Arm architecture family

ARM processors are the most widely used family of instruction set architectures

ARM Holdings licenses its RISC instruction set architectures to other companies for device production. These processors are integral to a vast array of devices, from smartphones to supercomputers. Their widespread adoption underscores ARM's significant impact on the technology industry.

Example

Fugaku, the world's fastest supercomputer from 2020 to 2022, uses ARM processors.

Remember this

Understanding ARM's dominance helps grasp the importance of RISC architectures in modern computing.

Text adapted from Wikipedia, licensed under CC BY-SA 4.0.

Related concepts

a Triton @triton.jit decorator does: compiles a Python function into a GPU kernel

@triton.jit decorator compiles Python function into a GPU kernel

SASS is: the actual machine code that runs on NVIDIA GPU hardware

SASS: compiled machine code executing on NVIDIA GPU hardware

instruction-level parallelism (ILP) achieves: multiple operations per clock cycle

ILP = average number of instructions per clock cycle

torch.compile does in PyTorch 2.0: traces and optimizes the computation graph

torch.compile optimizes computation graph by tracing and compiling it for efficiency

Triton differs from CUDA

Why does a super-fast computer sometimes run slower than a regular one?

CUDA

CUDA enables parallel computation on GPUs

Swipe through 100 ML concepts daily

Open Pocket Polymath