CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
229 lines
8.1 KiB
C++
229 lines
8.1 KiB
C++
//===- CallConvLoweringPass.cpp - Lower CIR to ABI calling convention ----===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This pass walks every cir.func and cir.call in the module, computes a
|
|
// FunctionClassification for it (via either an ABI target or a pre-built
|
|
// classification injected as a function attribute), and dispatches to
|
|
// CIRABIRewriteContext to perform the actual IR rewriting.
|
|
//
|
|
// Two driver modes (mutually exclusive):
|
|
//
|
|
// target=test
|
|
// Use the MLIR test ABI target (mlir/lib/ABI/Targets/Test/) to classify
|
|
// each function. Predictable rules that approximate x86_64 SysV. Real
|
|
// targets (x86_64, AArch64) will be added once the LLVM ABI library
|
|
// ships them.
|
|
//
|
|
// classification-attr=<name>
|
|
// Read a DictionaryAttr named <name> from each cir.func and parse it via
|
|
// mlir::abi::test::parseClassificationAttr. Used by tests to inject any
|
|
// classification (including shapes the test target itself does not
|
|
// produce) without depending on a real ABI target.
|
|
//
|
|
// The pass requires a `dlti.dl_spec` attribute on the module so the
|
|
// classifier can query type sizes and alignments.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "PassDetail.h"
|
|
#include "TargetLowering/CIRABIRewriteContext.h"
|
|
|
|
#include "mlir/ABI/ABIRewriteContext.h"
|
|
#include "mlir/ABI/Targets/Test/TestTarget.h"
|
|
#include "mlir/Dialect/DLTI/DLTI.h"
|
|
#include "mlir/IR/Builders.h"
|
|
#include "mlir/IR/BuiltinOps.h"
|
|
#include "mlir/IR/SymbolTable.h"
|
|
#include "mlir/Interfaces/DataLayoutInterfaces.h"
|
|
#include "mlir/Pass/Pass.h"
|
|
#include "clang/CIR/Dialect/IR/CIRDialect.h"
|
|
#include "clang/CIR/Dialect/Passes.h"
|
|
|
|
using namespace mlir;
|
|
using namespace mlir::abi;
|
|
using namespace cir;
|
|
|
|
namespace mlir {
|
|
#define GEN_PASS_DEF_CALLCONVLOWERING
|
|
#include "clang/CIR/Dialect/Passes.h.inc"
|
|
} // namespace mlir
|
|
|
|
namespace {
|
|
|
|
bool needsRewrite(const FunctionClassification &fc) {
|
|
if ((fc.returnInfo.kind != ArgKind::Direct) || fc.returnInfo.coercedType)
|
|
return true;
|
|
for (const ArgClassification &ac : fc.argInfos)
|
|
if ((ac.kind != ArgKind::Direct) || ac.coercedType)
|
|
return true;
|
|
return false;
|
|
}
|
|
|
|
struct CallConvLoweringPass
|
|
: public impl::CallConvLoweringBase<CallConvLoweringPass> {
|
|
using CallConvLoweringBase::CallConvLoweringBase;
|
|
void runOnOperation() override;
|
|
};
|
|
|
|
/// Classify \p func using whichever driver mode is configured. Returns
|
|
/// std::nullopt and emits an error on the function if classification fails
|
|
/// (e.g. injection-driver mode but the function is missing the attribute,
|
|
/// or the attribute is malformed).
|
|
std::optional<FunctionClassification>
|
|
classifyFunction(cir::FuncOp func, const DataLayout &dl, StringRef target,
|
|
StringRef classificationAttrName) {
|
|
ArrayRef<Type> argTypes = func.getFunctionType().getInputs();
|
|
Type returnType = func.getFunctionType().getReturnType();
|
|
|
|
if (!classificationAttrName.empty()) {
|
|
auto attr = func->getAttrOfType<DictionaryAttr>(classificationAttrName);
|
|
if (!attr) {
|
|
func.emitOpError()
|
|
<< "missing classification attribute '" << classificationAttrName
|
|
<< "' (CallConvLowering driver mode 'classification-attr')";
|
|
return std::nullopt;
|
|
}
|
|
return mlir::abi::test::parseClassificationAttr(
|
|
attr, [&]() { return func.emitOpError(); });
|
|
}
|
|
|
|
if (target == "test")
|
|
return mlir::abi::test::classify(argTypes, returnType, dl);
|
|
|
|
func.emitOpError() << "unknown target '" << target << "' (supported: test)";
|
|
return std::nullopt;
|
|
}
|
|
|
|
/// Find the cir.func declaration matching a direct cir.call / cir.try_call
|
|
/// callee, if any. Returns nullptr if the callee is indirect or the symbol
|
|
/// cannot be resolved. Takes a SymbolTable instead of a ModuleOp so the
|
|
/// symbol lookup is amortized across all the call sites the driver walks
|
|
/// (ModuleOp::lookupSymbol is linear per call).
|
|
cir::FuncOp lookupCallee(Operation *callOp, SymbolTable &symbolTable) {
|
|
FlatSymbolRefAttr callee;
|
|
if (auto call = dyn_cast<cir::CallOp>(callOp))
|
|
callee = call.getCalleeAttr();
|
|
else if (auto tryCall = dyn_cast<cir::TryCallOp>(callOp))
|
|
callee = tryCall.getCalleeAttr();
|
|
else
|
|
return nullptr;
|
|
if (!callee)
|
|
return nullptr;
|
|
return symbolTable.lookup<cir::FuncOp>(callee.getValue());
|
|
}
|
|
|
|
void CallConvLoweringPass::runOnOperation() {
|
|
ModuleOp moduleOp = getOperation();
|
|
MLIRContext *ctx = &getContext();
|
|
|
|
if (target.empty() == classificationAttr.empty()) {
|
|
moduleOp.emitOpError() << "CallConvLowering requires exactly one of "
|
|
"'target' or 'classification-attr' pass options";
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
|
|
if (!moduleOp->hasAttr(DLTIDialect::kDataLayoutAttrName)) {
|
|
moduleOp.emitOpError()
|
|
<< "CallConvLowering requires a DataLayout (dlti.dl_spec attribute "
|
|
"on the module)";
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
|
|
DataLayout dl(moduleOp);
|
|
CIRABIRewriteContext rewriteCtx(moduleOp, dl);
|
|
SymbolTable symbolTable(moduleOp);
|
|
|
|
// Classify every cir.func up front. No IR mutation happens here, so
|
|
// later walks can consult any function's classification regardless of
|
|
// visitation order.
|
|
llvm::MapVector<cir::FuncOp, FunctionClassification> classifications;
|
|
bool anyFailed = false;
|
|
moduleOp.walk([&](cir::FuncOp f) {
|
|
auto fc = classifyFunction(f, dl, target, classificationAttr);
|
|
if (!fc) {
|
|
anyFailed = true;
|
|
return;
|
|
}
|
|
classifications.insert({f, std::move(*fc)});
|
|
});
|
|
if (anyFailed) {
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
|
|
// Build a callee-to-callers index. One module walk collects every direct
|
|
// cir.call / cir.try_call to each cir.func; the loop below rewrites a
|
|
// function and all of its call sites together. Indirect or unresolved
|
|
// callees are skipped here; rewriteCallSite errors on those at the end.
|
|
llvm::DenseMap<cir::FuncOp, SmallVector<Operation *>> callers;
|
|
moduleOp.walk([&](Operation *op) {
|
|
if (!isa<cir::CallOp, cir::TryCallOp>(op))
|
|
return;
|
|
if (cir::FuncOp callee = lookupCallee(op, symbolTable))
|
|
callers[callee].push_back(op);
|
|
});
|
|
|
|
// Rewrite each function together with every direct call to it. By the
|
|
// time we move on to function F+1, F's signature and every direct call to
|
|
// F have already been brought into alignment, and F+1..FN are still in
|
|
// their original (mutually consistent) form, so the IR is verifier-clean
|
|
// at every outer-iteration boundary.
|
|
//
|
|
// There is still a brief inner window where F's signature has been
|
|
// rewritten but its callers have not yet caught up -- we have no way to
|
|
// mutate both sides of a call atomically. No verifier runs inside the
|
|
// pass, and at pass exit the module is verifier-clean. Fusing the inner
|
|
// loop here keeps the invalid window per-function rather than module-wide.
|
|
OpBuilder builder(ctx);
|
|
for (auto &kv : classifications) {
|
|
cir::FuncOp func = kv.first;
|
|
const FunctionClassification &fc = kv.second;
|
|
if (failed(rewriteCtx.rewriteFunctionDefinition(func, fc, builder))) {
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
for (Operation *callOp : callers.lookup(func)) {
|
|
if (failed(rewriteCtx.rewriteCallSite(callOp, fc, builder))) {
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
|
|
// Reject indirect calls when the module contains any ABI rewrite that
|
|
// would need call-site lowering. We cannot strip or coerce operands
|
|
// without a resolved callee symbol.
|
|
const FunctionClassification *rewriteFc = nullptr;
|
|
for (auto &kv : classifications) {
|
|
if (needsRewrite(kv.second)) {
|
|
rewriteFc = &kv.second;
|
|
break;
|
|
}
|
|
}
|
|
if (rewriteFc) {
|
|
moduleOp.walk([&](cir::CallOp c) {
|
|
if (!c.isIndirect())
|
|
return;
|
|
if (failed(rewriteCtx.rewriteCallSite(c, *rewriteFc, builder)))
|
|
anyFailed = true;
|
|
});
|
|
if (anyFailed) {
|
|
signalPassFailure();
|
|
return;
|
|
}
|
|
}
|
|
}
|
|
|
|
} // namespace
|
|
|
|
std::unique_ptr<Pass> mlir::createCallConvLoweringPass() {
|
|
return std::make_unique<CallConvLoweringPass>();
|
|
}
|