Marcos Kawazoe Aguilera

Marcos Kawazoe Aguilera

Auto-generated profile, based on publicly available information

Marcos Kawazoe Aguilera

NVIDIA, Santa Clara, USA

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
1 July 2019 in Proceedings of the VLDB Endowment
Verified
Journal Article
Open access
PDF file
MBMihai Budiu
Mihai Budiu
PGParikshit Gopalan
Parikshit Gopalan
LSLalith Suresh
Lalith Suresh
UWUdi Wieder
Udi Wieder
HKHan Kruiger
Han Kruiger
MAMarcos K. Aguilera
Marcos K. Aguilera

22 June 2023
Verified
Conference Paper
Open access
ZRZhenyuan Ruan
Zhenyuan Ruan
SLShihang Li
Shihang Li
KFKaiyan Fan
Kaiyan Fan
MAMarcos K. Aguilera
Marcos K. Aguilera
ABAdam Belay
Adam Belay
MSMalte Schwarzkopf
Malte Schwarzkopf
Today's clouds are inefficient: their utilization of resources like CPUs, GPUs, memory, and storage is low. This inefficiency occurs because applications consume resources at variable rates and ratios, while clouds offer resources at fixed rates and ratios. This mismatch of offering and consumption styles prevents fully realizing the utility computing vision. We advocate for fungible applications, that is, applications that can distribute, scale, and migrate their consumption of different resources independently while fitting their availability across different servers (e.g., memory at one server, CPU at another). Our goal is to make use of resources even if they are transiently available on a server for only a few milliseconds. We are developing a framework called Quicksand for building such applications and unleashing the utility computing vision. Initial results using Quicksand to implement a DNN training pipeline are promising: Quicksand saturates resources that are imbalanced across machines or rapidly shift in quantity.

28 November 2023
Verified
Conference Paper
Open access
EAEmmanuel Amaro
Emmanuel Amaro
SWStephanie Wang
Stephanie Wang
APAurojit Panda
Aurojit Panda
MAMarcos K. Aguilera
Marcos K. Aguilera
We propose logical memory pools, a memory disaggregation architecture for the emerging Compute Express Link (CXL) technology in datacenters. The key idea is to create a memory pool by carving out parts of the local memory in each server, rather than using a physical memory pool that is separate from servers. Logical pools provide significant benefits over physical pools, namely, lower cost, support for near-memory computing without extra hardware, and flexibility on designating whether memory is part of the memory pool or not. We demonstrate that logical pools can execute workloads that are unfeasible in physical pools, and that its faster access leads to better performance. Realizing logical memory pools poses five major challenges, which we believe can be overcome. Given the benefits of logical pools, we believe the CXL community should refocus efforts on logical, rather than physical memory pools.

4 November 2024
Verified
Conference Paper
Open access
AMAntoine Murat
Antoine Murat
CBClément Burgelin
Clément Burgelin
AXAthanasios Xygkis
Athanasios Xygkis
IZIgor Zablotchi
Igor Zablotchi
MAMarcos Kawazoe Aguilera
Marcos Kawazoe Aguilera
RGRachid Guerraoui
Rachid Guerraoui
Memory disaggregation is an emerging data center architecture that improves resource utilization and scalability. Replication is key to ensure the fault tolerance of applications, but replicating shared data in disaggregated memory is hard. We propose SWARM (Swift WAit-free Replication in disaggregated Memory), the first replication scheme for in-disaggregated-memory shared objects to provide (1) single-roundtrip reads and writes in the common case, (2) strong consistency (linearizability), and (3) strong liveness (wait-freedom). SWARM makes two independent contributions. The first is Safe-Guess, a novel wait-free replication protocol with single-roundtrip operations. The second is In-n-Out, a novel technique to provide conditional atomic update and atomic retrieval of large buffers in disaggregated memory in one roundtrip. Using SWARM, we build SWARM-KV, a low-latency, strongly consistent and highly available disaggregated key-value store. We evaluate SWARM-KV and find that it has marginal latency overhead compared to an unreplicated key-value store, and that it offers much lower latency and better availability than FUSEE, a state-of-the-art replicated disaggregated key-value store.

10 August 2009
Verified
Conference Paper
Open access
MAMarcos K. Aguilera
Marcos K. Aguilera
CDCarole Delporte-Gallet
Carole Delporte-Gallet
HFHugues Fauconnier
Hugues Fauconnier
STSam Toueg
Sam Toueg
We introduce a new model of partial synchrony for read-write shared memory systems. This model is based on the notion of set timeliness—a natural and straightforward generalization of the seminal concept of timeliness in the partially synchrony model of Dwork, Lynch and Stockmeyer (11). Despite its simplicity, the concept of set timeliness is pow erful enough to define a family of partially synchronous systems that closely match individual instances of the t-resilient k-set agreement prob- lem among n processes, henceforth denoted (t, k, n)-agreement. In particular, we use it to give a par- tially synchronous system that is is synchronous enough for solving (t, k, n)-agreement, but not enough for solving two incrementally stronger problems, namely, (t + 1, k, n)-agreement, which has a slightly stronger resiliency requirement, and (t, k − 1, n)-agreement, which has a slightly stronger agreement requirement. This is the first partially synchronous system that separates between these sub-consensus problems. The above results show that set timeliness can be used to study and compare the partial synchrony requirements of problems that are strictly weaker than consensus.

25 June 2010 in Distributed Computing
Verified
Journal Article
Closed access
PDF file
MAMarcos K. Aguilera
Marcos K. Aguilera
STSam Toueg
Sam Toueg