IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0184402
(2002-06-28)
|
등록번호 |
US-8090928
(2012-01-03)
|
발명자
/ 주소 |
- Schmidt, Dominik J.
- Sherburne, Jr., Robert Warren
|
출원인 / 주소 |
- Intellectual Ventures I LLC
|
인용정보 |
피인용 횟수 :
0 인용 특허 :
38 |
초록
▼
In one embodiment of the present invention, a processor includes a scalar computation unit; a vector co-processor coupled to the scalar computation unit; and one or more function-specific engines coupled to the scalar computation unit, where the engines are adapted to minimize data exchange penaltie
In one embodiment of the present invention, a processor includes a scalar computation unit; a vector co-processor coupled to the scalar computation unit; and one or more function-specific engines coupled to the scalar computation unit, where the engines are adapted to minimize data exchange penalties by processing small in-out bit slices.
대표청구항
▼
1. An apparatus, comprising: a scalar computation unit configured to execute control software to process data packets for transmission via a wireless protocol, wherein the control software includes scalar instructions, vector instructions, and a plurality of function calls respectively corresponding
1. An apparatus, comprising: a scalar computation unit configured to execute control software to process data packets for transmission via a wireless protocol, wherein the control software includes scalar instructions, vector instructions, and a plurality of function calls respectively corresponding to a plurality of digital signal processing functions;a vector co-processor coupled to the scalar computation unit; anda plurality of dedicated hardware engines configured to perform respective ones of the plurality of digital signal processing functions;wherein the scalar computation unit is configured to: perform scalar instructions included in the control software;cause the vector co-processor to perform vector instructions included in the control software; andcause at least first and second dedicated hardware engines of the plurality of dedicated hardware engines to perform digital signal processing functions corresponding to ones of the plurality of function calls included in the control software and subsequently send information to one or both of the scalar computation unit and the vector co-processor, wherein the first dedicated hardware engine is different from the second dedicated hardware engine, and wherein the first and the second dedicated hardware engines are selected from the group consisting of: a convolutional decoding engine, a modulation engine, a transform engine, an error correction engine, and a cryptographic engine. 2. The apparatus of claim 1, further comprising: a switch fabric coupled to the scalar computation unit, the vector co-processor, and the plurality of dedicated hardware engines;wherein the apparatus is configured to be reconfigured, using the switch fabric, to process data packets for transmission via at least two different wireless protocols. 3. The apparatus of claim 1, wherein the scalar computation unit is configured to provide configuration and parametric settings to the plurality of dedicated hardware engines at a beginning of a computation sequence, wherein the vector co-processor is configured to perform parallel computational operations, and wherein the plurality of dedicated hardware engines comprise a plurality of application circuit hardware engines. 4. The apparatus of claim 1, wherein the apparatus is configured to process data packets for transmission via at least two different wireless protocols, including a cellular radio protocol and a short-range wireless protocol. 5. The apparatus of claim 1, further comprising a clock coupled to the vector co-processor and each of the plurality of dedicated hardware engines, wherein the clock is configured to operate at a frequency scaled from a baseline crystal frequency to a maximum operating frequency. 6. The apparatus of claim 1, wherein at least one of the plurality of dedicated hardware engines is configured to perform a Gaussian filter operation. 7. The apparatus of claim 1, wherein one or more of the plurality of dedicated hardware engines are configured to be re-used from a first wireless protocol to a second wireless protocol by changing input parameters and a clock frequency. 8. The apparatus of claim 1, wherein the plurality of dedicated hardware engines includes an orthogonal frequency division multiplexing (OFDM) engine and a gaussian minimum shift keying (GMSK) engine. 9. The apparatus of claim 1, wherein the first dedicated hardware engine is a transform engine and the second dedicated hardware engine is an error correction engine. 10. The apparatus of claim 1, further comprising a memory coupled to the scalar computation unit and the vector co-processor, wherein the memory is configured for storing the control software such that the scalar instructions and the vector instructions are intermixed. 11. The apparatus of claim 1 further comprising a memory coupled to the scalar computation unit and the vector co-processor, the memory for storing instructions executable by the apparatus to cause the apparatus to disable one or more of the plurality of dedicated hardware engines without disabling remaining ones of the plurality of dedicated hardware engines. 12. The apparatus of claim 9, wherein the transform engine is an FHT engine and the error correction engine is a CRC engine. 13. The apparatus of claim 1, wherein the apparatus is configured to communicate one or more of the data packets in parallel via at least two different wireless protocols. 14. A wireless device, comprising: an analog portion, including: a radio frequency (RF) front-end configured to receive an RF signal from an antenna; andan analog to digital converter (ADC) coupled to the RF front-end to digitize the RF signal; anda digital portion, including: a processor module, including: a scalar computation unit configured to execute control software to process data packets for transmission via a wireless protocol, wherein the control software includes scalar instructions, vector instructions, and a plurality of function calls respectively corresponding to a plurality of digital signal processing functions;a vector co-processor coupled to the scalar computation unit; anda plurality of dedicated hardware engines configured to perform respective ones of the plurality of digital signal processing functions;wherein the scalar computation unit is configured to: perform scalar instructions included in the control software;cause the vector co-processor to perform vector instructions included in the control software; andcause at least first and second dedicated hardware engines of the plurality of dedicated hardware engines to perform digital signal processing functions corresponding to ones of the plurality of function calls included in the control software and subsequently send information to one or both of the scalar computation unit and the vector co-processor, wherein the first dedicated hardware engine is different from the second dedicated hardware engine, and wherein the first and the second dedicated hardware engines are selected from the group consisting of: a convolutional decoding engine, a modulation engine, a transform engine, an error correction engine, and a cryptographic engine. 15. The wireless device of claim 14, further comprising a cellular radio core and a short-range wireless transceiver core both coupled to the processor module, wherein the processor module is configured to process data packets for transmission via at least two different wireless protocols, wherein the cellular radio core is associated with a first of the at least two different wireless protocols, and wherein the short-range wireless transceiver core is associated with a second of the at least two different wireless protocols. 16. The wireless device of claim 14, wherein the first dedicated hardware engine is a modulation engine and the second dedicated hardware engine is a cryptographic engine. 17. The wireless device of claim 14, wherein the processor module further comprises a switch fabric coupled to the scalar computation unit, to the vector co-processor, and to the plurality of dedicated hardware engines, and wherein the processor module is configured to be reconfigurable, using the switch fabric, to process data packets for transmission via at least two different wireless protocols. 18. The wireless device of claim 14, wherein the scalar computation unit is configured to provide configuration and parametric settings to the plurality of dedicated hardware engines at a beginning of a computation sequence, wherein the vector co-processor is configured to perform parallel computational operations, and wherein the plurality of dedicated hardware engines comprise a plurality of application circuit hardware engines. 19. The wireless device of claim 14, wherein the processor module further includes a memory coupled to the scalar computation unit and the vector co-processor, the memory for storing instructions executable by the processor module to disable one or more engines of the plurality of dedicated hardware engines without disabling remaining ones of the plurality of dedicated hardware engines. 20. The wireless device of claim 16, wherein the modulation engine is an OFDM engine and the cryptographic engine is an AES engine. 21. The wireless device of claim 14, wherein the processor is configured to communicate one or more of the data packets in parallel via at least two different wireless protocols. 22. An apparatus, comprising: first means for executing instructions to generate: instructions for performance of a plurality of vector operations; anda plurality of function calls;second means for performing the plurality vector operations; andthird means for performing, responsive to the plurality of function calls, a plurality of different digital signal processing functions, the third means including a plurality of dedicated engines;wherein the apparatus is configured to send data packets via a wireless protocol by causing: the second means to execute the plurality of vector operations; andthe third means to execute the plurality of function calls and subsequently send information to the processor module, wherein executing the plurality of function calls includes causing at least first and second dedicated engines of the plurality of dedicated engines to perform digital signal processing functions corresponding to ones of the plurality of function calls, wherein the first dedicated engine is different from the second dedicated engine, and wherein the first and the second dedicated engines are selected from the group consisting of: a convolutional decoding engine, a modulation engine, a transform engine, an error correction engine, and a cryptographic engine.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.