Scheduler side-channels can leak critical information in real-time systems, thus posing serious threats to many safety-critical applications. The main culprit is the inherent determinism in the runtime timing behavior of such systems, e.g., the (expected) periodic behavior of critical tasks. In this paper, we introduce the notion of "schedule indistinguishability/", inspired by work in differential privacy, that introduces diversity into the schedules of such systems while offering analyzable security guarantees. We achieve this by adding a sufficiently large (controlled) noise to the task schedules in order to break their deterministic execution patterns. An "epsilon-Scheduler" then implements schedule indistinguishability in real-time Linux. We evaluate our system using two real applications: (a) an autonomous rover running on a real hardware platform (Raspberry Pi) and (b) a video streaming application that sends data across large geographic distances. Our results show that the epsilon-Scheduler offers better protection against scheduler side-channel attacks in real-time systems while still maintaining good performance and quality-of-service(QoS) requirements.
more »
« less
MAPPER: Managing Application Performance via Parallel Efficiency Regulation
State-of-the-art systems, whether in servers or desktops, provide ample computational and storage resources to allow multiple simultaneously executing potentially parallel applications. However, performance tends to be unpredictable, being a function of algorithmic design, resource allocation choices, and hardware resource limitations. In this article, we introduce MAPPER, a manager of application performance via parallel efficiency regulation. MAPPER uses a privileged daemon to monitor (using hardware performance counters) and coordinate all participating applications by making two coupled decisions: the degree of parallelism to allow each application to improve system efficiency while guaranteeing quality of service (QoS), and which specific CPU cores to schedule applications on. The QoS metric may be chosen by the application and could be in terms of execution time, throughput, or tail latency, relative to the maximum performance achievable on the machine. We demonstrate that using a normalized parallel efficiency metric allows comparison across and cooperation among applications to guarantee their required QoS. While MAPPER may be used without application or runtime modification, use of a simple interface to communicate application-level knowledge improves MAPPER’s efficacy. Using a QoS guarantee of 85% of the IPC achieved with a fair share of resources on the machine, MAPPER achieves up to 3.3 \( \times \) speedup relative to unmodified Linux and runtime systems, with an average improvement of 17% in our test cases. At the same time, MAPPER violates QoS for only 2% of the applications (compared to 23% for Linux), while placing much tighter bounds on the worst case. MAPPER relieves hardware bottlenecks via task-to-CPU placement and allocates more CPU contexts to applications that exhibit higher parallel efficiency while guaranteeing QoS, resulting in both individual application performance predictability and overall system efficiency.
more »
« less
- NSF-PAR ID:
- 10353129
- 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
-
-
Network emulation allows unmodified code execution on lightweight containers to enable accurate and scalable networked application testing. However, such testbeds cannot guarantee fidelity under high workloads, especially when many processes concurrently request resources (e.g., CPU, disk I/O, GPU, and network bandwidth) that are more than the underlying physical machine can offer. A virtual time system enables the emulated hosts to maintain their own notion of virtual time. A container can stop advancing its time when not running (e.g., in an idle or suspended state). The existing virtual time systems focus on precise time management for CPU-intensive applications but are not designed to handle other operations, such as disk I/O, network I/O, and GPU computation. In this paper, we develop a lightweight virtual time system that integrates precise I/O time for container-based network emulation. We model and analyze the temporal error during I/O operations and develop a barrier-based time compensation mechanism in the Linux kernel. We also design and implement Dynamic Load Monitor (DLM) to mitigate the temporal error during I/O resource contention. VT-IO enables accurate virtual time advancement with precise I/O time measurement and compensation. The experimental results demonstrate a significant improvement in temporal error with the introduction of DLM. The temporal error is reduced from 7.889 seconds to 0.074 seconds when utilizing the DLM in the virtual time system. Remarkably, this improvement is achieved with an overall overhead of only 1.36% of the total execution time.more » « less
-
null (Ed.)Causal profiling is a novel and powerful profiling technique that quantifies the potential impact of optimizing a code segment on the program runtime. A key application of causal profiling is to analyze what-if scenarios which typically require a large number of experiments. Besides, the execution of a program highly depends on the underlying machine resources, e.g., CPU, network, storage, so profiling results on one device does not translate directly to another. This is a major bottleneck in our ability to perform scalable performance analysis and greatly limits cross-platform software development. In this paper, we address the above challenges by leveraging a unique property of causal profiling: only relative performance of different resources affects the result of causal profiling, not their absolute performance. We first analytically model and prove causal profiling, the missing piece in the seminal paper. Then, we assert the necessary condition to achieve virtual causal profiling on a secondary device. Building upon the theory, we design VCoz, a virtual causal profiler that enables profiling applications on target devices using measurements on the host device. We implement a prototype of VCoz by tuning multiple hardware components to preserve the relative execution speeds of code segments. Our experiments on benchmarks that stress different system resources demonstrate that VCoz can generate causal profiling reports of Nexus 6P (an ARM-based device) on a host MacBook (x86 architecture) with less than 16% variance.more » « less
-
Computer scientists and programmers face the difficultly of improving the scalability of their applications while using conventional programming techniques only. As a base-line hypothesis of this paper we assume that an advanced runtime system can be used to take full advantage of the available parallel resources of a machine in order to achieve the highest parallelism possible. In this paper we present the capabilities of HPX - a distributed runtime system for parallel applications of any scale - to achieve the best possible scalability through asynchronous task execution [1]. OP2 is an active library which provides a framework for the parallel execution for unstructured grid applications on different multi-core/many-core hardware architectures [2]. OP2 generates code which uses OpenMP for loop parallelization within an application code for both single-threaded and multi-threaded machines. In this work we modify the OP2 code generator to target HPX instead of OpenMP, i.e. port the parallel simulation backend of OP2 to utilize HPX. We compare the performance results of the different parallelization methods using HPX and OpenMP for loop parallelization within the Airfoil application. The results of strong scaling and weak scaling tests for the Airfoil application on one node with up to 32 threads are presented. Using HPX for parallelization of OP2 gives an improvement in performance by 5%-21%. By modifying the OP2 code generator to use HPX's parallel algorithms, we observe scaling improvements by about 5% as compared to OpenMP. To fully exploit the potential of HPX, we adapted the OP2 API to expose a future and dataflow based programming model and applied this technique for parallelizing the same Airfoil application. We show that the dataflow oriented programming model, which automatically creates an execution tree representing the algorithmic data dependencies of our application, improves the overall scaling results by about 21% compared to OpenMP. Our results show the advantage of using the asynchronous programming model implemented by HPX.more » « less
-
Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3] as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3501767
