aclnnMoeInitRouting

📄 View Source Code

Applicable Products

Function

• Description: MoE routing computation. Performs routing processing based on the computation result of aclnnMoeGatingTopKSoftmax.

• Formula:

  Flattens expertIdx with the input shape [NUM_ROWS, K] into a single row for sorting, where NUM_ROWS is the number of input tokens and K is the number of experts selected for each token.

  $$expandedExpertIdxOut,sortedRowIdx=keyValueSort(expertIdx,rowIdx)$$ $$expandedRowIdxOut[sortedRowIdx[i]]=i$$ $$expandedXOut[i]=x[sortedRowIdx[i]\%NUM_ROWS]$$

Function Prototype

Each operator is divided into a two-phase API. The "aclnnMoeInitRoutingGetWorkspaceSize" API must be called first to obtain the workspace size required for computation and the executor that encapsulates the operator computation flow. Then, the "aclnnMoeInitRouting" API is called to perform the computation.

aclnnStatus aclnnMoeInitRoutingGetWorkspaceSize(
    const aclTensor  *x,
    const aclTensor  *rowIdx,
    const aclTensor  *expertIdx,
    int64_t           activeNum,
    const aclTensor  *expandedXOut,
    const aclTensor  *expandedRowIdxOut,
    const aclTensor  *expandedExpertIdxOut,
    uint64_t         *workspaceSize,
    aclOpExecutor   **executor)

aclnnStatus aclnnMoeInitRouting(
    void             *workspace,
    uint64_t          workspaceSize,
    aclOpExecutor    *executor,
    aclrtStream       stream)

aclnnMoeInitRoutingGetWorkspaceSize

• Parameters:

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  x	Input	Token feature input of MoE.	-	FLOAT16, BFLOAT16, FLOAT32	ND	Shape is (NUM_ROWS, H).	√
  rowIdx	Input	Indicates the original row position corresponding to each position.	The value of rowIdx starts from 0 and increments along dimension 1.	INT32	ND	The shape must be the same as that of expertIdx.	√
  expertIdx	Input	K processing experts corresponding to each row of features.	-	INT32	ND	Shape is (NUM_ROWS, K).	√
  activeNum	Input	Indicates the number of valid rows in expandedXOut.	-	-	-	-	-
  expandedXOut	Output	Features expanded based on expertIdx.	-	Same as x.	ND	Shape is (min(NUM_ROWS, activeNum) * k, H).	x
  expandedRowIdxOut	Output	Mapping between expandedX and x.	-	INT32	ND	Shape (NUM_ROWS*K, ).	x
  expandedExpertIdxOut	Output	Outputs the sorted result of expertIdx.	-	INT32	ND	Shape (NUM_ROWS*K, ).	x
  workspaceSize	Output	Returns the workspace size to be requested on the Device side.	-	-	-	-	-
  executor	Output	Returns the op executor, which contains the operator computation flow.	-	-	-	-	-

• Return Value

aclnnStatus: return code. For details, see aclnn Return Code.

The first-phase API performs input parameter validation and returns an error in the following scenarios:

aclnnMoeInitRouting

• Parameters:

  Parameter	Input/Output	Description
  workspace	Input	Memory address of the workspace applied for on the Device side.
  workspaceSize	Input	Size of the workspace applied for on the Device side, obtained from the first-phase API aclnnMoeInitRoutingGetWorkspaceSize.
  executor	Input	Operator executor, which contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return value

  aclnnStatus: return code. For details, see aclnn Return Code.

Constraints

Deterministic computation: aclnnMoeInitRouting defaults to a deterministic implementation. The values of elements in expertIdx must be greater than -2^24 and not exceed 2^24. Otherwise, precision issues may occur.

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include "acl/acl.h"
#include "aclnnop/aclnn_moe_init_routing.h"
#include <iostream>
#include <cstdio>
#include <vector>
#define CHECK_RET(cond, return_expr) \
  do {                               \
    if (!(cond)) {                   \
      return_expr;                   \
    }                                \
  } while (0)
#define LOG_PRINT(message, ...)     \
  do {                              \
    printf(message, ##__VA_ARGS__); \
  } while (0)
int64_t GetShapeSize(const std::vector<int64_t>& shape) {
    int64_t shape_size = 1;
    for (auto i : shape) {
        shape_size *= i;
    }
    return shape_size;
}
int Init(int32_t deviceId, aclrtStream* stream) {
    // Boilerplate for resource initialization.
    auto ret = aclInit(nullptr);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
    ret = aclrtSetDevice(deviceId);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
    ret = aclrtCreateStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
    return 0;
}
template <typename T>
int CreateAclTensor(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                    aclDataType dataType, aclTensor** tensor) {
    auto size = GetShapeSize(shape) * sizeof(T);
    // Call aclrtMalloc to apply for device memory.
    auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
    // Call aclrtMemcpy to copy host data to device memory.
    ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);
    // Calculate the strides of a contiguous tensor.
    std::vector<int64_t> strides(shape.size(), 1);
    for (int64_t i = shape.size() - 2; i >= 0; i--) {
        strides[i] = shape[i + 1] * strides[i + 1];
    }
    // Call aclCreateTensor to create an aclTensor.
    *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                              shape.data(), shape.size(), *deviceAddr);
    return 0;
}
int main() {
    // 1. Boilerplate: device/stream initialization. See the acl external API list.
    // Fill in the deviceId based on your actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    // Handle the check result as needed.
    CHECK_RET(ret == 0, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
    // 2. Construct the inputs and outputs based on the API definition.
    std::vector<int64_t> xShape = {3, 4};
    std::vector<int64_t> idxShape = {3, 2};
    std::vector<int64_t> expandedXOutShape = {6, 4};
    std::vector<int64_t> idxOutShape = {6};
    void* xDeviceAddr = nullptr;
    void* rowIdxDeviceAddr = nullptr;
    void* expertIdxDeviceAddr = nullptr;
    void* expandedXOutDeviceAddr = nullptr;
    void* expandedRowIdxOutDeviceAddr = nullptr;
    void* expandedExpertIdxOutDeviceAddr = nullptr;
    aclTensor* x = nullptr;
    aclTensor* rowIdx = nullptr;
    aclTensor* expertIdx = nullptr;
    int64_t activeNum = 3;
    aclTensor* expandedXOut = nullptr;
    aclTensor* expandedRowIdxOut = nullptr;
    aclTensor* expandedExpertIdxOut = nullptr;
    std::vector<float> xHostData = {0.1, 0.1, 0.1, 0.1, 0.2, 0.2, 0.2, 0.2, 0.3, 0.3, 0.3, 0.3};
    std::vector<int> expertIdxHostData = {1, 2, 0, 1, 0, 2};
    std::vector<int> rowIdxHostData = {0, 3, 1, 4, 2, 5};
    std::vector<float> expandedXOutHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
    std::vector<int> expandedRowIdxOutHostData = {0, 0, 0, 0, 0, 0};
    std::vector<int> expandedExpertIdxOutHostData = {0, 0, 0, 0, 0, 0};
    // Create the self aclTensor.
    ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    ret = CreateAclTensor(rowIdxHostData, idxShape, &rowIdxDeviceAddr, aclDataType::ACL_INT32, &rowIdx);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    ret = CreateAclTensor(expertIdxHostData, idxShape, &expertIdxDeviceAddr, aclDataType::ACL_INT32, &expertIdx);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the out aclTensor.
    ret = CreateAclTensor(expandedXOutHostData, expandedXOutShape, &expandedXOutDeviceAddr, aclDataType::ACL_FLOAT, &expandedXOut);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    ret = CreateAclTensor(expandedRowIdxOutHostData, idxOutShape, &expandedRowIdxOutDeviceAddr, aclDataType::ACL_INT32, &expandedRowIdxOut);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    ret = CreateAclTensor(expandedExpertIdxOutHostData, idxOutShape, &expandedExpertIdxOutDeviceAddr, aclDataType::ACL_INT32, &expandedExpertIdxOut);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // 3. Call the CANN operator library API. Replace with the specific API.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnMoeInitRouting.
    ret = aclnnMoeInitRoutingGetWorkspaceSize(x, rowIdx, expertIdx, activeNum, expandedXOut, expandedRowIdxOut, expandedExpertIdxOut, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMoeInitRoutingGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
    // Apply for device memory based on the workspaceSize calculated by the first-phase API.
    void* workspaceAddr = nullptr;
    if (workspaceSize > 0) {
        ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
        CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
    }
    // Call the second-phase API of aclnnMoeInitRouting.
    ret = aclnnMoeInitRouting(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnMoeInitRouting failed. ERROR: %d\n", ret); return ret);
    // 4. Boilerplate: synchronize and wait for task execution to complete.
    ret = aclrtSynchronizeStream(stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
    // 5. Obtain the output value and copy the result from device memory to the host. Modify based on the specific API definition.
    auto expandedXSize = GetShapeSize(expandedXOutShape);
    std::vector<float> expandedXData(expandedXSize, 0);
    ret = aclrtMemcpy(expandedXData.data(), expandedXData.size() * sizeof(expandedXData[0]), expandedXOutDeviceAddr, expandedXSize * sizeof(float),
                      ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
    for (int64_t i = 0; i < expandedXSize; i++) {
        LOG_PRINT("expandedXData[%ld] is: %f\n", i, expandedXData[i]);
    }
    auto expandedRowIdxSize = GetShapeSize(idxOutShape);
    std::vector<int> expandedRowIdxData(expandedRowIdxSize, 0);
    ret = aclrtMemcpy(expandedRowIdxData.data(), expandedRowIdxData.size() * sizeof(expandedRowIdxData[0]), expandedRowIdxOutDeviceAddr, expandedRowIdxSize * sizeof(int32_t),
                      ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
    for (int64_t i = 0; i < expandedRowIdxSize; i++) {
        LOG_PRINT("expandedRowIdxData[%ld] is: %d\n", i, expandedRowIdxData[i]);
    }
    auto expandedExpertIdxSize = GetShapeSize(idxOutShape);
    std::vector<int> expandedExpertIdxData(expandedExpertIdxSize, 0);
    ret = aclrtMemcpy(expandedExpertIdxData.data(), expandedExpertIdxData.size() * sizeof(expandedExpertIdxData[0]), expandedExpertIdxOutDeviceAddr, expandedExpertIdxSize * sizeof(int32_t),
                      ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return ret);
    for (int64_t i = 0; i < expandedExpertIdxSize; i++) {
        LOG_PRINT("expandedExpertIdxData[%ld] is: %d\n", i, expandedExpertIdxData[i]);
    }
    // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
    aclDestroyTensor(x);
    aclDestroyTensor(rowIdx);
    aclDestroyTensor(expertIdx);
    aclDestroyTensor(expandedXOut);
    aclDestroyTensor(expandedRowIdxOut);
    aclDestroyTensor(expandedExpertIdxOut);

    // 7. Release device resources. Modify based on the specific API definition.
    aclrtFree(xDeviceAddr);
    aclrtFree(rowIdxDeviceAddr);
    aclrtFree(expertIdxDeviceAddr);
    aclrtFree(expandedXOutDeviceAddr);
    aclrtFree(expandedRowIdxOutDeviceAddr);
    aclrtFree(expandedExpertIdxOutDeviceAddr);
    if (workspaceSize > 0) {
      aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}