For the Matrix Vector Multiply (GeMV) library element the list of configurable parameters and default values is presented below.
| Name | Type | Default | Description |
|---|---|---|---|
| DATA_A | typename | cint16 | Input Matrix A Data Type. |
| DATA_B | typename | cint16 | Input Vector B Data Type. |
| DIM_A | unsigned | 16 | Input Matrix A Dimension (number of matrix rows). |
| DIM_B | unsigned | 16 | Input Vector B Dimension (number of matrix columns). |
| SHIFT | unsigned | 16 | Acc results shift down value. |
| ROUND_MODE | unsigned | 0 | Rounding mode. |
| CASC_LEN | unsigned | 1 | Cascade length. |
| NUM_FRAMES | unsigned | 1 | The number of batches of input data that will be processed per iteration. |
| NITER | unsigned | 16 | Number of iterations to execute. |
| DIFF_TOLERANCE | unsigned | 0 | Tolerance value when comparing output sample with reference model, e.g. 0.0025 for floats and cfloats. |
| STIM_TYPE_A | unsigned | 0 | Supported types: 0 - random 3 - impulse 4 - all ones 5 - incrementing pattern 6 - sym incrementing pattern 8 - sine wave |
| STIM_TYPE_B | unsigned | 0 | Supported types: 0 - random 3 - impulse 4 - all ones 5 - incrementing pattern 6 - sym incrementing pattern 8 - sine wave |
| SAT_MODE | unsigned | Saturation mode | 0: ‘none’ 1: ‘saturate’ 3: ‘symmetric saturate’ |
Note
The above configurable parameters range may exceed a library element’s maximum supported range, in which case the compilation will end with a static_assert error informing about the exceeded range.