Intel Corporation

Li-An Tang

Guei-Yuan Lueh

Alexander Lyashevsky

Timothy R Bauer

Supratim Pal

Hao Yuan

Changwon D Rhee

Haihua Wu

Jiasheng Chen

Julia A Gould

Weike Chen

Samuel Hsu

Shih-Hsuan Hsu

An apparatus to facilitate large integer multiplication enhancements in a graphics environment is disclosed. The apparatus includes a processor comprising processing resources, the processing resources comprising multiplier circuitry to: receive operands for a multiplication operation, wherein the multiplication operation is part of a chain of multiplication operations for a large integer multiplication; and issue a multiply and add (MAD) instruction for the multiplication operation utilizing at least one of a double precision multiplier or a 48 bit output, wherein the MAD instruction to generate an output in a single clock cycle of the processor.

Large integer multiplication enhancements for graphics environment

Described herein are technologies related to enforcing thread dependency using a hybrid scoreboard. An encoded video information that includes a plurality of threads is received, a first set and a second set of threads from the plurality of thread is determined, the first and second sets of threads are assigned to a hardware and a software, respectively, and dependency threads in the first and second sets of threads is enforced.

Power efficient hybrid scoreboard method

In an embodiment, at least one computer readable storage medium has instructions stored thereon for causing a system to send, from a processor to a task execution device, a first call to execute a first subroutine of a set of chained subroutines. The first subroutine may have a first subroutine output argument that includes a first token to indicate that first output data from execution of the first subroutine is intermediate data of the set of chained subroutines. The instructions are also for causing the system, responsive to inclusion of the first token in the first subroutine output argument, to enable the processor to execute one or more operations while the task execution device executes the first subroutine. Other embodiments are described and claimed.

Method and apparatus to improve performance of chained tasks on a graphics processing unit

Systems and methods may determine a boundary value data unit in a large data set in parallel with determining an associated index of the determined boundary value data unit into the large data set using a single instruction multiple data (SIMD) instruction set architecture and a specialized data layout of array entries. In one example, the specialized data layout of array entries combines a data value and its associated index to an array into a single array entry.

Fast approach to finding minimum and maximum values in a large data set using SIMD instruction set architecture

Growing community of inventors

El Dorado Hills, CA, United States of America

Li-An Tang