Panthera: holistic memory management for big data processing over hybrid memories

Wang, Chenxi; Cui, Huimin; Cao, Ting; Zigman, John; Volos, Haris; Mutlu, Onur; Lv, Fang; Feng, Xiaobing; Xu, Guoqing

doi:10.1145/3314221.3314650

Cited by 39 publications

(33 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Related to this work are GC approaches that exploit scalable NVM to expand physical memory. Their pro-active and fine-grained nature outperforms OS and hardware solutions to manage hybrid memories [5,6,58]. Wang et al [58] use emulated NVM to store big data heaps on hybrid memory.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Intel Optane Memory for Managed Workloads

Akram

2021

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

Intel Optane memory offers non-volatility, byte addressability, and high capacity. It suits managed workloads that prefer large main memory heaps. We investigate Optane as the main memory for managed (Java) workloads, focusing on performance scalability. As the workload (core count) increases, we note Optane’s performance relative to DRAM. A few workloads incur a slight slowdown on Optane memory, which helps conserve limited DRAM capacity. Unfortunately, other workloads scale poorly beyond a few core counts. This article investigates scaling bottlenecks for Java workloads on Optane memory, analyzing the application, runtime, and microarchitectural interactions. Poorly scaling workloads allocate objects rapidly and access objects in Optane memory frequently. These characteristics slow down the mutator and substantially slow down garbage collection (GC). At the microarchitecture level, load, store, and instruction miss penalties rise. To regain performance, we partition heaps across DRAM and Optane memory, a hybrid that scales considerably better than Optane alone. We exploit state-of-the-art GC approaches to partition heaps. Unfortunately, existing GC approaches needlessly waste DRAM capacity because they ignore runtime behavior. This article also introduces performance impact-guided memory allocation (PIMA) for hybrid memories. PIMA maximizes Optane utilization, allocating in DRAM only if it improves performance. It estimates the performance impact of allocating heaps in either memory type by sampling. We target PIMA at graph analytics workloads, offering a novel performance estimation method and detailed evaluation. PIMA identifies workload phases that benefit from DRAM with high (94.33%) accuracy, incurring only a 2% sampling overhead. PIMA operates stand-alone or combines with prior approaches to offer new performance versus DRAM capacity trade-offs. This work opens up Optane memory to a real-life role as the main memory for Java workloads.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Their pro-active and fine-grained nature outperforms OS and hardware solutions to manage hybrid memories [5,6,58]. Wang et al [58] use emulated NVM to store big data heaps on hybrid memory. They store infrequently accessed resilient distributed datasets (RDDs) [70] in NVM and the rest in DRAM.…”

Section: Related Workmentioning

confidence: 99%

Performance Evaluation of Intel Optane Memory for Managed Workloads

Akram

2021

ACM Trans. Archit. Code Optim.

View full text Add to dashboard Cite

show abstract

“…RAMinate [22], Heteros [24], Yan et al [82] propose the state-of-the-art memory management solutions for general purpose which guides page placement based on an existing Linux page replacement mechanism. Application-specific HM management solutions [8,11,13,18,33,35,45,47,75,78,79,85] leverage domain knowledge to further improve performance. MyNVM [13] proposes a software-managed multi-level caches policy to treat DRAM and NVM as caches for hard drives.…”

Section: Related Workmentioning

confidence: 99%

Athena

Liu

Gioiosa

et al. 2021

Proceedings of the ACM International Conference on Supercomputing

View full text Add to dashboard Cite

Sparse tensor contraction sequence has been widely employed in many fields, such as chemistry and physics. However, how to efficiently implement the sequence faces multiple challenges, such as redundant computations and memory operations, massive memory consumption, and inefficient utilization of hardware. To address the above challenges, we introduce Athena, a high-performance framework for SpTC sequences. Athena introduces new data structures, leverages emerging Optane-based heterogeneous memory (HM) architecture, and adopts stage parallelism. In particular, Athena introduces shared hash table-represented sparse accumulator to eliminate unnecessary input processing and data migration; Athena uses a novel data-semantic guided dynamic migration solution to make the best use of the Optane-based HM for high performance; Athena also co-runs execution phases with different characteristics to enable high hardware utilization. Evaluating with 12 datasets, we show that Athena brings 327-7362× speedup over the state-ofthe-art SpTC algorithm. With the dynamic data placement guided by data semantics, Athena brings performance improvement on Optane-based HM over a state-of-the-art software-based data management solution, a hardware-based data management solution, and PMM-only by 1.58×, 1.82×, and 2.34× respectively. Athena also showcases its effectiveness in quantum chemistry and physics scenarios. CCS CONCEPTS• Mathematics of computing → Mathematical software performance; • Computing methodologies → Shared memory algorithms.

show abstract

“…As for workload, we first choose two applications in Spark: page-rank and kmeans. Those two have been used by prior work to study the runtime behavior in a heterogeneous memory environment [39]. We also extract four memory-intensive applications from the recently released Renaissance benchmark [32], which contains various workloads like machine learning, graph processing, and software transactional memory.…”

Section: Performance Analysis Atop Nvmmentioning

confidence: 99%

“…If the CAS instruction succeeds, the GC thread will install the forwarding pointer by storing the new address of an object to the value field of the entry (Line 31-32). During scanning, if the GC thread finds that the forwarding pointer has been installed by others, it will directly return with the value of the pointer (Line [35][36][37][38][39].…”

Section: Header Mapmentioning

confidence: 99%

Bridging the performance gap for copy-based garbage collectors atop non-volatile memory

Yang

Chen

et al. 2021

Proceedings of the Sixteenth European Conference on Computer Systems

View full text Add to dashboard Cite

Non-volatile memory (NVM) is expected to revolutionize the memory hierarchy with not only non-volatility but also large capacity and power efficiency. Memory-intensive applications, which are often written in managed languages like Java, would run atop NVM for better cost-efficiency. Unfortunately, such applications may suffer from performance slowdown due to the unmanaged performance gap between DRAM and NVM. This paper studies the performance of a series of Java applications atop NVM and uncovers that the copy-based garbage collection (GC), the mainstream GC algorithm, is an NVM-unfriendly component in JVM. GC becomes a severe performance bottleneck especially when memory resource is scarce. To this end, this paper analyzes the memory behavior of copy-based GC and uncovers that its inappropriate usage on NVM bandwidth is the main reason for its performance slowdown. This paper thus proposes two NVM-aware optimizations: write cache and header map, to effectively manage the limited NVM bandwidth. It further improves the GC performance with hardware instructions like non-temporal memory accesses and prefetching. We have implemented the optimizations on two mainstream copy-based garbage collectors in OpenJDK. Evaluation with various memory-intensive applications shows that our optimizations can improve the GC time, application execution time, application tail latency by up to 2.69×, 11.0%, and 5.09×, respectively. CCS Concepts: • Software and its engineering → Runtime environments; • Hardware → Memory and dense storage.

show abstract

Panthera: holistic memory management for big data processing over hybrid memories

Cited by 39 publications

References 39 publications

Performance Evaluation of Intel Optane Memory for Managed Workloads

Performance Evaluation of Intel Optane Memory for Managed Workloads

Athena

Bridging the performance gap for copy-based garbage collectors atop non-volatile memory

Contact Info

Product

Resources

About