/explore
|
You are here 
|
nullprogram.com | ||
| | | | |
www.nickwilcox.com
|
|
| | | | | In the previous article on auto-vectorization we looked at the different SIMD instruction set families on X86-64. We saw how he target-feature compiler flag and #[target_feature()] attribute gave us more control over the instructions used in the generated assembly. | |
| | | | |
huonw.github.io
|
|
| | | | | An overview of my work on improving SIMD in Rust. | |
| | | | |
mcyoung.xyz
|
|
| | | | | [AI summary] The text provides an in-depth exploration of SIMD (Single Instruction, Multiple Data) programming, focusing on its application in optimizing algorithms like base64 decoding. It outlines the challenges of writing portable SIMD code across different architectures, the role of compilers and instruction sets, and the importance of avoiding branches in performance-critical code. The article transitions into a practical example of implementing a SIMD version of the base64 decoding algorithm, emphasizing the use of shuffles and data reordering to efficiently process data in parallel. It also touches on the trade-offs between using intrinsics, portable SIMD libraries, and compiler optimizations, while highlighting the complexities of cross-platform deve... | |
| | | | |
lenholgate.com
|
|
| | | |||
