aclnnGeGlu

Applicable Products

Product	Supported
Ascend 950PR/Ascend 950DT	√
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas 200I/500 A2 inference products	×
Atlas inference products	√
Atlas training products	×

Function

Description: Gaussian Error Linear Unit (GeGlu) activation function.
Formula:
$out_{i}=GeGlu(self_{i}) = A \cdot Gelu(B)$
Where $A$ represents the first half of $self$ , and $B$ represents the second half of $self$ .

Function Prototype

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

aclnnStatus aclnnGeGluGetWorkspaceSize(
  const aclTensor *self,
  int64_t          dim,
  int64_t          approximate,
  aclTensor       *out,
  aclTensor       *outGelu,
  uint64_t        *workspaceSize,
  aclOpExecutor  **executor)

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

aclnnGeGluGetWorkspaceSize

Parameters:

Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Shape	Non-contiguous Tensor
self (aclTensor*)	Input	Input tensor for the GeGlu computation, corresponding to self in the formula.	-	FLOAT, FLOAT16, BFLOAT16	ND	0-8	√
dim (int64_t)	Input	Optional input parameter.	The specified slice axis requires the corresponding axis of self to be split in half. The axis of self corresponding to dim must be an even number.	INT	-	-	-
approximate (int64_t)	Input	Optional input parameter.	Activation function index used for GeGlu computation. 0 indicates none, and 1 indicates tanh.	INT	-	-	-
out (aclTensor*)	Output	Output parameter of the GeGlu computation, corresponding to out_i in the formula.	The shape of out must be consistent with the shape of self except for the axis specified by dim, where the axis specified by dim is half the size of the corresponding axis of self. The data type is the same as self.	FLOAT, FLOAT16, BFLOAT16	ND	0-8	√
outGelu (aclTensor*)	Output	Output parameter of the GeGlu computation.	The shape of out must be consistent with the shape of self except for the axis specified by dim, where the axis specified by dim is half the size of the corresponding axis of self. The data type is the same as that of self.	FLOAT, FLOAT16, BFLOAT16	ND	0-8	√
workspaceSize (uint64_t*)	Output	Returns the workspace size to be requested on the Device.	-	-	-	-	-
executor (aclOpExecutor**)	Output	Returns the operator executor, which contains the operator computation flow.	-	-	-	-	-

Atlas inference products, Atlas training products: The supported data types are FLOAT and FLOAT16.

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:

Return Code	Error Code	Description
ACLNN_ERR_PARAM_NULLPTR	161001	The self, out, and outGelu parameters are null pointers.
ACLNN_ERR_PARAM_INVALID	161002	The data type of the self, out, or outGelu parameter is not within the supported range.
		The data type of the out or outGelu parameter is inconsistent with that of self.
		The number of dimensions of self, out, and outGelu is greater than 8.
		When self.dim() = 0, the value of dim is not within the range [-1, 0]; when self.dim() > 0, the value of dim is not within the range [-self.dim, self.dim()-1].
		The size of out and outGelu in the dim dimension is not equal to 1/2 of the size of self in the dim dimension.

aclnnGeGlu

Parameters:

Parameter	Input/Output	Description
workspace	Input	Address of the workspace memory applied for on the Device side.
workspaceSize	Input	Size of the workspace applied for on the Device side, obtained through the first-phase API aclnnGeGluGetWorkspaceSize.
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:
- aclnnGeGlu defaults to a deterministic implementation.

Example

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

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_geglu.h"

#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 shapeSize = 1;
    for (auto i : shape) {
        shapeSize *= i;
    }
    return shapeSize;
}

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-side 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);
    // Copy host data to device memory using aclrtMemcpy.
    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 the 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 the aclCreateTensor API 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) Initialize the device/stream. See the ACL API manual.
    // Enter the deviceId based on the actual device.
    int32_t deviceId = 0;
    aclrtStream stream;
    auto ret = Init(deviceId, &stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);

    // 2. Construct the input and output. Customize the construction based on the API.
    std::vector<int64_t> selfShape = {2, 2};
    std::vector<int64_t> outShape = {2, 1};
    void* selfDeviceAddr = nullptr;
    void* outDeviceAddr = nullptr;
    void* outGeluDeviceAddr = nullptr;
    aclTensor* self = nullptr;
    aclTensor* out = nullptr;
    aclTensor* outGelu = nullptr;
    std::vector<float> selfHostData = {0, 1, 2, 3};
    std::vector<float> outHostData = {0, 0};
    std::vector<float> outGeluHostData = {0, 0};
    int dim = -1;
    int approximate = 1;
    // Create the self aclTensor.
    ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the out aclTensor.
    ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
    CHECK_RET(ret == ACL_SUCCESS, return ret);
    // Create the outGelu aclTensor.
    ret = CreateAclTensor(outGeluHostData, outShape, &outGeluDeviceAddr, aclDataType::ACL_FLOAT, &outGelu);
    CHECK_RET(ret == ACL_SUCCESS, return ret);

    // 3. Call the CANN operator library API. Replace with the specific API name.
    uint64_t workspaceSize = 0;
    aclOpExecutor* executor;
    // Call the first-phase API of aclnnGeGlu.
    ret = aclnnGeGluGetWorkspaceSize(self, dim, approximate, out, outGelu, &workspaceSize, &executor);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGeGluGetWorkspaceSize 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 aclnnGeGlu.
    ret = aclnnGeGlu(workspaceAddr, workspaceSize, executor, stream);
    CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnGeGlu 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 the device memory to the host memory. Modify this based on the specific API definition.
    auto size = GetShapeSize(outShape);
    std::vector<float> resultData(size, 0);
    ret = aclrtMemcpy(
        resultData.data(), resultData.size() * sizeof(resultData[0]), outDeviceAddr, size * sizeof(resultData[0]),
        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 < size; i++) {
        LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
    }

    std::vector<float> resultGeluData(size, 0);
    ret = aclrtMemcpy(
        resultGeluData.data(), resultGeluData.size() * sizeof(resultGeluData[0]), outGeluDeviceAddr,
        size * sizeof(resultGeluData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
    CHECK_RET(
        ret == ACL_SUCCESS, LOG_PRINT("copy resultGelu from device to host failed. ERROR: %d\n", ret); return ret);
    for (int64_t i = 0; i < size; i++) {
        LOG_PRINT("result[%ld] is: %f\n", i, resultGeluData[i]);
    }

    // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
    aclDestroyTensor(self);
    aclDestroyTensor(out);
    aclDestroyTensor(outGelu);

    // 7. Release device resources. Modify based on the specific API definition.
    aclrtFree(selfDeviceAddr);
    aclrtFree(outDeviceAddr);
    aclrtFree(outGeluDeviceAddr);
    if (workspaceSize > 0) {
        aclrtFree(workspaceAddr);
    }
    aclrtDestroyStream(stream);
    aclrtResetDevice(deviceId);
    aclFinalize();
    return 0;
}