Matmul Feature Scenarios
In addition to the basic computing capabilities of Matmul described above, you also need to master the basic knowledge and operator implementation of Matmul. In addition, Matmul matrix programming provides processing capabilities and multiple functions applicable to different scenarios. The following table lists the specific scenarios and key APIs or parameters used. For details, see the corresponding sections.
|
Category |
Feature Description |
Key API or Parameter |
|---|---|---|
|
Function implementation |
SetDim and EnableMultiCoreSplitK (multi-core K splitting) |
|
|
SetTail, SetDim, and EnableMultiCoreSplitK (multi-core K splitting) |
||
|
Iterate, GetTensorC, and IterateAll |
||
|
Upper triangular or lower triangular computation |
MatmulPolicy template parameters |
|
|
Category |
Feature Description |
Key API or Parameter |
|---|---|---|
|
Function implementation |
Quantization and Dequantization of Matrix Multiplication Outputs |
|
|
Category |
Feature Description |
Involved API |
|---|---|---|
|
Function implementation |
BatchMatmul in the NORMAL format: IterateBatch and SetBatchInfoForNormal |
|
|
BatchMatmul in the BSNGD, SBNGD and BNGS1S2 formats: IterateBatch, SetALayout, SetBLayout, SetCLayout, and SetBatchNum |
||