CreateVecIndex

Applicability

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

Function Usage

Creates a vector index with a specified start value.

Prototype

Computation of the first n data elements of a tensor

        
             template <typename T>
__aicore__ inline void CreateVecIndex(LocalTensor<T> dst, const T &firstValue, uint32_t count)

High-dimensional tensor sharding computation

Bitwise mask mode

          
               template <typename T>
__aicore__ inline void CreateVecIndex(LocalTensor<T> &dst, const T &firstValue, uint64_t mask[], uint8_t repeatTime, uint16_t dstBlkStride, uint8_t dstRepStride)

Contiguous mask mode

          
               template <typename T>
__aicore__ inline void CreateVecIndex(LocalTensor<T> &dst, const T &firstValue, uint64_t mask, uint8_t repeatTime, uint16_t dstBlkStride, uint8_t dstRepStride)

Parameters

**Table 1** Parameters in the template
Parameter	Description
T	Operand data type. For the Atlas inference product AI Core, the supported data types are int16_t, half, int32_t, and float. For the Atlas A2 training product / Atlas A2 inference product , the supported data types are int16_t, half, int32_t, and float. For the Atlas A3 training product / Atlas A3 inference product , the supported data types are int16_t, half, int32_t, and float. For the Atlas 200I/500 A2 inference product , the supported data types are int16_t, half, int32_t, and float. For the Atlas 350 Accelerator Card, the supported data types are int8_t, int16_t, half, int32_t, float, and int64_t.

**Table 2** Parameters
Parameter	Input/Output	Meaning
dst	Output	Destination operand. The type is LocalTensor, and TPosition can be VECIN, VECCALC, or VECOUT. The start address of LocalTensor must be 32-byte aligned.
firstValue	Input	First value of the index. The data type must be the same as that of the elements in dst.
count	Input	Number of elements involved in the computation.
mask/mask[]	Input	mask controls the elements that participate in computation in each iteration. 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 from the computation. The mask value is an array. The array length and the value range of the array elements are related to the operand data type. When the operand is 16-bit, the array length is 2, with mask[0] and mask[1] each in the range [0, 2⁶⁴ – 1], and they cannot both be 0 at the same time. When the operand is 32-bit, the array length is 1, with mask[0] in the range (0, 2⁶⁴ – 1]. When the operand is 64-bit, the array length is 1, with mask[0] in the range (0, 2³² – 1]. For example, if mask = [0, 8] and 8 = 0b1000, only the fourth element participates in computation. 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].
repeatTime	Input	Number of iteration repeats. The vector compute unit reads 256 bytes of contiguous data for computation each time. To process the input data, the data needs to be read and computed over multiple repeats. repeatTime indicates the number of repeats. For details about this parameter, see High-dimensional Sharding APIs.
dstBlkStride	Input	Address stride of the destination operand between different data blocks in a single repeat.
dstRepStride	Input	Address stride of the destination operand for the same data block between adjacent repeats.

Returns

None

Restrictions

For details about the operand address alignment requirements, see General Address Alignment Restrictions.
Ensure that the value of firstValue does not exceed the value range corresponding to the data type of elements in dst.
For the Atlas 350 Accelerator Card, only the APIs that compute the first n data elements of a tensor are supported for the int8_t and int64_t data types.

Examples

These examples show only part of the code used in the computation.

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

        
             // repeatTime = 1, mask = 128, 128 elements one repeat, 128 elements total
// The data type of firstValue is int16_t, and the data type of dstLocal is int16_t.
// dstBlkStride = 1. Data is continuously written in a single repeat.
// dstRepStride = 8, continuous data write between adjacent repeats.
AscendC::CreateVecIndex(dstLocal, (int16_t)0, mask, repeatTime, dstBlkStride, dstRepStride);

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

        
             uint64_t mask[2] = { UINT64_MAX, UINT64_MAX };
// repeatTime = 1, 128 elements one repeat, 128 elements total
// The data type of firstValue is int16_t, and the data type of dstLocal is int16_t.
// dstBlkStride = 1. Data is continuously written in a single repeat.
// dstRepStride = 8, continuous data write between adjacent repeats.
AscendC::CreateVecIndex(dstLocal, (int16_t)0, mask, repeatTime, dstBlkStride, dstRepStride);

Example of computing the first n data elements of a tensor

        
             uint32_t count = 128;    // Number of elements involved in computation
AscendC::CreateVecIndex(dstLocal, (int16_t)0, count);

Result example:

Input (firstValue): 0
Output (dstLocal): [0 1 2... 127]

Parent topic: Data Padding