Abstract: Peer-to-peer video streaming software that takes video from a host's Graphical Processing Unit (GPU), moves it to the encoder, manages the color conversions, moves the video into the networking software, and in turn manages the video on a client. This software also handles the inputs from the client and tells the host how to react to the client's inputs. In executing the video streaming, the host broadcasts and renders the video that is or will be streamed. It encodes the video frame with a hardware encoder that is part of the GPU to eliminate latency associated with transferring frames to the central processing unit (CPU). The host transmits compressed video and audio data to the client, and the client uses its hardware decoder and the video streaming software to render the video. The client sends mouse, keyboard, joystick, and controller signals to the host, which varies the bit rate based on the network connection.

Abstract: Peer-to-peer video streaming software that takes video from a host's Graphical Processing Unit (GPU), moves it to the encoder, manages the color conversions, moves the video into the networking software, and in turn manages the video on a client. This software also handles the inputs from the client and tells the host how to react to the client's inputs. In executing the video streaming, the host broadcasts and renders the video that is or will be streamed. It encodes the video frame with a hardware encoder that is part of the GPU to eliminate latency associated with transferring frames to the central processing unit (CPU). The host transmits compressed video and audio data to the client, and the client uses its hardware decoder and the video streaming software to render the video. The client sends mouse, keyboard, joystick, and controller signals to the host, which varies the bit rate based on the network connection.

Abstract: A server computer system identifies a first bloom filter using a schedule that rotates bloom filters based on time. The system identifies a first set of metaobjects to evaluate for ingestion using the first bloom filter and determines whether to add one or more of the metaobjects to a data store using the first bloom filter. The system identifies a second bloom filter using the rotation in the schedule and identifies a second set of metaobjects to evaluate for ingestion using the second bloom filter. The second set of metaobjects includes one or more metaobjects that are the same as one or more metaobjects in the first set of metaobjects. The system determines whether to add one or more of the second set of metaobjects to the data store using the second bloom filter.

Abstract: Embodiments of the invention include a mechanism for explicit communication in a clustered multiprocessor system that supports low-latency, protected, user-mode, communication across the machine boundaries of a clustered multiprocessor. Data transport may be accomplished over persistent, unidirectional, point-to point connections, each of which may be embodied in a small amount of state at each end, along with a statically allocated per-connection memory buffer, which may be directly accessible to the transport mechanism at both ends of each notional link. System Memory protection may be afforded by operating system (“OS”) facilitated allocation of both restricted control of the network interface, and responsibility for data transport, to an application thread that may execute in the context of the processor-managed virtual address space. Connection buffer protection may be afforded by restricting access to connection state to those entries associated with the currently controlling thread.

Abstract: Embodiments of the invention include a mechanism for explicit communication in a clustered multiprocessor system that supports low-latency, protected, user-mode, communication across the machine boundaries of a clustered multiprocessor. Data transport may be accomplished over persistent, unidirectional, point-to point connections, each of which may be embodied in a small amount of state at each end, along with a statically allocated per-connection memory buffer, which may be directly accessible to the transport mechanism at both ends of each notional link. System Memory protection may be afforded by operating system (“OS”) facilitated allocation of both restricted control of the network interface, and responsibility for data transport, to an application thread that may execute in the context of the processor-managed virtual address space. Connection buffer protection may be afforded by restricting access to connection state to those entries associated with the currently controlling thread.