Rakesh Nadig

Rakesh Nadig

Auto-generated profile, based on publicly available information

Rakesh Nadig

ETH Zurich, Zurich, Switzerland

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2023
Verified
Conference Paper
Open access
RNRakesh Nadig
Rakesh Nadig
MSMohammad Sadrosadati
Mohammad Sadrosadati
HMHaiyu Mao
Haiyu Mao
NGNika Mansouri Ghiasi
Nika Mansouri Ghiasi
ATArash Tavakkol
Arash Tavakkol
OMOnur Mutlu
Onur Mutlu

20 June 2025
Verified
Conference Paper
Open access
KCKangqi Chen
Kangqi Chen
RNRakesh Nadig
Rakesh Nadig
MFManos Frouzakis
Manos Frouzakis
NGNika Mansouri Ghiasi
Nika Mansouri Ghiasi
YLYu Liang
Yu Liang
OMOnur Mutlu
Onur Mutlu

8 June 2025
Verified
Conference Paper
Open access
MSMelina Soysal
Melina Soysal
KKKonstantina Koliogeorgi
Konstantina Koliogeorgi
CFCan Firtina
Can Firtina
NGNika Mansouri Ghiasi
Nika Mansouri Ghiasi
RNRakesh Nadig
Rakesh Nadig
OMOnur Mutlu
Onur Mutlu


26 February 2026 in IEEE Micro
Verified
Journal Article
Closed access
RBRahul Bera
Rahul Bera
RNRakesh Nadig
Rakesh Nadig
OMOnur Mutlu
Onur Mutlu
Despite the data-rich environment in which memory systems of modern computing platforms operate, many state-of-the-art architectural policies employed in memory system rely on static, human-designed heuristics that fail to adapt dynamically to workload and system behavior. In this article, we propose a fundamentally different design approach: using lightweight and practical machine learning (ML) methods to enable adaptive, data-driven control throughout the memory hierarchy. We present three ML-guided architectural policies: (1) Pythia, a reinforcement learning-based data prefetcher for on-chip caches, (2) Hermes, a perceptron learning-based off-chip predictor for multi-level cache hierarchies, and (3) Sibyl, a reinforcement learning-based data placement policy for hybrid storage system Our evaluation shows that Pythia, Hermes, and Sibyl significantly outperform the best-prior human-designed policies, while incurring modest hardware overheads. Collectively, this article demonstrates that integrating adaptive learning into memory subsystems can lead to intelligent, self-optimizing architectures that unlock performance and efficiency gains beyond what is possible with traditional human-designed approaches.