Back to results
US 2011/0298788 A1Published application
Performing vector multiplication
AssigneeInternational Business Machines Corporation
InventorsMark J. Hickey, Adam J. Muff, Matthew R. Tubbs, Charles D. Wait
Life of this patent
Estimating the term…
Abstract
A method includes receiving packed data corresponding to pixel components to be processed at a graphics pipeline. The method includes unpacking the packed data to generate floating point numbers that correspond to the pixel components. The method also includes routing each of the floating point numbers to a separate lane of the graphics pipeline. Each of the floating point numbers are to be processed by multiplier units of the graphics pipeline.
Claims20
A method, comprising:
- receiving packed data corresponding to pixel components to be processed at a graphics pipeline;
- unpacking the packed data to generate floating point numbers that correspond to the pixel components;
- and
- routing each of the floating point numbers to a separate lane of the graphics pipeline, each of the floating point numbers to be processed by a multiplier unit of the graphics pipeline.
1 more element
A method, comprising:
- receiving packed data corresponding to pixel components to be processed at a graphics pipeline;
- receiving a mapping instruction;
- in response to receiving the mapping instruction, unpacking the packed data to generate first floating point numbers that correspond to the pixel components;
- routing each of the first floating point numbers to a separate lane of the graphics pipeline via a set of mux units, each of the first floating point numbers to be processed by a multiplier unit of the graphics pipeline;
- and
- routing each of second floating point numbers to the separate lanes of the graphics pipeline via the set of mux units, each of the second floating point numbers to be processed by an aligner unit of the graphics pipeline.
3 more elements
A system, comprising:
- an unpack unit to receive packed data corresponding to pixel components and to unpack the packed data to generate floating point numbers that correspond to the pixel components, the pixel components including a red component, a green component, and a blue component;
- and
- a first plurality of mux units to selectively route each of the floating point numbers to a separate lane of a graphics pipeline, the floating point numbers to be processed by multiplier units of the graphics pipeline.
Dependencies are inferred from the claim text.