Abstract:
An ethernet controller for controlling the transmission of data between a station and an ethernet having four FIFOs for managing the transmission of data between the station CPU, a memory buffer, and the ethernet. The four FIFOs each have a selected size to maximize performance of the controller. The controller includes a arbiter to arbitrate which pending request from each of the FIFOs will have priority. The controller limits the transmission of data by each FIFO to 32 bytes per grant. Each FIFO includes logic to convert data in a first bit size format to a second bit size format. The controller also includes logic to convert a 16 bit address to two 8 bit portions for transmission over an 8 bit address bus and logic to reformat the two 8 bit portions to the 16 bit address.
Abstract:
A computer overall system (100) includes client systems (102, 104, 106) which are centered around customer computers. Client systems are connectable through a communications network (114) with server systems (122, 124, 126) by way of a LAN (108, 116): wan (110, 118); or POTS (112, 120). Communications network (114) can be any type of interconnect which is connected to respective server system. A computer which is part of a client system or a server system, includes therein a microprocessor that is programmed by the manufacturer with various items of information regarding the microprocessor itself. This programmed information defines a predetermined capability for the computer where its predetermined capability is defined by a set of parameters maintained within the computer system including several parameters such as the maximum core frequency (i.e. which is a measure of the speed or how many megahertz the central processing unit of the microprocessor is capable of running at), the maximum instruction set, a description of all the features available from the microprocessor, and other information related to the maximum capabilities of the microprocessor and the system it can operate, as appropriate for the specific application, for example, microprocessor may have parameters which broadly or narrowly defined the client system or the server system of which the microprocessor is a part. The microprocessor could also be provided with a hard coded electronic encryption key. Similarly, as is also known to those skilled in the art, the microprocessor could be configurable by changing internal software to change the core frequency or to modify yet other features.
Abstract:
A low permittivity interlevel structure comprising a dielectric formed on the topography of a semiconductor substrate. The dielectric comprises a lower region proximal to the semiconductor substrate, an intermediate region comprised of an oxide into which fluorine is incorporated in an atomic concentration of approximately four to ten percent, and an upper region. A method of forming the dielectric structure includes forming a first interconnect level on a substrate. A first dielectric layer, preferably a CVD oxide, is formed on the topography defined by the first interconnect and the substrate. A second dielectric layer, having a dielectric constant lower than the first dielectric layer, is then formed on the first dielectric layer. A third dielectric layer is formed on the second dielectric layer. The second dielectric layer is preferably formed in a CVD chamber from a silane or TEOS source and a fluorinating material such as SiF4.
Abstract:
A microprocessor (12) with automatic and dynamic partname determination including performance number. The microprocessor includes circuitry (38) that measures a core clock frequency for the microprocessor (12) and circuitry (36) that determines a performance indication for the microprocessor (12) in response to the measured core clock frequency.
Abstract:
A method for choosing a particular server on a network and performing a remote boot by a client, the network including a plurality of servers operating in accordance with a plurality of network operating systems, includes identifying (36) each of the plurality of servers by address and by type of operating system, and selecting (37) one of the identified servers by address and type for booting on the network. Identifying further includes sending a FIND frame (32) from the client to the network, and receiving a FOUND frame (34) from each of the plurality of servers. A remote program load protocol followed by the server according to the FOUND frame is determined. Additionally, choosing a particular server on a network and performing a remote boot by a client includes identifying each of a plurality of servers according to characteristics of a FOUND frame including a frequency characteristic, selecting one of the identified servers, and performing a remote program load by a boot ROM on a client through the selected one of the identified plurality of servers. Identifying further includes determining whether a destination address of the FOUND frame is repeated in a same order in a data portion of the FOUND frame, wherein when the destination address is repeated in a same order, a frequency characteristic of the FOUND frame is determined.
Abstract:
Submicron nLDD CMOS logic devices with improved current drive and reduced reverse short-channel effects having heavily doped As and lightly doped P nLDD region.
Abstract:
Formation of parasitic edge transistors at upper edges of trenches formed on a substrate of an integrated circuit is suppressed by implanting dopants into trench regions of the IC substrate before the trenches are formed in the trench regions by reactive ion etching. The widths of the trenches formed in the trench regions are narrower than the widths of the doped regions of the trench regions. The doped regions of the trench regions are formed by first implanting dopants into the trench regions and then heat treating the implanted regions to activate the dopants and to diffuse the dopants laterally from the implanted regions.
Abstract:
A data cache is provided which stores stack data within a stack memory separate from the cache line oriented storage used for non-cache data. Data may be pushed, popped, and accessed via an offset from the stack memory without generating main memory addresses. A load/store unit coupled to the data cache may be configured to perform the address generation associated with stack accesses in parallel with performing the access to the stack memory. If the corresponding data is not stored within the stack memory, then an access to the cache line oriented storage may be performed. Therefore, no time penalty may be assessed for missing the stack memory. A stack memory is contemplated for use with respect to subroutine parameter passing. The calling routine may perform multiple push commands to place parameters for use by the subroutine onto the stack. The subroutine may then access and modify the parameters upon the stack. Finally, the calling routine may perform multiple pop commands to remove the parameters from the stack.
Abstract:
A CPU or microprocessor which includes a general purpose CPU component, such as an X86 core, and also includes a DSP core. The CPU also includes an intelligent DSP function decoder or preprocessor which examines X86 opcode sequences and determines if a DSP function is being executed. If the DSP function decoder determines that a DSP function is being executed, the DSP function decoder converts or maps the opcodes to a DSP macro instruction that is provided to the DSP core. The DSP core executes one or more DSP instructions to implement the desired DSP function in response to the macro instruction. The DSP core implements or performs the DSP function using a lesser number of instructions and also in reduced number of clock cycles, thus increasing system performance. If the X86 opcodes in the instruction cache or instruction memory do not indicate or are not intended to perform a DSP-type function, the opcodes are provided to the X86 core as which occurs in current prior art computer systems. The X86 core and the DSP core are coupled to each other and communicate data and timing signals for synchronization purposes. Thus, the DSP core offloads these mathematical functions from the X86 core, thereby increasing system performance. The DSP core also operates in parallel with the X86 core, providing further performance benefits. The CPU of the present invention thus implements DSP functions more efficiently than X86 logic while requiring no additional X86 opcodes. The present invention also generates code that operates transparently on an X86 only CPU or a CPU according to the present invention which includes X86 and DSP cores. Thus the present invention is backwards compatible with existing software.
Abstract:
The PC audio circuit (10) described interfaces with and provides audio enhancement to a host personal computer of the type including a central processor, system memory and a system bus. The PC audio circuit (10) includes a digital signal processor (DSP) (16) for processing wavetable data and generating digital audio signals for a plurality of voices. The wavetable data is stored in the host computer's system memory and transferred in portions, as needed by the DSP (16) to a smaller, low-cost cache memory (22) included with the PC audio circuit (10). The DSP (16) processes several frames of data samples for an active voice before processing another voice. Processing in this manner alleviates concerns about the percentage use of system bus bandwidth and the maximum allowable system bus latency. These concerns are further alleviated by deriving frequency compensated wavetable data and storing it in system memory to be retrieved by the DSP (16) for generating digital audio signals having high frequency ratios. Digital audio signals generated for each active voice are accumulated in cache memory (22). When the digital audio signals for all active voices have been accumulated, the accumulated data is transmitted from the cache memory (22) to an external digital-to-analog converter. Since wavetable data is stored in system memory, the cache memory (22) is smaller and less expensive than the local memory in prior art PC audio circuits. Thus, the described PC audio circuit (10) has a lower overall cost.