MMA Instructions
19 PowerISA instructions in this extension - click any row for encoding, pseudocode, and full documentation.
| Mnemonic | Syntax | Format | Summary |
|---|---|---|---|
| pmxvf16ger2pp | pmxvf16ger2pp AT,XA,XB,XMSK,YMSK,PMSK | MMIRR:XX3-form | Performs a prefixed masked VSX vector 16-bit floating-point GER rank-2 update with positive multiply and positive accumulate. |
| pmxvf32gerpp | pmxvf32gerpp | MMIRR:XX3-form | Performs a prefixed masked VSX vector 32-bit floating-point GER rank-1 update with positive multiply and positive accumulate. |
| pmxvf64gernn | pmxvf64gernn AT,XAp,XB,XMSK,YMSK | MMIRR:XX3-form | Performs a prefixed masked VSX vector 64-bit floating-point GER (rank-1 update) with negative multiply and negative accumulate. |
| pmxvi8ger4pp | pmxvi8ger4pp AT,XA,XB,XMSK,YMSK,PMSK | MMIRR:XX3-form | Performs a prefixed masked VSX vector 8-bit signed/unsigned integer GER rank-4 update with positive multiply and positive accumulate, adding the result to the accumulator. |
| xvbf16ger2 | xvbf16ger2 AT, XA, XB | XX3-form | Performs BFloat16 (Brain Float) matrix multiply accumulate. |
| xvf16ger2 | xvf16ger2 AT, XA, XB | XX3-form | Performs a vector floating-point general element-wise rank-2 update operation. |
| xvf16ger2pn | xvf16ger2pn AT,XA,XB | XX3-form | Performs a rank-2 update of an accumulator register using 16-bit floating-point outer product, with positive multiply and negative accumulate. |
| xvf32ger | xvf32ger AT, XA, XB | XX3-form | Performs a vector floating-point general element-wise reduction with rank-1 update. |
| xvf64ger | xvf64ger AT, XA, XB | XX3-form | Performs a vector floating-point general element-wise reduction on 64-bit elements. |
| xvf64gernn | xvf64gernn AT,XAp,XB | XX3-form | Performs a VSX Vector 64-bit Floating-Point GER (rank-1 update) with negative multiply and negative accumulate, updating an accumulator register. |
| xvi16ger2 | xvi16ger2 AT, XA, XB | XX3-form | Performs a rank-2 update of the contents of two registers and updates the condition register. |
| xvi16ger2s | xvi16ger2s AT, XA, XB | XX3-form | Performs a vectorized signed integer multiply and accumulate operation with saturation. |
| xvi4ger8 | xvi4ger8 AT, XA, XB | XX3-form | Performs an accumulation of eight outer products (rank 8 update) using signed 4-bit integers from two vector scalar registers. |
| xvi4ger8pp | xvi4ger8pp AT, XA, XB | XX3-form | Unsigned 4-bit integer matrix multiply accumulate. |
| xvi8ger4 | xvi8ger4 AT, XA, XB | XX3-form | Performs an 8-bit integer outer product (GER) and accumulates into a 512-bit register. |
| xvi8ger4pp | xvi8ger4pp AT, XA, XB | XX3-form | Signed/Unsigned variations of 8-bit matrix multiply accumulate. |
| xxmfacc | xxmfacc AT | X-form | Copies data from an Accumulator back to 4 adjacent VSRs. |
| xxmtacc | xxmtacc AT | X-form | Copies data from 4 adjacent VSRs into an Accumulator. |
| xxsetaccz | xxsetaccz AT | X-form | Clears a 512-bit Accumulator register (composed of 4 VSRs) to zero. |