MOCA: Memory Object Classification and Allocation in Heterogeneous Memory Systems

Narayan, Aditya; Zhang, Tiansheng; Aga, Shaizeen; Narayanasamy, Satish; Coskun, Ayse K.

doi:10.1109/ipdps.2018.00042

Cited by 13 publications

(31 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the lack of actual device, we emulated STT-RAM over DRAM using the emulation platform, QUARTZ [32]. We compared our solution with MOCA framework [22]. The evaluation results show that our eMPlan outperforms MOCA in reducing the energy consumption up to 14% with the same performance on both of the application benchmarks.…”

Section: • Emdyn Consists Of An Ilp-based Migration Planner Andmentioning

confidence: 99%

“…Memory devices such as High Bandwidth Memory (HBM), Reduced Latency DRAM (RLDRAM), and Low Power DDR (LPDDR) are being produced and studied in a considerable pace [24]. On the other hand, PCM and STT-RAM are the two most rapidly growing NVM devices to be placed on a processor-memory bus in conjunction with DRAM to enable HMMS [12], [20], [22], [23], [34], [35], [37]. Various works [12], [22], [34] have already been studied to place memory objects on different memory modules in HMMS by considering their characteristics.…”

Section: B Object Placement In Hmmsmentioning

confidence: 99%

“…Therefore, it cannot serve as a complete replacement of DRAM. Thus, Hybrid Main Memory System (HMMS) has been proposed that incorporates both DRAM and NVM on the processor memory bus [12], [17], [22], [26], [34].…”

Section: Introductionmentioning

confidence: 99%

“…Several works to place memory objects in HMMS have been proposed [12], [22], [34]. These works classify the memory objects in an application into several categories, such as bandwidth, latency, streaming objects, and pointer tracking objects, and assign the application to the most appropriate memory module [12], [34].…”

Section: Introductionmentioning

confidence: 99%

“…These works classify the memory objects in an application into several categories, such as bandwidth, latency, streaming objects, and pointer tracking objects, and assign the application to the most appropriate memory module [12], [34]. Memory Object Classification and Allocation framework (MOCA) [22] optimizes the performance of the ternary HMMS by placing memory objects in the best-suited memory module. It considers their access behavior specifically based on the rate of the Last-Level Cache misses per kilo instruction (LLC MPKI) and reduce the energy consumption through object placement.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimizing Heap Memory Object Placement in the Hybrid Memory System With Energy Constraints

et al. 2020

View full text Add to dashboard Cite

Main memory significantly impacts the power and energy utilization of the overall server system. Non-Volatile Memory (NVM) devices, are suitable candidates for the main memory to reduce static energy consumption. But unlike DRAM, the access latencies and the dynamic energy consumption of write operation of the NVM devices are higher. Thus, Hybrid Main Memory Systems (HMMS) employing DRAM and NVM have been proposed to reduce the overall energy depletion of main memory while optimizing the performance of application. However, memory object placement is crucial for optimal performance and energy efficiency in HMMS due to high write latency and energy consumption of NVM devices. This paper proposes eMap, an optimal heap memory object placement planner for HMMS. eMap takes into account the object-level access patterns and energy consumption to provide an ideal placement policy for objects to mitigate performance and energy consumption. In particular, eMap is equipped with two modules, eMPlan and eMDyn. eMPlan is a static placement planner which provides one-time placement policies for memory objects to meet the energy budget. eMDyn is a runtime model to consider the requests of changes in the energy constraint during the application execution. Both modules are based in Integer Linear Programming(ILP) and consider three major constraints, namely decision, capacity and energy constraints to optimally placing the memory objects in HMMS. We evaluate the proposed solution with two scientific application benchmarks, NAS Parallel Benchmark (NPB) and Problem-based Benchmark Suit (PBBS), on two testbeds by emulating the NVM using QUARTZ [32]. Our extensive experiments in comparison with Memory Object Classification and Allocation (MOCA) framework showed that our solution is 4.17x less costly in terms of the memory object profiling and reduce the energy consumption up to 14% with the same performance. On the other hand, eMDyn module also meets the performance and energy requirement during the application execution by considering the migration cost in terms of time and energy.

show abstract

Section: • Emdyn Consists Of An Ilp-based Migration Planner Andmentioning

confidence: 99%

Section: B Object Placement In Hmmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimizing Heap Memory Object Placement in the Hybrid Memory System With Energy Constraints

et al. 2020

View full text Add to dashboard Cite

show abstract

Evolution-Based Real-Time Job Scheduling for Co-Optimizing Processor and Memory Power Savings

Bahn¹,

Cho²

2020

IEEE Access

View full text Add to dashboard Cite

With the recent advances in battery-based mobile computing technologies, power-saving techniques in real-time embedded devices are becoming increasingly important. This paper presents a novel job scheduling policy for real-time systems, which aims at minimizing the power consumption of processor and memory without missing the deadline constraints of real-time jobs. To do so, we formulate the power saving techniques of processor voltage/frequency scaling and memory job placement as a unified measure, and show that it is a complex search problem that has the exponential time complexity. Thus, an efficient heuristic based on evolutionary computation is performed to cut down the huge searching space and find a reasonable schedule within the feasible time budget. To evaluate the proposed scheduling policy, we conduct experiments under various workload conditions. Our experimental results show that the proposed policy significantly reduces the energy consumption of real-time systems. Specifically, the average reduction in the energy consumption is 41.7% without deadline misses. INDEX TERMS Real-time job scheduling; evolutionary computation; power saving; genetic algorithm; dynamic voltage/frequency scaling; deadline.

show abstract

Characterization of Android Memory References and Implication to Hybrid Memory Management

Lee

Bahn

2021

IEEE Access

View full text Add to dashboard Cite

In this article, we analyze Android applications' memory reference behaviors, and observe that smartphone memory accesses are different from traditional computer systems with respect to the following five aspects. 1) A limited number of hot pages account for a majority of memory writes, and these hot pages have similar logical addresses regardless of application types. 2) The identities of these hot pages are shared library, linker, and stack regions. 3) The memory access behaviors of hot pages do not change significantly as time progresses even after applications finish their launching. 4) The skewness of memory write accesses in Android is extremely stronger than that of desktop systems. 5) In predicting rereference likelihood of hot pages, temporal locality is better than reference frequency. Based on these observations, we present a new smartphone memory management scheme for DRAM-NVM hybrid memory. Adopting NVM is effective in power-saving of smartphones, but NVM has weaknesses in write operations. Thus, we aim to identify write-intensive pages and place them on DRAM. Unlike previous studies, we prevent migration of pages between DRAM and NVM, which eliminates unnecessary NVM write traffic that accounts for 32-42% of total write traffic. By judiciously managing the admission of hot pages in DRAM, our scheme reduces the write traffic to NVM by 42% on average without performance degradations.

show abstract

MOCA: Memory Object Classification and Allocation in Heterogeneous Memory Systems

Cited by 13 publications

References 28 publications

Optimizing Heap Memory Object Placement in the Hybrid Memory System With Energy Constraints

Optimizing Heap Memory Object Placement in the Hybrid Memory System With Energy Constraints

Evolution-Based Real-Time Job Scheduling for Co-Optimizing Processor and Memory Power Savings

Characterization of Android Memory References and Implication to Hybrid Memory Management

Contact Info

Product

Resources

About