AI Engine Intrinsics User Guide  (AIE) v(2024.1)
 All Data Structures Namespaces Functions Variables Typedefs Groups Pages
API Reference
Here is a list of all modules:
[detail level 12345678910]
oData TypesSummary of the vector and accumulator registers
|oScalar Data typesAll the standard C scalar data types are supported
|\Vector Data types
| oAccumulator Types
| |o320/384 bits Accumulator
| |o640/768 bits Double Accumulator
| |\Floating Point Accumulator Types
| oFloating Point Vector Types
| \Integer Vector Types
|  o1024 bits Vectors
|  o128 bits Vectors
|  o256 bits Vectors
|  \512 bits Vectors
\Intrinsics
 oApplication Specific Intrinsics
 |oDigital Pre-Distortion
 |oDirect Digital Synthesis (DDS) Interpolation
 |oFFT intrinsics
 |\Peak Cancellation Crest Factor Reduction (PC-CFR)
 oLoad/Store Operations
 |\Streams
 oScalar Operations
 |oAIE ID
 |oAddressing Operations
 ||oCyclic Addressing
 ||\FFT Addressing
 |oCycle Counter
 |oDatatype ConversionsSupport for converting floating-point numbers to fixed-point and fixed-point numbers to floating-point
 |oDelayed Scalar MovesIntrinsic that returns its input after 6 clock cycles. Used for scheduling optimization
 |oElementary Functions
 |oEvents
 |oInteger Operations
 ||oAIE ID
 ||oDigital Pre-Distortion
 ||\Peak Cancellation Crest Factor Reduction (PC-CFR)
 |\Locks
 oVector ConversionsVarious forms of conversions between vector data types
 |oCastingCasting intrinsics allow casting between vector types of the same size
 |oConcatenationsVector concat intrinsic functions allow creating a bigger vector from two or four smaller ones
 |oDatatype ConversionsSupport for converting floating-point vectors to fixed-point vectors and fixed-point vectors to floating-point vectors
 |oExtractExtraction intrinsics enable lanes to be selected from vector and accumulator types
 |oMoves between Scalar and Vector UnitThese intrinsics allow inserting or extracting of an individual element into/from a vector
 |oPack
 |oSetsVector set intrinsic functions allow creating a vector where only one part is intitialized and the other parts are undefined
 |oShift-Round-SaturateIntrinsics for moving values from accumulator data-types to vector data-types
 |oUpdatesVector update intrinsic functions allow substitution of the lanes within a vector value
 |oUpdates with memory load
 |\UpshiftIntrinsics for moving values from vector data types to accumulator data types
 \Vector Operations
  oConfiguration
  |\Mode SettingsMode setting intrinsics to get and set bits in the control and status register
  | oControl registerIntrinsics to set, get and clear bits of the control register
  | \Status registerIntrinsics to set, get and clear bits of the status register
  oFull Lane Addresssing Scheme
  oInitialization
  oMAC intrinsics
  |oMultiplication
  ||oAdvanced
  |||oFloat
  |||\Integer
  ||\Simple
  |\Self-Multiplication
  | oAdvanced
  | |o16 bit x 16 bit
  | |\32 bit x 32 bit
  | \Simple
  oReduced Lane Addressing Scheme
  oVector Arithmetic
  |oAdvanced
  ||oFloat
  ||\Integer
  |\Simple
  oVector Compares
  |oAdvanced
  ||oVector Max/Min
  |||oFloat
  |||\Integer
  ||oVector MaxDiff
  ||\Vector comparison
  || oFloat
  || \Integer
  |\SimpleLane by lane vector compare
  \Vector Lane Selection
   oAdvanced
   |oFloat
   |\Integer
   \Simple
    oFloat
    \Integer