Related papers: Hardware for converting floating-point to the micr…

Transformer-based large language models (LLMs) have demonstrated remarkable performance across a wide range of real-world tasks, but their inference cost remains prohibitively high due to the quadratic complexity of attention and the memory…

Resistive random access memory (ReRAM) is a promising technology that can perform low-cost and in-situ matrix-vector multiplication (MVM) in analog domain. Scientific computing requires high-precision floating-point (FP) processing.…

The torrential influx of floating-point data from domains like IoT and HPC necessitates high-performance lossless compression to mitigate storage costs while preserving absolute data fidelity. Leveraging GPU parallelism for this task…

This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and…

Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-constrained mobile devices or even desktop GPUs. Recent…

The widespread adoption of mixed-precision quantization in large language models (LLMs) has created demand for hardware that can efficiently perform multiply-accumulate (MAC) operations across mixed datatypes and switch datatypes at…

In recent work, Lemire (2021) presented a fast algorithm to convert number strings into binary floating-point numbers. The algorithm has been adopted by several important systems: e.g., it is part of the runtime libraries of GCC 12, Rust…

The study on the expressive power of transformers shows that transformers are permutation equivariant, and they can approximate all permutation-equivariant continuous functions on a compact domain. However, these results are derived under…

Mixed-precision algorithms have been proposed as a way for scientific computing to benefit from some of the gains seen for artificial intelligence (AI) on recent high performance computing (HPC) platforms. A few applications dominated by…

Pre-training Transformers in FP4 precision is becoming a promising approach to gain substantial speedup, but it comes with a considerable loss of accuracy. Microscaling (MX) data format provides a fine-grained per-group quantization method…

When sharing or logging numerical data, we must convert binary floating-point numbers into their decimal string representations. For example, the number $\pi$ might become 3.1415927. Engineers have perfected many algorithms for producing…

With disks and networks providing gigabytes per second, parsing decimal numbers from strings becomes a bottleneck. We consider the problem of parsing decimal numbers to the nearest binary floating-point value. The general problem requires…

Convolution and cross-correlation are the basis of filtering and pattern or template matching in multimedia signal processing. We propose two throughput scaling options for any one-dimensional convolution kernel in programmable processors…

Current integration, architectural design and manufacturing technologies are not suited for the computing density and power efficiency requested by Exascale computing. New approaches in hardware architecture are thus needed to overcome the…

This paper describes a flexible architecture for implementing a new fast computation of the discrete Fourier and Hartley transforms, which is based on a matrix Laurent series. The device calculates the transforms based on a single bit…

We present a tool flow and results for a model-based hardware design for FPGAs from Simulink descriptions which nicely integrates into existing environments. While current commercial tools do not exploit some high-level optimizations, we…

Accurate simulations of various physical processes on digital computers requires huge computing performance, therefore accelerating these scientific and engineering applications has a great importance. Density of programmable logic devices…

In video coding, it is expected that the encoder could adaptively select the encoding parameters (e.g., quantization parameter) to optimize the bit allocation to different sources under the given constraint. However, in hybrid video coding,…

Fault tolerance for the upcoming exascale generation has long been an area of active research. One of the components of a fault tolerance strategy is checkpointing. Petascale-level checkpointing is demonstrated through a new mechanism for…

The growing amount of XML encoded data exchanged over the Internet increases the importance of XML based publish-subscribe (pub-sub) and content based routing systems. The input in such systems typically consists of a stream of XML…