| 11709793 |
Graphics processors and graphics processing units having dot product accumulate instruction for hybrid floating point format |
Subramaniam Maiyuran, Shubra Marwaha, Ashutosh Garg, Jorge Parra, Chandra Gurram +3 more |
2023-07-25 |
| 11669329 |
Instructions and logic for vector multiply add with zero skipping |
Sasikanth Avancha, Ishwar Bhati, Wei-Yu Chen, Dipankar Das, Ashutosh Garg +7 more |
2023-06-06 |
| 11669490 |
Computing efficient cross channel operations in parallel computing machines using systolic arrays |
Subramaniam Maiyuran, Jorge Parra, Chandra Gurram |
2023-06-06 |
| 11640297 |
Instruction and logic for systolic dot product with accumulate |
Subramaniam Maiyuran, Guei-Yuan Lueh, Ashutosh Garg, Chandra Gurram, Jorge Parra +10 more |
2023-05-02 |
| 11636174 |
Scalable sparse matrix multiply acceleration using systolic arrays with feedback inputs |
Subramaniam Maiyuran, Jorge Parra, Ashutosh Garg, Shubra Marwaha, Chandra Gurram +3 more |
2023-04-25 |
| 11593069 |
Use of a single instruction set architecture (ISA) instruction for vector normalization |
Abhishek Rhisheekesan, Shashank Lakshminarayana, Subramaniam Maiyuran |
2023-02-28 |
| 11579878 |
Register sharing mechanism to equally allocate disabled thread registers to active threads |
Pratik J. Ashar, Subramaniam Maiyuran, Wei-Yu Chen, Guei-Yuan Lueh |
2023-02-14 |