip floorplanning has defied automation, requiring months of intense effort by physical design engineers to produce manufacturable layouts. Here we present a deep reinforcement learning approach to chip floorplanning. In under six hours, our method automatically generates chip floorplans that are superior or comparable to those produced by humans in all key metrics, including power consumption, performance and chip area. To achieve this, we pose chip floorplanning as a reinforcement learning problem, and develop an edge-based graph convolutional neural network architecture capable of learning rich and transferable representations of the chip. As a result, our method utilizes past experience to become better and faster at solving new instances of the problem, allowing chip design to be performed by artificial agents with more experience than any human designer. Our method was used to design the next generation of Google's artificial intelligence (AI) accelerators, and has the potential to save thousands of hours of human effort for each new generation. Finally, we believe that more powerful AI-designed hardware will fuel advances in AI, creating a symbiotic relationship between the two fields.

A new approach for calculating the relative risk level of pesticides.

The following paper describes a new, easier to use approach to the calculation of relative risk levels of alternative pesticides. An insect, a plant disease, and a weed were selected for describing the application procedure of a new ranking method that is based on the intrinsic properties of pesticides rather than on the processes that occur both on land and in water after they are applied to soil. The approach is based on the Toxicity-Human health-Persistency (THP) Hazard Rating System, and a consumption factor is added to the method in order to calculate the environmental risk of pesticides. The available substitute pesticides are ranked in terms of their relative risk levels from lowest to highest in order of magnitude difference. Such a ranking method may be used as a practical quantitative tool to generate significant findings aiding in the selection of the most environmentally friendly substitute against a certain pest, especially in developing countries that still face the misuse and/or unconscious use of pesticides.

Ozonation of aqueous solution of alpha endosulfan.

Ozonation of alpha endosulfan and the effects of some parameters such as pH, temperature and partial pressure on ozonation were investigated and the kinetic constants were calculated in this study. Alpha endosulfan solutions were ozonated in a lab-scale semi-batch reactor under variable experimental conditions. Increase in dissolved ozone concentration had a positive effect on oxidation rate. Alpha endosulfan could be removed up to 94% at pH 4 for an ozonation time of 60 minutes. The oxidation reaction was found to be of second order and of first order with respect to both ozone and alpha endosulfan. The temperature dependent reaction expression of alpha endosulfan was obtained as kd = (1.889 exp(- 2.21 x 10(-3)/T). It was concluded that, although the rate of reaction was lower than the rate of other pesticide oxidation reported in the literature. alpha endosulfan presented an obvious reaction to ozonation.