[mlir] Create a gpu.module operation for the GPU Dialect.

Summary:
This is based on the use of code constantly checking for an attribute on
a model and instead represents the distinct operaion with a different
op. Instead, this op can be used to provide better filtering.

Reviewers: herhut, mravishankar, antiagainst, rriddle

Reviewed By: herhut, antiagainst, rriddle

Subscribers: liufengdb, aartbik, jholewinski, mgorny, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, csigg, arpith-jacob, mgester, lucyrfox, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D72336

1 files changed, 13 insertions, 9 deletions

diff --git a/mlir/lib/Dialect/GPU/Transforms/KernelOutlining.cpp b/mlir/lib/Dialect/GPU/Transforms/KernelOutlining.cpp
index 37f9c2e7b84..0f8e2253980 100644
--- a/mlir/lib/Dialect/GPU/Transforms/KernelOutlining.cpp
+++ b/mlir/lib/Dialect/GPU/Transforms/KernelOutlining.cpp
@@ -140,8 +140,8 @@ namespace {
 /// inside a nested module. It also creates an external function of the same
 /// name in the parent module.
 ///
-/// The kernel modules are intended to be compiled to a cubin blob independently
-/// in a separate pass. The external functions can then be annotated with the
+/// The gpu.modules are intended to be compiled to a cubin blob independently in
+/// a separate pass. The external functions can then be annotated with the
 /// symbol of the cubin accessor function.
 class GpuKernelOutliningPass : public ModulePass<GpuKernelOutliningPass> {
 public:
@@ -174,15 +174,19 @@ public:
   }
 
 private:
-  // Returns a module containing kernelFunc and all callees (recursive).
-  ModuleOp createKernelModule(gpu::GPUFuncOp kernelFunc,
-                              const SymbolTable &parentSymbolTable) {
+  // Returns a gpu.module containing kernelFunc and all callees (recursive).
+  gpu::GPUModuleOp createKernelModule(gpu::GPUFuncOp kernelFunc,
+                                      const SymbolTable &parentSymbolTable) {
+    // TODO: This code cannot use an OpBuilder because it must be inserted into
+    // a SymbolTable by the caller. SymbolTable needs to be refactored to
+    // prevent manual building of Ops with symbols in code using SymbolTables
+    // and then this needs to use the OpBuilder.
     auto context = getModule().getContext();
     Builder builder(context);
-    auto kernelModule =
-        ModuleOp::create(builder.getUnknownLoc(), kernelFunc.getName());
-    kernelModule.setAttr(gpu::GPUDialect::getKernelModuleAttrName(),
-                         builder.getUnitAttr());
+    OperationState state(kernelFunc.getLoc(),
+                         gpu::GPUModuleOp::getOperationName());
+    gpu::GPUModuleOp::build(&builder, state, kernelFunc.getName());
+    auto kernelModule = cast<gpu::GPUModuleOp>(Operation::create(state));
     SymbolTable symbolTable(kernelModule);
     symbolTable.insert(kernelFunc);