Lune

HPCA2022Top-tier venue

Saving PAM4 Bus Energy with SMOREs: Sparse Multi-level Opportunistic Restricted Encodings

Mike O'Connor, Donghyuk Lee, Niladrish Chatterjee, Michael B. Sullivan, Stephen W. Keckler

Abstract

Pulse Amplitude Modulation (PAM) uses multiple voltage levels as different data symbols, transferring multiple bits of data simultaneously, thereby enabling higher communication bandwidth without increased operating frequencies. However, dividing the voltage into more symbols leads to a smaller voltage difference between adjacent symbols, making the interface more vulnerable to crosstalk and power noise. GDDR6X adopts four-level symbols (PAM4) with Maximum Transition Avoidance (MTA) coding, which reduces the effects of crosstalk. However, current coding approaches can consume excess energy and produce excess power noise. This paper introduces novel energy reduction techniques for PAM interfaces, specifically demonstrating them for GDDR6X PAM4. Inspired by prior work on conventional single-ended I/O interfaces, we leverage the unused idle periods in DRAM channels between data transmissions to apply longer but more energy-efficient codes. To maximize the energy savings, we build multiple sparse encoding schemes to fit different sized gaps in the DRAM traffic. These sparse encodings can provide energy reductions of up to 52% when transferring 4-bit data using a 3-symbol sequence. We evaluate these coding techniques using an NVIDIA RTX 3090 baseline, a recent GPU which uses GDDR6X with PAM4 signaling. Our evaluation shows the opportunity for large energy savings at the DRAM I/O interface (28.2% on average) over many HPC/DL applications with minimal performance degradation.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Sparsepipe: Sparse Inter-operator Dataflow Architecture with Cross-Iteration ReuseYunan Zhang, Po-An Tsai, Hung-Wei TsengMICRO 2024 · 2 citations

Related papers

  1. Charge-Aware DRAM Refresh Reduction with Value TransformationSeikwon Kim, Wonsang Kwak, Changdae Kim, Daehyeon Baek et al.HPCA 2020 · 16 citations
  2. Commutative Data Reordering: A New Technique to Reduce Data Movement Energy on Sparse Inference WorkloadsBen Feinberg, Benjamin C. Heyman, Darya Mikhailenko, Ryan Wong et al.ISCA 2020 · 6 citations
  3. PF-DRAM: A Precharge-Free DRAM StructureNezam Rohbani, Sina Darabi, Hamid Sarbazi-AzadISCA 2021 · 16 citations
  4. Exploiting Zero Data to Reduce Register File and Execution Unit Dynamic Power Consumption in GPGPUsAhmad M. Radaideh, Paul V. GratzDAC 2020 · 4 citations
  5. Efficient Multi-GPU Shared Memory via Automatic Optimization of Fine-Grained TransfersHarini Muthukrishnan, David W. Nellans, Daniel Lustig, Jeffrey A. Fessler et al.ISCA 2021 · 16 citations
Dusk over the sea between two cliffs drawn in fine vertical lines