5e50dd048e
This commit restructures how TypeID is implemented to ideally avoid the current problems related to shared libraries. This is done by changing the "implicit" fallback path to use the name of the type, instead of using a static template variable (which breaks shared libraries). The major downside to this is that it adds some additional initialization costs for the implicit path. Given the use of type names for uniqueness in the fallback, we also no longer allow types defined in anonymous namespaces to have an implicit TypeID. To simplify defining an ID for these classes, a new `MLIR_DEFINE_EXPLICIT_INTERNAL_INLINE_TYPE_ID` macro was added to allow for explicitly defining a TypeID directly on an internal class. To help identify when types are using the fallback, `-debug-only=typeid` can be used to log which types are using implicit ids. This change generally only requires changes to the test passes, which are all defined in anonymous namespaces, and thus can't use the fallback any longer. Differential Revision: https://reviews.llvm.org/D122775
75 lines
2.3 KiB
C++
75 lines
2.3 KiB
C++
//===- TestConvertGPUKernelToCubin.cpp - Test gpu kernel cubin lowering ---===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Dialect/GPU/Passes.h"
|
|
|
|
#include "mlir/Pass/Pass.h"
|
|
#include "mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h"
|
|
#include "mlir/Target/LLVMIR/Export.h"
|
|
#include "llvm/Support/TargetSelect.h"
|
|
|
|
using namespace mlir;
|
|
|
|
#if MLIR_CUDA_CONVERSIONS_ENABLED
|
|
namespace {
|
|
class TestSerializeToCubinPass
|
|
: public PassWrapper<TestSerializeToCubinPass, gpu::SerializeToBlobPass> {
|
|
public:
|
|
MLIR_DEFINE_EXPLICIT_INTERNAL_INLINE_TYPE_ID(TestSerializeToCubinPass)
|
|
|
|
StringRef getArgument() const final { return "test-gpu-to-cubin"; }
|
|
StringRef getDescription() const final {
|
|
return "Lower GPU kernel function to CUBIN binary annotations";
|
|
}
|
|
TestSerializeToCubinPass();
|
|
|
|
private:
|
|
void getDependentDialects(DialectRegistry ®istry) const override;
|
|
|
|
// Serializes PTX to CUBIN.
|
|
std::unique_ptr<std::vector<char>>
|
|
serializeISA(const std::string &isa) override;
|
|
};
|
|
} // namespace
|
|
|
|
TestSerializeToCubinPass::TestSerializeToCubinPass() {
|
|
this->triple = "nvptx64-nvidia-cuda";
|
|
this->chip = "sm_35";
|
|
this->features = "+ptx60";
|
|
}
|
|
|
|
void TestSerializeToCubinPass::getDependentDialects(
|
|
DialectRegistry ®istry) const {
|
|
registerNVVMDialectTranslation(registry);
|
|
gpu::SerializeToBlobPass::getDependentDialects(registry);
|
|
}
|
|
|
|
std::unique_ptr<std::vector<char>>
|
|
TestSerializeToCubinPass::serializeISA(const std::string &) {
|
|
std::string data = "CUBIN";
|
|
return std::make_unique<std::vector<char>>(data.begin(), data.end());
|
|
}
|
|
|
|
namespace mlir {
|
|
namespace test {
|
|
// Register test pass to serialize GPU module to a CUBIN binary annotation.
|
|
void registerTestGpuSerializeToCubinPass() {
|
|
PassRegistration<TestSerializeToCubinPass>([] {
|
|
// Initialize LLVM NVPTX backend.
|
|
LLVMInitializeNVPTXTarget();
|
|
LLVMInitializeNVPTXTargetInfo();
|
|
LLVMInitializeNVPTXTargetMC();
|
|
LLVMInitializeNVPTXAsmPrinter();
|
|
|
|
return std::make_unique<TestSerializeToCubinPass>();
|
|
});
|
|
}
|
|
} // namespace test
|
|
} // namespace mlir
|
|
#endif // MLIR_CUDA_CONVERSIONS_ENABLED
|