PIRM: Processing In Racetrack Memories

TL;DR

PIRM introduces a DWM-based in-memory computing approach that uses transverse nanowire access to perform bulk-bitwise operations, significantly improving speed and energy efficiency for arithmetic and query tasks.

Contribution

It presents a novel in-memory computing technique leveraging transverse access in DWM nanowires for efficient bulk-bitwise logic and arithmetic operations.

Findings

PIRM achieves 1.6x speedup over DRAM PIM for queries.

It improves DWM PIM performance by 6.9x for addition and 2.3x for multiplication.

PIRM reduces access latency by 2.1x and energy by 25.2x for arithmetic benchmarks.

Abstract

The growth in data needs of modern applications has created significant challenges for modern systems leading a "memory wall." Spintronic Domain Wall Memory (DWM), related to Spin-Transfer Torque Memory (STT-MRAM), provides near-SRAM read/write performance, energy savings and nonvolatility, potential for extremely high storage density, and does not have significant endurance limitations. However, DWM's benefits cannot address data access latency and throughput limitations of memory bus bandwidth. We propose PIRM, a DWM-based in-memory computing solution that leverages the properties of DWM nanowires and allows them to serve as polymorphic gates. While normally DWM is accessed by applying spin polarized currents orthogonal to the nanowire at access points to read individual bits, transverse access along the DWM nanowire allows the differentiation of the aggregate resistance of multiple bits in the nanowire, akin to a multilevel cell. PIRM leverages this transverse reading to directly provide bulk-bitwise logic of multiple adjacent operands in the nanowire, simultaneously. Based on this in-memory logic, PIRM provides a technique to conduct multi-operand addition and two operand multiplication using transverse access. PIRM provides a 1.6x speedup compared to the leading DRAM PIM technique for query applications that leverage bulk bitwise operations. Compared to the leading PIM technique for DWM, PIRM improves performance by 6.9x, 2.3x and energy by 5.5x, 3.4x for 8-bit addition and multiplication, respectively. For arithmetic heavy benchmarks, PIRM reduces access latency by 2.1x, while decreasing energy consumption by 25.2x for a reasonable 10% area overhead versus non-PIM DWM.