Cover Image

SGEMM-cube: Precision-Recovery FP32 GEMM Approximation on Ascend NPUs with FP16 Matrix Engines

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xue, Weicheng, Xu, Baisong, Yang, Kai, Liu, Yongxiang, Fan, Dengdeng, Xu, Pengxiang, Tian, Yonghong
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

W4A16 Mixed-Precision Matrix Multiplication on Decoupled Architecture: Kernel Design and Memory Bottleneck Analysis for Ascend NPUs
by: He, Yuanhong, et al.
Published: (2026)

Low-Rank GEMM: Efficient Matrix Multiplication via Low-Rank Approximation with FP8 Acceleration
by: Metere, Alfredo
Published: (2025)

Double-Precision Matrix Multiplication Emulation via Ozaki-II Scheme with FP8 Quantization
by: Uchino, Yuki, et al.
Published: (2026)

NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs
by: Lee, Haeun, et al.
Published: (2025)

Improving SpGEMM Performance Through Matrix Reordering and Cluster-wise Computation
by: Islam, Abdullah Al Raqibul, et al.
Published: (2025)

Accelerating Sparse DNNs Based on Tiled GEMM
by: Guo, Cong, et al.
Published: (2024)

Execution-Centric Characterization of FP8 Matrix Cores, Asynchronous Execution, and Structured Sparsity on AMD MI300A
by: Jarmusch, Aaron, et al.
Published: (2026)

FalconGEMM: Surpassing Hardware Peaks with Lower-Complexity Matrix Multiplication
by: Zhu, Honglin, et al.
Published: (2026)

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
by: Yang, Jinwu, et al.
Published: (2026)

Zen-Attention: A Compiler Framework for Dynamic Attention Folding on AMD NPUs
by: Deshmukh, Aadesh, et al.
Published: (2025)

High-Performance and Power-Efficient Emulation of Matrix Multiplication using INT8 Matrix Engines
by: Uchino, Yuki, et al.
Published: (2025)

Accelerating High-Order Finite Element Simulations at Extreme Scale with FP64 Tensor Cores
by: Tu, Jiqun, et al.
Published: (2026)

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection
by: Swann, Ryan, et al.
Published: (2025)

Parallel GPU-Enabled Algorithms for SpGEMM on Arbitrary Semirings with Hybrid Communication
by: McFarland, Thomas, et al.
Published: (2025)

Exceeding the Numerical and Performance Characteristics of IEEE-754 SGEMM with BFloat16 Tensor Cores on GPUs for Scientific Computing
by: Bayraktar, Harun, et al.
Published: (2026)

TurboFNO: High-Performance Fourier Neural Operator with Fused FFT-GEMM-iFFT on GPU
by: Wu, Shixun, et al.
Published: (2025)

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
by: Park, Gunho, et al.
Published: (2022)

MemAscend: System Memory Optimization for SSD-Offloaded LLM Fine-Tuning
by: Liaw, Yong-Cheng, et al.
Published: (2025)

A-IO: Adaptive Inference Orchestration for Memory-Bound NPUs
by: Zhang, Chen, et al.
Published: (2026)

A Real-Time, Auto-Regression Method for In-Situ Feature Extraction in Hydrodynamics Simulations
by: Yan, Kewei, et al.
Published: (2025)

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving
by: Hu, Huanqi, et al.
Published: (2025)

Leveraging Hardware-Aware Computation in Mixed-Precision Matrix Multiply: A Tile-Centric Approach
by: Zhang, Qiao, et al.
Published: (2025)

Matrix-Free 3D SIMP Topology Optimization with Fused Gather-GEMM-Scatter Kernels
by: Yang, Shaoliang, et al.
Published: (2026)

Multi-agent Reinforcement Learning-based In-place Scaling Engine for Edge-cloud Systems
by: Prodanov, Jovan, et al.
Published: (2025)

BurstEngine: an Efficient Distributed Framework for Training Transformers on Extremely Long Sequences of over 1M Tokens
by: Sun, Ao, et al.
Published: (2025)

Design in Tiles: Automating GEMM Deployment on Tile-Based Many-PE Accelerators
by: Shen, Aofeng, et al.
Published: (2025)

Communication-Avoiding SpGEMM via Trident Partitioning on Hierarchical GPU Interconnects
by: Bellavita, Julian, et al.
Published: (2026)

LOw-cOst yet High-Performant Sparse Matrix-Matrix Multiplication on Arm SME Architectures
by: Lei, Kelun, et al.
Published: (2025)

AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
by: Wen, Zhongzhen, et al.
Published: (2026)

Developing an Interactive OpenMP Programming Book with Large Language Models
by: Yi, Xinyao, et al.
Published: (2024)

AME: An Efficient Heterogeneous Agentic Memory Engine for Smartphones
by: Zhao, Xinkui, et al.
Published: (2025)

Fast Kronecker Matrix-Matrix Multiplication on GPUs
by: Jangda, Abhinav, et al.
Published: (2024)

LP-GEMM: Integrating Layout Propagation into GEMM Operations
by: Carneiro, César Guedes, et al.
Published: (2026)

Parallel Scan on Ascend AI Accelerators
by: Wróblewski, Bartłomiej, et al.
Published: (2025)

SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines
by: Cheng, Ke, et al.
Published: (2024)

SwarmSearch: Decentralized Search Engine with Self-Funding Economy
by: Gregoriadis, Marcel, et al.
Published: (2025)

Stencil Matrixization
by: Zhao, Wenxuan, et al.
Published: (2023)

Managing Forensic Recovery in the Cloud
by: Weir, George R. S., et al.
Published: (2024)

Sparsity-Aware Roofline Models for Sparse Matrix-Matrix Multiplication
by: Qian, Matthew, et al.
Published: (2026)

Centroid Approximation with Multidimensional Approximate Agreement Protocols
by: Cambus, Melanie, et al.
Published: (2023)