Axpy

Function Usage

Adds the product of each element in srcLocal and a scalar to the corresponding element in dstLocal using the following formula, where PAR indicates the number of elements that can be processed by the Vector Unit in one iteration.

$\text{[math]}$

Prototype

Computation of the first n pieces of data of a tensor

        
             template <typename T, typename U>
__aicore__ inline void Axpy(const LocalTensor<T>& dstLocal, const LocalTensor<U>& srcLocal, const U& scalarValue, const int32_t& calCount)

High-dimensional tensor sharding computation

Bitwise mask mode

          
               template <typename T, typename U, bool isSetMask = true>
__aicore__ inline void Axpy(const LocalTensor<T>& dstLocal, const LocalTensor<U>& srcLocal, const U& scalarValue, uint64_t mask[], const uint8_t repeatTimes, const UnaryRepeatParams& repeatParams)

Contiguous mask mode

          
               template <typename T, typename U, bool isSetMask = true>
__aicore__ inline void Axpy(const LocalTensor<T>& dstLocal, const LocalTensor<U>& srcLocal, const U& scalarValue, uint64_t mask, const uint8_t repeatTimes, const UnaryRepeatParams& repeatParams)

Parameters

**Table 1** Parameters in the template
Parameter	Description
T	Data type of the destination operand.
U	Data type of the source operand.
isSetMask	Indicates whether to set mask inside the API. true: sets mask inside the API. false: sets mask outside the API. Developers need to use the SetVectorMask API to set the mask value. In this mode, the mask value in the input parameter of this API must be set to MASK_PLACEHOLDER.

**Table 2** Parameters
Parameter	Input/Output	Meaning
dstLocal	Output	Destination operand. The type is LocalTensor, and the supported TPosition is VECIN, VECCALC, or VECOUT. The start address of the LocalTensor must be 32-byte aligned. For the Atlas Training Series Product , the supported data types are half and float.
srcLocal	Input	Source operand. The type is LocalTensor, and the supported TPosition is VECIN, VECCALC, or VECOUT. The start address of the LocalTensor must be 32-byte aligned. For the Atlas Training Series Product , the supported data types are half and float.
scalarValue	Input	Source operand (scalar). The supported data types are half and float. The data type of scalarValue must be the same as that of srcLocal.
calCount	Input	Number of elements of the input data. The parameter value range is related to the operand data type. The maximum number of elements that can be processed varies according to the data type. The Vector Unit reads 256 bytes of contiguous data for computation each time. The unit needs to read and compute the input data in multiple repeats. Therefore, when the operand is of 16-bit, calCount ∈ [1, 128255], where 255 indicates the maximum number of iterations, and 128 indicates that 128 pieces of 16-bit data can be processed in each iteration. When the operand is of 32-bit, calCount* ∈ [1, 64*255], where 64 indicates that 64 pieces of 32-bit data can be processed in each iteration.
mask	Input	mask is used to control the elements that participate in computation in each iteration. Contiguous mode: indicates the number of contiguous elements that participate in computation. The value range is related to the operand data type. The maximum number of elements that can be processed in each iteration varies according to the data type. When the operand is 16-bit, mask ∈ [1, 128]. When the operand is 32-bit, mask ∈ [1, 64]. When the operand is 64-bit, mask ∈ [1, 32]. Bitwise mode: controls the elements that participate in computation by bit. If a bit is set to 1, the corresponding element participates in the computation. If a bit is set to 0, the corresponding element is masked in the computation. The parameter type is a uint64_t array whose length is 2. For example, if mask = [0, 8] and 8 = 0b1000, only the fourth element participates in computation. The parameter value range is related to the operand data type. The maximum number of elements that can be processed in each iteration varies according to the data type. When the operand is 16-bit, mask[0] and mask[1] ∈ [0, 2⁶⁴ -1] and cannot be 0 at the same time. When the operand is 32-bit, mask[1] is 0 and mask[0] ∈ (0, 2⁶⁴ – 1]. When the operand is 64-bit, mask[1] is 0 and mask[0] ∈ (0, 2³² – 1].
repeatTimes	Input	Number of iteration repeats. The Vector Unit reads 256 bytes of contiguous data for computation each time. To read the complete data for processing, the unit needs to read the input data in multiple repeats. repeatTimes indicates the number of iterations. For details about this parameter, see Common Parameters.
repeatParams	Input	Parameters that control the operand address strides. They are of the UnaryRepeatParams type, and contain such parameters as those that specify the address stride of the operand for the same data block between adjacent iterations and address stride of the operand between different data blocks in a single iteration. For details about the address stride of the operand between adjacent iterations, see repeatStride. For details about the address stride of the operand between different data blocks in a single iteration, see dataBlockStride.

Returns

None

Availability

Atlas Training Series Product

Constraints

To save memory space, you can define a tensor shared by the source and destination operands (by address overlapping). The general instruction restrictions are as follows.
- For a single repeat, the source operand must completely overlap the destination operand.
- For multiple repeats (repeatTimes > 1), if there is a dependency between the source operand and the destination operand, that is, the destination operand of the Nth iteration is the source operand of the (N+1)th iteration, address overlapping is not allowed.

The supported precision combinations are as follows.
- half type: srcLocal data type = half; scalar data type = half; dstLocal data type = half; PAR = 128
- float type: srcLocal data type = float; scalar data type = float; dstLocal data type = float; PAR = 64
- mix type: srcLocal data type = half; scalar data type = half; dstLocal data type = float; PAR = 64

When the high-dimensional tensor sharding computation APIs and mixed precision are used, the number of source operand elements processed in an iteration must be the same as that of destination operand elements. Therefore, the first four data blocks are selected for computation in each iteration. This restriction needs to be considered when you set the repeatStride parameter, mask parameter, and address overlapping.

Examples

This example shows only part of the code used in the computation process (Compute). To run the sample code, copy the code snippet and replace parts of code of the Compute function in the complete sample template in More Samples.

Example of high-dimensional tensor sharding computation (contiguous mask mode)

        
             // repeatTimes = 4, mask = 128, 128 elements one repeat, 512 elements total
// half type
// dstBlkStride, srcBlkStride = 1, no gap between blocks in one repeat
// dstRepStride, srcRepStride = 8, no gap between repeats 
AscendC::Axpy(dstLocal, srcLocal, (half)2.0, 128, 4,{ 1, 1, 8, 8 });

// mix type, dstLocal data type = float
// repeatTimes = 8, mask = 64, 64 elements one repeat, 512 elements total
// dstBlkStride, srcBlkStride = 1, no gap between blocks in one repeat
// dstRepStride = 8, srcRepStride = 4, no gap between repeats 
AscendC::Axpy(dstLocal, srcLocal, (half)2.0, 64, 8,{ 1, 1, 8, 4 }); // Select the first four data blocks of the source operand for computation in each iteration.

Example of high-dimensional tensor sharding computation (bitwise mask mode)

        
             uint64_t mask[2] = { 0xFFFFFFFFFFFFFFFF, 0xFFFFFFFFFFFFFFFF };
// repeatTimes = 4, 128 elements one repeat, 512 elements total, half type
// dstBlkStride, srcBlkStride = 1, no gap between blocks in one repeat
// dstRepStride, srcRepStride = 8, no gap between repeats
AscendC::Axpy(dstLocal, srcLocal, (half)2.0, mask, 4,{ 1, 1, 8, 8 });

Example of computing the first n pieces of data of a tensor

        
             AscendC::Axpy(dstLocal, src0Local, (half)2.0, 512);// half type

Parent topic: Triple-operand Scalar Instructions