aclnnTransQuantParamV2
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“aclnnTransQuantParamV2GetWorkspaceSize”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“aclnnTransQuantParamV2”接口执行计算。
aclnnStatus aclnnTransQuantParamV2GetWorkspaceSize(const aclTensor* scale, const aclTensor* offset, const aclTensor* out, uint64_t* workspaceSize, aclOpExecutor** executor)
aclnnStatus aclnnTransQuantParamV2(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, const aclrtStream stream)
功能描述
- 算子功能:完成量化计算参数scale数据类型的转换
aclnnTransQuantParamV2GetWorkspaceSize
参数说明:
- scale(const aclTensor*, 计算输入):公式中的输入scale,量化参数,device侧的aclTensor,数据类型支持Float32,数据格式支持ND,shape是1维(t,),t = 1或n,以及2维(1,n)其中n与matmul计算中的x2的n一致。用户需要保证scale数据中不存在nan和inf。
- offset(const aclTensor*, 计算输入):公式中的输入offset,量化参数,device侧的aclTensor,数据类型支持Float32,数据格式支持ND,shape是1维(t,),以及2维(1,n),t = 1或n,其中n与matmul计算中的x2的n一致。用户需要保证offset数据中不存在nan和inf。
- out(aclTensor*, 计算输出):公式中的输出out,device侧的aclTensor, 数据类型支持UINT64,INT64, 支持非连续的Tensor,数据格式支持ND,shape和输入保持一致。当offset不为nullptr时,t取scale和offset维度值的最大值。
- 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验,出现以下场景时报错:
161001(ACLNN_ERR_PARAM_NULLPTR):1. 传入的scale或out是空指针。
161002(ACLNN_ERR_PARAM_INVALID):1. scale、offset或out的数据类型和数据格式不在支持的范围之内。
2. offset、scale的shape不是(t,)或者(1, n)。t = 1或n,其中n与matmul计算中的x2的n一致。
aclnnTransQuantParamV2
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aclnnTransQuantParamV2GetWorkspaceSize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 <memory>
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_trans_quant_param_v2.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 aclnnTransQuantParamV2Test(int32_t deviceId, 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> offsetShape = {3};
std::vector<int64_t> scaleShape = {3};
std::vector<int64_t> outShape = {3};
void* scaleDeviceAddr = nullptr;
void* offsetDeviceAddr = nullptr;
void* outDeviceAddr = nullptr;
aclTensor* scale = nullptr;
aclTensor* offset = nullptr;
aclTensor* out = nullptr;
std::vector<float> scaleHostData = {1, 1, 1};
std::vector<float> offsetHostData = {1, 1, 1};
std::vector<uint64_t> outHostData = {1, 1, 1};
// 创建scale aclTensor
ret = CreateAclTensor(scaleHostData, scaleShape, &scaleDeviceAddr, aclDataType::ACL_FLOAT, &scale);
std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> scaleTensorPtr(scale, aclDestroyTensor);
std::unique_ptr<void, aclError (*)(void *)> scaleDeviceAddrPtr(scaleDeviceAddr, aclrtFree);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建offset aclTensor
ret = CreateAclTensor(offsetHostData, offsetShape, &offsetDeviceAddr, aclDataType::ACL_FLOAT, &offset);
std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> offsetTensorPtr(offset, aclDestroyTensor);
std::unique_ptr<void, aclError (*)(void *)> offsetDeviceAddrPtr(offsetDeviceAddr, aclrtFree);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建out aclTensor
ret = CreateAclTensor(outHostData, outShape, &outDeviceAddr, aclDataType::ACL_UINT64, &out);
std::unique_ptr<aclTensor, aclnnStatus (*)(const aclTensor *)> outTensorPtr(out, aclDestroyTensor);
std::unique_ptr<void, aclError (*)(void *)> outDeviceAddrPtr(outDeviceAddr, aclrtFree);
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aclnnaclnnTransQuantParamV2第一段接口
ret = aclnnTransQuantParamV2GetWorkspaceSize(scale, offset, out, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTransQuantParamV2GetWorkspaceSize 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_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
workspaceAddrPtr.reset(workspaceAddr);
}
// 调用aclnnTransQuantParamV2第二段接口
ret = aclnnTransQuantParamV2(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTransQuantParamV2 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<uint64_t> 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: %lu\n", i, resultData[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 = aclnnTransQuantParamV2Test(deviceId, stream);
CHECK_FREE_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTransQuantParamV2Test failed. ERROR: %d\n", ret); return ret);
Finalize(deviceId, stream);
return 0;
}