文件最后提交记录最后更新时间
[NFC][TargetParser] Remove llvm/ADT/Triple.h I also ran git clang-format to get the headers in the right order for the new location, which has changed the order of other headers in two files.3 年前
[lldb] Fix duplicate word typos; NFC Those fixes were taken from https://reviews.llvm.org/D1373382 年前
[NFC][TargetParser] Remove llvm/ADT/Triple.h I also ran git clang-format to get the headers in the right order for the new location, which has changed the order of other headers in two files.3 年前
[lldb] Remove ConstString from ABI, Architecture and Disassembler plugin names4 年前
【bugfix】修复finish命令挂掉的问题 Co-authored-by: wangyixian<wangyixian3@huawei.com> # message auto-generated for no-merge-commit merge: !25 merge fix_step into master 【bugfix】修复finish命令挂掉的问题 Created-by: wiyr0 Commit-by: wangyixian Merged-by: ascend-robot Description: ### 1. 修改描述 - **修改原因:** 某些算子场景下,finish命令会导致msdebug工具挂了。因为本身hiipu64没实现自己的abi, step相关的操作,比如s, finish都会通过abi去找到函数的返回地址。abi实现的时候,默认是x86或者arm环境,会去读写寄存器,此时会访问空指针。 - **修改方案:** 发现是断点在device侧,则直接返回失败 - **修改内容:** ABI.cpp是个基类,里面调用派生类函数前,如果在断点在device侧,就直接返回空 - [ ] **涉及代码双合**(贴上另一个PR链接):NA ---- ### 2. 功能验证 - [x] **功能自验截图**(请确保不体现个人信息) `` [Launch of Kernel _Z17reduce_min_customPhS_S_ on Device 0] 2 locations added to breakpoint 1 Process 43238 stopped [Switching to focus on Kernel _Z17reduce_min_customPhS_S_, CoreId 38, Type aiv] * thread #1, name = 'ascendc_kernels', stop reason = breakpoint 1.4 frame #0: 0x000012c04120a208 device_debugdata_0_ZNK7AscendC11LocalTensorIDhEixEj_mix_aiv(this=0x00000000002ff840, offset=0) at kernel_tensor_impl.h:692:38 689 #endif 690 } else { 691 result.address_.dataLen -= (offset * sizeof(PrimType)); -> 692 result.address_.bufferAddr = result.address_.bufferAddr + offset * sizeof(PrimType); 693 } 694 return result; 695 } (msdebug) finish Process 43238 stopped [Switching to focus on Kernel _Z17reduce_min_customPhS_S_, CoreId 38, Type aiv] * thread #1, name = 'ascendc_kernels', stop reason = step out frame #0: 0x000012c041209bbc device_debugdata_0_ZN15KernelReduceMin6CopyInEi_mix_aiv(this=0x00000000002ff910, progress=0) at reduce_min.cpp:52:31 49 { 50 AscendC::LocalTensor<half> inputLocal = inQueue.AllocTensor<half>(); 51 for (int i = 0; i < BLOCK_GROUP_NUM; i++) { -> 52 AscendC::DataCopy(inputLocal[i * BLOCKLEN_CEIL], srcGlobal[i * BLOCK_ELEMENT_NUM], 53 BLOCKLEN_CEIL); // each time copy 16 half elements to UB 54 } 55 inQueue.EnQue(inputLocal); (msdebug) var (KernelReduceMin *__stack__) this = 0x00000000002ff910 (int32_t) progress = 0 (AscendC::LocalTensor<__fp16>) inputLocal = { AscendC::BaseLocalTensor<__fp16> = { address_ = (dataLen = 128, bufferAddr = 0, bufferHandle = "", logicPos = '\t') } shapeInfo_ = { shapeDim = '\x10' originalShapeDim = '\xf9' shape = ([0] = 0, [1] = 128, [2] = 288, [3] = 3144448, [4] = 0, [5] = 267, [6] = 1, [7] = 3143832) originalShape = ([0] = 0, [1] = 1092640480, [2] = 4800, [3] = 0, [4] = 0, [5] = 3145584, [6] = 0, [7] = 3143880) dataFormat = ND } } `` - [x] **冒烟是否通过** ![image.png](https://raw.gitcode.com/user-images/assets/8858745/06bee193-19e4-48c6-b5d5-c486e696c751/image.png 'image.png') ---- ### 3. 代码检视 - **要求:** - 合入功能代码大于 200 行,需要sig会议申报代码检视议题,并在PR中标注会议。 - committer评估是否需要在sig会议进行代码检视。 - 参与检视的committer人员名单与检视时间。 - 大于 1000 行代码原则上不允许合入,需进行备案。 - [x] **是否经过代码检视** - [ ] **是否具备UT测试用例看护** - [ ] **是否需要在sig会议中进行代码检视** NA - **检视committer人员名单与检视时间:** NA ---- ### 4. 资料修改自检 - **资料修改:** NA ---- See merge request: Ascend/msdebug!254 个月前
[lldb] Remove ConstString from ABI, Architecture and Disassembler plugin names4 年前
[NFC][TargetParser] Remove llvm/ADT/Triple.h I also ran git clang-format to get the headers in the right order for the new location, which has changed the order of other headers in two files.3 年前
[lldb][NFC] Fix more license headers Extra characters and one with an incorrect file name.2 年前
[lldb] Use std::optional instead of llvm::Optional (NFC) This patch replaces (llvm::|)Optional< with std::optional<. I'll post a separate patch to clean up the "using" declarations, #include "llvm/ADT/Optional.h", etc. This is part of an effort to migrate from llvm::Optional to std::optional: https://discourse.llvm.org/t/deprecating-llvm-optional-x-hasvalue-getvalue-getvalueor/637163 年前
[lldb] [ABI/X86] Add pseudo-registers if missing Differential Revision: https://reviews.llvm.org/D1088314 年前
[lldb] [ABI/X86] Split base x86 and i386 classes Split the ABIX86 class into two classes: base ABIX86 class that is common to 32-bit and 64-bit ABIs, and ABIX86_i386 class that is the base for 32-bit ABIs. This removes the confusing concept that ABIX86 initializes 64-bit ABIs but is only the base for 32-bit ABIs. Differential Revision: https://reviews.llvm.org/D1112164 年前
[lldb] [ABI/X86] Split base x86 and i386 classes Split the ABIX86 class into two classes: base ABIX86 class that is common to 32-bit and 64-bit ABIs, and ABIX86_i386 class that is the base for 32-bit ABIs. This removes the confusing concept that ABIX86 initializes 64-bit ABIs but is only the base for 32-bit ABIs. Differential Revision: https://reviews.llvm.org/D1112164 年前
[lldb] [ABI/X86] Split base x86 and i386 classes Split the ABIX86 class into two classes: base ABIX86 class that is common to 32-bit and 64-bit ABIs, and ABIX86_i386 class that is the base for 32-bit ABIs. This removes the confusing concept that ABIX86 initializes 64-bit ABIs but is only the base for 32-bit ABIs. Differential Revision: https://reviews.llvm.org/D1112164 年前
[Support] Move TargetParsers to new component This is a fairly large changeset, but it can be broken into a few pieces: - llvm/Support/*TargetParser* are all moved from the LLVM Support component into a new LLVM Component called "TargetParser". This potentially enables using tablegen to maintain this information, as is shown in https://reviews.llvm.org/D137517. This cannot currently be done, as llvm-tblgen relies on LLVM's Support component. - This also moves two files from Support which use and depend on information in the TargetParser: - llvm/Support/Host.{h,cpp} which contains functions for inspecting the current Host machine for info about it, primarily to support getting the host triple, but also for -mcpu=native support in e.g. Clang. This is fairly tightly intertwined with the information in X86TargetParser.h, so keeping them in the same component makes sense. - llvm/ADT/Triple.h and llvm/Support/Triple.cpp, which contains the target triple parser and representation. This is very intertwined with the Arm target parser, because the arm architecture version appears in canonical triples on arm platforms. - I moved the relevant unittests to their own directory. And so, we end up with a single component that has all the information about the following, which to me seems like a unified component: - Triples that LLVM Knows about - Architecture names and CPUs that LLVM knows about - CPU detection logic for LLVM Given this, I have also moved RISCVISAInfo.h into this component, as it seems to me to be part of that same set of functionality. If you get link errors in your components after this patch, you likely need to add TargetParser into LLVM_LINK_COMPONENTS in CMake. Differential Revision: https://reviews.llvm.org/D1378383 年前