Related papers: Tessera: Unlocking Heterogeneous GPUs through Kern…
In high-performance computing, hotspot GPU kernels are primary bottlenecks, and expert manual tuning is costly and hard to port. Large language model methods often assume kernels can be compiled and executed cheaply, which fails in large…
Tensor cores are specialized processing units within GPUs that have demonstrated significant efficiency gains in compute-bound applications such as Deep Learning Training by accelerating dense matrix operations. Given their success,…
3D Gaussian Splatting (3DGS) has become a leading technique for real-time neural rendering and 3D scene reconstruction, but its rendering cost remains too high for many latency-sensitive scenarios. In particular, the rasterization stage in…
GPUs are widely used to accelerate many important classes of workloads today. However, we observe that several important emerging classes of workloads, including simulation engines for deep reinforcement learning and dynamic neural…
As modern Coarse Grain Reconfigurable Arrays (CGRAs) grow in size, efficient utilization of the available fabric by a single application becomes increasingly difficult. Existing CGRA mappers either fail to utilize the available fabric or…
The paper considers the problem of implementation on graphics processors of numerical integration routines for higher order finite element approximations. The design of suitable GPU kernels is investigated in the context of general purpose…
Volumetric data structures typically prioritize data locality, focusing on efficient memory access patterns. This singular focus can neglect other critical performance factors, such as occupancy, communication, and kernel fusion. We…
Modern GPUs are able to perform significantly more arithmetic operations than transfers of a single word to or from global memory. Hence, many GPU kernels are limited by memory bandwidth and cannot exploit the arithmetic power of GPUs.…
This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have…
Modern computing workloads commonly involve matrix-matrix multiplication (mmul) as a core computing pattern. Coarse-Grained Reconfigurable Arrays (CGRAs) can flexibly and efficiently support it, since they combine operation-level…
Designing flexible graph kernels that can run well on various platforms is a crucial research problem due to the frequent usage of graphs for modeling data and recent architectural advances and variety. In this work, we propose a novel…
Frameworks for the agile development of modern system-on-chips are crucial to dealing with the complexity of designing such architectures. The open-source Vespa framework for designing large, FPGA-based, multi-core heterogeneous…
Memory-based Temporal Graph Neural Networks are powerful tools in dynamic graph representation learning and have demonstrated superior performance in many real-world applications. However, their node memory favors smaller batch sizes to…
Diffusion-based generation is increasingly powering production content pipelines; however, deploying these models at scale remains a significant challenge. Model weights frequently exceed the memory capacity of commodity GPUs, while the…
When considering different hardware platforms, not just the time-to-solution can be of importance but also the energy necessary to reach it. This is not only the case with battery powered and mobile devices but also with high-performance…
Recently, tensor algebra have witnessed significant applications across various domains. Each operator in tensor algebra features different computational workload and precision. However, current general accelerators, such as VPU, GPGPU, and…
Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution. It is already a complex process because of the…
Graphics processing units (GPUs) are continually evolving to cater to the computational demands of contemporary general-purpose workloads, particularly those driven by artificial intelligence (AI) utilizing deep learning techniques. A…
Analyzing large-scale performance logs from GPU profilers often requires terabytes of memory and hours of runtime, even for basic summaries. These constraints prevent timely insight and hinder the integration of performance analytics into…
Neural Radiance Fields (NeRF) enables 3D scene reconstruction from several 2D images but incurs high rendering latency via its point-sampling design. 3D Gaussian Splatting (3DGS) improves on NeRF with explicit scene representation and an…