SVE Instruction List by Dougall Johnson
UQRSHRN: Unsigned saturating rounding shift right narrow by immediate to interleaved integer
UQRSHRN Zd.B, { Zn1.H, Zn2.H }, #const (SVE2.3 (SME2.3
128-bit SVE
For each unsigned 16-bit integer element e from (1) and (2) compute ( e + ( 1 << ( const − 1 ) ) >> const, truncating to 8-bit with unsigned saturation to 0xFF. Set the even 8-bit elements of (3) to the results from (1), and the odd 8-bit elements of (3) to the results from (2). The shift amount is limited to 1 ≤ const ≤ 8.
256-bit SVE
For each unsigned 16-bit integer element e from (1) and (2) compute ( e + ( 1 << ( const − 1 ) ) >> const, truncating to 8-bit with unsigned saturation to 0xFF. Set the even 8-bit elements of (3) to the results from (1), and the odd 8-bit elements of (3) to the results from (2). The shift amount is limited to 1 ≤ const ≤ 8.
512-bit SVE
For each unsigned 16-bit integer element e from (1) and (2) compute ( e + ( 1 << ( const − 1 ) ) >> const, truncating to 8-bit with unsigned saturation to 0xFF. Set the even 8-bit elements of (3) to the results from (1), and the odd 8-bit elements of (3) to the results from (2). The shift amount is limited to 1 ≤ const ≤ 8.
Larger sizes
1024-bit SVE
For each unsigned 16-bit integer element e from (1) and (2) compute ( e + ( 1 << ( const − 1 ) ) >> const, truncating to 8-bit with unsigned saturation to 0xFF. Set the even 8-bit elements of (3) to the results from (1), and the odd 8-bit elements of (3) to the results from (2). The shift amount is limited to 1 ≤ const ≤ 8.
2048-bit SVE
For each unsigned 16-bit integer element e from (1) and (2) compute ( e + ( 1 << ( const − 1 ) ) >> const, truncating to 8-bit with unsigned saturation to 0xFF. Set the even 8-bit elements of (3) to the results from (1), and the odd 8-bit elements of (3) to the results from (2). The shift amount is limited to 1 ≤ const ≤ 8.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.