llvm/llvm/lib/Target/AMDGPU/AMDGPURewriteOutArguments.cpp

//===- AMDGPURewriteOutArgumentsPass.cpp - Create struct returns ----------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
/// \file This pass attempts to replace out argument usage with a return of a
/// struct.
///
/// We can support returning a lot of values directly in registers, but
/// idiomatic C code frequently uses a pointer argument to return a second value
/// rather than returning a struct by value. GPU stack access is also quite
/// painful, so we want to avoid that if possible. Passing a stack object
/// pointer to a function also requires an additional address expansion code
/// sequence to convert the pointer to be relative to the kernel's scratch wave
/// offset register since the callee doesn't know what stack frame the incoming
/// pointer is relative to.
///
/// The goal is to try rewriting code that looks like this:
///
///  int foo(int a, int b, int* out) {
///     *out = bar();
///     return a + b;
/// }
///
/// into something like this:
///
///  std::pair<int, int> foo(int a, int b) {
///     return std::pair(a + b, bar());
/// }
///
/// Typically the incoming pointer is a simple alloca for a temporary variable
/// to use the API, which if replaced with a struct return will be easily SROA'd
/// out when the stub function we create is inlined
///
/// This pass introduces the struct return, but leaves the unused pointer
/// arguments and introduces a new stub function calling the struct returning
/// body. DeadArgumentElimination should be run after this to clean these up.
//
//===----------------------------------------------------------------------===//

#include "AMDGPU.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/MemoryDependenceAnalysis.h"
#include "llvm/IR/AttributeMask.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"

#define DEBUG_TYPE …

usingnamespacellvm;

static cl::opt<bool> AnyAddressSpace(
  "amdgpu-any-address-space-out-arguments",
  cl::desc("Replace pointer out arguments with "
           "struct returns for non-private address space"),
  cl::Hidden,
  cl::init(false));

static cl::opt<unsigned> MaxNumRetRegs(
  "amdgpu-max-return-arg-num-regs",
  cl::desc("Approximately limit number of return registers for replacing out arguments"),
  cl::Hidden,
  cl::init(16));

STATISTIC(NumOutArgumentsReplaced,
          "Number out arguments moved to struct return values");
STATISTIC(NumOutArgumentFunctionsReplaced,
          "Number of functions with out arguments moved to struct return values");

namespace {

class AMDGPURewriteOutArguments : public FunctionPass { … };

} // end anonymous namespace

INITIALIZE_PASS_BEGIN(AMDGPURewriteOutArguments, DEBUG_TYPE,
                      "AMDGPU Rewrite Out Arguments", false, false)
INITIALIZE_PASS_DEPENDENCY(MemoryDependenceWrapperPass)
INITIALIZE_PASS_END(AMDGPURewriteOutArguments, DEBUG_TYPE,
                    "AMDGPU Rewrite Out Arguments", false, false)

char AMDGPURewriteOutArguments::ID = …;

Type *AMDGPURewriteOutArguments::getStoredType(Value &Arg) const { … }

Type *AMDGPURewriteOutArguments::getOutArgumentType(Argument &Arg) const { … }

bool AMDGPURewriteOutArguments::doInitialization(Module &M) { … }

bool AMDGPURewriteOutArguments::runOnFunction(Function &F) { … }

FunctionPass *llvm::createAMDGPURewriteOutArgumentsPass() { … }