SVE Instruction List by Dougall Johnson
See "FRINT<r>" in the exploration tools

FRINTX: Floating-point round to integral value (predicated)

FRINTX Zd.H, Pg/M, Zn.H (SVE (SME
svfloat16_t svrintx[_f16]_m(svfloat16_t inactive, svbool_t pg, svfloat16_t op)

128-bit SVE

For each 16-bit float round (1) to an integral floating-point value, raising the floating-point inexact exception if rounding occurs, and set (2) to the result. The current rounding mode selected by FPCR is used.

256-bit SVE

For each 16-bit float round (1) to an integral floating-point value, raising the floating-point inexact exception if rounding occurs, and set (2) to the result. The current rounding mode selected by FPCR is used.

512-bit SVE

For each 16-bit float round (1) to an integral floating-point value, raising the floating-point inexact exception if rounding occurs, and set (2) to the result. The current rounding mode selected by FPCR is used.

Larger sizes

1024-bit SVE

For each 16-bit float round (1) to an integral floating-point value, raising the floating-point inexact exception if rounding occurs, and set (2) to the result. The current rounding mode selected by FPCR is used.

2048-bit SVE

For each 16-bit float round (1) to an integral floating-point value, raising the floating-point inexact exception if rounding occurs, and set (2) to the result. The current rounding mode selected by FPCR is used.

Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.