aclnnCalculateMatmulWeightSizeV2

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

aclnnStatus aclnnCalculateMatmulWeightSizeV2(const aclIntArray *tensorShape, aclDataType dataType, uint64_t *weightTensorSize)

功能描述

• 算子功能： 在Matmul算子ND格式输入下，计算如果要转换到NZ格式下需要占用的空间大小（单位为元素个数），仅支持Float16, INT8数据类型，该接口仅仅用于判断对weight Tensor进行预处理需要使用多少size才可使Matmul算子执行性能最优。输入tensorShape最少是2维（n，k），最多是6维（batch，n，k）。 例如：

输入【510， 510】Float16 该函数出于性能角度考虑，会将shape变化为【512，512】 因此函数会将引用输入修改为262144

输入【510， 270】INT8 该函数出于性能角度考虑，会将shape变化为【512，288】 因此函数会将引用输入修改为147456

• 计算公式$$Float16: result = Align(Shapesize[0], 16) * Align(Shapesize[1], 16)$$ $$INT8： result = Align(Shapesize[0], 16) * Align(Shapesize[1], 32)$$

aclnnCalculateMatmulWeightSizeV2

• 参数说明：

  • tensorShape(const aclIntArray *, 计算输入)：用于表达该次Matmul载入权重矩阵的Shape, 输入shape最少是2维（n，k），最多是6维（batch，n，k）。
  • weightDtype(op::DataType *, 计算输入)：weight的Dtype, 支持Float16、INT8。
  • weightTensorSize(uint64_t *, 计算输出)：转换为NZ格式所占用的空间大小（单位为元素个数）。

• 返回值：

  aclnnStatus：返回状态码，具体参见aclnn返回码。

  161001(ACLNN_ERR_PARAM_NULLPTR)：1. 输入是空指针。
  161002(ACLNN_ERR_PARAM_INVALID)：原因有：
    - 不支持空Tensor输入
    - 输入shape的维度不满足要求
    - 输入的数据类型不满足要求
  361001(ACLNN_ERR_RUNTIME_ERROR): SocVersion不支持。

约束与限制

• 无

调用示例

• tensorShape为二维的场景示例代码如下，仅供参考，具体编译和执行过程请参考编译与运行样例。
• tensorShape为多维（3-6维）的场景示例代码请参考aclnnQuantMatmulV3。

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_cast.h"
#include "aclnnop/aclnn_weight_quant_batch_matmul_v2.h"
#include "aclnnop/aclnn_trans_matmul_weight.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 CreateAclTensorWeight(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
                          aclDataType dataType, aclTensor** tensor) {
  auto size = static_cast<uint64_t>(GetShapeSize(shape));

  const aclIntArray* mat2Size = aclCreateIntArray(shape.data(), shape.size());
  auto ret = aclnnCalculateMatmulWeightSizeV2(mat2Size, dataType, &size);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCalculateMatmulWeightSizeV2 failed. ERROR: %d\n", ret); return ret);
  size *= sizeof(T);

  // 调用aclrtMalloc申请device侧内存
  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];
  }

  std::vector<int64_t> storageShape;
  storageShape.push_back(GetShapeSize(shape));

  // 调用aclCreateTensor接口创建aclTensor
  *tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
                            storageShape.data(), storageShape.size(), *deviceAddr);
  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> xShape = {16, 32};
  std::vector<int64_t> weightShape = {16, 32};
  std::vector<int64_t> yShape = {16, 16};
  void* xDeviceAddr = nullptr;
  void* weightDeviceAddr = nullptr;
  void* yDeviceAddr = nullptr;
  aclTensor* x = nullptr;
  aclTensor* weight = nullptr;
  aclTensor* y = nullptr;
  std::vector<float> xHostData(512, 1);
  std::vector<int8_t> weightHostData(512, 1);
  std::vector<float> yHostData(256, 0);

  std::vector<int64_t> antiquantScaleShape = {16};
  void* antiquantScaleDeviceAddr = nullptr;
  aclTensor* antiquantScale = nullptr;
  std::vector<float> antiquantScaleHostData(16, 1);

  // 创建x aclTensor
  ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建weight aclTensor
  ret = CreateAclTensorWeight(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_INT8, &weight);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建y aclTensor
  ret = CreateAclTensor(yHostData, yShape, &yDeviceAddr, aclDataType::ACL_FLOAT, &y);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建antiquantScale aclTensor
  ret = CreateAclTensor(antiquantScaleHostData, antiquantScaleShape, &antiquantScaleDeviceAddr, aclDataType::ACL_FLOAT, &antiquantScale);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  // 创建xFp16 aclTensor
  void* xFp16DeviceAddr = nullptr;
  aclTensor* xFp16 = nullptr;
  ret = CreateAclTensor(xHostData, xShape, &xFp16DeviceAddr, aclDataType::ACL_FLOAT16, &xFp16);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建antiquantScale aclTensor
  void* antiquantScaleFp16DeviceAddr = nullptr;
  aclTensor* antiquantScaleFp16 = nullptr;
  ret = CreateAclTensor(antiquantScaleHostData, antiquantScaleShape, &antiquantScaleFp16DeviceAddr, aclDataType::ACL_FLOAT16, &antiquantScaleFp16);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  // 创建yFp16 aclTensor
  void* yFp16DeviceAddr = nullptr;
  aclTensor* yFp16 = nullptr;
  ret = CreateAclTensor(yHostData, yShape, &yFp16DeviceAddr, aclDataType::ACL_FLOAT16, &yFp16);
  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
  int8_t cubeMathType = 1;
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;
  void* workspaceAddr = nullptr;

  // 调用TransWeight
  ret = aclnnTransMatmulWeightGetWorkspaceSize(weight, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTransMatmulWeightGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存
  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aclnnTransMatmulWeight第二段接口
  ret = aclnnTransMatmulWeight(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnTransMatmulWeight failed. ERROR: %d\n", ret); return ret);

  workspaceSize = 0;
  // 调用cast生成FP16的输入
  ret = aclnnCastGetWorkspaceSize(x, aclDataType::ACL_FLOAT16, xFp16, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize0 failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存

  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);
  }
  ret = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast0 failed. ERROR: %d\n", ret); return ret);

  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  ret = aclnnCastGetWorkspaceSize(antiquantScale, aclDataType::ACL_FLOAT16, antiquantScaleFp16, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize1 failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存

  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);
  }
  ret = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast1 failed. ERROR: %d\n", ret); return ret);

  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 调用aclnnWeightQuantBatchMatmulV2第一段接口
  ret = aclnnWeightQuantBatchMatmulV2GetWorkspaceSize(xFp16, weight, antiquantScaleFp16, nullptr, nullptr, nullptr, nullptr, 0, yFp16, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnWeightQuantBatchMatmulV2GetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存

  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aclnnWeightQuantBatchMatmulV2第二段接口
  ret = aclnnWeightQuantBatchMatmulV2(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnWeightQuantBatchMatmulV2 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);

 // 将输出转为FP32
  ret = aclnnCastGetWorkspaceSize(yFp16, aclDataType::ACL_FLOAT, y, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize2 failed. ERROR: %d\n", ret); return ret);
  // 根据第一段接口计算出的workspaceSize申请device内存

  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);
  }
  ret = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast2 failed. ERROR: %d\n", ret); return ret);

  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(yShape);
  std::vector<float> resultData(size, 0);
  ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), yDeviceAddr,
                    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(x);
  aclDestroyTensor(weight);
  aclDestroyTensor(antiquantScale);
  aclDestroyTensor(y);
  aclDestroyTensor(xFp16);
  aclDestroyTensor(antiquantScaleFp16);
  aclDestroyTensor(yFp16);

  // 7. 释放device资源
  aclrtFree(xDeviceAddr);
  aclrtFree(weightDeviceAddr);
  aclrtFree(antiquantScaleDeviceAddr);
  aclrtFree(yDeviceAddr);
  aclrtFree(xFp16DeviceAddr);
  aclrtFree(antiquantScaleFp16DeviceAddr);
  aclrtFree(yFp16DeviceAddr);

  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}