Via Technologies, Inc.

Wen-Chung Chen

Liang Li

Li Sun

John Wakefield Brothers

Fang Liu

Boris Prokopenko

Yuanfeng Wang

Ping F Chen

Xi Xi Liu

Li Liang

Jiangming Xu

Shou-Yu Joyce Cheng

Tatsang Mak

Chenggang Liu

Yang (Jeff) Jiao

Yiping Chen

Chienkang Cheng

Dehai Kong

Dehai (Roy) Kong

Jianming Xu

Irene Chih-Yiieh Cheng

Roy (Dehai) Kong

Mitch Singer

Irene (Chih-Yiieh) Cheng

Shou-Yu (Joyce) Cheng

Huizhong Ou

Multiple graphics processor system and method embodiments are disclosed. One system embodiment, among others, comprises a multiple graphics processor system, comprising a first graphics processing unit having first status information and a second graphics processing unit having second status information, and first key logic corresponding to the first graphics processing unit, the first key logic configured to compare the first and second status information and communicate to the first graphics processing unit a key corresponding to the lowest completed stage of processing among the first and second graphics processing units.

Multiple graphics processor systems and methods

Packet processing system and method embodiments implemented in a peripheral component interconnect-express (PCIE) compliant system are disclosed. One method embodiment, among others, comprises receiving a packet having at least a first type of data and a second type of data over a PCIE connection, and segregating the entire packet into two contiguous groups, a first group comprising the first type of data and a second group comprising the second type of data.

Packet processing systems and methods

The present disclosure provides for processing units, which are capable of concurrently executing instructions, and a source arbitrator. The source arbitrator determines whether instructions for the processing units are read from different sources. If the source arbitrator determines that each processing unit reads its respective instruction from a different source, then the instructions from the various sources are provided to their corresponding processing units for substantially concurrent processing.

Selecting multiple threads for substantially concurrent processing

The present disclosure provides system and method embodiments for synchronizing access to memory between a plurality of modules in a pipelined system. One system embodiment, among others, includes an upstream module and a downstream module that each share one or more locations in memory. The upstream module is configured to receive a command pair having matched identifiers, one half (wait command) of which enables the upstream module to delay access to the memory to avoid read-after-write (RAW) hazard, the other half (signal command) which is passed to the downstream module. The downstream module passes the identifier from the signal command to the upstream module at a time corresponding to the downstream module reaching an idle state, thus ceasing access to the memory. The upstream module, upon determining that the identifier received over a direct connection from the downstream module is from the command pair, accesses the one or more locations in the memory.

Shared memory synchronization systems and methods

A system and method for supporting multiple graphics processing units (GPUs) includes a first communication path coupled to a root complex device and a first connection point of a first GPU. A second communication path is coupled to the root complex device and a first set of switches. The first set of switches is configured to route communications between the root complex device to either a second connection point of the first GPU via a second set of switches or to a first connection point of a second GPU. The second set of switches is coupled to a second connection point of the first GPU. The second set of switches is configured to route communications to and from the second connection point of the first GPU and to either the root complex device via the first set of switches or to a second connection point of the second GPU.

Switching method and system for multiple GPU support

Supporting multiple graphics processing units (GPUs) comprises a first path coupled to a north bridge device (or a root complex device) and a first GPU, which may include a portion of the first GPU's total communication lanes. A second communication path may be coupled to the north bridge device and a second GPU and may include a portion of the second GPU's total communication lanes. A third communication path may be coupled between the first and second GPUs directly or through one or more switches that can be configured for single or multiple GPU operations. The third communication path may include some or all of the remaining communication lanes for the first and second GPUs. As a nonlimiting example, the first and second GPUs may each utilize an 8-lane PCI express communication path with the north bridge device and an 8-lane PCI express communication path with each other.

Method and system for multiple GPU support

The computer graphics system is configured to improve the performance of a stencil shadow volume method for rendering shadows. The apparatus and methods utilize a combination of compressed and uncompressed stencil buffers in coordination with compressed and uncompressed depth data buffers. An uncompressed stencil buffer is capable of storing stencil shadow volume data for each pixel and a compressed stencil buffer is capable of storing stencil shadow volume data for a group of pixels. The compressed stencil buffer is utilized with a compressed stencil buffer cache to perform a stencil shadow volume operation more efficiently than present methods.

Apparatus and method of an improved stencil shadow volume operation

The computer graphics system is configured to generate a shadow effect with a stencil shadow volume method using a combination of compressed and uncompressed stencil buffers in coordination with compressed and uncompressed depth data buffers. An uncompressed stencil buffer is capable of storing stencil shadow volume data for each pixel and a compressed stencil buffer is capable of storing stencil shadow volume data for a group of pixels.

Method and apparatus for generating a shadow effect using shadow volumes

Growing community of inventors

Cupertino, CA, United States of America

Wen-Chung Chen