SVE Instruction List by Dougall Johnson
USDOT (vectors): Unsigned by signed integer dot product
USDOT Zda.S, Zn.B, Zm.B (SVE+I8MM (SME+I8MM
svint32_t svsudot[_s32](svint32_t op1, svint8_t op2, svuint8_t op3)
svint32_t svusdot[_s32](svint32_t op1, svuint8_t op2, svint8_t op3)
128-bit SVE
For each group of four unsigned 8-bit integers from (1) and signed 8-bit integers from (2), compute the dot-product, then add the result to the corresponding 32-bit integer accumulator from (3), setting (4) to the total.
256-bit SVE
For each group of four unsigned 8-bit integers from (1) and signed 8-bit integers from (2), compute the dot-product, then add the result to the corresponding 32-bit integer accumulator from (3), setting (4) to the total.
512-bit SVE
For each group of four unsigned 8-bit integers from (1) and signed 8-bit integers from (2), compute the dot-product, then add the result to the corresponding 32-bit integer accumulator from (3), setting (4) to the total.
Larger sizes
1024-bit SVE
For each group of four unsigned 8-bit integers from (1) and signed 8-bit integers from (2), compute the dot-product, then add the result to the corresponding 32-bit integer accumulator from (3), setting (4) to the total.
2048-bit SVE
For each group of four unsigned 8-bit integers from (1) and signed 8-bit integers from (2), compute the dot-product, then add the result to the corresponding 32-bit integer accumulator from (3), setting (4) to the total.
Report mistakes or give feedback
Inspired by and based on the x86/x64 SIMD Instruction List by Daytime.