[mlir][GPUToLLVM] Fix regression introduced with opaque-pointers when generate GPU launch func parameters

[zero9178]

Summary

This has caused build failures when enabling opaque pointers for the GPU integration tests as could be seen here:
https://lab.llvm.org/buildbot/#/builders/220/builds/16946 and here https://lab.llvm.org/buildbot/#/builders/61/builds/40822

The gist of the issue was the use of a wrong pointer base type within a GEP. There sadly was no test coverage for either the generating of that GEP, nor is LLVM Dialects GEP verifier currently capable of catching such issues, so it went unnoticed until the integration tests actually attempted to convert it to LLVM IR.

Required to reland https://reviews.llvm.org/D145585

[gysit]

LGTM!

mlir/lib/Conversion/GPUCommon/GPUToLLVMConversion.cpp

auto structPtr = builder.create<LLVM::AllocaOp>(
       /*alignment=*/0);
   auto arraySize =
       builder.create<LLVM::ConstantOp>(loc, llvmInt32Type, numArguments);
   auto arrayPtr = builder.create<LLVM::AllocaOp>(
       loc, llvmPointerPointerType, llvmPointerType, arraySize, /*alignment=*/0);
   for (const auto &en : llvm::enumerate(arguments)) {
     Value fieldPtr = builder.create<LLVM::GEPOp>(
         loc, getTypeConverter()->getPointerType(argumentTypes[en.index()]),
-        argumentTypes[en.index()], structPtr,
-        ArrayRef<LLVM::GEPArg>{0, en.index()});
+        structType, structPtr, ArrayRef<LLVM::GEPArg>{0, en.index()});
     builder.create<LLVM::StoreOp>(loc, en.value(), fieldPtr);
     auto elementPtr = builder.create<LLVM::GEPOp>(
         loc, llvmPointerPointerType, llvmPointerType, arrayPtr,
         ArrayRef<LLVM::GEPArg>{en.index()});
     if (!getTypeConverter()->useOpaquePointers())
       fieldPtr =
           builder.create<LLVM::BitcastOp>(loc, llvmPointerType, fieldPtr);
     builder.create<LLVM::StoreOp>(loc, fieldPtr, elementPtr);

mlir/test/Conversion/GPUCommon/lower-launch-func-to-gpu-runtime-calls.mlir

module attributes {gpu.container_module} {
   // CHECK: [[BINARY:%.*]] = llvm.getelementptr [[ADDRESSOF]]{{\[}}0, 0]
   // CHECK-SAME: -> !llvm.ptr
 
   // CHECK: [[MODULE:%.*]] = llvm.call @mgpuModuleLoad([[BINARY]])
   // CHECK: [[FUNC:%.*]] = llvm.call @mgpuModuleGetFunction([[MODULE]], {{.*}})
 
   // CHECK: [[STREAM:%.*]] = llvm.call @mgpuStreamCreate
 
+  // CHECK: %[[ONE:.*]] = llvm.mlir.constant(1 : i32)
+  // CHECK: %[[MEMREF:.*]] = llvm.alloca %[[ONE]] x !llvm.struct[[STRUCT_BODY:<.*>]]
   // CHECK: [[NUM_PARAMS:%.*]] = llvm.mlir.constant(6 : i32) : i32
   // CHECK-NEXT: [[PARAMS:%.*]] = llvm.alloca [[NUM_PARAMS]] x !llvm.ptr
 
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 1] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 3] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 4] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+  // CHECK: llvm.getelementptr %[[MEMREF]][0, 5] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
+
   // CHECK: [[EXTRA_PARAMS:%.*]] = llvm.mlir.null : !llvm.ptr
 
   // CHECK: llvm.call @mgpuLaunchKernel([[FUNC]], [[C8]], [[C8]], [[C8]],
   // CHECK-SAME: [[C8]], [[C8]], [[C8]], [[C256]], [[STREAM]],
   // CHECK-SAME: [[PARAMS]], [[EXTRA_PARAMS]])
   // CHECK: llvm.call @mgpuStreamSynchronize
   // CHECK: llvm.call @mgpuStreamDestroy
   // CHECK: llvm.call @mgpuModuleUnload
 }