[llvm] [AMDGPU][True16][CodeGen] FLAT_load using D16 pseudo instruction (PR #114500)

Tue Feb 18 08:30:04 PST 2025

llvm-ci wrote:

LLVM Buildbot has detected a new failure on builder `ml-opt-rel-x86-64` running on `ml-opt-rel-x86-64-b2` while building `llvm` at step 5 "build-unified-tree".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/185/builds/13321

<details>
<summary>Here is the relevant piece of the build log for the reference</summary>

```
Step 5 (build-unified-tree) failure: build (failure)
...
858.910 [806/64/2964] Building CXX object lib/Target/AArch64/CMakeFiles/LLVMAArch64CodeGen.dir/AArch64TargetTransformInfo.cpp.o
859.020 [805/64/2965] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUCallLowering.cpp.o
859.898 [804/64/2966] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUAsmPrinter.cpp.o
860.457 [803/64/2967] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPURemoveIncompatibleFunctions.cpp.o
861.548 [802/64/2968] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUInstCombineIntrinsic.cpp.o
863.922 [801/64/2969] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUCodeGenPrepare.cpp.o
865.621 [800/64/2970] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPULateCodeGenPrepare.cpp.o
866.605 [799/64/2971] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPURegBankLegalizeRules.cpp.o
866.635 [798/64/2972] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUSetWavePriority.cpp.o
866.937 [797/64/2973] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMCInstLower.cpp.o
FAILED: lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMCInstLower.cpp.o 
ccache /usr/bin/c++ -DGTEST_HAS_RTTI=0 -D_DEBUG -D_GLIBCXX_ASSERTIONS -D_GNU_SOURCE -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS -D__STDC_LIMIT_MACROS -I/b/ml-opt-rel-x86-64-b1/build/lib/Target/AMDGPU -I/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU -I/var/lib/buildbot/.local/lib/python3.7/site-packages/tensorflow/include -I/b/ml-opt-rel-x86-64-b1/build/include -I/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/include -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror=date-time -fno-lifetime-dse -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wno-missing-field-initializers -pedantic -Wno-long-long -Wimplicit-fallthrough -Wno-uninitialized -Wno-nonnull -Wno-class-memaccess -Wno-redundant-move -Wno-pessimizing-move -Wno-noexcept-type -Wdelete-non-virtual-dtor -Wsuggest-override -Wno-comment -Wno-misleading-indentation -fdiagnostics-color -ffunction-sections -fdata-sections -O3 -DNDEBUG -fvisibility=hidden  -fno-exceptions -funwind-tables -fno-rtti -UNDEBUG -std=c++17 -MD -MT lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMCInstLower.cpp.o -MF lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMCInstLower.cpp.o.d -o lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMCInstLower.cpp.o -c /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp: In member function ‘void AMDGPUMCInstLower::lowerT16D16Helper(const llvm::MachineInstr*, llvm::MCInst&) const’:
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:126: error: ‘OPERAND_LAST’ is not a member of ‘llvm::AMDGPU::OpName’
  126 |   uint16_t OpName = AMDGPU::OpName::OPERAND_LAST;
      | 
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:129: error: cannot convert ‘llvm::AMDGPU::OpName’ to ‘uint16_t’ {aka ‘short unsigned int’} in assignment
  129 |       OpName = llvm::AMDGPU::OpName::vdst;
      | 
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:131: error: cannot convert ‘llvm::AMDGPU::OpName’ to ‘uint16_t’ {aka ‘short unsigned int’} in assignment
  131 |       OpName = llvm::AMDGPU::OpName::data0;
      | 
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:136: error: cannot convert ‘llvm::AMDGPU::OpName’ to ‘uint16_t’ {aka ‘short unsigned int’} in assignment
  135 |     OpName = AMDGPU::hasNamedOperand(Opcode, llvm::AMDGPU::OpName::vdata)
      |     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  136 |                  ? llvm::AMDGPU::OpName::vdata
      |                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  137 |                  : llvm::AMDGPU::OpName::vdst;
      | 
/b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:141: error: cannot convert ‘uint16_t’ {aka ‘short unsigned int’} to ‘llvm::AMDGPU::OpName’
  141 |   int VDstOrVDataIdx = AMDGPU::getNamedOperandIdx(Opcode, OpName);
      | 
In file included from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h:24,
                 from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/SIInstrInfo.h:20,
                 from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/GCNSubtarget.h:22,
                 from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h:17,
                 from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.h:18,
                 from /b/ml-opt-rel-x86-64-b1/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUMCInstLower.cpp:15:
/b/ml-opt-rel-x86-64-b1/build/lib/Target/AMDGPU/AMDGPUGenInstrInfo.inc:135914: note:   initializing argument 2 of ‘int16_t llvm::AMDGPU::getNamedOperandIdx(uint16_t, llvm::AMDGPU::OpName)’
135914 | int16_t getNamedOperandIdx(uint16_t Opcode, OpName Name);
       | 
868.029 [797/63/2974] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUImageIntrinsicOptimizer.cpp.o
868.744 [797/62/2975] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUHSAMetadataStreamer.cpp.o
869.025 [797/61/2976] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/R600OpenCLImageTypeLoweringPass.cpp.o
871.281 [797/60/2977] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUMIRFormatter.cpp.o
873.877 [797/59/2978] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/R600MachineCFGStructurizer.cpp.o
875.445 [797/58/2979] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/GCNCreateVOPD.cpp.o
876.083 [797/57/2980] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/AMDGPUPreloadKernArgProlog.cpp.o
876.412 [797/56/2981] Building CXX object lib/Target/AMDGPU/CMakeFiles/LLVMAMDGPUCodeGen.dir/GCNDPPCombine.cpp.o

```

</details>

https://github.com/llvm/llvm-project/pull/114500