hgpu.org » Apple M1 Pro
Performant Unified GPU Kernels for Portable Singular Value Computation Across Hardware and Precision
Evelyne Ringoot, Rabab Alomairy, Valentin Churavy, Alan Edelman
Tags: AMD Radeon Instinct MI250, Apple M1 Pro, ATI, Computer science, HIP, Intel, Intel Ponte Vecchio Max 1100, Kokkos, Linear Algebra, Machine learning, nVidia, nVidia A100, nVidia GeForce RTX 4060, nVidia H100, OpenCL, SYCL
August 17, 2025 by hgpu
Recent source codes
* * *
Most viewed papers (last 30 days)
- DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
- CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
- KEET: Explaining Performance of GPU Kernels Using LLM Agents
- CUDAHercules: Benchmarking Hardware-Aware Expert-level CUDA Optimization for LLMs
- Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs
- KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
- Pretraining large language models with MXFP4 on Native FP4 Hardware
- Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures
- CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging
- Source-to-Source Transformations for GPU Code Generation
* * *



