Julia mixed precision GEMM codegen meets and exceeds CUBLAS

General Matrix Multiplication or GEMM kernels take center place in high performance
computing and machine learning. Recent NVIDIA GPUs include GEMM accelerators, such as
NVIDIA’s Tensor Cores. In this paper we show how it is possible to program these
acce… Read more

Read full article

Similar

Mjolnir.jl – Julia Code Tracing

A little less conversation, a little more abstraction - MikeInnes/Mjolnir.jl... (more…)

Julia joins the PetaFlop club – 650,000 cores, 1.3M threads, 56 TB of data

Berkeley, CA – Julia has joined the rarefied ranks of computing languages that have achieved peak performance exceeding one petaflop per second – the so-called ‘Petaflop Club.’... (more…)

Prisma-style deep learning transformations in Julia

Have you ever wondered how the app Prisma manages to turn your photos into impressionist paintings? They use, amongst other things, a special type of algorithm called neural styles.

Reduce Algebra Interface for Julia AST

Symbolic parser generator for Julia language expressions using REDUCE algebra term rewriter - chakravala/Reduce.jl... (more…)

Exploring Lazy Evaluation with Julia

“Any sufficiently advanced technology is indistinguishable from magic,” go the famous words of Arthur C. Clarke. Often when we see magic, a small dose of knowledge is enough to wash away our wide-eyed awe and bring us back to sweet, comfortable cynicism. ... (more…)

Latest News

AI Camera’s Ball-Tracking Fail – Mistakes Referee’s Bald Head for Ball

AI model detects asymptomatic Covid-19 infections through recorded coughs

AI Detects Hidden Earthquakes