SHIMP: A Shift-based Implication-enabled Architecture in ReRAM for In-Memory Cryptographic Computation

To propose SHIMP, a ReRAM-based in-memory computing architecture integrating implication logic with multidirectional and circular shift operations.

Prior works lack efficient shift/rotation and parallel data movement, primarily focusing on logic. SHIMP improves data movement and logic efficiency.

Modern cryptographic algorithms like AES and ChaCha20.

—Processing-in-memory(PIM) architecturesbasedon resistive random access memory (Re RAM) are promising candi- dates to overcome the von Neumann bottleneck. While prior works have demonstrated functionally complete logic compu- tation using 2 T 2 R and 3 T 2 R architectures, they lack efficient supportforshiftandrotationoperations, whichareessentialfor cryptographic workloads. This work proposes SHIMP (Shift and Implication), a Re RAM-basedin-memorycomputingarchitecturethatintegrates implication logic with multidirectional and circular shift op- erations. The architecture introduces routing-level innovations and a dual bit-line design enabling parallel data movement. Simulationusing Sky Water Open PDK validatesthefunctionality, with Re RAM cells exhibiting HRS ∼3.1 MΩ and LRS ∼10 kΩ, yieldingaresistanceratioof∼310×. Comparedtopriordesigns, SHIMP enhances flexibility and enables efficient mapping of cryptographic primitives.