KERNTROL: Kernel Shape Control Toward Ultimate Memory Utilization for In-Memory Convolutional Weight Map**

J Rhe, KE Jeon, JC Lee, S Jeong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Processing-in-memory (PIM) architectures have been highlighted as one of the most viable
options for faster and more power-efficient computation. Paired with a convolutional weight …

ConvMapSim: Modeling and Simulating Convolutional Weight Map** for PIM Arrays

KE Jeon, W Seo, J Rhe, JH Ko - 2024 IEEE 6th International …, 2024 - ieeexplore.ieee.org
While the selection of convolutional weight map** method significantly influences the
latency and energy efficiency of PIM systems, existing PIM simulators lack the flexibility …

Performance Analysis of 3D Stacked Memory Architectures in High Performance Computing

VTK Gannavaram, AK Gajula - 2024 4th International …, 2024 - ieeexplore.ieee.org
The increasing speed of the CPU is greater than that of the RAM. The 'Memory Wall'issue,
which occurs when the processor runs out of data, could occur. The I/O infrastructure is …