Patents by Inventor Harsh Sharangpani

Harsh Sharangpani 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: 7152153
    Abstract: A Next Return Target Address stack to maintain return addresses for call and return operations. The invention accommodates both definite return addresses and speculative return address in a single stack. Return addresses are written into the stack and read out of the stack at an entry/exit register interior to the stack. The stack has a lower portion below the entry/exit register for maintaining both actual and speculative return addresses, and an upper portion above the entry/exit register for maintaining return addresses that have been speculatively popped out. A branch history register keeps an ongoing record of the most recent calls and returns. In the event of a pipeline flush, such as would be caused by a branch mispredict, the contents of the branch history register are examined to determine how to adjust the contents of the stack. One or more depth counters keep track of which contents in the branch history register are to be examined.
    Type: Grant
    Filed: March 4, 2003
    Date of Patent: December 19, 2006
    Assignee: Intel Corporation
    Inventors: Vincent E. Hummel, Harsh Sharangpani
  • Publication number: 20030131220
    Abstract: A Next Return Target Address stack to maintain return addresses for call and return operations. The invention accommodates both definite return addresses and speculative return address in a single stack. Return addresses are written into the stack and read out of the stack at an entry/exit register interior to the stack. The stack has a lower portion below the entry/exit register for maintaining both actual and speculative return addresses, and an upper portion above the entry/exit register for maintaining return addresses that have been speculatively popped out. A branch history register keeps an ongoing record of the most recent calls and returns. In the event of a pipeline flush, such as would be caused by a branch mispredict, the contents of the branch history register are examined to determine how to adjust the contents of the stack. One or more depth counters keep track of which contents in the branch history register are to be examined.
    Type: Application
    Filed: March 4, 2003
    Publication date: July 10, 2003
    Inventors: Vincent E. Hummel, Harsh Sharangpani
  • Patent number: 6584558
    Abstract: An article representing a processor providing event handling functionality is described. According to one embodiment of the invention, the article includes a machine readable medium storing data representing a processor including an instruction set unit and an event handling unit, as well as a first plurality of event handlers that includes a first event handler. The instruction set unit is to support a first and second instruction sets. Problems that arise during the processing of instructions from the first and second unit are to cause the article to execute the appropriate one of the first plurality of event handlers. At least some of the first set of events are mapped to different ones of the first plurality of event handlers. All of the second set of events are mapped to the first event handler.
    Type: Grant
    Filed: April 24, 2002
    Date of Patent: June 24, 2003
    Assignee: Intel Corporation
    Inventors: Gary Hammond, Donald Alpert, Kevin Kahn, Harsh Sharangpani
  • Patent number: 6560696
    Abstract: A Next Return Target Address stack to maintain return addresses for call and return operations. The invention accommodates both definite return addresses and speculative return address in a single stack. Return addresses are written into the stack and read out of the stack at an entry/exit register interior to the stack. The stack has a lower portion below the entry/exit register for maintaining both actual and speculative return addresses, and an upper portion above the entry/exit register for maintaining return. addresses that have been speculatively popped out. A branch history register keeps an ongoing record of the most recent calls and returns. In the event of a pipeline flush, such as would be caused by a branch mispredict, the contents of the branch history register are examined to determine how to adjust the contents of the stack. One or more depth counters keep track of which contents in the branch history register are to be examined.
    Type: Grant
    Filed: December 29, 1999
    Date of Patent: May 6, 2003
    Assignee: Intel Corporation
    Inventors: Vincent E. Hummel, Harsh Sharangpani
  • Publication number: 20020120832
    Abstract: An article representing a processor providing event handling functionality is described. According to one embodiment of the invention, the article includes a machine readable medium storing data representing a processor including an instruction set unit and an event handling unit, as well as a first plurality of event handlers that includes a first event handler. The instruction set unit is to support a first and second instruction sets. Problems that arise during the processing of instructions from the first and second unit are to cause the article to execute the appropriate one of the first plurality of event handlers. At least some of the first set of events are mapped to different ones of the first plurality of event handlers. All of the second set of events are mapped to the first event handler.
    Type: Application
    Filed: April 24, 2002
    Publication date: August 29, 2002
    Applicant: Intel Corporation
    Inventors: Gary Hammond, Donald Alpert, Kevin Kahn, Harsh Sharangpani
  • Patent number: 6408386
    Abstract: Method And Apparatus for Providing Event Handling Functionality in a Computer System. According to one embodiment of the invention, a computer system includes an instruction set unit and an event handling unit in a processor, as well as a first plurality of event handlers that includes a first event handler. The instruction set unit is to support a first and second instruction sets. Problems that arise during the processing of instructions from the first and second unit is to cause the processor to execute the appropriate one of the first plurality of event handlers. At least some of the first set of events are mapped to different ones of the first plurality of event handlers. All of the second set of events are mapped to the first event handler.
    Type: Grant
    Filed: January 25, 2001
    Date of Patent: June 18, 2002
    Assignee: Intel Corporation
    Inventors: Gary Hammond, Donald Alpert, Kevin Kahn, Harsh Sharangpani
  • Patent number: 6219774
    Abstract: A Method and Apparatus for Providing Memory Management and Event Handling Functionality in a Computer System. According to one embodiment of the invention, a processor comprises an instruction set unit, a segmentation unit, and a paging unit. The instruction set unit is to support a first and second instruction sets. The segmentation unit is coupled to the instruction set unit to translate virtual addresses used by the first instruction set into translated addresses. The paging unit is coupled to the instruction set unit to translate both virtual addresses used by the second instruction set and the translated addresses into physical addresses. According to another embodiment of the invention, a computer system includes an instruction set unit and an event handling unit in a processor, as well as a first plurality of event handlers that includes a first event handler. The instruction set unit is to support a first and second instruction sets.
    Type: Grant
    Filed: March 25, 1998
    Date of Patent: April 17, 2001
    Assignee: Intel Corporation
    Inventors: Gary Hammond, Donald Alpert, Kevin Kahn, Harsh Sharangpani
  • Patent number: 6108772
    Abstract: A numerical processing method on a computer system in which an instruction having at least one operand and a type control is retrieved, and the operand is converted to a precision specified by the type control. The instruction is executed in the precision specified by the type control to obtain a result, and when the destination precision differs from the precision specified by the type control, the result is converted to the destination precision using a second instruction.
    Type: Grant
    Filed: June 28, 1996
    Date of Patent: August 22, 2000
    Assignee: Intel Corporation
    Inventor: Harsh Sharangpani
  • Patent number: 5774686
    Abstract: A processor having two system configurations is provided. The apparatus generally includes an instruction set unit, a system unit, an internal bus, and a bus unit. The instruction set unit, the system unit, and the bus unit are coupled together by the internal bus. The system unit is capable of selectively operating in one of two system configurations. The first system configuration provides a first system architecture, while the second system configuration provides a second system architecture. The bus unit is used for sending and receiving signals from the instruction set unit and the system unit. According to another aspect of the invention, the instruction set unit is capable of selectively operating in one of two instruction set configurations. The first instruction set configuration provides for the execution of instruction belonging to a first instruction set, while the second instruction set configuration provides for the execution of instructions belonging to a second instruction set.
    Type: Grant
    Filed: June 7, 1995
    Date of Patent: June 30, 1998
    Assignee: Intel Corporation
    Inventors: Gary Hammond, Donald Alpert, Kevin Kahn, Harsh Sharangpani