State-of-the-art on thermal energy storage technologies in data center
L Liu, Q Zhang, ZJ Zhai, C Yue, X Ma - Energy and Buildings, 2020 - Elsevier
Data center consumes a great amount of energy and accounts for an increasing proportion
of global energy demand. Low efficiency of cooling systems leads to a cooling cost at about …
of global energy demand. Low efficiency of cooling systems leads to a cooling cost at about …
Dynamollm: Designing llm inference clusters for performance and energy efficiency
J Stojkovic, C Zhang, Í Goiri, J Torrellas… - ar** to shave rare power peaks and add more servers to a
datacenter, thereby oversubscribing its resources and lowering capital costs. This works well …
datacenter, thereby oversubscribing its resources and lowering capital costs. This works well …
AsymNVM: An efficient framework for implementing persistent data structures on asymmetric NVM architecture
The byte-addressable non-volatile memory (NVM) is a promising technology since it
simultaneously provides DRAM-like performance, disk-like capacity, and persistency. The …
simultaneously provides DRAM-like performance, disk-like capacity, and persistency. The …
Flex: High-availability datacenters with zero reserved power
Cloud providers, like Amazon and Microsoft, must guarantee high availability for a large
fraction of their workloads. For this reason, they build datacenters with redundant …
fraction of their workloads. For this reason, they build datacenters with redundant …
[HTML][HTML] Thunderbolt:{Throughput-Optimized},{Quality-of-Service-Aware} Power Cap** at Scale
OSDI '20 Technical Sessions | USENIX Sign In Conferences Attend Registration Information
Student Grant Application Diversity Grant Application Grants for Black Computer Science …
Student Grant Application Diversity Grant Application Grants for Black Computer Science …
CuttleSys: Data-driven resource management for interactive services on reconfigurable multicores
Multi-tenancy for latency-critical applications leads to resource interference and
unpredictable performance. Core reconfiguration opens up more opportunities for …
unpredictable performance. Core reconfiguration opens up more opportunities for …
TAPAS: Thermal-and Power-Aware Scheduling for LLM Inference in Cloud Platforms
The rising demand for generative large language models (LLMs) poses challenges for
thermal and power management in cloud datacenters. Traditional techniques often are …
thermal and power management in cloud datacenters. Traditional techniques often are …