[clang] [llvm] [AMDGPU] Use a general form of intrinsic for tensor load/store (PR #182334)

[via llvm-commits]

github-actions[bot] wrote:

<!--PREMERGE ADVISOR COMMENT: Linux-->
# :penguin: Linux x64 Test Results

* 129017 tests passed
* 1968 tests skipped

All executed tests passed, but another part of the build **failed**. Click on a failure below to see the details.

<details>
<summary>tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL/CMakeFiles/obj.MLIRROCDLToLLVMIRTranslation.dir/ROCDLToLLVMIRTranslation.cpp.o</summary>

```
FAILED: tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL/CMakeFiles/obj.MLIRROCDLToLLVMIRTranslation.dir/ROCDLToLLVMIRTranslation.cpp.o
sccache /opt/llvm/bin/clang++ -D_DEBUG -D_GLIBCXX_ASSERTIONS -D_GLIBCXX_USE_CXX11_ABI=1 -D_GNU_SOURCE -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS -D__STDC_LIMIT_MACROS -I/home/gha/actions-runner/_work/llvm-project/llvm-project/build/tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL -I/home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/lib/Target/LLVMIR/Dialect/ROCDL -I/home/gha/actions-runner/_work/llvm-project/llvm-project/build/tools/mlir/include -I/home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/include -I/home/gha/actions-runner/_work/llvm-project/llvm-project/build/include -I/home/gha/actions-runner/_work/llvm-project/llvm-project/llvm/include -gmlt -fPIC -fno-semantic-interposition -fvisibility-inlines-hidden -Werror -Werror=date-time -Werror=unguarded-availability-new -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wmissing-field-initializers -pedantic -Wno-long-long -Wc++98-compat-extra-semi -Wimplicit-fallthrough -Wcovered-switch-default -Wno-noexcept-type -Wnon-virtual-dtor -Wdelete-non-virtual-dtor -Wsuggest-override -Wstring-conversion -Wno-pass-failed -Wmisleading-indentation -Wctad-maybe-unsupported -fdiagnostics-color -ffunction-sections -fdata-sections -Wundef -Werror=mismatched-tags -Werror=global-constructors -O3 -DNDEBUG -std=c++17 -UNDEBUG -fno-exceptions -funwind-tables -fno-rtti -MD -MT tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL/CMakeFiles/obj.MLIRROCDLToLLVMIRTranslation.dir/ROCDLToLLVMIRTranslation.cpp.o -MF tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL/CMakeFiles/obj.MLIRROCDLToLLVMIRTranslation.dir/ROCDLToLLVMIRTranslation.cpp.o.d -o tools/mlir/lib/Target/LLVMIR/Dialect/ROCDL/CMakeFiles/obj.MLIRROCDLToLLVMIRTranslation.dir/ROCDLToLLVMIRTranslation.cpp.o -c /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp
In file included from /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp:69:
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/tools/mlir/include/mlir/Dialect/LLVMIR/ROCDLConversions.inc:1733:61: error: no member named 'amdgcn_tensor_load_to_lds_d2' in namespace 'llvm::Intrinsic'; did you mean 'amdgcn_tensor_load_to_lds'?
1733 |       builder, moduleTranslation, &opInst, llvm::Intrinsic::amdgcn_tensor_load_to_lds_d2,0,{},{},{2},{StringLiteral("cachePolicy")});
|                                                             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
|                                                             amdgcn_tensor_load_to_lds
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/include/llvm/IR/IntrinsicsAMDGPU.h:1401:5: note: 'amdgcn_tensor_load_to_lds' declared here
1401 |     amdgcn_tensor_load_to_lds,                 // llvm.amdgcn.tensor.load.to.lds (IntrinsicsAMDGPU.td:4213)
|     ^
In file included from /home/gha/actions-runner/_work/llvm-project/llvm-project/mlir/lib/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp:69:
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/tools/mlir/include/mlir/Dialect/LLVMIR/ROCDLConversions.inc:1755:61: error: no member named 'amdgcn_tensor_store_from_lds_d2' in namespace 'llvm::Intrinsic'; did you mean 'amdgcn_tensor_store_from_lds'?
1755 |       builder, moduleTranslation, &opInst, llvm::Intrinsic::amdgcn_tensor_store_from_lds_d2,0,{},{},{2},{StringLiteral("cachePolicy")});
|                                                             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|                                                             amdgcn_tensor_store_from_lds
/home/gha/actions-runner/_work/llvm-project/llvm-project/build/include/llvm/IR/IntrinsicsAMDGPU.h:1402:5: note: 'amdgcn_tensor_store_from_lds' declared here
1402 |     amdgcn_tensor_store_from_lds,              // llvm.amdgcn.tensor.store.from.lds (IntrinsicsAMDGPU.td:4214)
|     ^
2 errors generated.
```
</details>

If these failures are unrelated to your changes (for example tests are broken or flaky at HEAD), please open an issue at https://github.com/llvm/llvm-project/issues and add the `infrastructure` label.

https://github.com/llvm/llvm-project/pull/182334