SVE Instruction List by Dougall Johnson
FCVTZS: Floating-point convert to signed integer, rounding toward zero (predicated)
FCVTZS Zd.D, Pg/M, Zn.H (SVE (SME
svint64_t svcvt_s64[_f16]_m(svint64_t inactive, svbool_t pg, svfloat16_t op)
128-bit SVE
Set each 64-bit lane of (2) by taking the lowest overlapping 16-bit floating point value from (1) and converting it to a signed 64-bit integer, rounding towards zero, with signed saturation to 0x7FFFFFFFFFFFFFFF or −0x8000000000000000.
256-bit SVE
Set each 64-bit lane of (2) by taking the lowest overlapping 16-bit floating point value from (1) and converting it to a signed 64-bit integer, rounding towards zero, with signed saturation to 0x7FFFFFFFFFFFFFFF or −0x8000000000000000.
512-bit SVE
Set each 64-bit lane of (2) by taking the lowest overlapping 16-bit floating point value from (1) and converting it to a signed 64-bit integer, rounding towards zero, with signed saturation to 0x7FFFFFFFFFFFFFFF or −0x8000000000000000.
Larger sizes
1024-bit SVE
Set each 64-bit lane of (2) by taking the lowest overlapping 16-bit floating point value from (1) and converting it to a signed 64-bit integer, rounding towards zero, with signed saturation to 0x7FFFFFFFFFFFFFFF or −0x8000000000000000.
2048-bit SVE
Set each 64-bit lane of (2) by taking the lowest overlapping 16-bit floating point value from (1) and converting it to a signed 64-bit integer, rounding towards zero, with signed saturation to 0x7FFFFFFFFFFFFFFF or −0x8000000000000000.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.