SVE Instruction List by Dougall Johnson
FCVTX: Floating-point down convert, rounding to odd (predicated)
FCVTX Zd.S, Pg/M, Zn.D (SVE2 (SME
svfloat32_t svcvtx_f32[_f64]_m(svfloat32_t inactive, svbool_t pg, svfloat64_t op)
128-bit SVE
Convert each 64-bit float from (1) to a 32-bit float, rounding to odd, writing the results to the even lanes of (2), zeroing the odd lanes.
256-bit SVE
Convert each 64-bit float from (1) to a 32-bit float, rounding to odd, writing the results to the even lanes of (2), zeroing the odd lanes.
512-bit SVE
Convert each 64-bit float from (1) to a 32-bit float, rounding to odd, writing the results to the even lanes of (2), zeroing the odd lanes.
Larger sizes
1024-bit SVE
Convert each 64-bit float from (1) to a 32-bit float, rounding to odd, writing the results to the even lanes of (2), zeroing the odd lanes.
2048-bit SVE
Convert each 64-bit float from (1) to a 32-bit float, rounding to odd, writing the results to the even lanes of (2), zeroing the odd lanes.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.