SubReluCast

Applicability

Product	Supported/Unsupported
Atlas A3 training products / Atlas A3 inference products	√
Atlas A2 training products / Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	√
Atlas inference product 's AI Core	√
Atlas inference product 's Vector Core	x
Atlas training products	x

Function Usage

Computes the difference element-wise, performs ReLU computation (chooses the larger between the result and 0), and converts precision based on the data types of the source and destination operand tensors. The calculation formula is as follows, where dstType indicates the data type of the destination operand:

$\text{[math]}$

Prototype

Computation of the first n pieces of data of a tensor

        
             template <typename T, typename U>
__aicore__ inline void SubReluCast(const LocalTensor<T>& dst, const LocalTensor<U>& src0, const LocalTensor<U>& src1, const uint32_t count)

High-dimensional tensor sharding computation

Bitwise mask mode

          
               template <typename T, typename U, bool isSetMask = true>
__aicore__ inline void SubReluCast(const LocalTensor<T>& dst, const LocalTensor<U>& src0, const LocalTensor<U>& src1, uint64_t mask[], const uint8_t repeatTime, const BinaryRepeatParams& repeatParams)

Contiguous mask mode

          
               template <typename T, typename U, bool isSetMask = true>
__aicore__ inline void SubReluCast(const LocalTensor<T>& dst, const LocalTensor<U>& src0, const LocalTensor<U>& src1, uint64_t mask, const uint8_t repeatTime, const BinaryRepeatParams& repeatParams)

Parameters

**Table 1** Parameters in the template
Parameter	Description
T	Data type of the destination operand. For details about precision conversion rules for different data types, see Table 3. Atlas A3 training products / Atlas A3 inference products : The supported data types are int8_t and half. Atlas A2 training products / Atlas A2 inference products : The supported data types are int8_t and half. Atlas 200I/500 A2 inference products : The supported data types are int8_t and half. Atlas inference product 's AI Core: The supported data types are int8_t and half.
U	Data type of the source operand. Atlas A3 training products / Atlas A3 inference products : The supported data types are int16_t, half, and float. Atlas A2 training products / Atlas A2 inference products : The supported data types are int16_t, half, and float. For the Atlas 200I/500 A2 inference products , the supported data types are half and float. Atlas inference product 's AI Core: The supported data types are int16_t, half, and float.
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 the placeholder MASK_PLACEHOLDER.

**Table 2** Parameters
Parameter	Input/Output	Description
dst	Output	Destination operand. The type is LocalTensor, and the supported TPosition is VECIN, VECCALC, or VECOUT.
src0, src1	Input	Source operand. The type is LocalTensor, and the supported TPosition is VECIN, VECCALC, or VECOUT.
count	Input	Number of elements involved in the computation.
mask[]/mask	Input	The mask parameter is used to control the elements involved 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 in the computation. The mask is in array form. The array length and the value range of the array elements are related to the data type of the operand. When the operand is 16-bit, the array length is 2. In this case, mask[0] and mask[1] must be in the range of [0, 2⁶⁴ – 1] and cannot be 0 at the same time. When the operand is 32-bit, the array length is 1. In this case, mask[0] must be in the range of (0, 2⁶⁴ – 1]. When the operand is 64-bit, the array length is 1. In this case, mask[0] must be in the range of (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 repeat 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]. When the number of bits of the source operand is different from that of the destination operand, the data type with more bytes is used for the computation. For example, if the source operand is of the half type and the destination operand is of the int8_t type, half is used to compute the mask.
repeatTime	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. repeatTime indicates the number of repeats. For details about this parameter, see High-dimensional Sharding APIs.
repeatParams	Input	Parameters that control the operand address strides. They are of the BinaryRepeatParams 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 parameters between adjacent iterations, see repeatStride. For details about the address stride parameters of DataBlock in the same iteration, see dataBlockStride.

**Table 3** Precision conversion rules
Source Operand	Destination Operand	Type Conversion Mode
float	half	Rounds the source operand according to CAST_NONE and writes the result in half format to the destination operand (the overflow part is saturated).
half	int8_t	Rounds the source operand according to CAST_NONE and writes the result in int8_t format to the destination operand (the overflow part is saturated).
int16_t	int8_t	Rounds the source operand according to CAST_NONE and writes the result in int8_t format to the destination operand (the overflow part is saturated).

Returns

None

Examples

In this example, srcLocal is of the half type, and dstLocal is of the int8_t type. The mask is computed based on half.

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

        
             uint64_t mask = 256 / sizeof(half); // 128
// repeatTime = 4. 128 elements are computed in each iteration, and 512 elements are computed in total.
// dstBlkStride, src0BlkStride, src1BlkStride = 1. Data is continuously read and written in a single repeat.
// dstRepStride = 4, src0RepStride, src1RepStride = 8. Data is continuously read and written between adjacent iterations.
AscendC::SubReluCast(dstLocal, src0Local, src1Local, mask, 4, { 1, 1, 1, 4, 8, 8 });

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

        
             uint64_t mask[2] = { UINT64_MAX, UINT64_MAX };
// repeatTime = 4. 128 elements are computed in each iteration, and 512 elements are computed in total.
// dstBlkStride, src0BlkStride, src1BlkStride = 1. Data is continuously read and written in a single repeat.
// dstRepStride = 4, src0RepStride, src1RepStride = 8. Data is continuously read and written between adjacent iterations.
AscendC::SubReluCast(dstLocal, src0Local, src1Local, mask, 4, { 1, 1, 1, 4, 8, 8 });

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

        
             AscendC::SubReluCast(dstLocal, src0Local, src1Local, 512);

Result example:

Input (src0Local): [1 2 3 ... 512]
Input (src1Local): [0 0.5 4 ... 513]
Output (dstLocal): [1 2 0 ... 0]

Parent topic: Complex computation