The following figure shows the Transpose Multiply-Accumulate architecture implementing a Transposed Direct-Form filter.
Figure 1. Transpose Direct - Form
The following figure shows a multi-MAC implementation for this architecture.
Figure 2. Transpose Multi - MAC Implementation
This architecture is also directly supported by the DSP Slice. This structure offers a low latency implementation, and for some configurations can also offer extra resource savings over the Systolic structure. It does not require an accumulator and can use fewer data memory resources, although it does not exploit coefficient symmetry.