SVE Instruction List by Dougall Johnson
# SMMLA: Signed integer matrix multiply-accumulate

SMMLA Zda.S, Zn.B, Zm.B (SVE+I8MM+NS

svint32_t svmmla[_s32](svint32_t op1, svint8_t op2, svint8_t op3)

## 128-bit SVE

Within each 128-bit segment, interpreting the signed 8-bit integers from (1) and (2) as 2-by-8 and 8-by-2 matrices respectively, and the 32-bit integers from (3) as a 2-by-2 matrix, multiply (1) by (2), add the resulting 2-by-2 matrix to (3), and write the result to (4).

## 256-bit SVE

Within each 128-bit segment, interpreting the signed 8-bit integers from (1) and (2) as 2-by-8 and 8-by-2 matrices respectively, and the 32-bit integers from (3) as a 2-by-2 matrix, multiply (1) by (2), add the resulting 2-by-2 matrix to (3), and write the result to (4).

## 512-bit SVE

Within each 128-bit segment, interpreting the signed 8-bit integers from (1) and (2) as 2-by-8 and 8-by-2 matrices respectively, and the 32-bit integers from (3) as a 2-by-2 matrix, multiply (1) by (2), add the resulting 2-by-2 matrix to (3), and write the result to (4).

## Larger sizes

## 1024-bit SVE

Within each 128-bit segment, interpreting the signed 8-bit integers from (1) and (2) as 2-by-8 and 8-by-2 matrices respectively, and the 32-bit integers from (3) as a 2-by-2 matrix, multiply (1) by (2), add the resulting 2-by-2 matrix to (3), and write the result to (4).

## 2048-bit SVE

Within each 128-bit segment, interpreting the signed 8-bit integers from (1) and (2) as 2-by-8 and 8-by-2 matrices respectively, and the 32-bit integers from (3) as a 2-by-2 matrix, multiply (1) by (2), add the resulting 2-by-2 matrix to (3), and write the result to (4).

Report mistakes or give feedback

Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.