SetCmpMask (ISASI)

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	x
Atlas inference product's AI Core	√
Atlas inference product's Vector Core	x
Atlas training products	x

Function Usage

Sets the comparison register for the APIs where Select does not specify the mask parameter. Different data is specified based on different selMode values.

Mode 0 (SELMODE::VSEL_CMPMASK_SPR)
The selMask LocalTensor is specified in SetCmpMask.

Mode 1 (SELMODE::VSEL_TENSOR_SCALAR_MODE)
Pass the src1 LocalTensor to SetCmpMask.

Mode 2 (SELMODE::VSEL_TENSOR_TENSOR_MODE)
LocalTensor is specified in SetCmpMask, and LocalTensor stores the address of selMask.

Prototype

template <typename T>
__aicore__ inline void SetCmpMask(const LocalTensor<T>& src)

Parameters

**Table 1** Parameters in the template
Parameter	Description
T	Data type of the operand.

**Table 2** Parameters
Parameter	Input/Output	Description
src	Input	The type is LocalTensor, and the supported TPosition is VECIN, VECCALC, or VECOUT. The start address of the LocalTensor must be 16-byte aligned.

Returns

None

Constraints

None

Examples

When selMode is set to mode 0 or mode 2:

uint32_t dataSize = 256;
uint32_t selDataSize = 8;
TPipe pipe;
TQue<TPosition::VECIN, 1> inQueueX;
TQue<TPosition::VECIN, 1> inQueueY;
TQue<TPosition::VECIN, 1> inQueueSel;
TQue<TPosition::VECOUT, 1> outQueue;
pipe.InitBuffer(inQueueX, 1, dataSize * sizeof(float));
pipe.InitBuffer(inQueueY, 1, dataSize * sizeof(float));
pipe.InitBuffer(inQueueSel, 1, selDataSize * sizeof(uint8_t));
pipe.InitBuffer(outQueue, 1, dataSize * sizeof(float));
AscendC::LocalTensor<float> dst = outQueue.AllocTensor<float>();
AscendC::LocalTensor<uint8_t> sel = inQueueSel.AllocTensor<uint8_t>();
AscendC::LocalTensor<float> src0 = inQueueX.AllocTensor<float>();
AscendC::LocalTensor<float> src1 = inQueueY.AllocTensor<float>();
uint8_t repeat = 4;
uint32_t mask = 64;
AscendC::BinaryRepeatParams repeatParams = { 1, 1, 1, 8, 8, 8 };

// Set selMode to mode 0 (SELMODE::VSEL_CMPMASK_SPR).
AscendC::SetCmpMask(sel);
AscendC::PipeBarrier<PIPE_V>();
AscendC::SetVectorMask<float>(mask);
AscendC::Select<float, AscendC::SELMODE::VSEL_CMPMASK_SPR>(dst, src0, src1, repeat, repeatParams);

// Set selMode to mode 2 (SELMODE::VSEL_TENSOR_TENSOR_MODE).
AscendC::LocalTensor<int32_t> tempBuf;
#if defined(ASCENDC_CPU_DEBUG) && (ASCENDC_CPU_DEBUG = = 1) // CPU debugging
tempBuf.ReinterpretCast<int64_t>().SetValue(0, reinterpret_cast<int64_t>(reinterpret_cast<__ubuf__ int64_t*>(sel.GetPhyAddr())));
event_t eventIdSToV = static_cast<event_t>(AscendC::GetTPipePtr()->FetchEventID(AscendC::HardEvent::S_V));
AscendC::SetFlag<AscendC::HardEvent::S_V>(eventIdSToV);
AscendC::WaitFlag<AscendC::HardEvent::S_V>(eventIdSToV);
#else // NPU debugging
uint32_t selAddr = static_cast<uint32_t>(reinterpret_cast<int64_t>(reinterpret_cast<__ubuf__ int64_t*>(sel.GetPhyAddr())));
AscendC::SetVectorMask<uint32_t>(32);
AscendC::Duplicate<uint32_t, false>(tempBuf.ReinterpretCast<uint32_t>(), selAddr, AscendC::MASK_PLACEHOLDER, 1, 1, 8);
AscendC::PipeBarrier<PIPE_V>();
#endif
AscendC::SetCmpMask<int64_t>(tempBuf.ReinterpretCast<int64_t>());
AscendC::PipeBarrier<PIPE_V>();
AscendC::SetVectorMask<float>(mask);
AscendC::Select<float, AscendC::SELMODE::VSEL_TENSOR_TENSOR_MODE>(dst, src0, src1, repeat, repeatParams);

When selMode is set to mode 1:

uint32_t dataSize = 256;
uint32_t selDataSize = 8;
TPipe pipe;
TQue<TPosition::VECIN, 1> inQueueX;
TQue<TPosition::VECIN, 1> inQueueY;
TQue<TPosition::VECIN, 1> inQueueSel;
TQue<TPosition::VECOUT, 1> outQueue;
pipe.InitBuffer(inQueueX, 1, dataSize * sizeof(float));
pipe.InitBuffer(inQueueY, 1, dataSize * sizeof(float));
pipe.InitBuffer(inQueueSel, 1, selDataSize * sizeof(uint8_t));
pipe.InitBuffer(outQueue, 1, dataSize * sizeof(float));
AscendC::LocalTensor<float> dst = outQueue.AllocTensor<float>();
AscendC::LocalTensor<uint8_t> sel = inQueueSel.AllocTensor<uint8_t>();
AscendC::LocalTensor<float> src0 = inQueueX.AllocTensor<float>();
AscendC::LocalTensor<float> tmpScalar = inQueueY.AllocTensor<float>();

uint8_t repeat = 4;
uint32_t mask = 64;
AscendC::BinaryRepeatParams repeatParams = { 1, 1, 1, 8, 8, 8 };

// Set selMode to mode 1 (SELMODE::VSEL_TENSOR_SCALAR_MODE).
AscendC::SetVectorMask<uint32_t>(32);
AscendC::Duplicate<float, false>(tmpScalar, static_cast<float>(1.0), MASK_PLACEHOLDER, 1, 1, 8);
AscendC::PipeBarrier<PIPE_V>();
AscendC::SetCmpMask(tmpScalar);
AscendC::PipeBarrier<PIPE_V>();
AscendC::SetVectorMask<float>(mask);
AscendC::Select(dst, sel, src0, repeat, repeatParams);

Parent topic: Comparison and selection