Abstract: An apparatus for processing variable length coded data includes a coefficient buffer unit and several lookup tables. The coefficient buffer unit includes a coefficient memory and an index register for storing an indication of a non-zero nature of coefficients stored in the coefficient memory. Advantageously, the lookup tables may be altered to adapt the apparatus for processing variable length coded data to handle encoding or decoding video adhering to a specific standard. Furthermore, the lookup tables may be adapted to accelerate the determination of the presence of escape codes and the subsequent handling of the escape codes.

Abstract: An apparatus and method utilizes system memory as backing stores so that local graphics memory may be oversubscribed. Surfaces may be paged in and out of system memory based on the amount of usage of the surfaces. The apparatus and method also prioritizes surfaces among different tiers of local memory (e.g. frame buffer), non-local memory (e.g. page locked system memory), and system memory backing stores (e.g. pageable system memory) locations based on predefined criteria and runtime statistics relating to the surfaces. As such, local memory may be, for example, expanded without extra memory costs such as adding a frame buffer memory to allow graphics applications to effectively use more memory and run faster.

Abstract: An impedance compensation circuit generates per-group pull-up impedance information and per-group pull-down impedance information to calibrate a plurality of input/output pads and dynamically updates impedance information on a per channel basis. A group refers to a group of I/O pads having similar output drive strengths in a channel. A channel refers to all I/O pads, which collectively provide a bus interface to an external device. For example, all the I/O pads interfacing with a memory module may be grouped into a channel, and address I/O pads in a channel may be arranged into a “group.” Memory I/O pads may be grouped together into a channel since memory interface pads have input/output characteristics that may be different from those of other types of I/O pads in the chip. According to one embodiment, per-group programmable offset information provides calibration information that may be different for each group in each channel.

Abstract: A computer. When an instruction calling for an architecturally-visible side-effect in an architecturally-visible storage location is recognized, a value is stored representative of an architecturally-visible representation of the side-effect, a format of the representative value being different than an architecturally-visible representation of the side-effect. Execution is resumed without generating the architecturally-visible side-effect. Later, the architecturally-visible representation corresponding to the representative value is written into the architecturally-visible storage location. On a context switch, a context of a first process is written and a context of a second process is loaded to place the second process into execution. At least some instructions maintain results in storage resources outside the context resource set, and instructions are marked to indicate whether or not a context switch may be performed at a boundary of the marked instruction.

Abstract: A method and system is provided for organizing and routing multiple memory requests from a plurality of clients to multiple memories. Requests from a plurality of clients, including a plurality of clients of the same type, such as multiple MPEG decoders, are directed to different memory controllers by a router. The memory controllers order the client requests by requests among similar client types. The memory controllers also order the client requests by different client types The ordered requests are then delivered to memory Returned data is sent back to the clients. A method of mapping motion pictures experts group (MPEG) video information for improved efficiency is presented, wherein image information is stored in blocks of memory referred to as tiles. Tiles are mapped in memory so that adjacent tiles only correspond to different banks of memory.

Abstract: In a method and apparatus for using a clock generating circuit to minimize settling time after dynamic power supply voltage ramping, a clock signal may be generated using a clock generating circuit having, among other things, open feedback loop switch logic and a dynamic fast lock control signal generator. Whereupon, when in operation, the open feedback loop switch logic is responsive to a controlled change in power supply voltage condition such that a feedback loop of the clock generating circuit is opened during power supply voltage ramping (e.g., during transitions to or from battery conservation modes). In response to opening the feedback loop, the dynamic fast lock control signal generator selectively applies a stabilizing control signal to a variable clock signal generator (e.g., a voltage controlled oscillator) such that the generated clock signal can quickly lock onto the proper target frequency.

Abstract: A frame buffer is divided into tiles of, for example, 32 by 32 pixels. Triangles (and portions thereof) that are within a given tile are rasterized one triangle at a time into the tile location. This process repeats for each tile in the image frame. A sorting circuit generates control bits representing a vertical order of the vertices of a current triangle. A series of multiplexers vertically sorts the vertices bases on these control bits. A region calculation circuit generates region bits representing a location each of the vertices with respect to the current tile. A trivial discard of the triangle data occurs if the region bits indicate that the entire triangle lies outside of the tile. Subsequently, an initial rasterization starting point is estimated based on the region bits to lower the time needed for the rasterizer to find the first pixel of the current triangle to be assigned values.

Abstract: According to the present disclosure, a transmitter for transmitting control characters to a display device over an interface includes a transmitter portion configured to transmit a control character having a plurality of bit values to the display device. The transmitter also includes logic configured to determine values of the bits in the control character and construct a corresponding plurality of rebalancing control characters based on the determination of the values of the plurality of bits in the control character to have bit values selected such that the combination of the control character and rebalancing control character is DC balanced. As such, the transmitter provides DC balance correction to non-DC balanced control characters in such a way as to allow DVI and HDMI to operate properly on an AC-coupled connection.

Abstract: A multi-die module is electrically connected to both an unpackaged die and a packaged die as disclosed herein. The multi-die module has a footprint that is the same as conventional multi-die packages, which do not include packaged die, thereby allowing the multi-die module to be interchangeable with conventional multi-die packages. In one embodiment, the unpackaged die is a graphics processor, and the packaged die is a standard memory that has been burned in, functionally tested, and speed rated.

Abstract: A method and apparatus provides context switching of logic in an integrated circuit using one or more test scan circuits that use test data during a test mode of operation of the integrated circuit to store and/or restore non-test data during normal operation of the integrated circuit. The integrated circuit includes context control logic operative to control the test scan circuit to at least one of: store and restore context state information contained in functional storage elements in response to detection of a request for a change in context during normal operation of the integrated circuit.

Abstract: A method and apparatus for enlarging an output display includes a message hook application capable of receiving a magnification event indicator, wherein the magnification event indicator includes a magnification factor. The method and apparatus further includes a character generator coupled to the message hook application wherein the character generator receives a text call from the message hook application. The character generator thereupon generates a magnified character set including a plurality of characters enlarged by the magnification factor. A display driver is coupled to the message hook application and the character generator, wherein the display driver receives the character set at the magnified font size and caches the character set. A direct draw surface is coupled to the display driver such that the direct draw surface receive one or more of the characters enlarged by the magnification factor.

Abstract: A digitally programmable gain control circuit and method of operating the same is disclosed. The gain control circuit includes a programmable gain amplifier having an amplifier structure represented by a plurality of overlapping discrete monotonic transfer function segments, wherein at least one point of non-monotonicity occurs among one or more of the plurality of overlapping discrete monotonic transfer function segments, and a gain segment translator circuit operative to translate a monotonic gain value to a segment code to match the non-monotonic characteristics of the programmable gain amplifier. The programmability of the gain amplifier is provided by a coarse gain control circuit and a fine gain control circuit.

Abstract: A method and system for higher level filtering uses a native bilinear filter, typically found in a texture mapper, and combines a plurality of bilinear filter results from the bilinear filter to produce a higher level filtered texel value. A native bilinear filter is operative to generate bilinear filtered texel values by performing a plurality of bilinearly filtered texture fetches using bilinear filter fetch coordinates. The method and system combines the plurality of bilinear filtered texel values with a plurality of weights to generate the higher level filtered texel value.

Abstract: A buffer is associated with each of a plurality of data lanes of a multi-lane serial data bus. Data words are timed through the buffers of active ones of the data lanes. Words timed through buffers of active data lanes are merged onto a parallel bus such that data words from each of the active data lanes are merged onto the parallel bus in a pre-defined repeating sequence of data lanes. This approach allows other, non-active, data lanes to remain in a power conservation state.

Abstract: A system and method are described for providing an improved ratiometric expansion of video images. Source video images are set to a lower resolution than the full resolution of a pixelated display device. The source video images are up-scaled to match the display resolution of the display device. Pixels in the source video image are replicated to form a partially up-scaled video image that has frequency content well below the Nyquist rate of the image. The replicated image is then re-sampled through the use of a two-tap filter to generate a video image with the same resolution as the display device.

Abstract: The present invention is directed to a method, computer program product, and system for processing memory access requests. The method includes the following features. First, page table entries of a page table are organized into at least one fragment that maps logical memory to at least one of logical memory or physical memory. The at least one fragment has a fragment size and an alignment boundary. Then, a subset of the page table entries stored in one of a plurality of cache banks is accessed to determine a mapping between a first logical memory address and at least one of a second logical memory address or a physical memory address. Each cache bank is configured to store at least one page table entry corresponding to a fragment of a predetermined set of fragment sizes and a predetermined alignment boundary.

Abstract: A variable reference voltage circuit controllable in closed loop, for calibrating off-chip and on-chip drivers, margining and optimizing a reference voltage, for interfaces such as DDR2 or any other suitable interface. In one example, the on-chip variable reference voltage circuit, coupled to external fixed reference voltage, includes control logic and an array of switchable resistor elements (pull-up and pull-down resistors) that may each be selectively switched in or out of the circuit to change the reference voltage being supplied to an on-chip receiver.

Abstract: Described are a graphics processing unit (GPU) and a sample-level screen-door transparency technique for rendering transparent objects. The GPU includes a scan converter and a shader. The scan converter identifies pixels to be processed for rendering a transparent object and divides each pixel into a plurality of samples. The shader generates, for one of the identified pixels, an application developer-specified transparency sample mask indicating which samples of the pixel are to be suppressed when determining a color of the pixel. Execution of an application developer-specified sample mask command produces a pattern of bits that map to samples of the pixel. The values of the bits determine which samples of the pixel may be used and which samples are to be suppressed when determining a color of the pixel.

Abstract: Embodiments of the present invention provide methods of processing nickel-titanium alloys including from greater than 50 up to 55 atomic percent nickel to provide a desired austenite transformation temperature and/or austenite transformation temperature range. In one embodiment, the method comprises selecting a desired austenite transformation temperature, and thermally processing the nickel-titanium alloy to adjust an amount of nickel in solid solution in a TiNi phase of the alloy such that a stable austenite transformation temperature is reached, wherein the stable austenite transformation temperature is essentially equal to the desired austenite transformation temperature.

Abstract: A robust data extension, added to a standard 8VSB digital television signal, is used to improve the performance of a digital television receiver. Robust data packets are encoded at a 1/3-trellis rate as compared to normal data packets that are encoded at a 2/3-trellis rate. In addition to delivery of robust data for mobile applications, the redundant robust data packets also improve the performance of the receiver in the normal tier of service. In particular, the robust data packets improve the performance of the receiver equalizer filter in the presence of rapidly changing transient channel conditions such as dynamic multipath for both robust data packets and normal data packets. The robust data packets improve the performance of the carrier recovery loop and the symbol timing recovery loop. Backward compatibility with existing receivers is maintained for 1) 8VSB signaling, 2) trellis encoding and decoding, 3) Reed Solomon encoding and decoding, and 4) MPEG compatibility.