aclnnBaddbmm/aclnnInplaceBaddbmm

Atlas 训练系列产品支持该算子。

Atlas A2训练系列产品支持该算子。

接口原型

  • aclnnBaddbmm和aclnnInplaceBaddbmm实现相同的功能，其使用区别如下，请根据自身实际场景选择合适的算子。
    • aclnnBaddbmm：需新建一个输出张量对象存储计算结果。
    • aclnnInplaceBaddbmm：无需新建输出张量对象，直接在输入张量的内存中存储计算结果。
  • 每个算子分为两段接口，必须先调用“aclnnXxxGetWorkspaceSize”接口获取入参并根据计算流程计算所需workspace大小，再调用“aclnnXxx”接口执行计算。

功能描述

aclnnBaddbmmGetWorkspaceSize

aclnnBaddbmm

aclnnInplaceBaddbmmGetWorkspaceSize

aclnnInplaceBaddbmm

约束与限制

对于Atlas 训练系列产品，Cube单元不支持FLOAT32计算。当输入为FLOAT32，可通过设置cubeMathType=1（ALLOW_FP32_DOWN_PRECISION）来允许接口内部cast到FLOAT16进行计算。

调用示例

  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
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_baddbmm.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, aclrtContext* context, 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 = aclrtCreateContext(context, deviceId);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateContext failed. ERROR: %d\n", ret); return ret);
  ret = aclrtSetCurrentContext(*context);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetCurrentContext 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/context/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;
  aclrtContext context;
  aclrtStream stream;
  auto ret = Init(deviceId, &context, &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> selfShape = {1, 2, 4};
  std::vector<int64_t> batch1Shape = {1, 2, 3};
  std::vector<int64_t> batch2Shape = {1, 3, 4};
  std::vector<int64_t> outShape = {1, 2, 4};
  void* selfDeviceAddr = nullptr;
  void* batch1DeviceAddr = nullptr;
  void* batch2DeviceAddr = nullptr;
  void* outDeviceAddr = nullptr;
  aclTensor* self = nullptr;
  aclTensor* batch1 = nullptr;
  aclTensor* batch2 = nullptr;
  aclScalar* alpha = nullptr;
  aclScalar* beta = nullptr;
  aclTensor* out = nullptr;
  std::vector<float> selfHostData = {0, 1, 2, 3, 4, 5, 6, 7};
  std::vector<float> batch1HostData = {1, 1, 1, 2, 2, 2};
  std::vector<float> batch2HostData = {1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4};
  std::vector<float> outHostData(8, 0);
  int8_t cubeMathType = 1;
  float alphaValue = 1.2f;
  float betaValue = 1.0f;
  // 创建self aclTensor
  ret = CreateAclTensor(selfHostData, selfShape, &selfDeviceAddr, aclDataType::ACL_FLOAT, &self);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建batch1 aclTensor
  ret = CreateAclTensor(batch1HostData, batch1Shape, &batch1DeviceAddr, aclDataType::ACL_FLOAT, &batch1);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建batch2 aclTensor
  ret = CreateAclTensor(batch2HostData, batch2Shape, &batch2DeviceAddr, aclDataType::ACL_FLOAT, &batch2);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建alpha aclScalar
  alpha = aclCreateScalar(&alphaValue,aclDataType::ACL_FLOAT);
  CHECK_RET(alpha != nullptr, return ret);
  // 创建beta aclScalar
  beta = aclCreateScalar(&betaValue,aclDataType::ACL_FLOAT);
  CHECK_RET(beta != nullptr, 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aclnnBaddbmm第一段接口
  ret = aclnnBaddbmmGetWorkspaceSize(self, batch1, batch2, alpha, beta, out, cubeMathType, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBaddbmmGetWorkspaceSize 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aclnnBaddbmm第二段接口
  ret = aclnnBaddbmm(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnBaddbmm 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(self);
  aclDestroyTensor(batch1);
  aclDestroyTensor(batch2);
  aclDestroyScalar(alpha);
  aclDestroyScalar(beta);
  aclDestroyTensor(out);
  return 0;
}
父主题： NN类算子接口