[AMDGPU] Replace non-kernel function uses of LDS globals by pointers.

The main motivation behind pointer replacement of LDS use within non-kernel
functions is - to *avoid* subsequent LDS lowering pass from directly packing
LDS (assume large LDS) into a struct type which would otherwise cause allocating
huge memory for struct instance within every kernel.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D103225

Author: hsmahesha

llvm/lib/Target/AMDGPU/AMDGPU.h

@@ -71,6 +71,7 @@ FunctionPass *createAMDGPUMachineCFGStructurizerPass();
 FunctionPass *createAMDGPUPropagateAttributesEarlyPass(const TargetMachine *);
 ModulePass *createAMDGPUPropagateAttributesLatePass(const TargetMachine *);
 FunctionPass *createAMDGPURewriteOutArgumentsPass();
+ModulePass *createAMDGPUReplaceLDSUseWithPointerPass();
 ModulePass *createAMDGPULowerModuleLDSPass();
 FunctionPass *createSIModeRegisterPass();
 
@@ -146,6 +147,14 @@ struct AMDGPUPropagateAttributesLatePass
   TargetMachine &TM;
 };
 
+void initializeAMDGPUReplaceLDSUseWithPointerPass(PassRegistry &);
+extern char &AMDGPUReplaceLDSUseWithPointerID;
+
+struct AMDGPUReplaceLDSUseWithPointerPass
+    : PassInfoMixin<AMDGPUReplaceLDSUseWithPointerPass> {
+  PreservedAnalyses run(Module &M, ModuleAnalysisManager &AM);
+};
+
 void initializeAMDGPULowerModuleLDSPass(PassRegistry &);
 extern char &AMDGPULowerModuleLDSID;
 

llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp

@@ -24,6 +24,13 @@
 // A possible future refinement is to specialise the structure per-kernel, so
 // that fields can be elided based on more expensive analysis.
 //
+// NOTE: Since this pass will directly pack LDS (assume large LDS) into a struct
+// type which would cause allocating huge memory for struct instance within
+// every kernel. Hence, before running this pass, it is advisable to run the
+// pass "amdgpu-replace-lds-use-with-pointer" which will replace LDS uses within
+// non-kernel functions by pointers and thereby minimizes the unnecessary per
+// kernel allocation of LDS memory.
+//
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"