aclnnSwiGluGrad
支持的产品型号
- Atlas A2训练系列产品/Atlas 800I A2推理产品。
- Atlas 推理系列产品。
接口原型
每个算子分为两段式接口,必须先调用“aclnnSwiGluGradGetWorkspaceSize”接口获取计算所需workspace大小以及包含了算子计算流程的执行器,再调用“aclnnSwiGluGrad”接口执行计算。
aclnnStatus aclnnSwiGluGradGetWorkspaceSize(const aclTensor *yGrad, const aclTensor *x, int64_t dimOptional, const aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)
aclnnStatus aclnnSwiGluGrad(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)
功能描述
- 算子功能:完成aclnnSwiGlu的反向计算, 完成x的SwiGlu反向梯度计算。
- 计算公式:
outA = yGradi*[sigmoid(A)+sigmoid(A)*(1-sigmoid(A)*A)]*B
outB = yGradi*sigmoid(A)*A
其中,A表示x的前半部分,B表示x的后半部分。 outA和outB合并为out。
aclnnSwiGluGradGetWorkspaceSize
参数说明:
- yGrad(aclTensor*,计算输入):Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,shape中除dimOptional维外,其它维的大小跟x一样,dimOptional维的大小是x的一半,支持非连续的Tensor,数据格式支持ND。
- x(aclTensor*,计算输入):Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,shape中除dimOptional维外,其它维的大小跟yGrad一样,dimOptional维的大小是yGrad的两倍,支持非连续的Tensor,数据格式支持ND。
- dimOptional(int64_t,入参):需要进行切分的维度序号,默认-1(表示最后一维),数据类型支持INT64。
- out(aclTensor*,计算输出):Device侧的aclTensor,数据类型支持FLOAT、FLOAT16、BFLOAT16,shape需要与x一样,支持非连续的Tensor,数据格式支持ND。
- workspaceSize(uint64_t*,出参):返回需要在Device侧申请的workspace大小。
- executor(aclOpExecutor**,出参):返回op执行器,包含了算子计算流程。
返回值: aclnnStatus:返回状态码,具体参见aclnn返回码。
aclnnSwiGluGrad
参数说明:
- workspace(void *, 入参):在Device侧申请的workspace内存地址。
- workspaceSize(uint64_t, 入参):在Device侧申请的workspace大小,由第一段接aclnnSwiGluGradGetWorkspaceSize获取。
- executor(aclOpExecutor *, 入参):op执行器,包含了算子计算流程。
- stream(aclrtStream, 入参):指定执行任务的AscendCL Stream流。
返回值: aclnnStatus:返回状态码,具体参见aclnn返回码。
约束与限制
- Atlas 推理系列产品:不支持BFLOAT16,不支持非64字节对齐。
调用示例
示例代码如下,仅供参考,具体编译和执行过程请参考编译与运行样例。
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_swi_glu_grad.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) {
// 固定写法,AscendCL初始化
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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
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);
// 计算连续tensor的strides
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];
}
// 调用aclCreateTensor接口创建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. (固定写法)device/stream初始化,参考AscendCL对外接口列表
// 根据自己的实际device填写deviceId
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. 构造输入与输出,需要根据API的接口自定义构造
std::vector<int64_t> yGradShape = {2, 16};
std::vector<int64_t> xShape = {2, 32};
std::vector<int64_t> outShape = {2, 32};
void* yGradDeviceAddr = nullptr;
void* xDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* yGrad = nullptr;
aclTensor* x = nullptr;
aclTensor* out = nullptr;
std::vector<float> yGradHostData = {-2, -1, 0, 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};
std::vector<float> xHostData = {-2, -1, 0, 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};
std::vector<float> outHostData = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
int dimOptional = -1;
// 创建yGrad aclTensor
ret = CreateAclTensor(yGradHostData, yGradShape, &yGradDeviceAddr, aclDataType::ACL_FLOAT,
&yGrad);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建x aclTensor
ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建out aclTensor
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_FLOAT, &out);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. 调用CANN算子库API,需要修改为具体的Api名称
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
// 调用aclnnSwiGluGrad第一段接口
ret = aclnnSwiGluGradGetWorkspaceSize(yGrad, x, dimOptional, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSwiGluGradGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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);
}
// 调用aclnnSwiGluGrad第二段接口
ret = aclnnSwiGluGrad(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSwiGluGrad failed. ERROR: %d\n", ret); return ret);
// 4. (固定写法)同步等待任务执行结束
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 5. 获取输出的值,将device侧内存上的结果拷贝至host侧,需要根据具体API的接口定义修改
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]);
}
// 6. 释放aclTensor和aclScalar,需要根据具体API的接口定义修改
aclDestroyTensor(yGrad);
aclDestroyTensor(x);
aclDestroyTensor(out);
// 7. 释放device资源,需要根据具体API的接口定义修改
aclrtFree(yGradDeviceAddr);
aclrtFree(xDeviceAddr);
aclrtFree(outDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}