On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “XLA”

Memory Safe Computations with XLA Compilercs.LG

XLA compiler extension improves memory efficiency for machine learning.

problem Memory constraints limit the scalability of memory-intensive machine learning algorithms.

method Developed an XLA compiler extension that adjusts algorithm data-flow representation to fit memory limits.

result k-nearest neighbour and sparse Gaussian process regression can be run at larger scales.

machine learning memory efficiency XLA compiler linear algebra neural networks

2022-06-28abs ↗pdf ↗

LeFlow: Enabling Flexible FPGA High-Level Synthesis of Tensorflow Deep Neural Networkscs.LG

LeFlow enables quick FPGA synthesis from Tensorflow models.

problem Manual translation of Tensorflow models to FPGA RTL is time-consuming and requires expertise.

method Uses XLA compiler to emit synthesizable LLVM code from Tensorflow specifications, which is then synthesized.

result Allows users to generate Deep Neural Networks with just a few lines of Python code.

FPGAs Tensorflow Deep Neural Networks High-Level Synthesis XLA

2018-07-14abs ↗pdf ↗

Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUscs.PL

Julia programs and ML models are compiled and offloaded to Google Cloud TPUs.

problem Efficiently compiling and executing machine learning models on Google Cloud TPUs.

method Developed a method to compile and offload Julia programs and ML models to Google Cloud TPUs using the Google XLA compiler.

result Successfully fused a VGG19 model into a single TPU executable, achieving 0.23s evaluation time on a batch of 100 images.

Julia Cloud TPUs Machine Learning TensorFlow Automatic Differentiation

2018-10-23abs ↗pdf ↗

GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcs.CL

GShard enables scaling of large neural networks with automatic sharding and lightweight APIs.

problem Scaling neural networks to handle vast training data and compute efficiently.

method GShard uses lightweight annotation APIs and XLA compiler extensions for parallel computation.

result GShard successfully trained a 600 billion parameter model on 2048 TPUs in 4 days.

neural networks scaling GShard Transformer TPU

2020-06-30abs ↗pdf ↗