The disparity between processor speed and memory bandwidth has become a growing performance bottleneck, particularly for memory-intensive workloads. Processing-in-Memory (PIM) mitigates this bottleneck by integrating computation directly within DRAM. However, the effectiveness of PIM varies significantly across workloads, architectures, and DRAM technologies, yet it is often assessed using tightly coupled simulators and benchmarks that lack portability and generality. This article extends PIMbench and PIMeval —a generalizable benchmark suite and an extensible PIM simulator to support a broader range of workloads, PIM architectures, and DRAM technologies. This evaluation incorporates roofline analysis and a breakdown of intra-memory execution stages to identify PIM-specific bottlenecks and performance scaling limits. The evaluation spans three classes of digital PIM architectures: subarray-level bit-serial, subarray-level bit-parallel, and bank-level bit-parallel. It further demonstrates how internal DRAM parameters such as subarray count and GDL width impact PIM performance. The code is publicly available at: https://github.com/UVA-LavaLab/PIMeval-PIMbench .

Motivated by the memory wall problem, researchers propose many new Processing-in-Memory (PiM) architectures to bring computation closer to data. However, evaluating the performance of these emerging architectures involves using a myriad of tools, including circuit simulators, behavioral RTL or software simulation models, hardware approximations, etc. It is challenging to mimic both software and hardware aspects of a PiM architecture using the currently available tools with high performance and fidelity. Until and unless actual products that include PiM become available, the next best thing is to emulate various hardware PiM solutions on FPGA fabric and boards. This paper presents a modular, parameterizable, FPGA synthesizable soft PiM model suitable for prototyping and rapid evaluation of Processing-in-Memory architectures. The PiM model is implemented in System Verilog and allows users to generate any desired memory configuration on the FPGA fabric with complete control over the structure and distribution of the PiM logic units. Moreover, the model is compatible with the LiteX framework, which provides a high degree of usability and compatibility with the FPGA and RISC-V ecosystem. Thus, the framework enables architects to easily prototype, emulate and evaluate a wide range of emerging PiM architectures and designs. We demonstrate strategies to model several pioneering bitwise-PiM architectures and provide detailed benchmark performance results that demonstrate the platform's ability to facilitate design space exploration. We observe an emulation vs. simulation weighted-average speedup of 28× when running a memory benchmark workload. The model can utilize 100% BRAM and only 1% FF and LUT of an Alveo U280 FPGA board. The project is entirely open-source.

Processing-in-memory (PIM) minimizes data movement overheads by placing processing units near each memory segment. Recent PIMs employ processing units with a SIMD architecture. However, kernels with random accesses, such as sparse-matrix-dense-vector (SpMV) and sparse-matrix-sparse-vector (SpMSpV), cannot effectively exploit the parallelism of SIMD units because SIMD's ALUs remain idle until all the operands are collected from local memory segments (memory segment attached to the processing unit) or remote memory segments (other segments of the memory).

Coverage-guided fuzzing is a powerful technique for finding security vulnerabilities and latent bugs in software. Such fuzzers usually store the coverage information in a small bitmap. Hash collision within this bitmap is a well-known issue and can reduce fuzzers' ability to discover potential bugs. Prior works noted that collision mitigation with naïvely enlarging the hash space leads to an unacceptable runtime overhead. This paper describes BigMap, a two-level hashing scheme that enables using an arbitrarily large coverage_bitmap with low overhead. The key observation is that the overhead stems from frequent operations performed on the full bitmap, although only a fraction of the map is actively used. BigMap condenses these scattered active regions on a second bitmap and limits the operations only on that condensed area. We implemented our approach on top of the popular fuzzer AFL and conducted experiments on 19 benchmarks from FuzzBench and OSS-Fuzz. The results indicate that BigMap does not suffer from increased runtime overhead even with large map sizes. Compared to AFL, BigMap achieved an average of 4.5x higher test case generation throughput for a 2MB map and 33.1x for an 8MB map. The throughput gain for the 2MB map increased further to 9.2x with parallel fuzzing sessions, indicating superior scalability of BigMap. More importantly, BigMap's compatibility with most coverage metrics, along with its efficiency on bigger maps, enabled exploring aggressive compositions of expensive coverage metrics and fuzzing algorithms, uncovering 33% more unique crashes. BigMap makes using large bitmaps practical and enables researchers to explore a wider design space of coverage metrics

Simulation is widely used for validation of Register-Transfer-Level (RTL) models. While simulating with millions of random (or constrained-random) tests can cover majority of the targets (functional scenarios), the number of remaining targets can still be huge (hundreds or thousands) in case of today's industrial designs. Prior work on directed test generation using concolic testing can cover only one target at a time. A naive extension of prior work to activate the remaining targets would be infeasible due to wasted effort in multiple overlapping searches. In this paper, we propose an automated test generation technique for activating multiple targets in RTL models using concolic testing. This paper makes three important contributions. First, it efficiently prunes the targets that can be covered by the tests generated for activating the other targets. Next, it minimizes the overlapping searches while trying to generate tests for activating multiple targets. Finally, our approach effectively utilizes clustering of related targets as well as common path sharing between the targets in the same cluster to drastically reduce the test generation time. Experimental results demonstrate that our approach significantly outperforms the existing methods in terms of overall coverage (up to 5X, 1.2X on average) as well as test generation time (up to 146X, 80X on average).

Dynamic cache reconfiguration has been widely explored for energy optimization and performance improvement for single-core systems. Cache partitioning techniques are introduced for the shared cache in multicore systems to alleviate inter-core interference. While these techniques focus only on performance and energy, they ignore vulnerability due to soft errors. In this article, we present a static profiling based algorithm to enable vulnerability-aware energy-optimization for real-time multicore systems. Our approach can efficiently search the space of cache configurations and partitioning schemes for energy optimization while task deadlines and vulnerability constraints are satisfied. A machine learning technique has been employed to minimize the static profiling time without sacrificing the accuracy of results. Our experimental results demonstrate that our approach can achieve 19.2% average energy savings compared with the base configuration, while drastically reducing the vulnerability (49.3% on average) compared to state-of-the-art techniques. Furthermore, the machine learning technique enabled more than 10x speedup in static profiling time with a negligible prediction error of 3%.

Dynamic cache reconfiguration (DCR) is an effective technique to optimize energy consumption in many-core architectures. While early work on DCR has shown promising energy saving opportunities, prior techniques are not suitable for many-core architectures since they do not consider the interactions and tight coupling between memory, caches, and network-on-chip (NoC) traffic. In this article, we propose an efficient cache reconfiguration framework in NoC-based many-core architectures. The proposed work makes three major contributions. First, we model a distributed directory based many-core architecture similar to Intel Xeon Phi architecture. Next, we propose an efficient cache reconfiguration framework that considers all significant components, including NoC, caches, and main memory. Finally, we propose a machine learning--based framework that can reduce the exploration time by an order of magnitude with negligible loss in accuracy. Our experimental results demonstrate 18.5% energy savings on average compared to base cache configuration.

Functional validation is one of the most time consuming steps in System-on-Chip (SoC) design methodology. In today's industrial practice, simulating designs using billions of random or constrained-random tests can lead to high functional coverage. However, it is hard to cover the remaining small fraction of corner cases and rare functional scenarios. While formal methods are promising in such cases, it is infeasible to apply them on large designs. In this paper, we propose a fully automated and scalable approach for generating directed tests using concolic testing of RTL models. While application of concolic testing on hardware designs has shown some promising results, existing approaches are tuned for improving overall coverage, rather than covering a specific target. We developed a Control Flow Graph (CFG) assisted directed test generation method that can efficiently generate a test to activate a given target. Our experimental results demonstrate that our approach is both efficient and scalable compared to the state-of-the-art test generation methods.

Intellectual Property (IP) based System-on-Chip (SoC) design is a widely used practice today. The IPs gathered from third-party vendors may not be trustworthy since they may contain malicious implants (hardware Trojans). To avoid the detection of the Trojan, adversaries usually hide it under rare branches or rare assignments triggered under extremely rare input sequences. Due to exponential input space complexity, state-of-the-art constrained-random test generation methods are not suitable for activating these rare scenarios. While existing model checking based directed test generation approaches are promising, they are not capable of generating tests for large RTL designs due to the capacity restrictions of formal methods. In this paper, we propose an automated and scalable test generation approach for activation of hardware Trojans in RTL designs. This paper makes three important contributions. First, it provides a scalable test generation framework by effective utilization of symbolic execution and concrete simulation. Next, it is a fully automated approach for generating directed tests for activating rare branches and rare assignments. Finally, our experimental results demonstrate that the generated tests are able to activate hard-to-cover Trojans in large and complex RTL benchmarks.

Input vector generation is an important step during validation and debugging of hardware designs. Validation using random and directed random tests are widely used today. However, these methods can lead to unacceptable functional coverage under tight deadlines. Concolic testing is a semi-formal method to address this issue. It combines concrete simulation guided by symbolic execution. Application of concolic testing in hardware domain is still in its infancy due to the lack of effective traversal strategies. In this paper, we present Qualifying Event Based Search (QUEBS) heuristic for concolic testing. During exhaustive concolic testing, same branch may be selected many times for traversal. Our heuristic limits the number of times a branch can be selected. By preventing repeated selection, it facilitates wider coverage within limited time. Also, whenever a previously uncovered branch is encountered, this limit is relaxed to permit thorough exploration of the newly reached area. Our experimental results demonstrate that this approach provides better branch coverage than state-of-the-art test generation methods in a given time budget. To further improve the performance of QUEBS, we provide two optimization techniques - unsolvable branch elimination and incremental solving by context reuse.