[Mlir-commits] [mlir] [mlir][gpu] Add builder to `gpu.launch_func` (PR #95541)

[Fabian Mora]

https://github.com/fabianmcg created https://github.com/llvm/llvm-project/pull/95541

This patch adds a builder to `gpu.launch_func` allowing it to be created using `SymbolRefAttr` instead of  `GPUFuncOp`. This allows creating `launch_func` when only a `gpu.binary` is present, instead of the full `gpu.module {...}`.

>From e3d3e75892da961c16f701869780c95676fc49b9 Mon Sep 17 00:00:00 2001
From: Fabian Mora <fmora.dev at gmail.com>
Date: Thu, 13 Jun 2024 20:32:57 +0000
Subject: [PATCH] [mlir][gpu] Add builder to `gpu.launch_func`

---
 mlir/include/mlir/Dialect/GPU/IR/GPUOps.td |  6 ++++++
 mlir/lib/Dialect/GPU/IR/GPUDialect.cpp     | 23 +++++++++++++++++-----
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td b/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
index 9c5f7ecd8cbe8..5943de103beba 100644
--- a/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
+++ b/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
@@ -653,6 +653,12 @@ def GPU_LaunchFuncOp :GPU_Op<"launch_func", [
       CArg<"Type", "nullptr">:$asyncTokenType,
       CArg<"ValueRange", "{}">:$asyncDependencies,
       CArg<"std::optional<KernelDim3>", "std::nullopt">:$clusterSize)>,
+    OpBuilder<(ins "SymbolRefAttr":$kernel, "KernelDim3":$gridSize,
+      "KernelDim3":$blockSize, "Value":$dynamicSharedMemorySize,
+      "ValueRange":$kernelOperands,
+      "Type":$asyncTokenType,
+      CArg<"ValueRange", "{}">:$asyncDependencies,
+      CArg<"std::optional<KernelDim3>", "std::nullopt">:$clusterSize)>,
     OpBuilder<(ins "SymbolRefAttr":$kernel, "KernelDim3":$gridSize,
       "KernelDim3":$blockSize, "Value":$dynamicSharedMemorySize,
       "ValueRange":$kernelOperands,
diff --git a/mlir/lib/Dialect/GPU/IR/GPUDialect.cpp b/mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
index d8e29da6512d4..17bf254b64b4d 100644
--- a/mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
+++ b/mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
@@ -1081,11 +1081,13 @@ BlockArgument LaunchOp::addPrivateAttribution(Type type, Location loc) {
 //===----------------------------------------------------------------------===//
 
 void LaunchFuncOp::build(OpBuilder &builder, OperationState &result,
-                         GPUFuncOp kernelFunc, KernelDim3 gridSize,
+                         SymbolRefAttr kernelSymbol, KernelDim3 gridSize,
                          KernelDim3 getBlockSize, Value dynamicSharedMemorySize,
                          ValueRange kernelOperands, Type asyncTokenType,
                          ValueRange asyncDependencies,
                          std::optional<KernelDim3> clusterSize) {
+  assert(kernelSymbol.getNestedReferences().size() == 1 &&
+         "expected a symbol reference with a single nested reference");
   result.addOperands(asyncDependencies);
   if (asyncTokenType)
     result.types.push_back(builder.getType<AsyncTokenType>());
@@ -1098,10 +1100,6 @@ void LaunchFuncOp::build(OpBuilder &builder, OperationState &result,
   if (dynamicSharedMemorySize)
     result.addOperands(dynamicSharedMemorySize);
   result.addOperands(kernelOperands);
-  auto kernelModule = kernelFunc->getParentOfType<GPUModuleOp>();
-  auto kernelSymbol =
-      SymbolRefAttr::get(kernelModule.getNameAttr(),
-                         {SymbolRefAttr::get(kernelFunc.getNameAttr())});
 
   Properties &prop = result.getOrAddProperties<Properties>();
   prop.kernel = kernelSymbol;
@@ -1122,6 +1120,21 @@ void LaunchFuncOp::build(OpBuilder &builder, OperationState &result,
   prop.operandSegmentSizes[segmentSizesLen - 1] = 0;
 }
 
+void LaunchFuncOp::build(OpBuilder &builder, OperationState &result,
+                         GPUFuncOp kernelFunc, KernelDim3 gridSize,
+                         KernelDim3 getBlockSize, Value dynamicSharedMemorySize,
+                         ValueRange kernelOperands, Type asyncTokenType,
+                         ValueRange asyncDependencies,
+                         std::optional<KernelDim3> clusterSize) {
+  auto kernelModule = kernelFunc->getParentOfType<GPUModuleOp>();
+  auto kernelSymbol =
+      SymbolRefAttr::get(kernelModule.getNameAttr(),
+                         {SymbolRefAttr::get(kernelFunc.getNameAttr())});
+  build(builder, result, kernelSymbol, gridSize, getBlockSize,
+        dynamicSharedMemorySize, kernelOperands, asyncTokenType,
+        asyncDependencies, clusterSize);
+}
+
 void LaunchFuncOp::build(OpBuilder &builder, OperationState &result,
                          SymbolRefAttr kernel, KernelDim3 gridSize,
                          KernelDim3 getBlockSize, Value dynamicSharedMemorySize,