Trunc

Applicability

Function

Truncates floating point numbers element-wise, that is, rounding towards zero. The formula is as follows:

Examples:

Trunc(3.9) = 3

Trunc(-3.9) = -3

Prototype

• Pass the temporary space through the sharedTmpBuffer input parameter.
  • All or part of the source operand tensors are involved in computation.

    1 2	template <typename T, bool isReuseSource = false> __aicore__ inline void Trunc(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const LocalTensor<uint8_t>& sharedTmpBuffer, const uint32_t calCount)

  • All source operand tensors are involved in computation.

    1 2	template <typename T, bool isReuseSource = false> __aicore__ inline void Trunc(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const LocalTensor<uint8_t>& sharedTmpBuffer)

• Allocate the temporary space through the API framework.
  • All or part of the source operand tensors are involved in computation.

    1 2	template <typename T, bool isReuseSource = false> __aicore__ inline void Trunc(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor, const uint32_t calCount)

  • All source operand tensors are involved in computation.

    1 2	template <typename T, bool isReuseSource = false> __aicore__ inline void Trunc(const LocalTensor<T>& dstTensor, const LocalTensor<T>& srcTensor)

Precision conversion is involved in the internal implementation of this API. Therefore, extra temporary space is required to store intermediate variables during computation. The temporary space can be allocated through the API framework or passed by developers through the sharedTmpBuffer input parameter.

• When the API framework is used for temporary space allocation, developers do not need to allocate the space, but must reserve the required size for the space.

• When the sharedTmpBuffer input parameter is used for passing the temporary space, the tensor serves as the temporary space. In this case, the API framework is not required for temporary space allocation. This enables developers to manage the sharedTmpBuffer space and reuse the buffer after calling the API, so that the buffer is not repeatedly allocated and deallocated, improving the flexibility and buffer utilization.

If the API framework is used, developers must reserve the temporary space. If sharedTmpBuffer is used, developers must allocate space for the tensor. To obtain the size of the temporary space (BufferSize) to be reserved, use the API provided in GetTruncMaxMinTmpSize.

Parameters

Returns

None

Restrictions

• For the Atlas inference product's AI Core, the input data must be within the range of [–2147483647.0, 2147483647.0].
• The source operand address can overlap the destination operand address.
• The address of sharedTmpBuffer must not overlap the addresses of the source operand and destination operand.
• For details about the operand address alignment requirements, see General Address Alignment Restrictions.

Example

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64

#include "kernel_operator.h"

template <typename srcType>
class KernelTrunc
{
public:
    __aicore__ inline KernelTrunc(){}
    __aicore__ inline void Init(GM_ADDR srcGm, GM_ADDR dstGm, uint32_t srcSize)
    {
        src_global.SetGlobalBuffer(reinterpret_cast<__gm__ srcType *>(srcGm), srcSize);
        dst_global.SetGlobalBuffer(reinterpret_cast<__gm__ srcType *>(dstGm), srcSize);
        pipe.InitBuffer(inQueueX, 1, srcSize * sizeof(srcType));
        pipe.InitBuffer(outQueue, 1, srcSize * sizeof(srcType));
        bufferSize = srcSize;
    }
    __aicore__ inline void Process()
    {
        CopyIn();
        Compute();
        CopyOut();
    }

private:
    __aicore__ inline void CopyIn()
    {
        AscendC::LocalTensor<srcType> srcLocal = inQueueX.AllocTensor<srcType>();
        AscendC::DataCopy(srcLocal, src_global, bufferSize);
        inQueueX.EnQue(srcLocal);
    }
    __aicore__ inline void Compute()
    {
        AscendC::LocalTensor<srcType> dstLocal = outQueue.AllocTensor<srcType>();
        AscendC::LocalTensor<srcType> srcLocal = inQueueX.DeQue<srcType>();
        AscendC::Trunc<srcType, false>(dstLocal, srcLocal);
        outQueue.EnQue<srcType>(dstLocal);
        inQueueX.FreeTensor(srcLocal);
    }
    __aicore__ inline void CopyOut()
    {
        AscendC::LocalTensor<srcType> dstLocal = outQueue.DeQue<srcType>();
        AscendC::DataCopy(dst_global, dstLocal, bufferSize);
        outQueue.FreeTensor(dstLocal);
    }

private:
    AscendC::GlobalTensor<srcType> src_global;
    AscendC::GlobalTensor<srcType> dst_global;
    AscendC::TPipe pipe;
    AscendC::TQue<AscendC::TPosition::VECIN, 1> inQueueX;
    AscendC::TQue<AscendC::TPosition::VECOUT, 1> outQueue;
    uint32_t bufferSize = 0;
};
template <typename dataType>
__aicore__ void kernel_trunc_operator(GM_ADDR srcGm, GM_ADDR dstGm, uint32_t srcSize)
{
    KernelTrunc<dataType> op;
    op.Init(srcGm, dstGm, srcSize);
    op.Process();
}

extern "C" __global__ __aicore__ void trunc_operator(GM_ADDR srcGm, GM_ADDR dstGm, uint32_t srcSize)
{
    kernel_trunc_operator<half>(srcGm, dstGm, srcSize);
}

1
2

Input data (srcLocal): [0.5317103  -6.37912032  5.53408647 ...  11.11059642 -11.67860335]
Output data (dstLocal): [0.0        -6.0         5.0        ...  11.0        -11.0       ]