Related papers: Dissecting the NVidia Turing T4 GPU via Microbench…
The rapid scaling of large language models (LLMs) has unveiled critical limitations in current hardware architectures, including constraints in memory capacity, computational efficiency, and interconnection bandwidth. DeepSeek-V3, trained…
Efficient mixed-precision matrix multiply accumulate (MMA) operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source dot product implementations for Tensor Cores rely on discrete arithmetic…
Tensor Core is a mixed-precision matrix-matrix multiplication unit on NVIDIA GPUs with a theoretical peak performance of more than 300 TFlop/s on Ampere architectures. Tensor Cores were developed in response to the high demand of dense…
Graphics Processing Units (GPUs) are the state-of-the-art architecture for essential tasks, ranging from rendering 2D/3D graphics to accelerating workloads in supercomputing centers and, of course, Artificial Intelligence (AI). As GPUs…
Recent advances in graph processing on FPGAs promise to alleviate performance bottlenecks with irregular memory access patterns. Such bottlenecks challenge performance for a growing number of important application areas like machine…
FPGA is appropriate for fix-point neural networks computing due to high power efficiency and configurability. However, its design must be intensively refined to achieve high performance using limited hardware resources. We present an…
This technical report covers a set of experiments on the 64-core SPARC T3-4 system, comparing it to two similar AMD and Intel systems. Key characteristics as maximum integer and floating point arithmetic throughput are measured as well as…
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…
Real-world node embedding applications often contain hundreds of billions of edges with high-dimension node features. Scaling node embedding systems to efficiently support these applications remains a challenging problem. In this paper we…
In order to satisfy timing constraints, modern real-time applications require massively parallel accelerators such as General Purpose Graphic Processing Units (GPGPUs). Generation after generation, the number of computing clusters made…
Driven by the insatiable needs to process ever larger amount of data with more complex models, modern computer processors and accelerators are beginning to offer half precision floating point arithmetic support, and extremely optimized…
NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs. We…
The GPU has emerged as the go-to accelerator for high throughput and parallel workloads, spanning scientific simulations to AI, thanks to its performance and power efficiency. Given that 6 out of the top 10 fastest supercomputers in the…
Space missions increasingly deploy high-fidelity sensors that produce data volumes exceeding onboard buffering and downlink capacity. This work evaluates FPGA acceleration of neural networks (NNs) across four space use cases on the AMD…
Modern AI hardware, such as Nvidia's Blackwell architecture, is increasingly embracing low-precision floating-point (FP) formats to handle the pervasive activation outliers in Large Language Models (LLMs). Despite this industry trend, a…
Massive multi-threading in GPU imposes tremendous pressure on memory subsystems. Due to rapid growth in thread-level parallelism of GPU and slowly improved peak memory bandwidth, the memory becomes a bottleneck of GPU's performance and…
Gaussian processes (GPs) are a widely used regression tool, but the cubic complexity of exact solvers limits their scalability. To address this challenge, we extend the GPRat library by incorporating a fully GPU-resident GP prediction…
Accurate hardware performance models are critical to efficient code generation. They can be used by compilers to make heuristic decisions, by superoptimizers as a minimization objective, or by autotuners to find an optimal configuration for…
Recently Nvidia has released a new GPU model: GTX Titan X (TX) in a linage of the Maxwell architecture. We use our conjugate gradient code and non-perturbative renormalization code to measure the performance of TX. The results are compared…
Architectures with multiple classes of memory media are becoming a common part of mainstream supercomputer deployments. So called multi-level memories offer differing characteristics for each memory component including variation in…