MulticoreWare

Compilers & Platforms Solutions
Engineering Optimal Performance

VaLVe - Programmer Productivity Tool for SVE

VaLVe-A programmer productivity tool for users of ARM V9 and RISC-V architectures

MulticoreWare announces limited availability of VaLVe – A programmer productivity tool for users of ARM V9 and RISC-V architectures. VaLVe includes a portable vector intrinsic layer which can be used directly in place of SVE or RVV intrinsics to achieve portability and a C++ vector productivity library for easy and efficient usage of variable length vectors.

Developing performance-sensitive applications while reducing the cost of adopting variable-length vectors, a challenging new model of computation.

Use Cases:

Keep using current methodology. Software is either not performance-sensitive, or sufficiently supported by autovectorization compiler features
Vendors may update their libraries to use new architecture features, but consider whether portability needs are being met, and whether an in-house or externally-sourced library that provides portability with equivalent performance may be worthwhile.
MCW VaLVe will make porting current code faster and easier, with portability insurance for the future.

GET IN TOUCH

Our team is happy to answer your questions. Please fill out the form and we will be in touch with you as soon as possible.

    Please note: Personal emails like Gmail, Hotmail, etc. are not accepted
    (Max 2000 characters)