BFCLAMP: BFloat16 floating-point clamp to minimum/maximum number

BFCLAMP Zd.H, Zn.H, Zm.H (SVE2+B16B16 (SME2+B16B16

128-bit SVE

For each BFloat16, clamp (1) to be between the lower-bound (2), and the upper-bound (3), and write the result to (4).

(4) = min( max( (2), (1) ), (3) )

256-bit SVE

For each BFloat16, clamp (1) to be between the lower-bound (2), and the upper-bound (3), and write the result to (4).

(4) = min( max( (2), (1) ), (3) )

512-bit SVE

For each BFloat16, clamp (1) to be between the lower-bound (2), and the upper-bound (3), and write the result to (4).

(4) = min( max( (2), (1) ), (3) )

Larger sizes

1024-bit SVE

For each BFloat16, clamp (1) to be between the lower-bound (2), and the upper-bound (3), and write the result to (4).

(4) = min( max( (2), (1) ), (3) )

2048-bit SVE

For each BFloat16, clamp (1) to be between the lower-bound (2), and the upper-bound (3), and write the result to (4).

(4) = min( max( (2), (1) ), (3) )

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