MulticoreWare Inc. has launched a new tool called VaLVe to enhance explicit vector programming and enable the portability of vectorized applications across different architectures.
VaLVe offers a versatile vector programming layer that provides the portability and ease of use of standard C/C++ with the efficiency of platform-specific intrinsics.
It helps developers optimize for new ISAs like SVE and RVV more quickly while maintaining support for established technologies like NEON and AVX in a single codebase.
Read more: MulticoreWare launches VaLVe, a replacement for platform-specific intrinsics in SIMD Programming