Adrian Cristal

Barcelona Supercomputing Center

This paper explores the implications of employing non-volatile memory (NVM) as primary storage for a data base management system (DBMS). We investigate the modifications necessary to be applied on top of a traditional relational DBMS to take advantage of NVM features. As a case study, we modify the storage engine (SE) of PostgreSQL enabling efficie...

Ensemble data assimilation techniques form an indispensable part of numerical weather prediction. As the ensemble size grows and model resolution increases, the amount of required storage becomes a major issue. Data compression schemes may come to the rescue not only for operational weather prediction, but also for weather history archives. In this...

High-Performance Computing (HPC) systems are designed for large-scale processing and complex dataset analysis leveraging scalability, efficiency, and parallelism, often integrating specialized hardware structures such as Vector Processing Units (VPUs). As these systems have grown in complexity and scale, their vulnerability to errors and failures h...

Efficiently computing Deep Neural Networks (DNNs) has become a primary challenge in today’s computers, especially on devices targeting mobile or edge applications. Recent progress on Post-Training Quantization (PTQ) and Quantization- Aware Training (QAT) has shown that the key to high energy efficiency lies in executing deep learning models with lo...

La Red de Computación, es una de las doce redes institucionales de investigadores del Instituto Politécnico Nacional. Es una plataforma que promueve la colaboración entre profesores e investigadores del Instituto Politécnico Nacional a través del desarrollo de proyectos académicos, proyectos de investigación multidisciplinarios y proyectos de innov...

The maturity level of RISC-V and the availability of domain-specific instruction set extensions, like vector processing, make RISC-V a good candidate for supporting the integration of specialized hardware in processor cores for the High Performance Computing (HPC) application domain. In this paper, we present Vitruvius+, the vector processing accel...

Transactional Memory (TM) potentially simplifies parallel programming by providing atomicity and isolation for executed transactions. One of the key mechanisms to provide such properties is version management, which defines where and how transactional updates (new values) are stored. Version management can be implemented either eagerly or lazily. I...

This paper proposes a novel L1 data cache design with dual-versioning SRAM cells (dvSRAM) for chip multi-processors (CMP) that implement optimistic concurrency proposals. In this new cache architecture, each dvSRAM cell has two cells, a main cell and a secondary cell, which keep two versions of the same data. These values can be accessed, modified...

As more neural networks on field-programmable gate arrays (FPGAs) are used in a wider context, the importance of power efficiency increases. However, the focus on power should never compromise application accuracy. One technique to increase power efficiency is reducing the FPGAs’ supply voltage (“undervolting”), which can cause accuracy problems. T...

Ensemble data assimilation is a powerful tool for increasing the accuracy of climatological states. It is based on combining observations with the results from numerical model simulations. The method comprises two steps, (1) the propagation, where the ensemble states are advanced by the numerical model and (2) the analysis, where the model states a...

Modern scientific applications are getting more diverse, and the vector lengths in those applications vary widely. Contemporary Vector Processors (VPs) are designed either for short vector lengths, e.g., Fujitsu A64FX with 512-bit ARM SVE vector support, or long vectors, e.g., NEC Aurora Tsubasa with 16Kbits Maximum Vector Length (MVL). Unfortunate...

Vector architectures lack tools for research. Consider the gem5 simulator, which is possibly the leading platform for computer-system architecture research. Unfortunately, gem5 does not have an available distribution that includes a flexible and customizable vector architecture model. In consequence, researchers have to develop their own simulation...

On-chip memory (usually based on Static RAMs—SRAMs) are crucial components for various computing devices including heterogeneous devices, e.g., GPUs, FPGAs, and ASICs, to achieve high performance. Modern workloads such as deep neural networks (DNNs) running on these heterogeneous fabrics are highly dependent on the on-chip memory architecture for e...

On-chip memory (usually based on Static RAMs-SRAMs) are crucial components for various computing devices including heterogeneous devices, e.g., GPUs, FPGAs, ASICs to achieve high performance. Modern workloads such as Deep Neural Networks (DNNs) running on these heterogeneous fabrics are highly dependent on the on-chip memory architecture for effici...

Modern computing devices employ High-Bandwidth Memory (HBM) to meet their memory bandwidth requirements. An HBM-enabled device consists of multiple DRAM layers stacked on top of one another next to a compute chip (e.g. CPU, GPU, and FPGA) in the same package. Although such HBM structures provide high bandwidth at a small form factor, the stacked me...

The design presented in this paper, called preDRAC, is a RISC-V general purpose processor capable of booting Linux jointly developed by BSC, CIC-IPN, IMB-CNM (CSIC), and UPC. The preDRAC processor is the first RISC-V processor designed and fabricated by a Spanish or Mexican academic institution, and will be the basis of future RISC-V designs jointl...

Vector architectures lack tools for research. Consider the gem5 simulator, which is possibly the leading platform for computer-system architecture research. Unfortunately, gem5 does not have an available distribution that includes a flexible and customizable vector architecture model. In consequence, researchers have to develop their own simulation...

Modern large-scale computing systems (data centers, supercomputers, cloud and edge setups and high-end cyber-physical systems) employ heterogeneous architectures that consist of multicore CPUs, general-purpose many-core GPUs, and programmable FPGAs. The effective utilization of these architectures poses several challenges, among which a primary one...

In this paper, we exploit the aggressive supply voltage underscaling technique in Block RAMs (BRAMs) of Field Programmable Gate Arrays (FPGAs) to improve the energy efficiency of Multi-Layer Perceptrons (MLPs). Additionally, we evaluate and improve the resilience of this accelerator. Through experiments on several representative FPGA fabrics, we ob...

We empirically evaluate an undervolting technique, i.e., underscaling the circuit supply voltage below the nominal level, to improve the power-efficiency of Convolutional Neural Network (CNN) accelerators mapped to Field Programmable Gate Arrays (FPGAs). Undervolting below a safe voltage level can lead to timing faults due to excessive circuit late...

Modern large-scale computing systems (data centers, supercomputers, cloud and edge setups and high-end cyber-physical systems) employ heterogeneous architectures that consist of multicore CPUs, general-purpose many-core GPUs, and programmable FPGAs. The effective utilization of these architectures poses several challenges, among which a primary one...

Deep Neural Networks (DNNs) are inherently computation-intensive and also power-hungry. Hardware accelerators such as Field Programmable Gate Arrays (FPGAs) are a promising solution that can satisfy these requirements for both embedded and High-Performance Computing (HPC) systems. In FPGAs, as well as CPUs and GPUs, aggressive voltage scaling below...

This paper presents a deeply pipelined and massively parallel Binary Search Tree (BST) accelerator for Field Programmable Gate Arrays (FPGAs). Our design relies on the extremely parallel on-chip memory, or Block RAMs (BRAMs) architecture of FPGAs. To achieve significant throughput for the search operation on BST, we present several novel mechanisms...

The LEGaTO project leverages task-based programming models to provide a software ecosystem for Made in-Europe heterogeneous hardware composed of CPUs, GPUs, FPGAs and dataflow engines. The aim is to attain one order of magnitude energy savings from the edge to the converged cloud/HPC, balanced with the security and resilience challenges. LEGaTO is...

Modern large-scale computing systems (data centers, supercomputers, cloud and edge setups and high-end cyber-physical systems) employ heterogeneous architectures that consist of multicore CPUs, general-purpose many-core GPUs, and programmable FPGAs. The effective utilization of these architectures poses several challenges, among which a primary one...

In this paper, we propose TauRieL and target Traveling Salesman Problem (TSP) since it has broad applicability in theoretical and applied sciences. TauRieL utilizes an actor-critic inspired architecture that adopts ordinary feedforward nets to obtain a policy update vector $v$. Then, we use $v$ to improve the state transition matrix from which we g...

Voltage underscaling below the nominal level is an effective solution for improving energy efficiency in digital circuits, e.g., Field Programmable Gate Arrays (FPGAs). However, further undervolting below a safe voltage level and without accompanying frequency scaling leads to timing related faults, potentially undermining the energy savings. Throu...

Voltage underscaling below the nominal level is an effective solution for improving energy efficiency in digital circuits, e.g., Field Programmable Gate Arrays (FPGAs). However, further undervolting below a safe voltage level and without accompanying frequency scaling leads to timing related faults, potentially undermining the energy savings. Throu...

To manage power and memory wall affects, the HPC industry supports FPGA reconfigurable accelerators and vector processing cores for data-intensive scientific applications. FPGA based vector accelerators are used to increase the performance of high-performance application kernels. Adding more vector lanes does not affect the performance, if the proc...

LEGaTO is a three-year EU H2020 project which started in December 2017. The LEGaTO project will leverage task-based programming models to provide a software ecosystem for Made-in-Europe heterogeneous hardware composed of CPUs, GPUs, FPGAs and dataflow engines. The aim is to attain one order of magnitude energy savings from the edge to the converged...

Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural Networks (NNs), hardware accelerators emerge as a promising solution. However, with technology node scaling below...

LEGaTO is a three-year EU H2020 project which started in December 2017. The LEGaTO project will leverage task-based programming models to provide a software ecosystem for Made-in-Europe heterogeneous hardware composed of CPUs, GPUs, FPGAs and dataflow engines. The aim is to attain one order of magnitude energy savings from the edge to the converged...

The use of low-precision fixed-point arithmetic along with stochastic rounding has been proposed as a promising alternative to the commonly used 32-bit floating point arithmetic to enhance training neural networks training in terms of performance and energy efficiency. In the first part of this paper, the behaviour of the 12-bit fixed-point arithme...

With the increase in the density and performance of digital electronics, the demand for a power-efficient high-performance computing (HPC) system has been increased for embedded applications. The existing embedded HPC systems suffer from issues like programmability, scalability, and portability. Therefore, a parameterizable and programmable high-pe...

As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs), or silent errors, are one of the major sources that corrupt the execution results of HPC applications without being detected...

The need for power efficiency is driving a rethink of design decisions in processor architectures. While vector processors succeeded in the high-performance market in the past, they need a retailoring for the mobile market that they are entering now. Floating-point (FP) fused multiply-add (FMA), being a functional unit with high power consumption,...

The resurgence of machine learning since the late 1990s has been enabled by significant advances in computing performance and the growth of big data. The ability of these algorithms to detect complex patterns in data which are extremely difficult to achieve manually, helps to produce effective predictive models. Whilst computer architects have been...

In the low-end mobile processor market, power, energy, and area budgets are significantly lower than in the server/desktop/laptop/high-end mobile markets. It has been shown that vector processors are a highly energy-efficient way to increase performance; however, adding support for them incurs area and power overheads that would not be acceptable f...

Extracting valuable information from the rapidly growing field of Big Data faces serious performance constraints, especially in the software-based database management systems (DBMS). In a query processing system, hash-based computational primitives such as the hash join and the group-by are the most time-consuming operations, as they frequently nee...

In this chapter, we explain NEMsCAM cell, a new content-addressable memory (CAM) cell, which is designed based on both CMOS technologies and nanoelectromechanical (NEM) switches. The memory part of NEMsCAM is designed with two complementary nonvolatile NEM switches and located on top of the CMOS-based comparison component. As a use case, we evaluat...

Deterministic execution of a multi-threaded application guarantees that threads access shared memory in the same order and the application gives the same output whenever it runs with the same input parameters. Determinism provides repeatability, which helps a programmer in testing and debugging. Additionally, Transactional Memory (TM) simplifies de...

In the low-end mobile processor market, power, energy and area budgets are significantly lower than in other markets (e.g. servers or high-end mobile markets). It has been shown that vector processors are a highly energy-efficient way to increase performance; however adding support for them incurs area and power overheads that would not be acceptab...

Multi-core processors are ubiquitous in all market segments from embedded to high performance computing, but only few applications can efficiently utilize them. Existing parallel frameworks aim to support thread-level parallelism in applications, but the imposed overhead prevents their usage for small problem instances. This work presents Micro-thr...

The need for power-efficiency is driving a rethink of design decisions in processor architectures. While vector processors succeeded in the high-performance market in the past, they need a re-tailoring for the mobile market that they are entering now. Floating point fused multiply-add, being a power consuming functional unit, deserves special atten...

Recent years have seen a new generation of HLS tools, which do not only allow to generate hardware architectures from hardware behavioral models, but perform synthesis starting from algorithms specified in HLLs. One of the reasons for this development is the ever growing popularity of reconfigurable logic, which aims at providing the performance an...

As the rate of annual data generation grows exponentially, there is a demand to aggregate and summarise vast amounts of information quickly. In the past, frequency scaling was relied upon to push application throughput. Today, Dennard scaling has ceased and further performance must come from exploiting parallelism. Single instruction-multiple data...

In the low-end mobile processor market, power, energy and area budgets are significantly lower than in the server/desktop/laptop/high-end mobile markets. It has been shown that vector processors are a highly energy-efficient way to increase performance but adding support for them incurs area and power overheads that could not be acceptable for low-...

Modern workloads suffer high execution-time overhead due to page-based virtual memory. The authors introduce range translations that map arbitrary-sized virtual memory ranges to contiguous physical memory pages while retaining the flexibility of paging. A range translation reduces address translation to a range lookup that delivers near zero virtua...

With the increase in FPGA density and performance, the demand for multiple high-performance computing (HPC) units has been increased for various scientific and technological fields. Multi-scalar processor architectures do not give the best performance on FPGAs for HPC applications. This performance degradation demands a parameterizable high-perform...

Thanks to programming approaches like actor-based models, message passing is regaining popularity outside large-scale scientific computing for building scalable distributed applications in multi-core processors. Unfortunately, the mismatch between message passing models and today’s shared-memory hardware provided by commercial vendors results in su...

To prove Moore's law, the future multi-core architecture will have a vast number of heterogeneous processors, memories, and analog components. Network on a chip architecture is not appropriate for such systems due to high latency issues. With the increase of processor cores, the systems face address translation delay, data management delay and timi...

Power dissipation and energy consumption became the primary design constraint for almost all computer systems in the last 15 years. Both computer architects and circuit designers intent to reduce power and energy (without a performance degradation) at all design levels, as it is currently the main obstacle to continue with further scaling according...

The relentless push in technology scaling driven by Moore's law has witnessed fantastic gains in the quantities of transistors available on chips. Computer architects have exploited the extra transistors by incorporating several computing cores within a single processor. Heterogeneous processing in particular has become a useful technique for deali...