llvm/clang/lib/CodeGen/CGGPUBuiltin.cpp

//===------ CGGPUBuiltin.cpp - Codegen for GPU builtins -------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// Generates code for built-in GPU calls which are not runtime-specific.
// (Runtime-specific codegen lives in programming model specific files.)
//
//===----------------------------------------------------------------------===//

#include "CodeGenFunction.h"
#include "clang/Basic/Builtins.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Instruction.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Transforms/Utils/AMDGPUEmitPrintf.h"

usingnamespaceclang;
usingnamespaceCodeGen;

namespace {
llvm::Function *GetVprintfDeclaration(llvm::Module &M) { … }

// Transforms a call to printf into a call to the NVPTX vprintf syscall (which
// isn't particularly special; it's invoked just like a regular function).
// vprintf takes two args: A format string, and a pointer to a buffer containing
// the varargs.
//
// For example, the call
//
//   printf("format string", arg1, arg2, arg3);
//
// is converted into something resembling
//
//   struct Tmp {
//     Arg1 a1;
//     Arg2 a2;
//     Arg3 a3;
//   };
//   char* buf = alloca(sizeof(Tmp));
//   *(Tmp*)buf = {a1, a2, a3};
//   vprintf("format string", buf);
//
// buf is aligned to the max of {alignof(Arg1), ...}.  Furthermore, each of the
// args is itself aligned to its preferred alignment.
//
// Note that by the time this function runs, E's args have already undergone the
// standard C vararg promotion (short -> int, float -> double, etc.).

std::pair<llvm::Value *, llvm::TypeSize>
packArgsIntoNVPTXFormatBuffer(CodeGenFunction *CGF, const CallArgList &Args) { … }

bool containsNonScalarVarargs(CodeGenFunction *CGF, const CallArgList &Args) { … }

RValue EmitDevicePrintfCallExpr(const CallExpr *E, CodeGenFunction *CGF,
                                llvm::Function *Decl, bool WithSizeArg) { … }
} // namespace

RValue CodeGenFunction::EmitNVPTXDevicePrintfCallExpr(const CallExpr *E) { … }

RValue CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) { … }