相关论文: Interconnect Bandwidth Heterogeneity on AMD MI250x…
The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms,…
While FPGA accelerator boards and their respective high-level design tools are maturing, there is still a lack of multi-FPGA applications, libraries, and not least, benchmarks and reference implementations towards sustained HPC usage of…
The rapid advancement of embedded multicore and many-core systems has revolutionized computing, enabling the development of high-performance, energy-efficient solutions for a wide range of applications. As models scale up in size, data…
Manufacturers have been developing new graphics processing unit (GPU) nodes with large capacity, high bandwidth memory and very high bandwidth intra-node interconnects. This enables moving large amounts of data between GPUs on the same node…
Multimodal deep learning models enable joint learning across heterogeneous data sources, including text, images, and video, but their rapid scaling introduces significant memory and communication bottlenecks. As model sizes and sequence…
The last decade has seen a shift in the computer systems industry where heterogeneous computing has become prevalent. Graphics Processing Units (GPUs) are now present in supercomputers to mobile phones and tablets. GPUs are used for…
GPUs in High-Performance Computing systems remain under-utilised due to the unavailability of schedulers that can safely schedule multiple applications to share the same GPU. The research reported in this paper is motivated to improve the…
Recent computational advances enable protein design pipelines to run end-to-end on GPUs, yet their heterogeneous computational behaviors remain undercharacterized at the system level. We implement and profile a representative pipeline at…
Memory latency, bandwidth, capacity, and energy increasingly limit performance. In this paper, we reconsider proposed system architectures that consist of huge (many-terabyte to petabyte scale) memories shared among large numbers of CPUs.…
Emerging agentic LLM workloads are driving rapidly growing demand on both memory capacity and bandwidth, with different phases of inference (e.g., prefill and decode) imposing distinct requirements. Industry is responding by composing…
Last level cache management and core interconnection network play important roles in performance and power consumption in multicore system. Large scale chip multicore uses mesh interconnect widely due to scalability and simplicity of the…
Heterogeneous computing is the strategy of deploying multiple types of processing elements within a single workflow, and allowing each to perform the tasks to which is best suited. To fully harness the power of heterogeneity, we want to be…
We present a single-node, multi-GPU programmable graph processing library that allows programmers to easily extend single-GPU graph algorithms to achieve scalable performance on large graphs with billions of edges. Directly using the…
3D integration offers key advantages in improving system performance and efficiency for the End-of-Scaling era. It enables the incorporation of heterogeneous system components and disparate technologies, eliminates off-chip communication…
Heterogeneous computing is widely used at all levels of computing from data center to edge due to its power/performance characteristics. However, heterogeneity presents challenges. Interoperability---the management of workloads across…
In next-generation communications, sub-6GHz and millimeter-wave (mmWave) links typically coexist, with the sub-6GHz link always active and the mmWave link active when high-rate transmission is required. Due to the spatial similarities…
FPGA-based data processing in datacenters is increasing in popularity due to the demands of modern workloads and the ensuing necessity for specialization in hardware. Driven by this trend, vendors are rapidly adapting reconfigurable devices…
Optical interconnects have attracted significant research interest for use in short-reach board-level optical communication links in supercomputers and data centres. Multimode polymer waveguides in particular constitute an attractive…
Optical interconnect is seen as a potential solution to meet the performance requirements of current and future generation of data processors. Optical interconnects have negligible frequency dependent loss, low cross talk and high band…
GPUs offer massive compute parallelism and high-bandwidth memory accesses. GPU database systems seek to exploit those capabilities to accelerate data analytics. Although modern GPUs have more resources (e.g., higher DRAM bandwidth) than…