MulDstAdd

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	x
Atlas A2 training product/Atlas A2 inference product	x
Atlas 200I/500 A2 inference product	x
Atlas inference product AI Core	x
Atlas inference product Vector Core	x
Atlas training product	x

Function Usage

Multiplies dstReg by srcReg0, adds the result to srcReg1, and writes the result to dstReg based on mask. The formula is as follows:

$\text{[math]}$

Prototype

template <typename T = DefaultType, MaskMergeMode mode = MaskMergeMode::ZEROING, typename U>
__simd_callee__ inline void MulDstAdd(U& dstReg, U& srcReg0, U& srcReg1, MaskReg& mask)

Parameters

**Table 1** Template parameters
Parameter	Description
T	Operand data type. For the Atlas 350 Accelerator Card, the supported data types are half, bfloat16_t, and float.
mode	Set it to MERGING or ZEROING. Currently, only ZEROING is supported. ZEROING: The elements that are not filtered by mask are set to zero in dst.
U	RegTensor type of the destination operand, for example, RegTensor<half>. It is automatically inferred by the compiler and does not need to be specified.

**Table 2** Parameters
Parameter	Input/Output	Description
dstReg	Output	Destination operand. The type is RegTensor.
srcReg0	Input	Source operand. The type is RegTensor. The data type must be the same as that of the destination operand.
srcReg1	Input	Source operand. The type is RegTensor. The data type must be the same as that of the destination operand.
mask	Input	Valid indication of the source operand element operation. For details, see MaskReg.

Returns

None

Constraints

None

Example

template<typename T>
__simd_vf__ inline void MulDstAddVF(__ubuf__ T* dstAddr, __ubuf__ T* src0Addr, __ubuf__ T* src1Addr, __ubuf__ T* src2Addr, uint32_t count, uint32_t oneRepeatSize, uint16_t repeatTimes)
{
    AscendC::Reg::RegTensor<T> srcReg0;
    AscendC::Reg::RegTensor<T> srcReg1;
    AscendC::Reg::RegTensor<T> dstReg;
    AscendC::Reg::MaskReg mask;
    for (uint16_t i = 0; i < repeatTimes; i++) {
        mask = AscendC::Reg::UpdateMask<T>(count);
        AscendC::Reg::LoadAlign(srcReg0, src0Addr + i * oneRepeatSize);
        AscendC::Reg::LoadAlign(srcReg1, src1Addr + i * oneRepeatSize);
        AscendC::Reg::LoadAlign(dstReg, src2Addr + i * oneRepeatSize);
        AscendC::Reg::MulDstAdd(dstReg, srcReg0, srcReg1, mask);
        AscendC::Reg::StoreAlign(dstAddr + i * oneRepeatSize, dstReg, mask);
    }
}

Parent topic: Compound Computation