Daniel S. Berger
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Daniel S. Berger has a total of 106 co-authors. Here are the top co-authors by number of shared publications:
- Ricardo Bianchini
Microsoft Corporation, Redmond, WA, USA
5 shared publications - Rodrigo Fonseca
Microsoft Corporation, Redmond, WA, USA
4 shared publications - Celine Irvene
Microsoft, USA
3 shared publications - Fiodar Kazhamiaka
Microsoft, Redmond, WA, USA
3 shared publications - Pantea Zardoshti
Microsoft Corporation, Redmond, WA, USA
3 shared publications - Antonis Psistakis
University of Illinois Urbana-Champaign, Champaign, Illinois, USA
2 shared publications
Latest Publications
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1413-1429
Performance Predictability in Heterogeneous Memory
Heterogeneous memory combining DRAM and CXL exhibits variable performance, yet existing metrics correlate weakly with actual slowdown. We present CAMP, a principled framework for predicting CXL-induced slowdown. Our key insight is that a DRAM run (plus a CXL run for bandwidth-bound workloads) exposes the causal microarchitectural pressure points where CXL latency translates into additional processor stall cycles. CAMP captures these signals using 12 performance counters to analytically decompose slowdown into three orthogonal components: demand reads, cache/prefetching, and stores. CAMP also introduces a closed-form model for software-based weighted interleaving that predicts performance across DRAM--CXL ratios. Across 265 workloads on NUMA and three CXL devices, CAMP achieves 91--97% prediction accuracy within 10% absolute error. We demonstrate that these models enable practical system policies, including ''Best-shot'' interleaving and colocated workload placement, improving performance by up to 21% and 23% over existing tiering and colocation approaches.
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1413-1429
Open AccessPerformance Predictability in Heterogeneous Memory
Heterogeneous memory combining DRAM and CXL exhibits variable performance, yet existing metrics correlate weakly with actual slowdown. We present CAMP, a principled framework for predicting CXL-induced slowdown. Our key insight is that a DRAM run (plus a CXL run for bandwidth-bound workloads) exposes the causal microarchitectural pressure points where CXL latency translates into additional processor stall cycles. CAMP captures these signals using 12 performance counters to analytically decompose slowdown into three orthogonal components: demand reads, cache/prefetching, and stores. CAMP also introduces a closed-form model for software-based weighted interleaving that predicts performance across DRAM--CXL ratios. Across 265 workloads on NUMA and three CXL devices, CAMP achieves 91--97% prediction accuracy within 10% absolute error. We demonstrate that these models enable practical system policies, including ''Best-shot'' interleaving and colocated workload placement, improving performance by up to 21% and 23% over existing tiering and colocation approaches.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (4) , 1234-1246
CXL in Cloud Practice: Practical Lessons for Incrementally Scaling Deployment
This paper explores learnings from first-generation Compute Express Link (CXL) memory expansion to accelerate CXL’s journey to broad, robust use. While broad adoption will be a long journey similar to that of RDMA, we argue that the first step—CXL.mem expansion—is viable on today’s hardware. Through an end-to-end analysis, we revisit common showstoppers: we decompose memory access latency and show that CPU and DRAM internals, rather than the CXL protocol, dominate latency and variability, and we demonstrate how system slack absorbs link error rates above nominal specifications. Along the way, we distill practical guidance on device validation, monitoring, failure modes, security, and multi-tenant interference, and we outline a pragmatic adoption pathway: solidify robust expansion first, prototype micro-pooling next, and move to selective sharing as the ecosystem matures.
- 24 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (4) , 1234-1246
CXL in Cloud Practice: Practical Lessons for Incrementally Scaling Deployment
This paper explores learnings from first-generation Compute Express Link (CXL) memory expansion to accelerate CXL’s journey to broad, robust use. While broad adoption will be a long journey similar to that of RDMA, we argue that the first step—CXL.mem expansion—is viable on today’s hardware. Through an end-to-end analysis, we revisit common showstoppers: we decompose memory access latency and show that CPU and DRAM internals, rather than the CXL protocol, dominate latency and variability, and we demonstrate how system slack absorbs link error rates above nominal specifications. Along the way, we distill practical guidance on device validation, monitoring, failure modes, security, and multi-tenant interference, and we outline a pragmatic adoption pathway: solidify robust expansion first, prototype micro-pooling next, and move to selective sharing as the ecosystem matures.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 21 (4) , 1-34
FairyWREN: A Sustainable Cache for Emerging Write-Read-Erase Flash Interfaces
Datacenters need to reduce embodied carbon emissions, particularly for flash, which accounts for 40% of embodied carbon in servers. However, decreasing flash’s embodied emissions is challenging due to flash’s limited write endurance, which more than halves with each generation of denser flash. Reducing embodied emissions requires extending flash lifetime, stressing its limited write endurance even further. The legacy Logical Block-Addressable Device (LBAD) interface exacerbates the problem by forcing devices to perform garbage collection, leading to even more writes. Flash-based caches in particular write frequently, limiting the lifetimes and densities of the devices they use. These flash caches illustrate the need to break away from LBAD and switch to the new Write-Read-Erase iNterfaces (WREN) now coming to market. WREN affords applications control over data placement and garbage collection. We present Fairy Wren , 1 a flash cache designed for WREN. Fairy Wren reduces writes by co-designing caching policies and flash garbage collection. Fairy Wren provides a 12.5× write reduction over state-of-the-art LBAD caches. This decrease in writes allows flash devices to last longer, decreasing flash cost by 35% and flash carbon emissions by 33%.
- 3 November 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 21 (4) , 1-34
Open AccessFairyWREN: A Sustainable Cache for Emerging Write-Read-Erase Flash Interfaces
Datacenters need to reduce embodied carbon emissions, particularly for flash, which accounts for 40% of embodied carbon in servers. However, decreasing flash’s embodied emissions is challenging due to flash’s limited write endurance, which more than halves with each generation of denser flash. Reducing embodied emissions requires extending flash lifetime, stressing its limited write endurance even further. The legacy Logical Block-Addressable Device (LBAD) interface exacerbates the problem by forcing devices to perform garbage collection, leading to even more writes. Flash-based caches in particular write frequently, limiting the lifetimes and densities of the devices they use. These flash caches illustrate the need to break away from LBAD and switch to the new Write-Read-Erase iNterfaces (WREN) now coming to market. WREN affords applications control over data placement and garbage collection. We present Fairy Wren , 1 a flash cache designed for WREN. Fairy Wren reduces writes by co-designing caching policies and flash garbage collection. Fairy Wren provides a 12.5× write reduction over state-of-the-art LBAD caches. This decrease in writes allows flash devices to last longer, decreasing flash cost by 35% and flash carbon emissions by 33%.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 101-119
Oasis: Pooling PCIe Devices Over CXL to Boost Utilization
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 101-119
Open AccessOasis: Pooling PCIe Devices Over CXL to Boost Utilization
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 45 (4) , 19-28
Enabling Sustainable Cloud Computing With Low-Carbon Server Design
To combat climate change, we must reduce carbon emissions from hyperscale cloud computing. We find that compute servers cause the majority of a general-purpose cloud’s emissions. Thus, we motivate designing carbon-efficient compute server Stock Keeping Units (SKUs), or GreenSKUs, using recently-available low-carbon components. We build three GreenSKU prototypes, integrating energy-efficient CPUs, reused old DRAM via CXL, and reused old SSDs. We reveal challenges that limit GreenSKUs’ carbon savings at scale and may prevent their adoption by cloud providers. To address these challenges, we develop a novel framework, GSF (GreenSKU Framework), that enables cloud providers to systematically evaluate GreenSKUs’ carbon savings at scale. By implementing GSF within Microsoft Azure’s production constraints, we demonstrate that GreenSKUs reduce net cloud emissions by 8%, which is globally significant. This work is the first to demonstrate and quantify how carbon-efficient server designs translate to measurable cloud-scale emissions reductions, enabling meaningful contributions to cloud sustainability goals.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 45 (4) , 19-28
Enabling Sustainable Cloud Computing With Low-Carbon Server Design
To combat climate change, we must reduce carbon emissions from hyperscale cloud computing. We find that compute servers cause the majority of a general-purpose cloud’s emissions. Thus, we motivate designing carbon-efficient compute server Stock Keeping Units (SKUs), or GreenSKUs, using recently-available low-carbon components. We build three GreenSKU prototypes, integrating energy-efficient CPUs, reused old DRAM via CXL, and reused old SSDs. We reveal challenges that limit GreenSKUs’ carbon savings at scale and may prevent their adoption by cloud providers. To address these challenges, we develop a novel framework, GSF (GreenSKU Framework), that enables cloud providers to systematically evaluate GreenSKUs’ carbon savings at scale. By implementing GSF within Microsoft Azure’s production constraints, we demonstrate that GreenSKUs reduce net cloud emissions by 8%, which is globally significant. This work is the first to demonstrate and quantify how carbon-efficient server designs translate to measurable cloud-scale emissions reductions, enabling meaningful contributions to cloud sustainability goals.
- Open Access
- 14 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 58-66
My CXL Pool Obviates Your PCIe Switch
- 14 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 58-66
Open AccessMy CXL Pool Obviates Your PCIe Switch
- Top Cited PapersOpen Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1203-1217
Systematic CXL Memory Characterization and Performance Analysis at Scale
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1203-1217
Top Cited PapersOpen AccessSystematic CXL Memory Characterization and Performance Analysis at Scale
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 164-181
Coach: Exploiting Temporal Patterns for All-Resource Oversubscription in Cloud Platforms
Cloud platforms remain underutilized despite multiple proposals to improve their utilization (e.g., disaggregation, harvesting, and oversubscription). Our characterization of the resource utilization of virtual machines (VMs) in Azure reveals that, while CPU is the main underutilized resource, we need to provide a solution to manage all resources holistically. We also observe that many VMs exhibit complementary temporal patterns, which can be leveraged to improve the oversubscription of underutilized resources. Based on these insights, we propose Coach: a system that exploits temporal patterns for all-resource oversubscription in cloud platforms. Coach uses long-term predictions and an efficient VM scheduling policy to exploit temporally complementary patterns. We introduce a new general-purpose VM type, called CoachVM, where we partition each resource allocation into a guaranteed and an oversubscribed portion. Coach monitors the oversubscribed resources to detect contention and mitigate any potential performance degradation. We focus on memory management, which is particularly challenging due to memory's sensitivity to contention and the overhead required to reassign it between CoachVMs. Our experiments show that Coach enables platforms to host up to ~26% more VMs with minimal performance degradation.
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 164-181
Open AccessCoach: Exploiting Temporal Patterns for All-Resource Oversubscription in Cloud Platforms
Cloud platforms remain underutilized despite multiple proposals to improve their utilization (e.g., disaggregation, harvesting, and oversubscription). Our characterization of the resource utilization of virtual machines (VMs) in Azure reveals that, while CPU is the main underutilized resource, we need to provide a solution to manage all resources holistically. We also observe that many VMs exhibit complementary temporal patterns, which can be leveraged to improve the oversubscription of underutilized resources. Based on these insights, we propose Coach: a system that exploits temporal patterns for all-resource oversubscription in cloud platforms. Coach uses long-term predictions and an efficient VM scheduling policy to exploit temporally complementary patterns. We introduce a new general-purpose VM type, called CoachVM, where we partition each resource allocation into a guaranteed and an oversubscribed portion. Coach monitors the oversubscribed resources to detect contention and mitigate any potential performance degradation. We focus on memory management, which is particularly challenging due to memory's sensitivity to contention and the overhead required to reassign it between CoachVMs. Our experiments show that Coach enables platforms to host up to ~26% more VMs with minimal performance degradation.
- Open Access
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-20
Dense Server Design for Immersion Cooling
The growing demands for computational power in cloud computing have led to a significant increase in the deployment of high-performance servers. The growing power consumption of servers and the heat they produce is on track to outpace the capacity of conventional air cooling systems, necessitating more efficient cooling solutions such as liquid immersion cooling. The superior heat exchange capabilities of immersion cooling both eliminates the need for bulky heat sinks, fans, and air flow channels while also unlocking the potential go beyond conventional 2D blade servers to three-dimensional designs. In this work, we present a computational framework to explore designs of servers in three-dimensional space, specifically targeting the maximization of server density within immersion cooling tanks. Our tool is designed to handle a variety of physical and electrical server design constraints. We demonstrate our optimized designs can reduce server volume by 25--52% compared to traditional flat server designs. This increased density reduces land usage as well as the amount of liquid used for immersion, with significant reduction in the carbon emissions embodied in datacenter buildings. We further create physical prototypes to simulate dense server designs and perform real-world experiments in an immersion cooling tank demonstrating they operate at safe temperatures. This approach marks a critical step forward in sustainable and efficient datacenter management.
- 19 November 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 43 (6) , 1-20
Open AccessDense Server Design for Immersion Cooling
The growing demands for computational power in cloud computing have led to a significant increase in the deployment of high-performance servers. The growing power consumption of servers and the heat they produce is on track to outpace the capacity of conventional air cooling systems, necessitating more efficient cooling solutions such as liquid immersion cooling. The superior heat exchange capabilities of immersion cooling both eliminates the need for bulky heat sinks, fans, and air flow channels while also unlocking the potential go beyond conventional 2D blade servers to three-dimensional designs. In this work, we present a computational framework to explore designs of servers in three-dimensional space, specifically targeting the maximization of server density within immersion cooling tanks. Our tool is designed to handle a variety of physical and electrical server design constraints. We demonstrate our optimized designs can reduce server volume by 25--52% compared to traditional flat server designs. This increased density reduces land usage as well as the amount of liquid used for immersion, with significant reduction in the carbon emissions embodied in datacenter buildings. We further create physical prototypes to simulate dense server designs and perform real-world experiments in an immersion cooling tank demonstrating they operate at safe temperatures. This approach marks a critical step forward in sustainable and efficient datacenter management.
- Top Cited PapersOpen Access
- 8 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (11) , 1-37
An Introduction to the Compute Express Link (CXL) Interconnect
The Compute Express Link (CXL) is an open industry-standard interconnect between processors and devices such as accelerators, memory buffers, smart network interfaces, persistent memory, and solid-state drives. CXL offers coherency and memory semantics with bandwidth that scales with PCIe bandwidth while achieving significantly lower latency than PCIe. All major CPU vendors, device vendors, and datacenter operators have adopted CXL as a common standard. This enables an inter-operable ecosystem that supports key computing use cases including highly efficient accelerators, server memory bandwidth and capacity expansion, multi-server resource pooling and sharing, and efficient peer-to-peer communication. This survey provides an introduction to CXL covering the standards CXL 1.0, CXL 2.0, and CXL 3.0. We further survey CXL implementations, discuss CXL's impact on the datacenter landscape, and future directions.
- 8 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 56 (11) , 1-37
Top Cited PapersOpen AccessAn Introduction to the Compute Express Link (CXL) Interconnect
The Compute Express Link (CXL) is an open industry-standard interconnect between processors and devices such as accelerators, memory buffers, smart network interfaces, persistent memory, and solid-state drives. CXL offers coherency and memory semantics with bandwidth that scales with PCIe bandwidth while achieving significantly lower latency than PCIe. All major CPU vendors, device vendors, and datacenter operators have adopted CXL as a common standard. This enables an inter-operable ecosystem that supports key computing use cases including highly efficient accelerators, server memory bandwidth and capacity expansion, multi-server resource pooling and sharing, and efficient peer-to-peer communication. This survey provides an introduction to CXL covering the standards CXL 1.0, CXL 2.0, and CXL 3.0. We further survey CXL implementations, discuss CXL's impact on the datacenter landscape, and future directions.