相关论文: The right tool for the job

We show communication schedulers' recent work proposed for ML collectives does not scale to the increasing problem sizes that arise from training larger models. These works also often produce suboptimal schedules. We make a connection with…

The development of an open and free RISC-V architecture is of great interest for a wide range of areas, including high-performance computing and numerical simulation in mathematics, physics, chemistry and other problem domains. In this…

Interactive massively parallel computations are critical for machine learning and data analysis. These computations are a staple of the MIT Lincoln Laboratory Supercomputing Center (LLSC) and has required the LLSC to develop unique…

As data rates for multi-gigabit serial interfaces within multi-node compute systems approach and exceed 10 Gigabits per second (Gbps), board-to-board and chip-to-chip optical signaling solutions become more attractive, particularly for…

Linear type systems have a long and storied history, but not a clear path forward to integrate with existing languages such as OCaml or Haskell. In this paper, we study a linear type system designed with two crucial properties in mind:…

Integer octagonal constraints (a.k.a. ``Unit Two Variables Per Inequality'' or ``UTVPI integer constraints'') constitute an interesting class of constraints for the representation and solution of integer problems in the fields of constraint…

Increasing demands for computing power also propel the need for energy-efficient SoC accelerator architectures. One class of such accelerators are so-called processor arrays, which typically integrate a two-dimensional mesh of…

Current open source applications which allow for cross-platform data visualization of OLAP cubes feature issues of high overhead and inconsistency due to data oversimplification. To improve upon this issue, there is a need to cut down the…

An in-house developed 2D ultrasound computerized Tomography system is fully automated. Performance analysis of instrument and software interfacing soft tools, namely the LabVIEW, MATLAB, C, and Python, is presented. The instrument…

Reasoning over multiple modalities, e.g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains. Despite the widespread success of end-to-end learning, today's multimodal pipelines by and large…

As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…

This note is a very basic introduction to wavelets. It starts with an orthogonal basis of piecewise constant functions, constructed by dilation and translation. The ``wavelet transform'' maps each $f(x)$ to its coefficients with respect to…

This paper is a general introduction to the t\={u}Q toolchain (https://github.com/QSI-BAQS/tuQ) and a discussion of its two main workflows, 'reduce and optimise' and 'draft and compile'. The t\={u}Q toolchain was designed to advance…

Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties. However, existing tactile sensors lack standardization, leading to redundant features that hinder…

Modern architectures for high-performance computing and deep learning increasingly incorporate specialized tensor instructions, including tensor cores for matrix multiplication and hardware-optimized copy operations for multi-dimensional…

To explore the possibilities of a near-term intermediate-scale quantum algorithm and long-term fault-tolerant quantum computing, a fast and versatile quantum circuit simulator is needed. Here, we introduce Qulacs, a fast simulator for…

In our work we analyze computational aspects of the problem of numerical integration in finite element calculations and consider an OpenCL implementation of related algorithms for processors with wide vector registers. As a platform for…

Since the advent of LISP, the fifth generation programming language has developed for decades. However, compared with the fourth generation programming language, the fifth generation programming language has not been widely used because of…

Low latency and low power consumption are the main goals for our future networks. Fiber optics are already widely used for their faster speed. We want to investigate if optical decoding has further advantages to reaching future goals. We…

Software-controlled heterogeneous memory systems have the potential to improve performance, efficiency, and cost tradeoffs in emerging systems. Delivering on this promise requires an efficient operating system (OS) mechanisms and policies…