MOTIVATION: Advances in DNA sequencing have outpaced advances in computation, making sequence alignment a major bottleneck in genome data analyses. Classical dynamic programming (DP) algorithms are particularly memory-intensive, especially when computing gap-affine and dual gap-affine alignments. Existing strategies to reduce memory consumption often sacrifice speed or alignment accuracy. RESULTS: We present Singletrack, an efficient algorithm for backtrace gap-affine and dual gap-affine alignments that requires storing a single DP matrix while preserving optimal alignment results. Compared to classical DP algorithms, Singletrack removes the need to store additional matrices (i.e. 2 for gap-affine and 4 for dual gap-affine), significantly reducing memory consumption and, in turn, reducing pressure on the memory hierarchy and improving overall performance. Most importantly, Singletrack is a general backtrace method compatible with state-of-the-art DP-based algorithms and heuristics, such as the Suzuki-Kasahara (SK) and the Wavefront Alignment (WFA) algorithms. We demonstrate that Singletrack reduces memory consumption for both SK and WFA algorithms, lowering SK usage by 2× and 4× and WFA usage by 3× and 5× for gap-affine and dual gap-affine alignments, respectively. Moreover, replacing KSW2's memory-reduction technique with Singletrack accelerates its SK implementation by up to 1.4× at the cost of doubling memory consumption, while Singletrack increases the performance of the WFA implementation in WFA2-lib by 1.2-2.1×. Compared to the efficient linear-memory BiWFA algorithm, the Singletrack-accelerated version of WFA trades a practical increase in memory usage for up to 5.2× higher performance. AVAILABILITY AND IMPLEMENTATION: The Singletrack implementations presented in this work are available on Zenodo (DOI: 10.5281/zenodo.18770585) and GitHub (https://github.com/LorienLV/singletrack).

Multiple HPC applications are often bottlenecked by compute-intensive kernels implementing complex dependency patterns (data-dependency bound). Traditional general-purpose accelerators struggle to effectively exploit fine-grain parallelism due to limitations in implementing convoluted data-dependency patterns (like SIMD) and overheads due to synchronization and data transfers (like GPGPUs). In contrast, custom FPGA and ASIC designs offer improved performance and energy efficiency at a high cost in hardware design and programming complexity and often lack the flexibility to process different workloads. We propose Squire, a general-purpose accelerator designed to exploit fine-grain parallelism effectively on dependency-bound kernels. Each Squire accelerator has a set of general-purpose low-power in-order cores that can rapidly communicate among themselves and directly access data from the L2 cache. Our proposal integrates one Squire accelerator per core in a typical multicore system, allowing the acceleration of dependency-bound kernels within parallel tasks with minimal software changes. As a case study, we evaluate Squire’s effectiveness by accelerating five kernels that implement complex dependency patterns. We use three of these kernels to build an end-to-end read-mapping tool that will be used to evaluate Squire. Squire obtains speedups up to $7.64 \times$ in dynamic programming kernels. Overall, Squire provides an acceleration for an end-to-end application of $3.66 \times$. In addition, Squire reduces energy consumption by up to 56% with a minimal area overhead of $\mathbf{1 0. 5 \%}$ compared to a NeoverseN1 baseline.

Data prefetching is crucial for performance in modern processors by effectively masking long-latency memory accesses. Over the past decades, numerous data prefetching mechanisms have been proposed, which have continuously reduced the access latency to the memory hierarchy. Several state-of-the-art prefetchers, namely Instruction Pointer Classifier Prefetcher (IPCP) and Berti, target the first-level data cache, and thus, they are able to completely hide the miss latency for timely prefetched cache lines. Berti exploits timely local deltas to achieve high accuracy and performance. This paper extends Berti with a larger evaluation and with extra optimizations on top of the previous conference paper. The result is a complexity-effective version of Berti that outperforms it for a large amount of workloads and simplifies its control logic. The key for those advancements is a simple mechanism for learning timely deltas without the need to track the fetch latency of each cache miss. Our experiments conducted with a wide range of workloads (CVP traces by Qualcomm, SPEC CPU2017, and GAP) show performance improvements by 4.0% over a mainstream stride prefetcher, and by a non-negligible 1.4% over the previously published version of Berti requiring similar storage.

Arm usage has substantially grown in the High-Performance Computing (HPC) community. Japanese supercomputer Fugaku, powered by Arm-based A64FX processors, held the top position on the Top500 list between June 2020 and June 2022, currently sitting in the fourth position. The recently released 7th generation of Amazon EC2 instances for compute-intensive workloads (C7 g) is also powered by Arm Graviton3 processors. Projects like European Mont-Blanc and U.S. DOE/NNSA Astra are further examples of Arm irruption in HPC. In parallel, over the last decade, the rapid improvement of genomic sequencing technologies and the exponential growth of sequencing data has placed a significant bottleneck on the computational side. While most genomics applications have been thoroughly tested and optimized for x86 systems, just a few are prepared to perform efficiently on Arm machines. Moreover, these applications do not exploit the newly introduced Scalable Vector Extensions (SVE). This paper presents GenArchBench, the first genome analysis benchmark suite targeting Arm architectures. We have selected computationally demanding kernels from the most widely used tools in genome data analysis and ported them to Arm-based A64FX and Graviton3 processors. Overall, the GenArch benchmark suite comprises 13 multi-core kernels from critical stages of widely-used genome analysis pipelines, including base-calling, read mapping, variant calling, and genome assembly. Our benchmark suite includes different input data sets per kernel (small and large), each with a corresponding regression test to verify the correctness of each execution automatically. Moreover, the porting features the usage of the novel Arm SVE instructions, algorithmic and code optimizations, and the exploitation of Arm-optimized libraries. We present the optimizations implemented in each kernel and a detailed performance evaluation and comparison of their performance on four different HPC machines (i.e., A64FX, Graviton3, Intel Xeon Skylake Platinum, and AMD EPYC Rome). Overall, the experimental evaluation shows that Graviton3 outperforms other machines on average. Moreover, we observed that the performance of the A64FX is significantly constrained by its small memory hierarchy and latencies. Additionally, as proof of concept, we study the performance of a production-ready tool that exploits two of the ported and optimized genomic kernels.

Sequence alignment pipelines for human genomes are an emerging workload that will dominate in the precision medicine field. BWA-MEM2 is a tool widely used in the scientific community to perform read mapping studies. In this paper, we port BWA-MEM2 to the AArch64 architecture using the ARMv8-A specification, and we compare the resulting version against an Intel Skylake system both in performance and in energy-to-solution. The porting effort entails numerous code modifications, since BWA-MEM2 implements certain kernels using x86_64 specific intrinsics, e.g., AVX-512. To adapt this code we use the recently introduced Arm's Scalable Vector Extensions (SVE). More specifically, we use Fujitsu's A64FX processor, the first to implement SVE. The A64FX powers the Fugaku Supercomputer that led the Top500 ranking from June 2020 to November 2021. After porting BWA-MEM2 we define and implement a number of optimizations to improve performance in the A64FX target architecture. We show that while the A64FX performance is lower than that of the Skylake system, A64FX delivers 11.6% better energy-to-solution on average. All the code used for this article is available at https://gitlab.bsc.es/rlangari/bwa-a64fx.

Abstract The management of shared resources in multicore processors is an open problem due to the continuous evolution of these systems. The trend toward increasing the number of cores and organizing them in clusters sets out new challenges not considered in previous works. In this paper, we characterize the use of the shared cache and memory bandwidth of an AMD Rome processor executing multiprogrammed workloads and propose several mechanisms that control the use of these resources to improve the system performance and fairness. Our control mechanisms require no hardware or operating system modifications. We evaluate Balancer on a real system running SPEC CPU2006 and CPU2017 applications. Balancer tuned for performance shows an average increase of 7.1% in system performance and an unfairness reduction of 18.6% with respect to a system without any control mechanism. Balancer tuned for fairness decreases the performance by 1.3% in exchange for a 64.5% reduction of unfairness.

Data prefetching is a technique that plays a crucial role in modern high-performance processors by hiding long latency memory accesses. Several state-of-the-art hardware prefetchers exploit the concept of deltas, defined as the difference between the cache line addresses of two demand accesses. Existing delta prefetchers, such as best offset prefetching (BOP) and multi-lookahead prefetching (MLOP), train and predict future accesses based on global deltas. We observed that the use of global deltas results in missed opportunities to anticipate memory accesses.In this paper, we propose Berti, a first-level data cache prefetcher that selects the best local deltas, i.e., those that consider only demand accesses issued by the same instruction. Thanks to a high-confidence mechanism that precisely detects the timely local deltas with high coverage, Berti generates accurate prefetch requests. Then, it orchestrates the prefetch requests to the memory hierarchy, using the selected deltas.Our empirical results using ChampSim and SPEC CPU2017 and GAP workloads show that, with a storage overhead of just 2.55 KB, Berti improves performance by 8.5% compared to a baseline IP-stride and 3.5% compared to IPCP, a state-of-the-art prefetcher. Our evaluation also shows that Berti reduces dynamic energy at the memory hierarchy by 33.6% compared to IPCP, thanks to its high prefetch accuracy.

The FM-index is a data structure used in genomics for exact search of input sequences over large reference genomes. Algorithms based on the FM-index show an irregular memory access pattern, resulting in a memory bound problem. We analyze a recent implementation of the FM-index and highlight existing throughput-memory trade-offs, showing that memory requirements limit implementation of large k-steps. We propose COFI, a COmpressed FM-Index for large K-steps. COFI enables a 15-step FM-index using less than 16 GB for a human genome reference of 3 giga base pairs. An algorithm based on this new layout is evaluated on both a Knights Landing (KNL) and an Skylake-based system (SKX). We achieve average speed-ups of 1.46× and 1.39×, respectively, with respect to an state-of-the-art FM-index implementation that is already well optimized.

The complexity of efficient synchronization design increases with the continuous growth in the number of physical and logical cores on today's machines. Opinion is divided on which synchronization strategy is more powerful, opposing typical mechanisms, such as locks and atomic primitives, to emergent technologies, like transactional memory. We perform an extensive scalability study on many-core systems, evaluating most widely-used synchronization mechanisms in terms of application throughput and operation latency. We show that, from a performance perspective, current best-effort implementations of hardware transactional memory (HTM) are comparable to well-established locking or lock-free mechanisms. We also find that they scale better with the number of threads. We then showcase the ease-of-use of HTM in real-life applications. Finally, we analyze the impact of simultaneous multithreading (SMT) technologies on HTM performance. We propose a new cache replacement strategy that takes into account the transactional state of each cache line and aims to mitigate SMT-induced transactional overflow aborts.

FM-index is a compact data structure suitable for fast matches of short reads to large reference genomes. The matching algorithm using this index exhibits irregular memory access patterns that cause frequent cache misses, resulting in a memory bound problem. This paper analyzes different FM-index versions presented in the literature, focusing on those computing aspects related to the data access. As a result of the analysis, we propose a new organization of FM-index that minimizes the demand for memory bandwidth, allowing a great improvement of performance on processors with high-bandwidth memory, such as the second-generation Intel Xeon Phi (Knights Landing, or KNL), integrating ultra high-bandwidth stacked memory technology. As the roofline model shows, our implementation reaches 95 percent of the peak random access bandwidth limit when executed on the KNL and almost all of the available bandwidth when executed on other Intel Xeon architectures with conventional DDR memory. In addition, the obtained throughput in KNL is much higher than the results reported for GPUs in the literature.

The rapid development of DNA sequencing technologies has demanded for compressed data structures supporting fast pattern matching queries. FM-index is a widely-used compressed data structure that also supports fast pattern matching queries. It is common for the exact matching algorithm to be memory bound, resulting in poor performance. We propose a new data-layout of FM-index that compacts all data needed to perform the searching process. This results in an improvement of the search computing time for genomic data.

Scaling supply voltage to values near the threshold voltage allows a dramatic decrease in the power consumption of processors; however, the lower the voltage, the higher the sensitivity to process variation, and, hence, the lower the reliability. Large SRAM structures, like the last-level cache (LLC), are extremely vulnerable to process variation because they are aggressively sized to satisfy high density requirements. In this paper, we propose Concertina, an LLC designed to enable reliable operation at low voltages with conventional SRAM cells. Based on the observation that for many applications the LLC contains large amounts of null data, Concertina compresses cache blocks in order that they can be allocated to cache entries with faulty cells, enabling use of 100 percent of the LLC capacity. To distribute blocks among cache entries, Concertina implements a compression- and fault-aware insertion/replacement policy that reduces the LLC miss rate. Concertina reaches the performance of an ideal system implementing an LLC that does not suffer from parameter variation with a modest storage overhead. Specifically, performance degrades by less than 2 percent, even when using small SRAM cells, which implies over 90 percent of cache entries having defective cells, and this represents a notable improvement on previously proposed techniques.

Power density has become the limiting factor in technology scaling as power budget restricts the amount of hardware that can be active at the same time. Reducing supply voltage to ultra-low voltage ranges close to the threshold region has the promise of great energy savings. However, the potential savings of voltage scaling are limited by the correct operation of SRAM cells, which is not guaranteed below Vddmin, the minimum voltage in which cache structures operate reliably. Understanding the effects of operating below Vddmin requires complex modelling, so we introduce an updated probability failure model of SRAM cells at 22nm and explore the reliability impact of lowering the chip voltage supply below Vddmin in shared memory coherent chip-multiprocessors (CMP) running a variety of parallel workloads. A micro architectural technique to cope with cache reliability at ultra-low voltages is block disabling, however, in many cases, the savings in on-chip caches do not compensate for the consumption in the rest of the system, as the consumption increase of the off-chip memory may offset the on-chip gain. We make the case that existing coherence mechanisms can provide the substrate to improve energy savings with block disabling and propose two low-complexity techniques. Taking the best of both techniques we can scale voltage below Vddmin and reduce system energy up to 39%, and system energy-delay up to 10%. Besides, by lowering the CMP consumption in a power constrained scenario, we could activate offline cores, reaching a potential speedup between 3.7 and 4.4.

The performance impact of the Physical Register File(PRF) size on Simultaneous Multithreading processors has not been extensively studied in spite of being a critical shared resource. In this paper we analyze the effect on performance of the PRF size for a broad set of resource allocation policies (Icount, Stall, Flush, Flush++, Static,Dcra and Hill-climbing) and evaluate them under two metrics: instructions per second (IPS) for throughput and harmonic mean of weighted IPCs (Hmean-wIPC) for fairness. We have found that resource allocation policy and PRF size should be considered together in order to obtain the best score in the proposed metrics. For instance, for the analyzed 2 and 4-threaded SPEC CPU2000 workloads,small PRFs are best managed by Flush, whereas for larger PRFs, Hill-climbing and Static lead to the best values for the throughput and fairness metrics, respectively.The second contribution of this work is a simple procedure that, for a given resource allocation policy, selects the PRF size that maximizes IPS and obtains for Hmean-wIPC a value close to its maximum. According to our results, Hill-climbing with a 320-entry PRF achieves the best figures for 2-threaded workloads. When executing 4-threaded workloads, Hill-Climbing with a 384-entry PRF achieves the best throughput whereas Static obtains the best throughput-fairness balance.

This paper proposes and evaluates a new microarchitecture for out-of-order processors that supports speculative renaming. We call speculative renaming to the speculative omission of physical register allocation along with the speculative early release of physical registers. These renaming policies may cause a register operand not to be kept in the physical register file (PRF). Thus, we add a low-ported auxiliary register file (XRF) located outside the processor core that keeps the values absent in PRF and supplies them at higher latency. To support the location of register operands being either in PRF or XRF, we use virtual registers. We consider omission and release policies directed by hardware prediction. Namely, we use a single last-use predictor that directs both speculative omission and release. We call this mechanism SR-LUP (speculative renaming based on last-use prediction). Two last-use predictor designs of incremental complexity and performance are analyzed. In a 256-ROB, 8-way processor with an 80int+80fp PRF, SR-LUP with an 11-port 256int+256fp XRF, speeds up computations up to 11.5% and 29% for INT and FP SPEC2K benchmarks, respectively. For FP benchmarks, if the PRF limits the clock frequency, a conventionally managed 128int+128fp PRF can be replaced using SR-LUP by a 64int+64fp PRF backed up with a 10-port 224int+224fp XRF, showing 19% IPS gain.