aclnnSignBitsPack
支持的产品型号
Atlas 推理系列产品 。Atlas A2 训练系列产品/Atlas 800I A2 推理产品 。
接口原型
每个算子分为两段式接口,必须先调用“aclnnSignBitsPackGetWorkspaceSize”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“aclnnSignBitsPack”接口执行计算。
aclnnStatus aclnnSignBitsPackGetWorkspaceSize(const aclTensor* self, int64_t size, aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)
aclnnStatus aclnnSignBitsPack(void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)
功能描述
将float16类型或者float32类型的1位Adam打包为uint8。
aclnnSignBitsPackGetWorkspaceSize
参数说明:
self(aclTensor*,计算输入):表示用于计算的1D张量,Device侧的tensor,支持空tensor场景,数据类型支持FLOAT16和FLOAT。支持非连续的Tensor。支持数据格式为ND。
size(int64_t,计算输入): 表示处理维度,reshape时输出张量的第一个维度。
out(aclTensor*,计算输出): 输出的tensor,数据类型支持UINT8。支持数据格式为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。
第一段接口完成入参校检,出现以下场景时报错:
161001 (ACLNN_ERR_PARAM_NULLPTR):1. 传入的self或out是空指针。
161002 (ACLNN_ERR_PARAM_INVALID):1. 传入的self或out的数据类型/数据格式不在支持的范围之内。
2. self的维度不是一维。
3. size小于0。
4. self的元素个数/8不能被size整除。
aclnnSignBitsPack
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,由第一段接口aclnnSignBitsPackGetWorkspaceSize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
无。
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 <memory>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_sign_bits_pack.h"
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while (0)
#define CHECK_FREE_RET(cond, return_expr) \
do { \
if (!(cond)) { \
Finalize(deviceId, stream); \
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;
}
void Finalize(int32_t deviceId, aclrtStream& stream)
{
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
}
int aclnnSignBitsPackTest(int32_t deviceId, aclrtStream& stream) {
auto ret = Init(deviceId, &stream);
CHECK_FREE_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
int64_t outsize = 2;
std::vector<int64_t> selfShape = {14};
std::vector<int64_t> outShape = {2,1};
void* selfDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* self = nullptr;
aclTensor* out = nullptr;
std::vector<float> selfHostData{5, 4, 3, 2, 0, -1, -2, 4, 3, 2, 1, 0, -1, -2};
std::vector<uint8_t> outHostData{0, 0};
// 创建self aclTensor
ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> selfTensorPtr(self, aclDestroyTensor);
std::unique_ptr<void, aclError (*)(void *)> selfDeviceAddrPtr(selfDeviceAddr, aclrtFree);
CHECK_FREE_RET(ret == ACL_SUCCESS, return ret);
// 创建out aclTensor
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_UINT8, &out);
std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> outTensorPtr(out, aclDestroyTensor);
std::unique_ptr<void, aclError (*)(void *)> outDeviceAddrPtr(outDeviceAddr, aclrtFree);
CHECK_FREE_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aclnnSignBitsPack第一段接口
ret = aclnnSignBitsPackGetWorkspaceSize(self,
outsize,
out,
&workspaceSize,
&executor);
CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSignBitsPackGetWorkspaceSize 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;
std::unique_ptr<void, aclError (*)(void *)> workspaceAddrPtr(nullptr, aclrtFree);
if (workspaceSize > 0) {
ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
workspaceAddrPtr.reset(workspaceAddr);
}
// 调用aclnnSignBitsPack第二段接口
ret = aclnnSignBitsPack(workspaceAddr, workspaceSize, executor, stream);
CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSignBitsPack 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_FREE_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<uint8_t> outData(size, 0);
ret = aclrtMemcpy(outData.data(), outData.size() * sizeof(outData[0]), outDeviceAddr,
size * sizeof(outData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
CHECK_FREE_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("out result[%ld] is: %u\n", i, outData[i]);
}
return ACL_SUCCESS;
}
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 = aclnnSignBitsPackTest(deviceId, stream);
CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnSignBitsPackTest failed. ERROR: %d\n", ret); return ret);
Finalize(deviceId, stream);
return 0;
}