变更摘要

本 PR 完成 CANN Code Detective Challenge05 中 MulCustom 逐元素乘法算子（z[i] = x[i] * y[i]），提交范围包含 mul_custom.asc、CMakeLists.txt 与 run.sh（不含构建产物）。mul_custom.asc 实现了设备侧 KernelMul 类（8 核数据切分、Double Buffer 双缓冲、CopyIn -> Compute -> CopyOut 流水）与主机侧 kernel_mul 封装（ACL 初始化、内存管理、Kernel 直调、流同步与结果回拷），并通过 main 中的 VerifyResult 完成真机精度验证。

主要改动

• 设备侧算子实现（mul_custom.asc）: 新增 KernelMul 类，在 Init 中按 GetBlockNum()/GetBlockIdx() 计算每核 blockLength 及 GM 地址偏移（blockOffset），并以 BUFFER_NUM = 2 的 TQue（inQueueX/inQueueY/outQueueZ）初始化 Double Buffer。
• 流水处理流程: Process 按 tileNum * BUFFER_NUM 次循环依次执行 CopyIn → Compute → CopyOut：CopyIn 通过 DataCopy 将 GM 数据搬入 UB，Compute 调用 AscendC::Mul 完成逐元素乘法，CopyOut 将结果从 UB 写回 GM。
• Kernel 入口与 Host 侧封装: 新增 __global__ __aicore__ 入口函数 mul_custom 及 kernel_mul 函数，完成 aclInit/aclrtSetDevice 初始化、aclrtMalloc/aclrtMallocHost 内存分配、mul_custom<<<blockDim, nullptr, stream>>> Kernel 直调、aclrtSynchronizeStream 同步与 ACL_MEMCPY_DEVICE_TO_HOST 结果回拷，并逐一释放资源。
• 结果验证: main 构造 1.2f * 2.3f 的输入与 golden 向量，调用 kernel_mul 后由 VerifyResult 逐元素比较并输出 [Success]/[Failed] 判定。
• 构建运行脚本（run.sh）: 新增脚本，负责激活 CANN 环境（source "$ASCEND_TOOLKIT_HOME/set_env.sh"）、创建 build 目录并通过 cmake + make 构建后运行 ./mul_test。

Hi @Qianqiuer, welcome to submitting your first PR to cann-outreach!

PR Merge Steps

1. CLA Signing

If the current PR label includes cann-cla/yes, it means you have signed the CLA and can proceed to the next step. If the label includes cann-cla/no, please sign the CLA first. If you have any questions, please refer to the FAQ.

2. CI Check

Please comment /compile to trigger the CI pipeline check. If the CI run is successful, the PR will be tagged with ci-pipeline-passed and you can proceed to the next step. If the CI run fails, the PR will be tagged with ci-pipeline-failed, please check the CI logs to fix the issues in the PR. If you have any questions, please refer to the FAQ.

3. Code Review

After CI passes, please refer to the PR Approval Progress and proactively @ the committers in the table to review the code. After approval, committers will comment /lgtm and /approve. Once the lgtm and approved labels are successfully added, the PR will be merged automatically.

代码审查

✅ 未发现问题

Thanks for your pull-request.
The full list of commands accepted by me can be found at here.
You can get sig-info at here.
You can self-configure the PR merge rules for this repository. For more details, please refer to Here.
For more, you also can visit HICANN.

PR Approval Progress

⚠️ This PR does not yet meet the following requirements:lgtm (requires ≥ 2 person(s) per module)、approve (requires ≥ 1 person(s) per module)

Module Approval Details

💡 Tip:

• Committer can comment /approve or /lgtm
• Commenting /approve implies both code review (lgtm) and intent to merge (approve)

CLA Signature Pass

Qianqiuer, thanks for your pull request. All authors of the commits have signed the CLA. 👍