Heiner Litz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Heiner Litz has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Chen Qian
University of California Santa Cruz, Santa Cruz, California, USA
4 shared publications - Minghao Xie
University of California, Santa Cruz, Santa Cruz, CA, USA
4 shared publications - Shouqian Shi
Nanjing University, Nanjing, China
3 shared publications - Yi Liu
University of California Santa Cruz, Santa Cruz, USA
3 shared publications - Baris Kasikci
University of Washington, Seattle, WA, USA
2 shared publications - Gilles Pokam
Intel, Santa Clara, USA
2 shared publications
Latest Publications
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1445-1460
PIPM: Partial and Incremental Page Migration for Multi-host CXL Disaggregated Shared Memory
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1445-1460
Open AccessPIPM: Partial and Incremental Page Migration for Multi-host CXL Disaggregated Shared Memory
- Open Access
- 28 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-52
RIFS: Run-Time Invariant Function Specialization
- 28 January 2026
- Published by Association for Computing Machinery (ACM)
- p. 40-52
Open AccessRIFS: Run-Time Invariant Function Specialization
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 705-718
ATR: Out-of-Order Register Release Exploiting Atomic Regions
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 705-718
Open AccessATR: Out-of-Order Register Release Exploiting Atomic Regions
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Sharc: Simulator for Hardware Architecture and Real-time Control
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessSharc: Simulator for Hardware Architecture and Real-time Control
- Open Access
Thallus: An RDMA-based Columnar Data Transport Protocol
The volume of data generated and stored in contemporary global data centers is experiencing exponential growth. This rapid data growth necessitates efficient processing and analysis to extract valuable business insights. In distributed data processing systems, data undergoes exchanges between the compute servers that contribute significantly to the total data processing duration in adequately large clusters, necessitating efficient data transport protocols. Traditionally, data transport frameworks such as JDBC and ODBC have used TCP/IP-over-Ethernet as their underlying network protocol. Such frameworks require serializing the data into a single contiguous buffer before handing it off to the network card, primarily due to the requirement of contiguous data in TCP/IP. In OLAP use cases, this serialization process is costly for columnar data batches as it involves numerous memory copies that hurt data transport duration and overall data processing performance. We study the serialization overhead in the context of a widely-used columnar data format, Apache Arrow, and propose leveraging RDMA to transport Arrow data over Infiniband in a zero-copy manner. We design and implement Thallus, an RDMA-based columnar data transport protocol for Apache Arrow based on the Thallium framework from the Mochi ecosystem, compare it with a purely Thallium RPC-based implementation, and show substantial performance improvements can be achieved by using RDMA for columnar data transport.
Open AccessThallus: An RDMA-based Columnar Data Transport Protocol
The volume of data generated and stored in contemporary global data centers is experiencing exponential growth. This rapid data growth necessitates efficient processing and analysis to extract valuable business insights. In distributed data processing systems, data undergoes exchanges between the compute servers that contribute significantly to the total data processing duration in adequately large clusters, necessitating efficient data transport protocols. Traditionally, data transport frameworks such as JDBC and ODBC have used TCP/IP-over-Ethernet as their underlying network protocol. Such frameworks require serializing the data into a single contiguous buffer before handing it off to the network card, primarily due to the requirement of contiguous data in TCP/IP. In OLAP use cases, this serialization process is costly for columnar data batches as it involves numerous memory copies that hurt data transport duration and overall data processing performance. We study the serialization overhead in the context of a widely-used columnar data format, Apache Arrow, and propose leveraging RDMA to transport Arrow data over Infiniband in a zero-copy manner. We design and implement Thallus, an RDMA-based columnar data transport protocol for Apache Arrow based on the Thallium framework from the Mochi ecosystem, compare it with a purely Thallium RPC-based implementation, and show substantial performance improvements can be achieved by using RDMA for columnar data transport.
- Open Access
- 20 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 160-177
En4S: Enabling SLOs in Serverless Storage Systems
Serverless computing promises scalability and cost-efficiency by decomposing monolithic tasks into small, stateless, self-contained functions. As functions only reserve hardware resources during their lifetime, and serverless providers such as Amazon Lambda define strict data size limits [50], data required for the whole lifetime of a monolithic task needs to be kept in an external ephemeral data store. This approach increases costs and introduces performance variability, causing serverless applications to violate service level objectives (SLOs). Traditional cloud storage solutions, such as AWS S3 and Redis, fail to provide low-cost and the enforcement of SLOs, while prior works on disaggregated data stores do not scale sufficiently due to: (1) increased scheduling costs when supporting many SLOs; (2) performance degradation in the presence of burst allowances and worsened interference with lenient ones; and (3) failed service differentiation with increased number of SLO. These challenges make SLO enforcement in serverless environments difficult, leading to unpredictable performance and costs that undermine the benefits of serverless computing. We introduce En4S, a high-performance, flash-based storage system designed for data-intensive serverless applications. En4S employs a profile-based scheduling framework with adaptive strategies to efficiently scale to many tenants with different SLOs. Key features include dynamic tenant handling, adaptive burst control, token reclaim control, and various optimizations to minimize scheduling costs while maintaining superior performance. By re-enabling SLO enforcement for disaggregated flash storage in cloud-native environments, En4S is crucial for modern serverless applications. Our implementation on Amazon EC2 and Lambda demonstrates substantial performance and cost improvements while reliably ensuring SLO compliance, enhancing the viability of serverless storage systems.
- 20 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 160-177
Open AccessEn4S: Enabling SLOs in Serverless Storage Systems
Serverless computing promises scalability and cost-efficiency by decomposing monolithic tasks into small, stateless, self-contained functions. As functions only reserve hardware resources during their lifetime, and serverless providers such as Amazon Lambda define strict data size limits [50], data required for the whole lifetime of a monolithic task needs to be kept in an external ephemeral data store. This approach increases costs and introduces performance variability, causing serverless applications to violate service level objectives (SLOs). Traditional cloud storage solutions, such as AWS S3 and Redis, fail to provide low-cost and the enforcement of SLOs, while prior works on disaggregated data stores do not scale sufficiently due to: (1) increased scheduling costs when supporting many SLOs; (2) performance degradation in the presence of burst allowances and worsened interference with lenient ones; and (3) failed service differentiation with increased number of SLO. These challenges make SLO enforcement in serverless environments difficult, leading to unpredictable performance and costs that undermine the benefits of serverless computing. We introduce En4S, a high-performance, flash-based storage system designed for data-intensive serverless applications. En4S employs a profile-based scheduling framework with adaptive strategies to efficiently scale to many tenants with different SLOs. Key features include dynamic tenant handling, adaptive burst control, token reclaim control, and various optimizations to minimize scheduling costs while maintaining superior performance. By re-enabling SLO enforcement for disaggregated flash storage in cloud-native environments, En4S is crucial for modern serverless applications. Our implementation on Amazon EC2 and Lambda demonstrates substantial performance and cost improvements while reliably ensuring SLO compliance, enhancing the viability of serverless storage systems.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 44 (3) , 6-7
Special Issue on Hot Chips 2023
This special issue of IEEE Micro is devoted to selected top-pick articles presented at Hot Chips 2023. The Hot Chips Conference serves as a leading venue for presenting the technical details of innovative microchips on a wide range of topics, including computing, memory, interconnection, and cooling technologies. This particular issue features articles from AMD, Intel, UC Berkeley, Samsung, Cerebras, and Fabric8Labs on different topics including server CPUs, photonic interconnects, processing-in-memory, and artificial intelligence accelerators, as well as new cooling technologies.
- 21 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 44 (3) , 6-7
Special Issue on Hot Chips 2023
This special issue of IEEE Micro is devoted to selected top-pick articles presented at Hot Chips 2023. The Hot Chips Conference serves as a leading venue for presenting the technical details of innovative microchips on a wide range of topics, including computing, memory, interconnection, and cooling technologies. This particular issue features articles from AMD, Intel, UC Berkeley, Samsung, Cerebras, and Fabric8Labs on different topics including server CPUs, photonic interconnects, processing-in-memory, and artificial intelligence accelerators, as well as new cooling technologies.
- Open Access
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 999-1013
RPG 2 : Robust Profile-Guided Runtime Prefetch Generation
Data cache prefetching is a well-established optimization to overcome the limits of the cache hierarchy and keep the processor pipeline fed with data. In principle, accurate, well-timed prefetches can sidestep the majority of cache misses and dramatically improve performance. In practice, however, it is challenging to identify which data to prefetch and when to do so. In particular, data can be easily requested too early, causing eviction of useful data from the cache, or requested too late, failing to avoid cache misses. Competition for limited off-chip memory bandwidth must also be balanced between prefetches and a program's regular "demand" accesses. Due to these challenges, prefetching can both help and hurt performance, and the outcome can depend on program structure, decisions about what to prefetch and when to do it, and, as we demonstrate in a series of experiments, program input, processor microarchitecture, and their interaction as well. To try to meet these challenges, we have designed the RPG2 system for online prefetch injection and tuning. RPG2 is a pure-software system that operates on running C/C++ programs, profiling them, injecting prefetch instructions, and then tuning those prefetches to maximize performance. Across dozens of inputs, we find that RPG2 can provide speedups of up to 2.15×, comparable to the best profile-guided prefetching compilers, but can also respond when prefetching ends up being harmful and roll back to the original code - something that static compilers cannot. RPG2 improves prefetching robustness by preserving its performance benefits, while avoiding slowdowns.
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 999-1013
Open AccessRPG 2 : Robust Profile-Guided Runtime Prefetch Generation
Data cache prefetching is a well-established optimization to overcome the limits of the cache hierarchy and keep the processor pipeline fed with data. In principle, accurate, well-timed prefetches can sidestep the majority of cache misses and dramatically improve performance. In practice, however, it is challenging to identify which data to prefetch and when to do so. In particular, data can be easily requested too early, causing eviction of useful data from the cache, or requested too late, failing to avoid cache misses. Competition for limited off-chip memory bandwidth must also be balanced between prefetches and a program's regular "demand" accesses. Due to these challenges, prefetching can both help and hurt performance, and the outcome can depend on program structure, decisions about what to prefetch and when to do it, and, as we demonstrate in a series of experiments, program input, processor microarchitecture, and their interaction as well. To try to meet these challenges, we have designed the RPG2 system for online prefetch injection and tuning. RPG2 is a pure-software system that operates on running C/C++ programs, profiling them, injecting prefetch instructions, and then tuning those prefetches to maximize performance. Across dozens of inputs, we find that RPG2 can provide speedups of up to 2.15×, comparable to the best profile-guided prefetching compilers, but can also respond when prefetching ends up being harmful and roll back to the original code - something that static compilers cannot. RPG2 improves prefetching robustness by preserving its performance benefits, while avoiding slowdowns.
- Open Access
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 216-232
Enabling Multi-tenancy on SSDs with Accurate IO Interference Modeling
Technological advancements in the past decades have substantially increased the capacity and performance of Solid State Drives (SSDs). Provisioning such high-capacity SSDs among tenants can reap multiple benefits, such as elevated performance, efficient resource utilization, and cost savings through reduced Total Cost of Ownership. However, workloads perform poorly when co-located with others on the same SSD due to IO Interference, potentially violating Service Level Objectives (SLOs). High overprovisioning can address the SLO issue, however, it entails low utilization. Prior works proposed Machine Learning (ML) techniques to predict SSD performance in the presence of interfering tenants for optimizing workload placement. However, we find that these works suffer from two notable limitations. First, previous ML models do not capture interference impact due to the non-uniform workload characteristics and SSD internals. Second, they fail to compute interference of an arbitrary number of workloads due to a lack of feature aggregation. As a result, these works still offer low utilization and can only enforce weak SLOs. To address these limitations, we propose a Gray-box feature representation and aggregation technique to capture the IO interference impact of multiple non-uniform workloads based on internal SSD characteristics. Our technique improves prediction accuracy by 12x (lower mean absolute error) over prior works, resulting in up to 60% higher resource utilization or enforcing up to 2.5× stricter SLOs.
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 216-232
Open AccessEnabling Multi-tenancy on SSDs with Accurate IO Interference Modeling
Technological advancements in the past decades have substantially increased the capacity and performance of Solid State Drives (SSDs). Provisioning such high-capacity SSDs among tenants can reap multiple benefits, such as elevated performance, efficient resource utilization, and cost savings through reduced Total Cost of Ownership. However, workloads perform poorly when co-located with others on the same SSD due to IO Interference, potentially violating Service Level Objectives (SLOs). High overprovisioning can address the SLO issue, however, it entails low utilization. Prior works proposed Machine Learning (ML) techniques to predict SSD performance in the presence of interfering tenants for optimizing workload placement. However, we find that these works suffer from two notable limitations. First, previous ML models do not capture interference impact due to the non-uniform workload characteristics and SSD internals. Second, they fail to compute interference of an arbitrary number of workloads due to a lack of feature aggregation. As a result, these works still offer low utilization and can only enforce weak SLOs. To address these limitations, we propose a Gray-box feature representation and aggregation technique to capture the IO interference impact of multiple non-uniform workloads based on internal SSD characteristics. Our technique improves prediction accuracy by 12x (lower mean absolute error) over prior works, resulting in up to 60% higher resource utilization or enforcing up to 2.5× stricter SLOs.
- Open Access
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 376-393
TMC
Main memory dominates data center server cost, and hence data center operators are exploring alternative technologies such as CXL-attached and persistent memory to improve cost without jeopardizing performance. Introducing multiple tiers of memory introduces new challenges, such as selecting the appropriate memory configuration for a given workload mix. In particular, we observe that inefficient configurations increase cost by up to 2.6× for clients, and resource stranding increases cost by 2.2× for cloud operators. To address this challenge, we introduce TMC, a system for recommending cloud configurations according to workload characteristics and the dynamic resource utilization of a cluster. Whereas prior work utilized extensive simulation or costly machine learning techniques, incurring significant search costs, our approach profiles applications to reveal internal properties that lead to fast and accurate performance estimations. Our novel configuration-selection algorithm incorporates a new heuristic, packing penalty, to ensure that recommended configurations will also achieve good resource efficiency. Our experiments demonstrate that TMC reduces the search cost by up to 4× over the state-of-the-art, while improving resource utilization by up to 17% as compared to a naive policy that requests optimal tiered memory allocations in isolation.
- 30 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 376-393
Open AccessTMC
Main memory dominates data center server cost, and hence data center operators are exploring alternative technologies such as CXL-attached and persistent memory to improve cost without jeopardizing performance. Introducing multiple tiers of memory introduces new challenges, such as selecting the appropriate memory configuration for a given workload mix. In particular, we observe that inefficient configurations increase cost by up to 2.6× for clients, and resource stranding increases cost by 2.2× for cloud operators. To address this challenge, we introduce TMC, a system for recommending cloud configurations according to workload characteristics and the dynamic resource utilization of a cluster. Whereas prior work utilized extensive simulation or costly machine learning techniques, incurring significant search costs, our approach profiles applications to reveal internal properties that lead to fast and accurate performance estimations. Our novel configuration-selection algorithm incorporates a new heuristic, packing penalty, to ensure that recommended configurations will also achieve good resource efficiency. Our experiments demonstrate that TMC reduces the search cost by up to 4× over the state-of-the-art, while improving resource utilization by up to 17% as compared to a naive policy that requests optimal tiered memory allocations in isolation.