Abstract: Method, apparatus, and program means for performing a dot-product operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store to a storage location a result value equal to a dot-product of at least two operands.

Abstract: Method, apparatus, and program means for performing a dot-product operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store to a storage location a result value equal to a dot-product of at least two operands.

Abstract: Method, apparatus, and program means for performing a dot-product operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store to a storage location a result value equal to a dot-product of at least two operands.

Abstract: Method, apparatus, and program means for performing a dot-product operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store to a storage location a result value equal to a dot-product of at least two operands.

Abstract: Method, apparatus, and program means for performing a dot-product operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store to a storage location a result value equal to a dot-product of at least two operands.

Abstract: Methods, systems, and apparatus profile the processing of a graphics application. Performance data of a processing graphics application is monitored and dynamically presented on a display of a viewer at defined intervals. The performance data includes hardware and driver performance data for the processing graphics application at the defined intervals. The viewer can inspect the performance data for purposes of customizing the graphics application for a targeted hardware and software platform.

Abstract: Systems and techniques to monitor instruction mix in a processor. In general, in one implementation, the technique includes: identifying instruction types of sampled machine instructions being performed by a processor, and presenting a metric indicating utilization of the processor by identified instruction types. Presenting the metric may involve displaying a representation of real-time instruction mix utilization including an indication of a percent of the machine instructions that are optimized for the processor.