3 results about "Range constraint" patented technology

The invention discloses a random excitation generation method, system and device for a chip verification test, and relates to the technical field of chip verification, and the method comprises the steps: determining the priority of all variables in excitation according to the constraint condition of excitation needed by a to-be-tested chip verification test case; whether inequality constraints exist in the constraint conditions or not is detected, if yes, the inequality constraints are equivalently replaced with a unified representation form, then subsequent steps are executed, and if not, the subsequent steps are directly executed; on the basis of the priorities of the variables, intersection of all the related constraints of each variable in the constraint conditions is solved, all the related constraints of each variable are converted into a range constraint, and thus an optimized constraint condition is generated; and on the basis of the optimized constraint conditions, according to the priorities of the variables, the random excitation required by the verification test case of the to-be-tested chip is obtained through successive stochastic operation from high to low.

The application provides a language model federated fine-tuning method and device and electronic equipment. The method comprises: receiving first information sent by N clients, wherein the first information comprises a data importance index of the client; determining ideal ranks of the N clients based on the data importance index and a preset total rank budget; determining assigned ranks of the N clients that satisfy a preset constraint condition according to the ideal ranks of the N clients and a preset delay; the preset constraint condition comprises at least one constraint: an efficiency constraint, a rank budget constraint and a rank range constraint; sending corresponding assigned ranks to the N clients respectively, wherein the assigned ranks are used to train local low-rank adaptive matrices of the clients; receiving trained local low-rank adaptive matrices sent by the N clients; and adjusting a weight matrix of the language model based on the trained local low-rank adaptive matrices of the N clients. The performance of the language model can be improved.

The present application discloses a method, system and device for generating random stimuli for chip verification testing, which relates to the field of chip verification technology. The method comprises: determining the priority of all variables in the stimulus according to the constraint conditions of the stimulus required for the verification test case of the chip to be tested; detecting whether there is an inequality constraint in the constraint conditions, and if so, replacing the inequality constraint with a unified representation and executing subsequent steps, otherwise directly executing subsequent steps; based on the priority of the variable, finding the intersection of all relevant constraints of each variable in the constraint conditions, converting all relevant constraints of each variable into a range constraint, thereby generating optimized constraint conditions; based on the optimized constraint conditions, randomizing the variables from high to low according to their priority, thereby obtaining the random stimuli required for the verification test case of the chip to be tested.