| 11615256 |
Hybrid accumulation method in multiply-accumulate for machine learning |
Ali Tasdighi Far |
2023-03-28 |
|
| 10365930 |
Instructions for managing a parallel cache hierarchy |
John R. Nickolls, Brett W. Coon |
2019-07-30 |
|
| 9922457 |
Computing tessellation coordinates using dedicated hardware |
Justin S. Legakis, Emmett M. Kilgariff |
2018-03-20 |
$451,508,000 |
| 9830161 |
Tree-based thread management |
John Erik Lindholm |
2017-11-28 |
$39,910,000 |
| 9760968 |
Reduction of graphical processing through coverage testing |
Derek J. Lentz, Ignacio Llamas |
2017-09-12 |
|
| 9639479 |
Instructions for managing a parallel cache hierarchy |
John R. Nickolls, Brett W. Coon |
2017-05-02 |
$52,442,000 |
| 9536341 |
Distributing primitives to multiple rasterizers |
Johnny S. Rhoades, Emmett M. Kilgariff, Ziyad S. Hakura, Dale L. Kirkland, James Daniel Kelly |
2017-01-03 |
$141,840,000 |
| 9483264 |
Trace-based instruction execution processing |
Mitchell Alsup, Boris Beylin, SungSoo Park |
2016-11-01 |
|
| 9223578 |
Coalescing memory barrier operations across multiple parallel threads |
John R. Nickolls, Steven James Heinrich, Brett W. Coon |
2015-12-29 |
$15,890,000 |
| 8947444 |
Distributed vertex attribute fetch |
Ziyad S. Hakura, Emmett M. Kilgariff, James C. Bowman, Philip Browning Johnson, Johnny S. Rhoades +1 more |
2015-02-03 |
$4,737,000 |
| 8860742 |
Coverage caching |
Anjul Patney |
2014-10-14 |
$3,953,000 |
| 8817031 |
Distributed stream output in a parallel processing unit |
Ziyad S. Hakura, Rohit Gupta, Emmett M. Kilgariff |
2014-08-26 |
$26,734,000 |
| 8704836 |
Distributing primitives to multiple rasterizers |
Johnny S. Rhoades, Steven E. Molnar, Emmett M. Kilgariff, Ziyad S. Hakura, Dale L. Kirkland +1 more |
2014-04-22 |
$4,341,000 |
| 8700877 |
Address mapping for a parallel thread processor |
Yan Yan Tang, John R. Nickolls |
2014-04-15 |
$1,804,000 |
| 8599202 |
Computing tessellation coordinates using dedicated hardware |
Justin S. Legakis, Emmett M. Kilgariff |
2013-12-03 |
$8,245,000 |
| 8533435 |
Reordering operands assigned to each one of read request ports concurrently accessing multibank register file to avoid bank conflict |
Xiaogang Qiu, Ming Y. Siu, Yan Yan Tang, John Erik Lindholm, Stuart F. Oberman |
2013-09-10 |
$15,985,000 |
| 8522000 |
Trap handler architecture for a parallel processing unit |
Jack Choquette, Brett W. Coon, Steven James Heinrich, Aravind Kalaiah, John R. Nickolls +4 more |
2013-08-27 |
$11,381,000 |
| 8458440 |
Deferred complete virtual address computation for local memory space requests |
— |
2013-06-04 |
$7,022,000 |
| 8223158 |
Method and system for connecting multiple shaders |
John Erik Lindholm, Jerome F. Duluk, Jr. |
2012-07-17 |
$12,933,000 |
| 8127181 |
Hardware warning protocol for processing units |
John S. Montrym, Richard A. Silkebakken, Robert C. Keller |
2012-02-28 |
$10,154,000 |
| 8035648 |
Runahead execution for graphics processing units |
Matthias M. Wloka |
2011-10-11 |
$14,320,000 |
| 8019978 |
Unit status reporting protocol |
Robert C. Keller, Richard A. Silkebakken |
2011-09-13 |
$19,562,000 |
| 7916146 |
Halt context switching method and system |
Robert C. Keller, Makarand Dharmapurikar |
2011-03-29 |
$12,889,000 |
| 7627723 |
Atomic memory operators in a parallel processor |
Ian A. Buck, John R. Nickolls, Lars Nyland |
2009-12-01 |
$7,246,000 |
| 7512773 |
Context switching using halt sequencing protocol |
Robert C. Keller, Richard A. Silkebakken, Benjamin J. Garlick |
2009-03-31 |
$16,068,000 |
