Announcing the SCALE BETA

Announcing SCALE: a GPGPU toolchain allowing CUDA programs to be natively run on AMD GPUs. Support for more vendors is in development.

We want everyone to have the freedom to use the best GPGPU programming tools, and the GPU hardware that best suits their needs. Write once, run anywhere.

Get started with SCALE today.

Why SCALE?

We believe that it should be possible to write code once, and build/run it on any hardware platform. This has been a reality for CPU code for many years, so why not GPUs?

We set out to directly solve this problem by bridging the compatibility gap between the popular CUDA programming language and other hardware vendors.

One codebase, multiple vendors.

What is SCALE?

SCALE is a GPGPU toolkit, similar to NVIDIA's CUDA Toolkit, with the capability to produce binaries for non-NVIDIA GPUs when compiling CUDA code.

SCALE aims to be source-compatible with CUDA, including support for inline PTX and nvcc's C++ quirks.

Instead of providing a new programming language for GPUs, SCALE embraces the widely-popular CUDA language and allows its use with non-NVIDIA hardware. This frees developers from the challenges associated with maintaining multiple versions of their codebase.

Beyond CUDA

SCALE supports a superset of the CUDA language. It also offers various opt-in language extensions that go beyond the featureset of NVIDIA's CUDA, improving developer experience and productivity. Why should multi-vendor support be less convenient than a single-vendor solution?

Download the free SCALE beta today, and begin the liberation of the GPUGPU market.

Dive Deeper

Jump into the technical manual for all the gory details.