SVE Instruction List by Dougall Johnson
FDOT (4-way, indexed): 8-bit floating-point dot product by indexed element to single-precision
FDOT Zda.S, Zn.B, Zm.B[imm] (SVE2+FP8DOT4+NS (SSVE-FP8DOT4
128-bit SVE
For each 32-bit element, multiply four adjacent groups of 8-bit float elements from (1) and an indexed group from (2), and add the four products to the corresponding single-precision element of (3). The FP8 format for each 8-bit source operand is selected independently by FPMR.
256-bit SVE
For each 32-bit element, multiply four adjacent groups of 8-bit float elements from (1) and an indexed group from (2), and add the four products to the corresponding single-precision element of (3). The FP8 format for each 8-bit source operand is selected independently by FPMR.
512-bit SVE
For each 32-bit element, multiply four adjacent groups of 8-bit float elements from (1) and an indexed group from (2), and add the four products to the corresponding single-precision element of (3). The FP8 format for each 8-bit source operand is selected independently by FPMR.
Larger sizes
1024-bit SVE
For each 32-bit element, multiply four adjacent groups of 8-bit float elements from (1) and an indexed group from (2), and add the four products to the corresponding single-precision element of (3). The FP8 format for each 8-bit source operand is selected independently by FPMR.
2048-bit SVE
For each 32-bit element, multiply four adjacent groups of 8-bit float elements from (1) and an indexed group from (2), and add the four products to the corresponding single-precision element of (3). The FP8 format for each 8-bit source operand is selected independently by FPMR.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.