| Arithmetic |
14 |
| Asynchronous Warpgroup Level Matrix Multiply-Accumulate Instructions |
5 |
| Comparison and Selection Instructions |
4 |
| Control Flow Instructions |
5 |
| Data Movement and Conversion Instructions |
39 |
| Extended-Precision Integer Arithmetic Instructions |
6 |
| Fabric Instructions |
6 |
| Floating-Point Instructions |
7 |
| Half Precision Floating-Point Instructions |
2 |
| Integer Arithmetic Instructions |
15 |
| Logic and Shift Instructions |
9 |
| Miscellaneous Instructions |
5 |
| Parallel Synchronization and Communication Instructions |
31 |
| SIMD Video Instructions |
6 |
| Scalar Video Instructions |
6 |
| Stack Manipulation Instructions |
3 |
| Surface Instructions |
4 |
| Tensor Memory Allocation and Management Instructions |
3 |
| Tensor Memory Data Movement Instructions |
2 |
| Tensor Memory and Register Load/Store Instructions |
3 |
| TensorCore 5th Generation Family Instructions |
2 |
| TensorCore 5th Generation of MMA Instructions |
4 |
| Texture Instructions |
4 |
| Warp Level Matrix Multiply-Accumulate Instructions |
5 |