llvm/llvm/lib/Target/NVPTX/NVPTXLowerUnreachable.cpp

//===-- NVPTXLowerUnreachable.cpp - Lower unreachables to exit =====--===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// PTX does not have a notion of `unreachable`, which results in emitted basic
// blocks having an edge to the next block:
//
//   block1:
//     call @does_not_return();
//     // unreachable
//   block2:
//     // ptxas will create a CFG edge from block1 to block2
//
// This may result in significant changes to the control flow graph, e.g., when
// LLVM moves unreachable blocks to the end of the function. That's a problem
// in the context of divergent control flow, as `ptxas` uses the CFG to
// determine divergent regions, and some intructions may not be executed
// divergently.
//
// For example, `bar.sync` is not allowed to be executed divergently on Pascal
// or earlier. If we start with the following:
//
//   entry:
//     // start of divergent region
//     @%p0 bra cont;
//     @%p1 bra unlikely;
//     ...
//     bra.uni cont;
//   unlikely:
//     ...
//     // unreachable
//   cont:
//     // end of divergent region
//     bar.sync 0;
//     bra.uni exit;
//   exit:
//     ret;
//
// it is transformed by the branch-folder and block-placement passes to:
//
//   entry:
//     // start of divergent region
//     @%p0 bra cont;
//     @%p1 bra unlikely;
//     ...
//     bra.uni cont;
//   cont:
//     bar.sync 0;
//     bra.uni exit;
//   unlikely:
//     ...
//     // unreachable
//   exit:
//     // end of divergent region
//     ret;
//
// After moving the `unlikely` block to the end of the function, it has an edge
// to the `exit` block, which widens the divergent region and makes the
// `bar.sync` instruction happen divergently.
//
// To work around this, we add an `exit` instruction before every `unreachable`,
// as `ptxas` understands that exit terminates the CFG. We do only do this if
// `unreachable` is not lowered to `trap`, which has the same effect (although
// with current versions of `ptxas` only because it is emited as `trap; exit;`).
//
//===----------------------------------------------------------------------===//

#include "NVPTX.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Type.h"
#include "llvm/Pass.h"

usingnamespacellvm;

namespace llvm {
void initializeNVPTXLowerUnreachablePass(PassRegistry &);
}

namespace {
class NVPTXLowerUnreachable : public FunctionPass { … };
} // namespace

char NVPTXLowerUnreachable::ID = …;

INITIALIZE_PASS(…)

StringRef NVPTXLowerUnreachable::getPassName() const { … }

// =============================================================================
// Returns whether a `trap` intrinsic should be emitted before I.
//
// This is a copy of the logic in SelectionDAGBuilder::visitUnreachable().
// =============================================================================
bool NVPTXLowerUnreachable::isLoweredToTrap(const UnreachableInst &I) const { … }

// =============================================================================
// Main function for this pass.
// =============================================================================
bool NVPTXLowerUnreachable::runOnFunction(Function &F) { … }

FunctionPass *llvm::createNVPTXLowerUnreachablePass(bool TrapUnreachable,
                                                    bool NoTrapAfterNoreturn) { … }