Skip to content
naulon
Not checkedNot checked for notices yet.

Thermal-Aware Design Space Exploration of 3-D Systolic ML Accelerators

Rahul Mathur, Ajay Krishna Ananda Kumar, Lizy John and 1 more

IEEE Journal on Exploratory Solid-State Computational Devices and Circuits · 2021

doi:10.1109/jxcdc.2021.3092436 (opens in a new tab)

We email you when a new notice or a question about this paper appears.

Abstract

Machine learning (ML) accelerators have a broad spectrum of use cases that pose different requirements on accelerator design for latency, energy, and area. In the case of systolic array-based ML accelerators, this puts different constraints on processing element (PE) array dimensions and SRAM buffer sizes. The 3-D integration packs more compute or memory in the same 2-D footprint, which can be utilized to build more powerful or energy-efficient accelerators. However, 3-D also expands the design space of ML accelerators by additionally including different possible ways of partitioning the PE array and SRAM buffers among the vertical tiers. Moreover, the partitioning approach may also have different thermal implications. This work provides a systematic framework for performing system-level design space exploration of 3-D systolic accelerators. Using this framework, different 3-D-partitioned accelerator configurations are proposed and evaluated. The 3-D-stacked accelerator designs are modeled using the hybrid wafer bonding technique with a 1.44-<inline-formula> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula> pitch of 3-D connection. Results show that different partitioning of the systolic array and SRAM buffers in a four-tier 3-D configuration can lead to either 1.1&#x2013;<inline-formula> <tex-math notation="LaTeX">$3.9\times $ </tex-math></inline-formula> latency reduction or 1&#x2013;<inline-formula> <tex-math notation="LaTeX">$3\times $ </tex-math></inline-formula> energy reduction compared to the baseline design of the same 2-D area footprint. It is also shown that by carefully organizing the systolic array and SRAM tiers using logic over memory, the temperature rise with 3-D across benchmarks can be limited to 6 &#x00B0;C.

Abstract licence: CC BY-NC-ND

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.