1 citations · 1 across the 16 of their papers we have counts for
18 papers
NinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space
Takanori Kotama, Shun-ichiro Hayashi, Daichi Mukunoki +2
In this paper we propose NinaXander, a series of composed language models obtained by connecting layers of frozen language models from different architecture families with a single…
AWE: Adaptive Weight Encoding for Exact Integer Matrix Products with Fewer GEMMs on FP4 Tensor Cores
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +1
Emulation of high-accuracy floating-point matrix multiplication, as in the Ozaki scheme, splits the inputs into low-precision components and multiplies them pairwise. These product…
Validation-Centric AI-Assisted GPU Porting of a 250,000+ Line Legacy Weather Simulation Code
Tetsuya Hoshino, Masaya Kato, Kazuhisa Tsuboki +3
Recent advances in large language models have made CLI-based AI agents a practical tool for accelerating GPU porting of large legacy scientific applications. Such applications, how…
DGEMM with Ozaki Scheme I/II on FP4 Tensor Cores: A Base-13 E2M1 Limb Representation
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +1
This paper proposes a method and its implementation for emulating FP64 matrix multiplication (DGEMM) by constructing, on FP4 (E2M1; 2 exponent bits and 1 mantissa bit) Tensor Cores…
ATFlash: Per-RoPE-Wavelength Attention Windows for Compute/Memory-Efficient LLM Inference
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +1
The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can disc…
Formulation-Level Auto-Tuning for QUBO-Based Machine Learning: A Case Study Across Multiple Quantum-Inspired Annealers
Naoya Mizuki, Takahiro Katagiri, Daichi Mukunoki +1
This paper presents an Optuna-based formulation-level auto-tuning framework for support vector machines (SVMs) implemented on multiple quantum-inspired annealers. In an annealing-b…
LLM-Based Porting of Optimized C++ to CUDA Through Deoptimization and Reoptimization
Daichi Mukunoki, Ryo Mikasa, Shunichiro Hayashi +2
When porting high-performance computing (HPC) code from CPU to GPU, CPU-oriented optimizations may obstruct LLM-based CUDA translation. We design and evaluate a Deopt-Reopt workflo…
Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancy
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +1
In LLM-based code generation, multiple code candidates are often generated in parallel from the same prompt -- for example, in best-of-N sampling or multi-candidate code completion…
Improving HPC Code Generation Capability of LLMs via Online Reinforcement Learning with Real-Machine Benchmark Rewards
Ryo Mikasa, Shun-ichiro Hayashi, Daichi Mukunoki +2
Large language models (LLMs) have demonstrated strong code generation capabilities, yet the runtime performance of generated code is not guaranteed, and there have been few attempt…
Learning-Augmented Performance Model for Tensor Product Factorization in High-Order FEM
Xuanzhengbo Ren, Yuta Kawai, Tetsuya Hoshino +4
Accurate performance prediction is essential for optimizing scientific applications on modern high-performance computing (HPC) architectures. Widely used performance models primari…
Sparse Iterative Solvers Using High-Precision Arithmetic with Quasi Multi-Word Algorithms
Daichi Mukunoki, Katsuhisa Ozaki
To obtain accurate results in numerical computation, high-precision arithmetic is a straightforward approach. However, most processors lack hardware support for floating-point form…
3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino +2
This paper proposes "3Dify," a procedural 3D computer graphics (3D-CG) generation framework utilizing Large Language Models (LLMs). The framework enables users to generate 3D-CG co…
VibeCodeHPC: An Agent-Based Iterative Prompting Auto-Tuner for HPC Code Generation Using LLMs
Shun-ichiro Hayashi, Koki Morita, Daichi Mukunoki +2
In this study, we propose VibeCodeHPC, a multi-agent system based on large language models (LLMs) for the automatic tuning of high-performance computing (HPC) programs on supercomp…
DGEMM without FP64 Arithmetic - Using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme
Daichi Mukunoki
As the demand for AI computation rapidly increases, more hardware is being developed to efficiently perform the low-precision matrix multiplications required by such workloads. How…
Towards Generalized Parameter Tuning in Coherent Ising Machines: A Portfolio-Based Approach
Tatsuro Hanyu, Takahiro Katagiri, Daichi Mukunoki +1
Coherent Ising Machines (CIMs) have recently gained attention as a promising computing model for solving combinatorial optimization problems. In particular, the Chaotic Amplitude C…
Performance Evaluation of General Purpose Large Language Models for Basic Linear Algebra Subprograms Code Generation
Daichi Mukunoki, Shun-ichiro Hayashi, Tetsuya Hoshino +1
Generative AI technology based on Large Language Models (LLM) has been developed and applied to assist or automatically generate program codes. In this paper, we evaluate the capab…
Matrix Engines for High Performance Computing:A Paragon of Performance or Grasping at Straws?
Jens Domke, Emil Vatai, Aleksandr Drozd +8
Matrix engines or units, in different forms and affinities, are becoming a reality in modern processors; CPUs and otherwise. The current and dominant algorithmic approach to Deep L…
White Paper from Workshop on Large-scale Parallel Numerical Computing Technology (LSPANC 2020): HPC and Computer Arithmetic toward Minimal-Precision Computing
Roman Iakymchuk, Daichi Mukunoki, Artur Podobas +15
In numerical computations, precision of floating-point computations is a key factor to determine the performance (speed and energy-efficiency) as well as the reliability (accuracy…