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
71 lines
2.4 KiB
C++
71 lines
2.4 KiB
C++
//===-- CUFLaunchAttachAttr.cpp -------------------------------------------===//
|
|
//
|
|
// 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 "flang/Optimizer/Dialect/CUF/CUFDialect.h"
|
|
#include "flang/Optimizer/Dialect/FIROps.h"
|
|
#include "flang/Optimizer/Dialect/FIROpsSupport.h"
|
|
#include "mlir/Dialect/GPU/IR/GPUDialect.h"
|
|
#include "mlir/Pass/Pass.h"
|
|
#include "mlir/Transforms/DialectConversion.h"
|
|
|
|
namespace fir {
|
|
#define GEN_PASS_DEF_CUFLAUNCHATTACHATTR
|
|
#include "flang/Optimizer/Transforms/Passes.h.inc"
|
|
} // namespace fir
|
|
|
|
using namespace mlir;
|
|
|
|
namespace {
|
|
|
|
static constexpr llvm::StringRef cudaKernelInfix = "_cufk_";
|
|
|
|
class CUFGPUAttachAttrPattern
|
|
: public OpRewritePattern<mlir::gpu::LaunchFuncOp> {
|
|
using OpRewritePattern<mlir::gpu::LaunchFuncOp>::OpRewritePattern;
|
|
LogicalResult matchAndRewrite(mlir::gpu::LaunchFuncOp op,
|
|
PatternRewriter &rewriter) const override {
|
|
op->setAttr(cuf::getProcAttrName(),
|
|
cuf::ProcAttributeAttr::get(op.getContext(),
|
|
cuf::ProcAttribute::Global));
|
|
return mlir::success();
|
|
}
|
|
};
|
|
|
|
struct CUFLaunchAttachAttr
|
|
: public fir::impl::CUFLaunchAttachAttrBase<CUFLaunchAttachAttr> {
|
|
|
|
void runOnOperation() override {
|
|
auto *context = &this->getContext();
|
|
|
|
mlir::RewritePatternSet patterns(context);
|
|
patterns.add<CUFGPUAttachAttrPattern>(context);
|
|
|
|
mlir::ConversionTarget target(*context);
|
|
target.addIllegalOp<mlir::gpu::LaunchFuncOp>();
|
|
target.addDynamicallyLegalOp<mlir::gpu::LaunchFuncOp>(
|
|
[&](mlir::gpu::LaunchFuncOp op) -> bool {
|
|
if (op.getKernelName().getValue().contains(cudaKernelInfix)) {
|
|
if (op.getOperation()->getAttrOfType<cuf::ProcAttributeAttr>(
|
|
cuf::getProcAttrName()))
|
|
return true;
|
|
return false;
|
|
}
|
|
return true;
|
|
});
|
|
|
|
if (mlir::failed(mlir::applyPartialConversion(this->getOperation(), target,
|
|
std::move(patterns)))) {
|
|
mlir::emitError(mlir::UnknownLoc::get(context),
|
|
"Pattern conversion failed\n");
|
|
this->signalPassFailure();
|
|
}
|
|
}
|
|
};
|
|
|
|
} // end anonymous namespace
|