Patents by Inventor Rami Rachamim
Rami Rachamim has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8719742Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: GrantFiled: February 20, 2012Date of Patent: May 6, 2014Assignee: Mentor Graphics CorporationInventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Patent number: 8468475Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: GrantFiled: February 20, 2012Date of Patent: June 18, 2013Assignee: Mentor Graphics CorporationInventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Patent number: 8417504Abstract: A system and method are described for converting a circuit description into transaction-based description at a higher level of abstraction. Thus, a designer can readily view a series of transactions that occurred in the simulation of a circuit. In one aspect, the simulated signals are analyzed and converted into messages of a protocol used by the design. A combination of the messages represents a transaction. Thus, the simulated signals are then converted into a series of protocol transactions. In another aspect, a message recognition module performs the analysis of the simulated signals and converts the simulated signals into messages (e.g., request for bus, bus acknowledge, etc.). A transaction recognition module analyzes the messages and converts the messages into transactions (e.g., Read, Write, etc.). Using both the system and method the circuit description is converted into a higher level of abstraction that allows more comprehensive system-level analysis.Type: GrantFiled: June 11, 2007Date of Patent: April 9, 2013Assignee: Mentor Graphics CorporationInventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Publication number: 20120151424Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: ApplicationFiled: February 20, 2012Publication date: June 14, 2012Inventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Publication number: 20120150522Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: ApplicationFiled: February 20, 2012Publication date: June 14, 2012Inventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Patent number: 8122398Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: GrantFiled: June 11, 2007Date of Patent: February 21, 2012Assignee: Mentor Graphics CorporationInventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Publication number: 20070276645Abstract: A system and method is described for generating a power model of a circuit from a lower level description, such as Gate-level or RTL. In one aspect, simulation data is converted into a series of messages or transactions. Power is then determined on a per message or per transaction basis. In another aspect, an abstract power model is generated using a neural network. The neural network generates a system of weighted equations representing an accurate power model.Type: ApplicationFiled: June 11, 2007Publication date: November 29, 2007Inventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Publication number: 20070277144Abstract: A system and method is disclosed for converting an existing circuit description from a lower level description, such as RTL, to a higher-level description, such as TLM, while raising the abstraction level. By changing the abstraction level, the conversion is not simply a code conversion from one language to another, but a process of learning the circuit using neural networks and representing the circuit using a system of equations that approximate the circuit behavior, particularly with respect to timing aspects. A higher level of abstraction eliminates much of the particular implementation details, and allows easier and faster design exploration, analysis, and test, before implementation. In one aspect, a model description of the circuit, protocol information relating to the circuit, and simulation data associated with the lower level description of the circuit are used to generate an abstract model of the circuit that approximates the circuit behavior.Type: ApplicationFiled: June 11, 2007Publication date: November 29, 2007Inventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim
-
Publication number: 20070276644Abstract: A system and method are described for converting a circuit description into transaction-based description at a higher level of abstraction. Thus, a designer can readily view a series of transactions that occurred in the simulation of a circuit. In one aspect, the simulated signals are analyzed and converted into messages of a protocol used by the design. A combination of the messages represents a transaction. Thus, the simulated signals are then converted into a series of protocol transactions. In another aspect, a message recognition module performs the analysis of the simulated signals and converts the simulated signals into messages (e.g., request for bus, bus acknowledge, etc.). A transaction recognition module analyzes the messages and converts the messages into transactions (e.g., Read, Write, etc.). Using both the system and method the circuit description is converted into a higher level of abstraction that allows more comprehensive system-level analysis.Type: ApplicationFiled: June 11, 2007Publication date: November 29, 2007Inventors: Yossi Veller, Vasile Hanga, Alexander Rozenman, Rami Rachamim