LT-PIM: An LUT-Based Processing-in-DRAM Architecture With RowHammer Self-Tracking
Ranyang Zhou, Sepehr Tabrizchi, Arman Roohi, Shaahin Angizi
Abstract
Herein, we propose LT-PIM as a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\ul{L}}$</tex-math></inline-formula> ookup <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\ul{T}}$</tex-math></inline-formula> able-based <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\ul{P}}$</tex-math></inline-formula> rocessing- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\ul{I}}$</tex-math></inline-formula> n- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${\ul{M}}$</tex-math></inline-formula> emory architecture leveraging the high density of DRAM to enable massively parallel and flexible computation. LT-PIM supports lookup table queries to execute complex arithmetic operations, such as multiplication via only memory read operation. In addition, LT-PIM enables bulk bit-wise in-memory logic by elevating the analog operation of the DRAM sub-array to implement Boolean functions between operands in the same bit-line. With this, LT-PIM enables a complete and inexpensive in-DRAM RowHammer (RH) self-tracking approach. Our results demonstrate that LT-PIM achieves <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 70% higher energy efficiency than the fastest charge-sharing-based designs and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 32% over the best LUT-based designs. As for the RH self-tracking, with a worst-case slowdown of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 0.2%, LT-PIM archives up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 80% energy-saving over the best designs.