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
60 lines
2.0 KiB
C++
60 lines
2.0 KiB
C++
//===- AMDGPUGlobalISelUtils -------------------------------------*- C++ -*-==//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUGLOBALISELUTILS_H
|
|
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUGLOBALISELUTILS_H
|
|
|
|
#include "llvm/ADT/DenseSet.h"
|
|
#include "llvm/CodeGen/Register.h"
|
|
#include <utility>
|
|
|
|
namespace llvm {
|
|
|
|
class MachineRegisterInfo;
|
|
class GCNSubtarget;
|
|
class GISelValueTracking;
|
|
class LLT;
|
|
class MachineFunction;
|
|
class MachineIRBuilder;
|
|
class RegisterBankInfo;
|
|
|
|
namespace AMDGPU {
|
|
|
|
/// Returns base register and constant offset.
|
|
std::pair<Register, unsigned>
|
|
getBaseWithConstantOffset(MachineRegisterInfo &MRI, Register Reg,
|
|
GISelValueTracking *ValueTracking = nullptr,
|
|
bool CheckNUW = false);
|
|
|
|
// Currently finds S32/S64 lane masks that can be declared as divergent by
|
|
// uniformity analysis (all are phis at the moment).
|
|
// These are defined as i32/i64 in some IR intrinsics (not as i1).
|
|
// Tablegen forces(via telling that lane mask IR intrinsics are uniform) most of
|
|
// S32/S64 lane masks to be uniform, as this results in them ending up with sgpr
|
|
// reg class after instruction-select, don't search for all of them.
|
|
class IntrinsicLaneMaskAnalyzer {
|
|
SmallDenseSet<Register, 8> S32S64LaneMask;
|
|
MachineRegisterInfo &MRI;
|
|
|
|
public:
|
|
IntrinsicLaneMaskAnalyzer(MachineFunction &MF);
|
|
bool isS32S64LaneMask(Register Reg) const;
|
|
|
|
private:
|
|
void initLaneMaskIntrinsics(MachineFunction &MF);
|
|
};
|
|
|
|
void buildReadAnyLane(MachineIRBuilder &B, Register SgprDst, Register VgprSrc,
|
|
const RegisterBankInfo &RBI);
|
|
void buildReadFirstLane(MachineIRBuilder &B, Register SgprDst, Register VgprSrc,
|
|
const RegisterBankInfo &RBI);
|
|
}
|
|
}
|
|
|
|
#endif
|