Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSpecial Session: Reliability Analysis for ML/AI Hardware
124
0
0.0
(
0
)
Added by
Anup Das
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Artificial intelligence (AI) and Machine Learning (ML) are becoming pervasive in todays applications, such as autonomous vehicles, healthcare, aerospace, cybersecurity, and many critical applications. Ensuring the reliability and robustness of the underlying AI/ML hardware becomes our paramount importance. In this paper, we explore and evaluate the reliability of different AI/ML hardware. The first section outlines the reliability issues in a commercial systolic array-based ML accelerator in the presence of faults engendering from device-level non-idealities in the DRAM. Next, we quantified the impact of circuit-level faults in the MSB and LSB logic cones of the Multiply and Accumulate (MAC) block of the AI accelerator on the AI/ML accuracy. Finally, we present two key reliability issues -- circuit aging and endurance in emerging neuromorphic hardware platforms and present our system-level approach to mitigate them.
rate research
Read More
Customized hardware accelerators have been developed to provide improved performance and efficiency for DNN inference and training. However, the existing hardware accelerators may not always be suitable for handling various DNN models as their architecture paradigms and configuration tradeoffs are highly application-specific. It is important to benchmark the accelerator candidates in the earliest stage to gather comprehensive performance metrics and locate the potential bottlenecks. Further demands also emerge after benchmarking, which require adequate solutions to address the bottlenecks and improve the current designs for targeted workloads. To achieve these goals, in this paper, we leverage an automation tool called DNNExplorer for benchmarking customized DNN hardware accelerators and exploring novel accelerator designs with improved performance and efficiency. Key features include (1) direct support to popular machine learning frameworks for DNN workload analysis and accurate analytical models for fast accelerator benchmarking; (2) a novel accelerator design paradigm with high-dimensional design space support and fine-grained adjustability to overcome the existing design drawbacks; and (3) a design space exploration (DSE) engine to generate optimized accelerators by considering targeted AI workloads and available hardware resources. Results show that accelerators adopting the proposed novel paradigm can deliver up to 4.2X higher throughput (GOP/s) than the state-of-the-art pipeline design in DNNBuilder and up to 2.0X improved efficiency than the recently published generic design in HybridDNN given the same DNN model and resource budgets. With DNNExplorers benchmarking and exploration features, we can be ahead at building and optimizing customized AI accelerators and enable more efficient AI applications.
Hardware flaws are permanent and potent: hardware cannot be patched once fabricated, and any flaws may undermine any software executing on top. Consequently, verification time dominates implementation time. The gold standard in hardware Design Verification (DV) is concentrated at two extremes: random dynamic verification and formal verification. Both struggle to root out the subtle flaws in complex hardware that often manifest as security vulnerabilities. The root problem with random verification is its undirected nature, making it inefficient, while formal verification is constrained by the state-space explosion problem, making it infeasible against complex designs. What is needed is a solution that is directed, yet under-constrained. Instead of making incremental improvements to existing DV approaches, we leverage the observation that existing software fuzzers already provide such a solution, and adapt them for hardware DV. Specifically, we translate RTL hardware to a software model and fuzz that model. The central challenge we address is how best to mitigate the differences between the hardware execution model and software execution model. This includes: 1) how to represent test cases, 2) what is the hardware equivalent of a crash, 3) what is an appropriate coverage metric, and 4) how to create a general-purpose fuzzing harness for hardware. To evaluate our approach, we fuzz four IP blocks from Googles OpenTitan SoC. Our experiments reveal a two orders-of-magnitude reduction in run time to achieve Finite State Machine (FSM) coverage over traditional dynamic verification schemes. Moreover, with our design-agnostic harness, we achieve over 88% HDL line coverage in three out of four of our designs -- even without any initial seeds.
Programmable switches have emerged as powerful and flexible alternatives to fixed-function forwarding devices. But because of the unique hardware constraints of network switches, the design and implementation of compilers targeting these devices is tedious and error prone. Despite the important role that compilers play in software development, there is a dearth of tools for testing compilers for programmable network devices. We present Druzhba, a programmable switch simulator used for testing compilers targeting programmable packet-processing substrates. We show that we can model the low-level behavior of a switchs programmable hardware. We further show how our machine model can be used by compiler developers to target Druzhba as a compiler backend. Generated machine code programs are fed into Druzhba and tested using a fuzzing-based approach that allows compiler developers to test the correctness of their compilers. Using a program-synthesis-based compiler as a case study, we demonstrate how Druzhba has been successful in testing compiler-generated machine code for our simulated switch pipeline instruction set.
The current mobile applications have rapidly growing memory footprints, posing a great challenge for memory system design. Insufficient DRAM main memory will incur frequent data swaps between memory and storage, a process that hurts performance, consumes energy and deteriorates the write endurance of typical flash storage devices. Alternately, a larger DRAM has higher leakage power and drains the battery faster. Further, DRAM scaling trends make further growth of DRAMin the mobile space prohibitive due to cost. Emerging non-volatile memory (NVM) has the potential to alleviate these issues due to its higher capacity per cost than DRAM and mini-mal static power. Recently, a wide spectrum of NVM technologies, including phase-change memories (PCM), memristor, and 3D XPoint have emerged. Despite the mentioned advantages, NVM has longer access latency compared to DRAMand NVM writes can incur higher latencies and wear costs. Therefore integration of these new memory technologies in the memory hierarchy requires a fundamental rearchitect-ing of traditional system designs. In this work, we propose a hardware-accelerated memory manager (HMMU) that addresses both types of memory in a flat space address space. We design a set of data placement and data migration policies within this memory manager, such that we may exploit the advantages of each memory technology. By augmenting the system with this HMMU, we reduce the overall memory latency while also reducing writes to the NVM. Experimental results show that our design achieves a 39% reduction in energy consumption with only a 12% performance degradation versus an all-DRAM baseline that is likely untenable in the future.
Polar codes are a class of linear block codes that provably achieves channel capacity. They have been selected as a coding scheme for the control channel of enhanced mobile broadband (eMBB) scenario for $5^{text{th}}$ generation wireless communication networks (5G) and are being considered for additional use scenarios. As a result, fast decoding techniques for polar codes are essential. Previous works targeting improved throughput for successive-cancellation (SC) decoding of polar codes are semi-parallel implementations that exploit special maximum-likelihood (ML) nodes. In this work, we present a new fast simplified SC (Fast-SSC) decoder architecture. Compared to a baseline Fast-SSC decoder, our solution is able to reduce the memory requirements. We achieve this through a more efficient memory utilization, which also enables to execute multiple operations in a single clock cycle. Finally, we propose new special node merging techniques that improve the throughput further, and detail a new Fast-SSC-based decoder architecture to support merged operations. The proposed decoder reduces the operation sequence requirement by up to $39%$, which enables to reduce the number of time steps to decode a codeword by $35%$. ASIC implementation results with 65 nm TSMC technology show that the proposed decoder has a throughput improvement of up to $31%$ compared to previous Fast-SSC decoder architectures.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
