aclnnFlashAttentionUnpaddingScoreGradV2

Applicable Products

Function

• Description: Computes the backward output of attention in training scenarios, i.e., the backward computation of aclnnFlashAttentionVarLenScoreV2. Compared with the aclnnFlashAttentionUnpaddingScoreGrad API, this API adds the pseType parameter:

  • When pseType=1, the implementation is the same as aclnnFlashAttentionUnpaddingScoreGrad.

  • When pseType is set to other values, mul is performed first, followed by add.

• Formula:

  Given the forward computation formula of the attention mechanism (when pseType=1, the formula is the same as that of aclnnFlashAttentionUnpaddingScoreGrad; when pseType takes other values, the formula is as follows):

  $$Y=Dropout(Softmax(Mask(\frac{QK^T}{\sqrt{d}}+pse),atten\_mask),keep\_prob)V$$

  For ease of expression, the formula is expressed using variables $S$ and $P$:

  $$S=Mask(\frac{QK^T}{\sqrt{d}}+pse),atten\_mask$$ $$P=Dropout(Softmax(S),keep\_prob)$$ $$Y=PV$$

  The backward formula for the attention is:

  $$dV=P^TdY$$ $$dQ=\frac{((dS)*K)}{\sqrt{d}}$$ $$dK=\frac{((dS)^T*Q)}{\sqrt{d}}$$

Function Prototype

Each operator is divided into a two-phase API. You must first call the "aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize" API to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call the "aclnnFlashAttentionUnpaddingScoreGradV2" API to perform the computation.

aclnnStatus aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize(
  const aclTensor   *query,
  const aclTensor   *keyIn,
  const aclTensor   *value,
  const aclTensor   *dy,
  const aclTensor   *pseShiftOptional,
  const aclTensor   *dropMaskOptional,
  const aclTensor   *paddingMaskOptional,
  const aclTensor   *attenMaskOptional,
  const aclTensor   *softmaxMaxOptional,
  const aclTensor   *softmaxSumOptional,
  const aclTensor   *softmaxInOptional,
  const aclTensor   *attentionInOptional,
  const aclIntArray *prefixOptional,
  const aclIntArray *actualSeqQLenOptional,
  const aclIntArray *actualSeqKvLenOptional,
  const aclIntArray *qStartIdxOptional,
  const aclIntArray *kvStartIdxOptional,
  double             scaleValue,
  double             keepProb,
  int64_t            preTokens,
  int64_t            nextTokens,
  int64_t            headNum,
  char              *inputLayout,
  int64_t            innerPrecise,
  int64_t            sparseMode,
  int64_t            pseType,
  const aclTensor   *dqOut,
  const aclTensor   *dkOut,
  const aclTensor   *dvOut,
  const aclTensor   *dpseOut,
  uint64_t          *workspaceSize,
  aclOpExecutor    **executor)

aclnnStatus aclnnFlashAttentionUnpaddingScoreGradV2(
  void             *workspace,
  uint64_t          workspaceSize,
  aclOpExecutor    *executor,
  const aclrtStream stream)

aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize

• Parameters

  Parameter	Input/Output	Description	Instruction	Data Type	Data Format	Dimension (Shape)	Non-contiguous Tensor
  query	Input	Q in the formula.	The data type is the same as that of keyIn/value.	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  keyIn	Input	K in the formula.	The data type is the same as that of query and value.	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  value	Input	Represents V in the formula.	Has the same data type as query/keyIn.	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  dy	Input	dY in the formula.	-	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  pseShiftOptional	Optional input	pse in the formula.	The data type is the same as that of query. This parameter must be used together with pseType.	FLOAT16, BFLOAT16, FLOAT32	ND	[B,N,1024,Skv], [1,N,1024,Skv], [B,N], [N]	√
  dropMaskOptional	optional input	Dropout mask.	-	UINT8	ND	0, 1	√
  paddingMaskOptional	Optional input.	Reserved parameter. Not currently used.	Pass NULL when calling.	-	-	-	-
  qStartIdxOptional	Optional input	Represents the start index of the current chunk's query sequence in the global context under an external chunking scenario.	-	INT64	ND	0, 1	-
  kvStartIdxOptional	Optional input	Represents the outer cut scenario, indicating the starting index of the current chunk's key and value sequence in the global context.	-	INT64	ND	0, 1	-
  attenMaskOptional	Optional input	The atten_mask in the formula.	A value of 1 indicates that the position does not participate in the computation, and 0 indicates that the position participates in the computation.	BOOL, UINT8	ND	[B,N,Sq,Skv], [B,1,Sq,Skv], [1,1,Sq,Skv], [Sq,Skv]	√
  softmaxMaxOptional	Optional input	Intermediate output of the forward softmax.	-	FLOAT	ND	[N,T,8]	√
  softmaxSumOptional	optional input	Intermediate output of the forward softmax.	-	FLOAT	ND	[N,T,8]	√
  softmaxInOptional	Optional input	Intermediate output of the forward softmax.	Reserved parameter, not currently used.	-	-	-	-
  attentionInOptional	optional input	Forward attention output.	Same data type and shape as query.	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  prefixOptional	optional input	N of each batch in the prefix sparse scenario.	-	INT64	ND	0, 1	-
  actualSeqQLenOptional	Optional input	Actual query sequence length.	-	INT64	ND	1	-
  actualSeqKvLenOptional	Optional input	Actual Key/Value sequence length.	-	INT64	ND	1	-
  scaleValue	Optional input	Scale factor.	-	DOUBLE	-	-	-
  keepProb	Optional input	Proportion of 1s in dropMaskOptional.	-	DOUBLE	-	-	-
  preTokens	Optional input	Specifies the left boundary of the sliding window during sparse computation.	-	INT64	-	-	-
  nextTokens	Optional input	Right boundary of the sliding window during sparse computation.	-	INT64	-	-	-
  headNum	Input	Specifies the number of heads on a single card, that is, the length of the N-axis of Query.	-	INT64	-	-	-
  inputLayout	Input	Data layout of the input Q/K/V.	Supports TND.	String	-	-	-
  innerPrecise	optional input	Internal computation precision control.	Reserved parameter. Not currently used.	INT64	-	-	-
  sparseMode	Optional input	Sparse mode.	Supports configuration from 0 to 8. 5 is not supported.	INT64	-	-	-
  pseType	Optional input	The data type supports INT64.	The supported configuration values are 0, 1, 2, and 3.	INT64	-	-	-
  dqOut	Output	dQ in the formula, representing the gradient of Query.	-	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	Yes
  dkOut	Output	dK in the formula, representing the gradient of Key.	-	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  dvOut	Output	dV in the formula, representing the gradient of Value.	-	FLOAT16, BFLOAT16, FLOAT32	ND	[TND]	√
  dpseOut	Output	Gradient of d(pse).	Reserved parameter, not currently used.	-	-	-	-
  workspaceSize	Output	Returns the workspace size to be allocated on the Device side.	-	-	-	-	-
  executor	Output	Returns the operator executor that contains the operator computation flow.	-	-	-	-	-

• Return Value

  aclnnStatus: return code. For details, see aclnn Return Code.

  The first-phase API performs input parameter validation and returns an error in the following scenarios:

  Return Value	Error Code	Description
  ACLNN_ERR_PARAM_NULLPTR	161001	The input parameter is a required input, output, or required attribute, and is a null pointer.
  ACLNN_ERR_PARAM_INVALID	161002	The data type of query, keyIn, value, dy, pseShiftOptional, dropMaskOptional, paddingMaskOptional, attenMaskOptional, softmaxMaxOptional, softmaxSumOptional, softmaxInOptional, attentionInOptional, dqOut, dkOut, or dvOut is not within the supported range.
  		The data format of query, keyIn, value, dy, pseShiftOptional, dropMaskOptional, paddingMaskOptional, attenMaskOptional, softmaxMaxOptional, softmaxSumOptional, softmaxInOptional, attentionInOptional, dqOut, dkOut, or dvOut is not within the supported range.

aclnnFlashAttentionUnpaddingScoreGradV2

• Parameters

  Parameter	Input/Output	Description
  workspace	Input	Address of the workspace memory allocated on the Device side.
  workspaceSize	Input	Size of the workspace allocated on the Device side, obtained from the first-phase API aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize.
  executor	Input	Operator executor that contains the operator computation flow.
  stream	Input	Specifies the stream for task execution.

• Return Value

  aclnnStatus: return code. For details, see aclnn Return Code.

Constraints

• Deterministic computation:

  • aclnnFlashAttentionUnpaddingScoreGradV2 defaults to a non-deterministic implementation. Deterministic computation can be enabled through aclrtCtxSetSysParamOpt.

• When this API is used with PyTorch, ensure that the versions of CANN-related packages and PyTorch-related packages match.

• For the B dimension of the input query, key, value, and dy: the batchsize must be equal, and the inputLayout must be consistent.

• The D (Head Dim) of the input query, key, and value must satisfy (qD == kD && kD >= vD).

• The data types of the input query, key, value, and pseShiftOptional must be consistent.

• The shapes of the input key and value must be consistent except for D. When the D dimensions of query, key, and value are the same, the shapes of query and dy must be consistent.

• The N of the input query and the N of key/value can be different, but they must be in a proportional relationship, that is, Nq/Nkv must be a non-zero integer, and Nq ranges from 1 to 256.

• For constraints on data shapes, take inputLayout TND as an example, where:

  • T: value range is 1 to 1M.

  • N: value range is 1 to 256.

  • D: value range is 1 to 768.

  • KeepProb: value range is (0, 1].

• The data layout of query, key, and value supports only TND, where T is the tightly packed data of the B and S concatenated axes (SeqLenQ and SeqLenKV of each batch). B (Batch) indicates the input sample batch size, S (Seq-Length) indicates the input sample sequence length, H (Head-Size) indicates the hidden layer size, N (Head-Num) indicates the number of heads, and D (Head-Dim) indicates the minimum unit size of the hidden layer, satisfying D = H/N.

• pseShiftOptional: If Sq is greater than 1024, and Sq and Skv of each batch have the same length, and the scenario is a lower triangular mask with sparseMode being 0, 2, or 3, alibi position encoding compression can be enabled. In this case, only the last 1024 rows of the original PSE need to be input, achieving memory optimization, i.e., alibi_compress = ori_pse[:, :, -1024:, :], as detailed below:

  • When the parameter differs for each batch, the shape is BNHSkv (H=1024).

  • When the parameter is the same for each batch, the shape is 1NHSkv (H=1024).

  • When pseType is 2 or 3, the data type must be FLOAT32, and the corresponding supported shape range is [B,N] or [N].

  • If this parameter is not enabled, nullptr must be passed for pseShiftOptional, and 1 must be passed for pseType.

• Meaning of each pseType value

  pseType	Meaning	Note
  0	Externally passed pse, first mul then add.	-
  1	Externally passed pse, first add then mul.	Consistent with the implementation of FlashAttentionUnpaddingScoreGrad.
  2	Internally generated pse, first mul then add.	-
  3	Internally generated pse, first mul then add then sqrt.	-

• Constraints on sparseMode are as follows:

  • When all attenMaskOptional have the same shape smaller than 2048, the default mode is recommended to reduce memory usage.

  • When configured as 1, 2, or 3, the user-configured preTokens and nextTokens do not take effect.

  • When configured as 0 or 4, ensure that attenMaskOptional is consistent with the ranges of preTokens and nextTokens.

  • It is recommended to pass 0 when no specific configuration is required.

  • For detailed descriptions of different sparse modes, see sparse mode description.

  • When configured as 7, the optional input pseShiftOptional is not supported.

  • When configured as 8, the optional input pseShiftOptional is supported when q and kv of each sequence have equal lengths, and pse is generated globally. Outer split along the q direction is supported, which requires that q and kv of each sequence have equal lengths before the outer split, and after the outer split, actualSeqQLenOptional[0] - actualSeqKvLenOptional[0] + qStartIdxOptional - kvStartIdxOptional == 0 (this feature is experimental).

• In some scenarios, if the computation workload is too large, the operator execution may time out (aicore error, with errorStr: timeout or trap error). In this case, axis splitting is recommended. Note: The computation workload here is affected by parameters such as B, S, N, and D. Larger values result in a heavier computation workload.

• The prefixOptional sparse computation supports only the compressed scenario, with sparseMode=6. When Sq > Skv, the value range of N for prefix is [0, Skv]. When Sq <= Skv, the value range of N for prefix is [Skv-Sq, Skv].

• The actualSeqQLenOptional input supports an S length of 0 on a certain batch, but the optional input pseShiftOptional is not supported in this case. The length of actualSeqQLenOptional ranges from 1 to 2K. When the prefixOptional input is present, its maximum supported length is 1K.

• Constraints on the softmaxMax and softmaxSum parameters: The input format is fixed as [B, N, S, 8], except for the TND input format, where it is [T, N, 8]. Note: T = B * S.

• The value of headNum must be consistent with the N value in the input Query.

Example

The following provides example code for reference only. For details about compilation and running, see Compile and Run Samples.

#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_flash_attention_score_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;
}

void PrintOutResult(std::vector<int64_t> &shape, void** deviceAddr) {
  auto size = GetShapeSize(shape);
  std::vector<float> resultData(size, 0);
  auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]),
                         *deviceAddr, 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);
  for (int64_t i = 0; i < size; i++) {
    LOG_PRINT("mean result[%ld] is: %f\n", i, resultData[i]);
  }
}

int Init(int32_t deviceId, aclrtStream* stream) {
  // Boilerplate: resource initialization.
  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);
  // Call aclrtMalloc to apply for device-side memory.
  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);
  // Call aclrtMemcpy to copy data from the host to the device memory.
  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);

  // Calculate the strides of a contiguous tensor.
  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];
  }

  // Call the aclCreateTensor API to create an 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. (Boilerplate) Initialize the device/stream. See the ACL API manual.
  // Set deviceId based on the actual device.
  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. Construct the inputs and outputs. Custom construction is required based on the API.
  std::vector<int64_t> qShape = {256, 1, 128};
  std::vector<int64_t> kShape = {256, 1, 128};
  std::vector<int64_t> vShape = {256, 1, 128};
  std::vector<int64_t> dxShape = {256, 1, 128};
  std::vector<int64_t> attenmaskShape = {256, 256};
  std::vector<int64_t> softmaxMaxShape = {256, 1, 8};
  std::vector<int64_t> softmaxSumShape = {256, 1, 8};
  std::vector<int64_t> attentionInShape = {256, 1, 128};

  std::vector<int64_t> dqShape = {256, 1, 128};
  std::vector<int64_t> dkShape = {256, 1, 128};
  std::vector<int64_t> dvShape = {256, 1, 128};

  void* qDeviceAddr = nullptr;
  void* kDeviceAddr = nullptr;
  void* vDeviceAddr = nullptr;
  void* dxDeviceAddr = nullptr;
  void* attenmaskDeviceAddr = nullptr;
  void* softmaxMaxDeviceAddr = nullptr;
  void* softmaxSumDeviceAddr = nullptr;
  void* attentionInDeviceAddr = nullptr;
  void* dqDeviceAddr = nullptr;
  void* dkDeviceAddr = nullptr;
  void* dvDeviceAddr = nullptr;

  aclTensor* q = nullptr;
  aclTensor* k = nullptr;
  aclTensor* v = nullptr;
  aclTensor* dx = nullptr;
  aclTensor* pse = nullptr;
  aclTensor* dropMask = nullptr;
  aclTensor* padding = nullptr;
  aclTensor* attenmask = nullptr;
  aclTensor* softmaxMax = nullptr;
  aclTensor* softmaxSum = nullptr;
  aclTensor* softmaxIn = nullptr;
  aclTensor* attentionIn = nullptr;
  aclTensor* dq = nullptr;
  aclTensor* dk = nullptr;
  aclTensor* dv = nullptr;
  aclTensor* dpse = nullptr;

  std::vector<float> qHostData(32768, 1);
  std::vector<float> kHostData(32768, 1);
  std::vector<float> vHostData(32768, 1);
  std::vector<float> dxHostData(32768, 1);
  std::vector<uint8_t> attenmaskHostData(65536, 0);
  std::vector<float> softmaxMaxHostData(2048, 3.0);
  std::vector<float> softmaxSumHostData(2048, 3.0);
  std::vector<float> attentionInHostData(32768, 1);
  std::vector<float> dqHostData(32768, 0);
  std::vector<float> dkHostData(32768, 0);
  std::vector<float> dvHostData(32768, 0);

  ret = CreateAclTensor(qHostData, qShape, &qDeviceAddr, aclDataType::ACL_FLOAT, &q);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(kHostData, kShape, &kDeviceAddr, aclDataType::ACL_FLOAT, &k);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(vHostData, vShape, &vDeviceAddr, aclDataType::ACL_FLOAT, &v);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(dxHostData, dxShape, &dxDeviceAddr, aclDataType::ACL_FLOAT, &dx);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(attenmaskHostData, attenmaskShape, &attenmaskDeviceAddr, aclDataType::ACL_UINT8, &attenmask);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(softmaxMaxHostData, softmaxMaxShape, &softmaxMaxDeviceAddr, aclDataType::ACL_FLOAT, &softmaxMax);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(softmaxSumHostData, softmaxSumShape, &softmaxSumDeviceAddr, aclDataType::ACL_FLOAT, &softmaxSum);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(attentionInHostData, attentionInShape, &attentionInDeviceAddr, aclDataType::ACL_FLOAT, &attentionIn);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(dqHostData, dqShape, &dqDeviceAddr, aclDataType::ACL_FLOAT, &dq);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(dkHostData, dkShape, &dkDeviceAddr, aclDataType::ACL_FLOAT, &dk);
  CHECK_RET(ret == ACL_SUCCESS, return ret);
  ret = CreateAclTensor(dvHostData, dvShape, &dvDeviceAddr, aclDataType::ACL_FLOAT, &dv);
  CHECK_RET(ret == ACL_SUCCESS, return ret);

  std::vector<int64_t> prefixOp = {0};
  aclIntArray* prefix = aclCreateIntArray(prefixOp.data(), 1);
  std::vector<int64_t>  acSeqQLenOp = {256};
  std::vector<int64_t>  acSeqKvLenOp = {256};
  aclIntArray* acSeqQLen = aclCreateIntArray(acSeqQLenOp.data(), acSeqQLenOp.size());
  aclIntArray* acSeqKvLen = aclCreateIntArray(acSeqKvLenOp.data(), acSeqKvLenOp.size());
  std::vector<int64_t> qStartIdxOp = {0};
  std::vector<int64_t> kvStartIdxOp = {0};
  aclIntArray *qStartIdx = aclCreateIntArray(qStartIdxOp.data(), 1);
  aclIntArray *kvStartIdx = aclCreateIntArray(kvStartIdxOp.data(), 1);
  double scaleValue = 0.088388;
  double keepProb = 1;
  int64_t preTokens = 65536;
  int64_t nextTokens = 65536;
  int64_t headNum = 1;
  int64_t innerPrecise = 0;
  int64_t sparseMode = 0;
  int64_t pseType = 1;
  char layOut[5] = {'T', 'N', 'D', 0};

  // 3. Call the CANN operator library API. Replace with the specific API name.
  uint64_t workspaceSize = 0;
  aclOpExecutor* executor;

  // Call the first-phase API of aclnnFlashAttentionUnpaddingScoreGradV2.
  ret = aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize(q, k, v, dx, pse, dropMask, padding,
            attenmask, softmaxMax, softmaxSum, softmaxIn, attentionIn, prefix, acSeqQLen, acSeqKvLen, qStartIdx, kvStartIdx,
            scaleValue, keepProb, preTokens, nextTokens, headNum, layOut, innerPrecise, sparseMode, pseType,
            dq, dk, dv, dpse, &workspaceSize, &executor);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlashAttentionUnpaddingScoreGradV2GetWorkspaceSize failed. ERROR: %d\n", ret); return ret);

  // Apply for device memory based on the workspaceSize calculated by the first-phase API.
  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);
  }

  // Call the second-phase API of aclnnFlashAttentionUnpaddingScoreGradV2.
  ret = aclnnFlashAttentionUnpaddingScoreGradV2(workspaceAddr, workspaceSize, executor, stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnFlashAttentionUnpaddingScoreGradV2 failed. ERROR: %d\n", ret); return ret);

  // 4. (Boilerplate) Synchronously wait for task execution to complete.
  ret = aclrtSynchronizeStream(stream);
  CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);

  // 5. Obtain the output value and copy the result from the device memory to the host memory. Modify this based on the specific API definition.
  PrintOutResult(dqShape, &dqDeviceAddr);
  PrintOutResult(dkShape, &dkDeviceAddr);
  PrintOutResult(dvShape, &dvDeviceAddr);

  // 6. Release aclTensor and aclScalar. Modify based on the specific API definition.
  aclDestroyTensor(q);
  aclDestroyTensor(k);
  aclDestroyTensor(v);
  aclDestroyTensor(dx);
  aclDestroyTensor(attenmask);
  aclDestroyTensor(softmaxMax);
  aclDestroyTensor(softmaxSum);
  aclDestroyTensor(attentionIn);
  aclDestroyTensor(dq);
  aclDestroyTensor(dk);
  aclDestroyTensor(dv);

  // 7. Release device resources.
  aclrtFree(qDeviceAddr);
  aclrtFree(kDeviceAddr);
  aclrtFree(vDeviceAddr);
  aclrtFree(dxDeviceAddr);
  aclrtFree(attenmaskDeviceAddr);
  aclrtFree(softmaxMaxDeviceAddr);
  aclrtFree(softmaxSumDeviceAddr);
  aclrtFree(attentionInDeviceAddr);
  aclrtFree(dqDeviceAddr);
  aclrtFree(dkDeviceAddr);
  aclrtFree(dvDeviceAddr);
  if (workspaceSize > 0) {
    aclrtFree(workspaceAddr);
  }
  aclrtDestroyStream(stream);
  aclrtResetDevice(deviceId);
  aclFinalize();

  return 0;
}