Nvidia Corporation

Sonny S Yeoh

Jonah Matthew Alben

Barry A Wagner

Saurabh Gupta

Jeffrey J Irwin

John H Edmondson

Shane J Keil

Dennis K Ma

Colyn Scott Case

Peter Tong

David Alan Jarosh

In some applications, such as video motion compression processing for example, a request pattern or 'stream' of requests for accesses to memory (e.g., DRAM) may have, over a large number of requests, a relatively small number of requests to the same page. Due to the small number of requests to the same page, conventionally sorting to aggregate page hits may not be very effective. Reordering the stream can be used to 'bury' or &#x201c;hide&#x201d; much of the necessary precharge/activate time, which can have a highly positive impact on overall throughput. For example, separating accesses to different rows of the same bank by at least a predetermined number of clocks can effectively hide the overhead involved in precharging/activating the rows.

Page stream sorter for poor locality access patterns

Methods, circuits, and apparatus for changing a frequency of a clock signal provided to a graphics memory while reducing any resulting visual glitch or disturbance on a monitor. A specific embodiment provides multiple clock sources that may be multiplexed or selected to provide a memory clock signal to the graphics memory. The multiplexer switches from providing a first clock source signal as the memory clock signal to providing a second clock source signal as the memory clock signal. The first clock source changes its frequency of operation. After the first clock source settles or stabilizes, the multiplexer switches back to providing the first clock source signal as the memory clock signal.

Dynamic memory clock adjustments

Circuits, methods, and apparatus that allow the elimination of a frame buffer connected directly to a graphics processing unit. The graphics processing unit includes an on-chip memory. Following system power-up or reset, the GPU initially renders comparatively low-resolution images to the on-chip memory for display. Afterward, the GPU renders images, which are typically higher resolution, and stores them in a system memory, apart from the graphics processing unit. The on-chip memory, which is no longer needed for image storage, instead stores address information, referred to as page tables, identifying the location of data stored by the GPU in the separate system memory.

Zero frame buffer

Method of providing a second clock while changing a first supplied clock frequency then supplying the changed first clock

Growing community of inventors

San Jose, CA, United States of America

Sonny S Yeoh