Related papers: Online Application Guidance for Heterogeneous Memo…
The widely-adopted practice is to train deep learning models with specialized hardware accelerators, e.g., GPUs or TPUs, due to their superior performance on linear algebra operations. However, this strategy does not employ effectively the…
There is a growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Equipped with a variety of processing units such as CPUs, GPUs, and NPUs, the…
Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities. Recently, modern embedded platforms started being equipped with such accelerators, resulting in a…
Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is essential for robust collocation, and GPU utilization…
Scalable persistent memory (PM) has opened up new opportunities for building indexes that operate and persist data directly on the memory bus, potentially enabling instant recovery, low latency and high throughput. When real PM hardware…
We present a thorough analysis of the use of modern heterogeneous systems interconnected by various cachecoherent links, including CXL, NVLink-C2C, and Infinity Fabric. We studied a wide range of server systems that combined CPUs from…
Many HPC applications can be expressed as mixed-mode computations, in which each node of a computational DAG is itself a parallel computation that can be molded at runtime to allocate different amounts of processing resources. At the same…
With an ever growing number of heterogeneous applicational services running on equally heterogeneous computational systems, the problem of resource management becomes more essential. Although current solutions consider some network and time…
The trend in industry is towards heterogeneous multicore processors (HMCs), including chips with CPUs and massively-threaded throughput-oriented processors (MTTOPs) such as GPUs. Although current homogeneous chips tightly couple the cores…
Hybrid main memory systems combine both performance and capacity advantages from heterogeneous memory technologies. With larger capacities, higher associativities, and finer granularities, hybrid memory systems currently exhibit significant…
Recent advances in reprogrammable hardware (e.g., FPGAs) and memory technology (e.g., DDR4, HBM) promise to solve performance problems inherent to graph processing like irregular memory access patterns on traditional hardware (e.g., CPU).…
In order to improve system performance efficiently, a number of systems choose to equip multi-core and many-core processors (such as GPUs). Due to their discrete memory these heterogeneous architectures comprise a distributed system within…
In most modern systems, the memory subsystem is managed and accessed at multiple different granularities at various resources. We observe that such multi-granularity management results in significant inefficiency in the memory subsystem.…
Emerging applications, such as big data analytics and machine learning, require increasingly large amounts of main memory, often exceeding the capacity of current commodity processors built on DRAM technology. To address this, recent…
Many performance critical systems today must rely on performance enhancements, such as multi-port memories, to keep up with the increasing demand of memory-access capacity. However, the large area footprints and complexity of existing…
Heterogeneous computing is one of the most important computational solutions to meet rapidly increasing demands on system performance. It typically allows the main flow of applications to be executed on a CPU while the most computationally…
SSDs are emerging storage devices which unlike HDDs, do not have mechanical parts and therefore, have superior performance compared to HDDs. Due to the high cost of SSDs, entirely replacing HDDs with SSDs is not economically justified.…
In recent years, as the demand for low energy and high performance computing has steadily increased, heterogeneous computing has emerged as an important and promising solution. Because most workloads can typically run most efficiently on…
Traditional heterogeneous parallel algorithms, designed for heterogeneous clusters of workstations, are based on the assumption that the absolute speed of the processors does not depend on the size of the computational task. This assumption…
Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…