Hi, this is Tecca. In this post I will be going over SVE2 which stands for (Scalable Vector Extension version 2)
SVE2 is an SIMD (Single Input, Multiple Data) instruction set that is only used in the AArch64 computer architecture.
SVE2 enable vectorization of loops for High Performance Computing, basically means making the program to run faster!
By applying SVE enables software that process large amount of data to be ported more easily (for example the volume scaling lab). The greatest advantage of using SVE is the ability to write and build software only once, then we can run program on different AArch64 hardware with those binaries.
The main difference between SVE2 and SVE is the functional coverage of the instruction set. SVE was designed for HPC and ML applications. SVE2 extends the SVE instruction set to enable data-processing domains beyond HPC and ML. The SVE2 instruction set can also accelerate the common algorithms that are used in the following applications:
- Computer vision
- Multimedia
- Long-Term Evolution (LTE) baseband processing
- Genomics
- In-memory database
- Web serving
- General-purpose software
Source from: Introducing SVE2
The goal of this experiment is to try to convert our code from previous post # Source code to be converted to adapt SVE.
In the next post, I will be applying the conversion and verify the result.
Top comments (0)