CANN ops-nn PReLU算子

aclnnPrelu【免费下载链接】ops-nn本项目是CANN提供的神经网络类计算算子库实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-nn产品支持情况产品是否支持Atlas A2 训练系列产品/Atlas A2 推理系列产品√功能说明算子功能计算输入张量的 PReLU 值。当输入元素大于 0 时输出该元素本身当输入元素小于等于 0 时输出该元素与weight的乘积。计算公式$$ y_i \begin{cases} x_i, x_i 0 \ x_i \times weight, x_i \le 0 \end{cases} $$其中weight可以为标量也可以为通道维权重。输入self维度大于 1 时通道维为第 1 维输入self维度不大于 1 时通道数按 1 处理。函数原型每个算子分为两段式接口必须先调用“aclnnPreluGetWorkspaceSize”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“aclnnPrelu”接口执行计算。aclnnStatus aclnnPreluGetWorkspaceSize( const aclTensor *self, const aclTensor *weight, aclTensor *out, uint64_t *workspaceSize, aclOpExecutor **executor)aclnnStatus aclnnPrelu( void* workspace, uint64_t workspaceSize, aclOpExecutor* executor, aclrtStream stream)aclnnPreluGetWorkspaceSize参数说明参数名输入/输出描述使用说明数据类型数据格式维度(shape)非连续Tensorself输入待进行 Prelu 计算的输入张量公式中的 x。支持空Tensor。shape需要与out一致。FLOAT、FLOAT16、BFLOAT16ND0-8√weight输入Prelu 负半轴权重。支持空Tensor。元素个数为1或者元素个数与self输入的channels一致。self.shape为1维及以下时channels 1self.shape大于1维时channels self.shape[1]。FLOAT、FLOAT16、BFLOAT16ND0-8√out输出Prelu 计算后的输出张量公式中的 y。数据类型、shape需要与self一致。FLOAT、FLOAT16、BFLOAT16ND0-8√workspaceSize输出返回需要在Device侧申请的workspace大小。-----executor输出返回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。 第一段接口会完成入参校验出现以下场景时报错返回码错误码描述ACLNN_ERR_PARAM_NULLPTR161001传入的self、weight或out是空指针。ACLNN_ERR_PARAM_INVALID161002self、weight或out的数据类型和数据格式不在支持的范围之内。self、weight和out的数据类型不一致。self和out shape不一致。weight元素个数既不是1也不等于self的通道数。aclnnPrelu参数说明参数名输入/输出描述workspace输入在Device侧申请的workspace内存地址。workspaceSize输入在Device侧申请的workspace大小由第一段接口aclnnPreluGetWorkspaceSize获取。executor输入op执行器包含了算子计算流程。stream输入指定执行任务的Stream。返回值aclnnStatus返回状态码具体参见aclnn返回码。约束说明self、weight、out的数据类型需要一致。out的shape必须与self完全一致。weight的元素个数必须为1或与self的通道数一致。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 vector #include acl/acl.h #include aclnnop/aclnn_prelu.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::vectorint64_t shape) { int64_t shapeSize 1; for (auto i : shape) { shapeSize * i; } return shapeSize; } int Init(int32_t deviceId, aclrtStream* stream) { 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::vectorT hostData, const std::vectorint64_t shape, void** deviceAddr, aclDataType dataType, aclTensor** tensor) { auto size GetShapeSize(shape) * sizeof(T); 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); 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); std::vectorint64_t strides(shape.size(), 1); for (int64_t i shape.size() - 2; i 0; i--) { strides[i] shape[i 1] * strides[i 1]; } *tensor aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND, shape.data(), shape.size(), *deviceAddr); return 0; } int main() { 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); std::vectorint64_t selfShape {2, 4}; std::vectorint64_t weightShape {1}; std::vectorint64_t outShape {2, 4}; void* selfDeviceAddr nullptr; void* weightDeviceAddr nullptr; void* outDeviceAddr nullptr; aclTensor* self nullptr; aclTensor* weight nullptr; aclTensor* out nullptr; std::vectorfloat selfHostData {-2, 1, 2, -3, -4.7, 5.3, -6.9, 7}; std::vectorfloat weightHostData {3}; std::vectorfloat outHostData {0, 0, 0, 0, 0, 0, 0, 0}; ret CreateAclTensor(selfHostData, selfShape, selfDeviceAddr, aclDataType::ACL_FLOAT, self); CHECK_RET(ret ACL_SUCCESS, return ret); ret CreateAclTensor(weightHostData, weightShape, weightDeviceAddr, aclDataType::ACL_FLOAT, weight); CHECK_RET(ret ACL_SUCCESS, return ret); ret CreateAclTensor(outHostData, outShape, outDeviceAddr, aclDataType::ACL_FLOAT, out); CHECK_RET(ret ACL_SUCCESS, return ret); uint64_t workspaceSize 0; aclOpExecutor* executor; ret aclnnPreluGetWorkspaceSize(self, weight, out, workspaceSize, executor); CHECK_RET(ret ACL_SUCCESS, LOG_PRINT(aclnnPreluGetWorkspaceSize failed. ERROR: %d\n, ret); return ret); 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); } ret aclnnPrelu(workspaceAddr, workspaceSize, executor, stream); CHECK_RET(ret ACL_SUCCESS, LOG_PRINT(aclnnPrelu 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); auto size GetShapeSize(outShape); std::vectorfloat 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 resultData from device to host failed. ERROR: %d\n, ret); return ret); aclDestroyTensor(self); aclDestroyTensor(weight); aclDestroyTensor(out); aclrtFree(outDeviceAddr); aclrtFree(weightDeviceAddr); aclrtFree(selfDeviceAddr); if (workspaceSize 0) { aclrtFree(workspaceAddr); } aclrtDestroyStream(stream); aclrtResetDevice(deviceId); aclFinalize(); return 0; }【免费下载链接】ops-nn本项目是CANN提供的神经网络类计算算子库实现网络在NPU上加速计算。项目地址: https://gitcode.com/cann/ops-nn创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考