Function core::arch::mips64::__msa_sld_h

source ·
pub unsafe fn __msa_sld_h(a: v8i16, b: v8i16, c: i32) -> v8i16
🔬This is a nightly-only experimental API. (stdsimd #48556)
Available on (MIPS or MIPS-64) and target feature msa and MIPS-64 only.
Expand description

GPR Columns Slide

Vector registers a (eight signed 16-bit integer numbers) and b (eight signed 16-bit integer numbers) contain 2-dimensional byte arrays (rectangles) stored row-wise with as many rows as bytes in integer data format df. The two source rectangles b and a are concatenated horizontally in the order they appear in the syntax, i.e. first a and then b. Place a new destination rectangle over b and then slide it to the left over the concatenation of a and b by the number of columns given in GPR c. The result is written to vector (eight signed 16-bit integer numbers). GPR c value is interpreted modulo the number of columns in destination rectangle, or equivalently, the number of data format df elements in the destination vector.