See "BFMLSLT (indexed)" in the exploration tools

BFMLSLT (indexed): BFloat16 multiply-subtract by indexed element from single-precision (top)

BFMLSLT Zda.S, Zn.H, Zm.H[imm] (SVE2.1 (SME2

svfloat32_t svbfmlslt_lane[_f32](svfloat32_t zda, svbfloat16_t zn, svbfloat16_t zm, uint64_t imm_idx)

128-bit SVE

Multiply each odd BFloat16 from (2), with the BFloat16 specified by imm from (1), then subtract this from to the 32-bit float from (3), and set (4) to the result.

256-bit SVE

Multiply each odd BFloat16 from (2), with the BFloat16 specified by imm from (1), then subtract this from to the 32-bit float from (3), and set (4) to the result.

512-bit SVE

Multiply each odd BFloat16 from (2), with the BFloat16 specified by imm from (1), then subtract this from to the 32-bit float from (3), and set (4) to the result.

Larger sizes

1024-bit SVE

Multiply each odd BFloat16 from (2), with the BFloat16 specified by imm from (1), then subtract this from to the 32-bit float from (3), and set (4) to the result.

2048-bit SVE

Multiply each odd BFloat16 from (2), with the BFloat16 specified by imm from (1), then subtract this from to the 32-bit float from (3), and set (4) to the result.

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