SVE Instruction List by Dougall Johnson
ST1B (scalar plus scalar, consecutive registers): Contiguous store of bytes from multiple consecutive vectors (scalar index)
ST1B { Zt1.B, Zt2.B, Zt3.B, Zt4.B }, PNg, [Xn, Xm] (SVE2.1 (SME2+S
128-bit SVE
Store 8-bit values from the four consecutive registers (2), (3), (4), and (5) to the memory operand (6). After decoding the predicate (1) from its predicate-as-counter representation to a quadruple-length predicate, if the predicate bit corresponding to an element is zero, that store is skipped, and cannot cause a fault, and the corresponding value in memory is unchanged. The first register number (2) must be divisible by four.
256-bit SVE
Store 8-bit values from the four consecutive registers (2), (3), (4), and (5) to the memory operand (6). After decoding the predicate (1) from its predicate-as-counter representation to a quadruple-length predicate, if the predicate bit corresponding to an element is zero, that store is skipped, and cannot cause a fault, and the corresponding value in memory is unchanged. The first register number (2) must be divisible by four.
512-bit SVE
Store 8-bit values from the four consecutive registers (2), (3), (4), and (5) to the memory operand (6). After decoding the predicate (1) from its predicate-as-counter representation to a quadruple-length predicate, if the predicate bit corresponding to an element is zero, that store is skipped, and cannot cause a fault, and the corresponding value in memory is unchanged. The first register number (2) must be divisible by four.
Larger sizes
1024-bit SVE
Store 8-bit values from the four consecutive registers (2), (3), (4), and (5) to the memory operand (6). After decoding the predicate (1) from its predicate-as-counter representation to a quadruple-length predicate, if the predicate bit corresponding to an element is zero, that store is skipped, and cannot cause a fault, and the corresponding value in memory is unchanged. The first register number (2) must be divisible by four.
2048-bit SVE
Store 8-bit values from the four consecutive registers (2), (3), (4), and (5) to the memory operand (6). After decoding the predicate (1) from its predicate-as-counter representation to a quadruple-length predicate, if the predicate bit corresponding to an element is zero, that store is skipped, and cannot cause a fault, and the corresponding value in memory is unchanged. The first register number (2) must be divisible by four.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.