Half-Day Tutorial · ISCA 2026

Full-Stack Carbon Accounting and Life Cycle Assessment for AI Systems

A comprehensive tutorial on end-to-end carbon modeling methodologies for the AI era — from IC supply chain uncertainty to software-level carbon attribution in shared cloud environments.

📅 Date: 06/28/2026 📍 Venue: ISCA 2026 Workshops / Tutorials ⏱ 1:30 PM – 5:00 PM EDT
~4%
of global carbon emissions from computing
5 Tools
Open-source modeling suite
7 Papers
ISCA, ICCAD, DATE, MobiSys, ISLPED

About This Tutorial

The Challenge

The rapid proliferation of AI and large-scale machine learning has placed computing at a sustainability crossroads. Computing now accounts for up to 4% of global carbon emissions — rivaling the aviation industry — with AI training and inference serving as primary drivers of this growth.

Carbon emissions have shifted from being dominated solely by operational energy to a combination of operational energy and hardware manufacturing. To prevent environmental impact from becoming the scaling bottleneck for next-generation systems, sustainability must be elevated to a first-order design target.

Our Approach

This tutorial introduces a suite of end-to-end modeling methodologies designed to make carbon accounting fast, accessible, and rigorous for the AI era. Building on ACT [ISCA 2022], this expanded framework addresses the specific complexities of the AI hardware-software stack.

Since ACT's introduction in 2022, a large community of computer architects and systems researchers has adopted these methodologies — now incorporated into industry frameworks such as Meta’s sustainability reporting. Our mission has shifted from providing a standalone tool to establishing a rigorous, multi-dimensional accounting standard.

Tutorial Goals

1
Advocate for Sustainability in Research
Encourage investigation of environmental impact alongside performance, power, energy, and efficiency targets in academic research.
2
Hands-on Tooling
Provide researchers with practical skills to use and extend ACT, FAIR-CO₂, CarbonClarity, COFFEE, and MicroGreen.
3
Address Uncertainty
Demonstrate uncertainty-aware modeling for more credible and rigorous sustainability claims in academic research.
4
Enable System-Level Analysis
Teach methodologies for modeling the lifecycle of complex systems, including GPUs and embedded mobile devices.

The Toolset

A cross-stack methodology spanning recent publications at ISCA, ICCAD, and DATE.

Software Applications & Systems
FAIR-CO₂
Operational Carbon
FAIR-CO2 chart
Hardware Systems & Infrastructure
MicroGreen
Edge ML & IoT Lifecycle
MicroGreen chart
EServe
Inference Server Lifecycle
EServe chart
Architecture & Components / IC
ACT
Embodied Carbon
ACT chart
CarbonClarity
Supply Chain Uncertainty
CarbonClarity chart
3D-IC
3D Integration Carbon
3D-IC chart
Circuits & Devices
COFFEE
Circuit-level AI Hardware
COFFEE chart
EPiCarbon
Device-level Emissions
EPiCarbon chart

Click any tool to view the paper. Hover to highlight.

ACT
ISCA 2022 · Foundation

The first fast, accessible tool for estimating embodied carbon during early hardware design space exploration. Enables carbon as a first-order design target alongside power and performance.

ACT chart
CarbonClarity
New
ICCAD 2025 · Uncertainty

Uncertainty estimation in the global IC supply chain for AI chips — enabling more credible and rigorous carbon claims in research.

CarbonClarity chart
COFFEE
New
DATE 2026 · In-Memory Computing

AI-specific hardware accounting including emerging non-volatile memories for in-memory computing architectures.

COFFEE chart
MicroGreen
New
MobiSys 2026 · Carbon-aware Edge ML

MicroGreen is the first design space exploration framework that enables edge system designers to move beyond cost and energy-efficiency to optimize end-to-end life cycle emissions.

MicroGreen chart
EServe
New
ArXiV · GPU Lifecycle

Full-system lifecycle analysis for GPUs and high-performance AI accelerators, including EServe for large-scale inference systems.

EServe chart
FAIR-CO₂
New
ISCA 2025 · Software Attribution

Software-level carbon attribution for fair accounting in shared AI cloud environments, drawing on ideas from economics and game theory.

FAIR-CO2 chart
3D-IC
DAC 2024 · 3D Integration

Carbon modeling for 3D integrated circuits, capturing the unique manufacturing and assembly footprint of chiplet-based designs.

3D-IC chart
EPiCarbon
IEEE · Device-level Emissions

Device-level carbon emission modeling for advanced semiconductor processes, enabling fab-aware sustainability analysis.

EPiCarbon chart

Schedule

Half-day tutorial · 1:30 PM – 5:00 PM EDT · New sessions are new additions from the previous iteration

Time Topic Presenter
1:30–2:00
Motivation & Introduction
Overview of sustainable computing and the case for full-stack carbon accounting
 Udit Gupta
2:00–2:30
Hands-on: ACT
How to use and extend ACT for embodied carbon estimation
 Leo Han
2:30–2:50
Hands-on: Device-Level Carbon Accounting New
Circuits & Devices COFFEE — circuit-level carbon accounting for AI hardware
Xuesi Chen
2:50–3:10
Hands-on: Uncertainty in Carbon Accounting New
Supply Chain / IC CarbonClarity — IC supply chain uncertainty estimation
Xuesi Chen
3:10–3:30
Hands-on: Mobile & Embedded System Lifecycle New
Hardware Systems MicroGreen — edge ML & IoT lifecycle carbon
Xuesi Chen
3:30–4:00
☕ Coffee Break
4:00–4:20
Hands-on: GPU & Inference Server Lifecycle New
Hardware Systems EServe — large-scale inference server lifecycle carbon
Leo Han
4:20–4:40
Hands-on: Application-Level Carbon Attribution
Software Applications FAIR-CO₂ — fair accounting in shared cloud environments
Leo Han
4:40–5:00
Discussion
Open Q&A and discussion on open problems in sustainable computing
 All

Organizers

Leo Han

Leo Han

Cornell Tech

PhD Student

Research interests at the intersection of sustainable computing and computing for sustainability. Recent work focuses on fair carbon attribution in cloud ecosystems using ideas from economics and game theory. Recipient of the Digital Life Initiative Fellowship at Cornell Tech (2024).

Xuesi Chen

Xuesi Chen

Cornell Tech

PhD Student

Research in computer architecture, energy-efficient computing, AI at the edge, and sustainable computing. Develops mathematical models to quantify uncertainty in carbon accounting across the IC supply chain and designs energy-efficient and sustainable mobile devices.

Udit Gupta

Udit Gupta

Cornell Tech

Assistant Professor, ECE

Research at the intersection of computer architecture, systems, ML, and environmental sustainability. Recognized as IEEE MICRO Top Picks (2022, 2023), SIGARCH Outstanding Ph.D. Dissertation Honorable Mention, and SIGMICRO Outstanding Ph.D. Dissertation Honorable Mention.

Prerequisites

  • ✓ Basic knowledge of Python
  • ✓ Basic knowledge of computer architecture
  • ✓ No prior experience with Life Cycle Analysis (LCA) required

A pre-configured environment (Docker images / cloud-hosted JupyterHub) will be provided so attendees can begin modeling immediately without local environment setup.

Access & Materials

  • ✓ All slides and materials published online after the tutorial
  • ✓ All tools open-source on GitHub
  • ✓ Workshop summary published to foster collaboration
GitHub Repository →

Community & Inclusivity

Enabling sustainable computing requires solutions across the entire computing stack. An important mission for this workshop is to foster a diverse, collaborative, and innovative environment. Our speakers and organizers represent diversity in technical expertise (application developers to data center designers), organizations (universities and industry), professional experience, ethnic backgrounds, and genders.