![]() |
AI Engine Intrinsics
(AIE) r2p21
|
| All the standard C scalar data-types are supported | |
| Support for converting floating-point numbers to fixed-point and fixed-point numbers to floating-point | |
| Intrinsic that returns its input after 6 clock cycles. Used for scheduling optimization | |
| Various forms of conversions between vector data-types | |
| Casting intrinsics allow casting between vector types of the same size | |
| Vector concat intrinsic functions allow creating a bigger vector from two or four smaller ones | |
| Support for converting floating-point vectors to fixed-point vectors and fixed-point vectors to floating-point vectors | |
| Extraction intrinsics enable lanes to be selected from vector and accumulator types | |
| These intrinsics allow inserting or extracting of an individual element into/from a vector | |
| Vector set intrinsic functions allow creating a vector where only one part is intitialized and the other parts are undefined | |
| Intrinsics for moving values from accumulator data-types to vector data-types | |
| Vector update intrinsic functions allow substitution of the lanes within a vector value | |
| Intrinsics for moving values from vector data-types to accumulator data-types | |
| Mode setting intrinsics to get and set bits in the control and status register | |
| Intrinsics to set, get and clear bits of the control register | |
| Intrinsics to set, get and clear bits of the status register | |
| Lane by lane vector compare | |
| These functions setup stream accesses in native mode |