An official website of the United States government
Because FPGAs outperform traditional processing cores like CPUs and GPUs in terms of performance per watt and flexibility, they are being used more and more in cloud and data center applications. There are growing worries about the security risks posed by multi-tenant sharing as the demand for hardware acceleration increases and gradually gives way to FPGA multi-tenancy in the cloud. The confidentiality, integrity, and availability of FPGA-accelerated applications may be compromised if space-shared FPGAs are made available to many cloud tenants. We propose a root of trust-based trusted execution mechanism called TrustToken to prevent harmful software-level attackers from getting unauthorized access and jeopardizing security. With safe key creation and truly random sources, TrustToken creates a security block that serves as the foundation of trust-based IP security. By offering crucial security characteristics, such as secure, isolated execution and trusted user interaction, TrustToken only permits trustworthy connection between the non-trusted third-party IP and the rest of the SoC environment. The suggested approach does this by connecting the third-party IP interface to the TrustToken Controller and running run-time checks on the correctness of the IP authorization(Token) signals. With an emphasis on software-based assaults targeting unauthorized access and information leakage, we offer a noble hardware/software architecture for trusted execution in FPGA-accelerated clouds and data centers.
more »
« less
Telekine: Secure Computing with Cloud GPUs
GPUs have become ubiquitous in the cloud due to the dramatic performance gains they enable in domains such as machine learning and computer vision. However, offloading GPU computation to the cloud requires placing enormous trust in providers and administrators. Recent proposals for GPU trusted execution environments (TEEs) are promising but fail to address very real side-channel concerns. To illustrate the severity of the problem, we demonstrate a novel attack that enables an attacker to correctly classify images from ImageNet by observing only the timing of GPU kernel execution, rather than the images themselves. Telekine enables applications to use GPU acceleration in the cloud securely, based on a novel GPU stream abstraction that ensures execution and interaction through untrusted components are independent of any secret data. Given a GPU with support for a TEE, Telekine employs a novel variant of API remoting to partition application-level software into components to ensure secret-dependent behaviors occur only on trusted components. Telekine can securely train modern image recognition models on MXNet with 10%–22% performance penalty relative to an insecure baseline with a locally attached GPU. It runs graph algorithms using Galois on one and two GPUs with 18%–41% overhead.
more »
« less
- Award ID(s):
- 1900457
- PAR ID:
- 10188585
- Date Published:
- Journal Name:
- 17th USENIX Symposium on Networked Systems Design and Implementation
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The demand for Deep Neural Network (DNN) execution (including both inference and training) on mobile system-on-a-chip (SoCs) has surged, driven by factors like the need for real-time latency, privacy, and reducing vendors’ costs. Mainstream mobile GPUs (e.g., Qualcomm Adreno GPUs) usually have a 2.5D L1 texture cache that offers throughput superior to that of on-chip memory. However, to date, there is limited understanding of the performance features of such a 2.5D cache, which limits the optimization potential. This paper introduces TMModel, a framework with three components: 1) a set of micro-benchmarks and a novel performance assessment methodology to characterize a non-well-documented architecture with 2D memory, 2) a complete analytical performance model configurable for different data access pattern(s), tiling size(s), and other GPU execution parameters for a given operator (and associated size and shape), and 3) a compilation framework incorporating this model and generating optimized code with low overhead. TMModel is validated both on a set of DNN kernels and for training complete models on a mobile GPU, and compared against both popular mobile DNN frameworks and another GPU performance model. Evaluation results demonstrate that TMModel outperforms all baselines, achieving 1.48 − 3.61× speedup on individual kernels and 1.83 − 66.1× speedup for end-to-end on-device training with only 0.25% − 18.5% the tuning cost of the baselines.more » « less
-
The demand for Deep Neural Network (DNN) execution (including both inference and training) on mobile system-ona-chip (SoCs) has surged, driven by factors like the need for real-time latency, privacy, and reducing vendors’ costs. Mainstream mobile GPUs (eg, Qualcomm Adreno GPUs) usually have a 2.5 D L1 texture cache that offers throughput superior to that of on-chip memory. However, to date, there is limited understanding of the performance features of such a 2.5 D cache, which limits the optimization potential. This paper introduces TMModel, a framework with three components: 1) a set of micro-benchmarks and a novel performance assessment methodology to characterize a non-well-documented architecture with 2D memory, 2) a complete analytical performance model configurable for different data access pattern (s), tiling size (s), and other GPU execution parameters for a given operator (and associated size and shape), and 3) a compilation framework incorporating this model and generating optimized code with low overhead. TMModel is validated both on a set of DNN kernels and for training complete models on mobile GPU.more » « less
-
The demand for Deep Neural Network (DNN) execution (including both inference and training) on mobile system-ona-chip (SoCs) has surged, driven by factors like the need for real-time latency, privacy, and reducing vendors’ costs. Mainstream mobile GPUs (eg, Qualcomm Adreno GPUs) usually have a 2.5 D L1 texture cache that offers throughput superior to that of on-chip memory. However, to date, there is limited understanding of the performance features of such a 2.5 D cache, which limits the optimization potential. This paper introduces TMModel, a framework with three components: 1) a set of micro-benchmarks and a novel performance assessment methodology to characterize a non-well-documented architecture with 2D memory, 2) a complete analytical performance model configurable for different data access pattern (s), tiling size (s), and other GPU execution parameters for a given operator (and associated size and shape), and 3) a compilation framework incorporating this model and generating optimized code with low overhead. TMModel is validated both on a set of DNN kernels and for training complete models on mobile GPU.more » « less
-
Abstract Cloud microphysics is one of the most time‐consuming components in a climate model. In this study, we port the cloud microphysics parameterization in the Community Atmosphere Model (CAM), known as Parameterization of Unified Microphysics Across Scales (PUMAS), from CPU to GPU to seek a computational speedup. The directive‐based methods (OpenACC and OpenMP target offload) are determined as the best fit specifically for our development practices, which enable a single version of source code to run either on the CPU or GPU, and yield a better portability and maintainability. Their performance is first examined in a PUMAS stand‐alone kernel and the directive‐based methods can outperform a CPU node as long as there is enough computational burden on the GPU. A consistent behavior is observed when we run PUMAS on the GPU in a practical CAM simulation. A 3.6× speedup of the PUMAS execution time, including data movement between CPU and GPU, is achieved at a coarse horizontal resolution (8 NVIDIA V100 GPUs against 36 Intel Skylake CPU cores). This speedup further increases up to 5.4× at a high resolution (24 NVIDIA V100 GPUs against 108 Intel Skylake CPU cores), which highlights the fact that GPU favors larger problem size. This study demonstrates that using GPU in a CAM simulation can save noticeable computational costs even with a small portion of code being GPU‐enabled. Therefore, we are encouraged to port more parameterizations to GPU to take advantage of its computational benefit.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
