Lei.Chat()

Gluon enhances the Triton language and compiler solutions with an additional approach towards GPU kernel programming.

Hopefully the previous articles covering linear layout concepts and examples facilitate building a solid understanding of the core generic layer powering various Triton code generation lowering and optimizations.

The previous blog post talked about Triton linear layout concepts, aiming to provide some underlying motivations and an intuitive understanding.

Layout is a core concept in Triton for representing and optimizing distribution mappings from source problems to the target hardware compute and memory hierarchy.

Triton provides an elegant solution to program GPU kernels in Python, positioning itself as a critical component in the modern AI software stack.

Time flies—almost 9 years have passed since I joined Google.

Previous blog posts overviewed the MLIR dialect hierarchy for kernel code generation (CodeGen) and zoomed in on the Linalg and Vector dialects among them.

之前的文章介绍了 Vector dialect 及其相关 pattern。

I explained the Vector dialect and related patterns in the previous blog post.

The vector dialect and related transformations are crucial components in the MLIR CodeGen flow for machine learning (ML).

在这个系列的首篇文章中我分享了对编译器和中间表示 (IR) 演进趋势的整体理解， 也讨论了 LLVM IR, SPIR-V, 和 MLIR 所要解决的问题以及相应的设计着眼点。

The initial blog post in this series captured my overall take on the evolution trends of compilers and IRs.

编译器 (compiler) 通常是各种提高开发效率的工具链中不可或缺的部分。

Compilers are often critical components in various development toolchains that boosts developer productivity.

This blog post talks about how to generate performant code for convolution ops using MLIR’s multiple levels of abstractions and transformations.

Today I would like to describe one way to build a scalable and frictionless benchmarking pipeline for Android native libraries, aiming to support different benchmark and device variants.

Nowadays GPUs are utilized for both graphics rendering and general-purpose compute (GPGPU).

These days if you would like to learn about machine learning, there are abundant great resources on the web discussing model architectures and how to code and train them.

In a previous blog post I gave a general introduction to GPU driver internals in Android/Linux systems.

Recently I have been working on a library that needs to directly interact with GPU kernel drivers from various vendors on Android/Linux systems.

Vulkan is designed to be both a graphics and compute API.

On 2018 Vulkan Developer Day in Montréal, I gave a talk regarding “Shader Toolchain: HLSL in Vulkan”.

This blog post discusses how HLSL semantic strings are translated into SPIR-V location numbers for Vulkan shader inter-stage interface matching in the SPIR-V CodeGen of DirectXShaderCompiler (DXC).

This blog post discusses how to manage resources in HLSL for Vulkan, using the SPIR-V CodeGen of DirectXShaderCompiler (DXC).

This blog post discusses how HLSL matrices are translated into SPIR-V for Vulkan consumption in the SPIR-V CodeGen of DirectXShaderCompiler.