An official website of the United States government
The advent of non-volatile memory (NVM) invalidates fundamental design decisions that are deeply embedded in today’s software systems. In a recent blog post, Steve Swanson presented the three milestones that mark different stages of NVM adoption. The proposed steps would certainly enable general applications to leverage NVM with limited development effort. However, recent research in the database systems community points out that the opportunity for NVM-aware applications does not stop with bespoke NVM-aware data structures. We believe that the next level of evolution, or level 4.0 in the original milestones, is tailoring fundamental protocols and algorithms for NVM. This blog post details how database systems are being redesigned for NVM. We first present a new logging and recovery protocol for NVM and then describe a data processing algorithm for sorting NVM-resident data. We hope that this blog post will give the computer architecture community a better idea of the different ways in which NVM may be used by data-intensive applications.
more »
« less
Preserving Addressability Upon GC-Triggered Data Movements on Non-Volatile Memory
This article points out an important threat that application-level Garbage Collection (GC) creates to the use of non-volatile memory (NVM). Data movements incurred by GC may invalidate the pointers to objects on NVM and, hence, harm the reusability of persistent data across executions. The article proposes the concept of movement-oblivious addressing (MOA), and develops and compares three novel solutions to materialize the concept for solving the addressability problem. It evaluates the designs on five benchmarks and a real-world application. The results demonstrate the promise of the proposed solutions, especially hardware-supported Multi-Level GPointer, in addressing the problem in a space- and time-efficient manner.
more »
« less
- PAR ID:
- 10358551
- Date Published:
- Journal Name:
- ACM Transactions on Architecture and Code Optimization
- Volume:
- 19
- Issue:
- 2
- ISSN:
- 1544-3566
- Page Range / eLocation ID:
- 1 to 26
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Much of environmental law and policy rests on an unspoken premise that accomplishing environmental goals may not require addressing root causes of environmental problems. For example, rather than regulating risks directly, society may adopt warnings that merely avoid risk, and rather than limiting plastic use and reducing plastic waste, society may adopt recycling programs. Such approaches may be well-intended and may come at a relatively low economic or political cost. However, they often prove ineffective or even harmful, and they may mislead society into believing that further responses are unnecessary. This Article proposes the concept of “too-easy solutions” to describe these approaches. Too easy solutions can be classified into three subcategories: fig leaves—policy approaches that appear to do something about a problem without necessarily solving it; pipe dreams—policy approaches that are adopted with the good faith expectation of solving the problem but are inherently flawed; and myopic solutions—approaches that address part of the problem but may impede its overall resolution. Too-easy solutions analysis can serve as a powerful mechanism for evaluating policies and improving decisionmaking in the environmental arena and other areas as well.more » « less
-
On large-scale high performance computing (HPC) systems, applications are provisioned with aggregated resources to meet their peak demands for brief periods. This results in resource underutilization because application requirements vary a lot during execution. This problem is particularly pronounced for deep learning applications that are running on leadership HPC systems with a large pool of burst buffers in the form of flash or non-volatile memory (NVM) devices. In this paper, we examine the I/O patterns of deep neural networks and reveal their critical need of loading many small samples randomly for successful training. We have designed a specialized Deep Learning File System (DLFS) that provides a thin set of APIs. Particularly, we design the metadata management of DLFS through an in-memory tree-based sample directory and its file services through the user-level SPDK protocol that can disaggregate the capabilities of NVM Express (NVMe) devices to parallel training tasks. Our experimental results show that DLFS can dramatically improve the throughput of training for deep neural networks on NVMe over Fabric, compared with the kernel-based Ext4 file system. Furthermore, DLFS achieves efficient user-level storage disaggregation with very little CPU utilization.more » « less
-
Managed programming languages including Java and Scala are very popular for data analytics and mobile applications. However, they often face challenging issues due to the overhead caused by the automatic memory management to detect and reclaim free available memory. It has been observed that during their Garbage Collection (GC), excessively long pauses can account for up to 40 % of the total execution time. Therefore, mitigating the GC overhead has been an active research topic to satisfy today's application requirements. This paper proposes a new technique called SwapVA to improve data copying in the copying/moving phases of GCs and reduce the GC pause time, thereby mitigating the issue of GC overhead. Our contribution is twofold. First, a SwapVA system call is introduced as a zero-copy technique to accelerate the GC copying/moving phase. Second, for the demonstration of its effectiveness, we have integrated SwapVA into SVAGC as an implementation of scalable Full GC on multi-core systems. Based on our results, the proposed solutions can dramatically reduce the GC pause in applications with large objects by as much as 70.9% and 97%, respectively, in the Sparse.large/4 (one quarter of the default input size) and Sigverify benchmarks.more » « less
-
Garbage collection (GC) support for unmanaged languages can reduce programming burden in reasoning about liveness of dynamic objects. It also avoids temporal memory safety violations and memory leaks.SoundGC for weakly-typed languages such as C/C++, however, remains an unsolved problem. Current value-based GC solutions examine values of memory locations to discover the pointers, and the objects they point to. The approach is inherently unsound in the presence of arbitrary type casts and pointer manipulations, which are legal in C/C++. Such language features are regularly used, especially in low-level systems code. In this paper, we propose Dynamic Pointer Provenance Tracking to realize sound GC. We observe that pointers cannot be created out-of-thin-air, and they must have provenance to at least one valid allocation. Therefore, by tracking pointer provenance from the source (e.g., malloc) through both explicit data-flow and implicit control-flow, our GC has sound and precise information to compute the set of all reachable objects at any program state. We discuss several static analysis optimizations, that can be employed during compilation aided with profiling, to significantly reduce the overhead of dynamic provenance tracking from nearly 8× to 16% for well-behaved programs that adhere to the C standards. Pointer provenance based sound GC invocation is also 13% faster and reclaims 6% more memory on average, compared to an unsound value-based GC.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3511706
