[Mlir-commits] [mlir] [MLIR] Update convert-gpu-to-spirv pass to prepare using GPU compilat… (PR #69941)

[Jakub Kuderski]

================
@@ -54,22 +55,63 @@ void GPUToSPIRVPass::runOnOperation() {
 
   SmallVector<Operation *, 1> gpuModules;
   OpBuilder builder(context);
+
+  auto getTargetEnvFromGPUModuleOp = [=](gpu::GPUModuleOp moduleOp) {
+    Operation *gpuModule = moduleOp.getOperation();
+    auto targetAttr = spirv::lookupTargetEnvOrDefault(gpuModule);
+    std::unique_ptr<ConversionTarget> target =
+        SPIRVConversionTarget::get(targetAttr);
+
+    SPIRVConversionOptions options;
+    options.use64bitIndex = this->use64bitIndex;
+    SPIRVTypeConverter typeConverter(targetAttr, options);
+    const spirv::TargetEnv &targetEnv = typeConverter.getTargetEnv();
+    return targetEnv;
+  };
+
   module.walk([&](gpu::GPUModuleOp moduleOp) {
     // Clone each GPU kernel module for conversion, given that the GPU
     // launch op still needs the original GPU kernel module.
-    builder.setInsertionPoint(moduleOp.getOperation());
+    // SPIRV module insertion point by is after original GPU module.
+    // This works fine for Vulkan shader that has a dedicated runner.
+    // But OpenCL kernel needs SPIRV module placed inside original GPU module as
+    // OpenCL uses GPU compilation pipeline.
+    auto targetEnv = getTargetEnvFromGPUModuleOp(moduleOp);
----------------
kuhar wrote:

nit: I realize this comes from existing code elsewhere in this file, but could you write the full type here instead of `auto`? It's not obvious from the RHS, which is the general criterium for `auto` in MLIR.

https://github.com/llvm/llvm-project/pull/69941