[llvm] [KernelInfo] Implement new LLVM IR pass for GPU code analysis (PR #102944)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,121 @@
+//=- KernelInfo.h - Kernel Analysis -------------------------------*- 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the KernelInfo, KernelInfoAnalysis, and KernelInfoPrinter
+// classes used to extract function properties from a GPU kernel.
+//
+// See llvm/docs/KernelInfo.rst.
+// ===---------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_KERNELINFO_H
+#define LLVM_ANALYSIS_KERNELINFO_H
+
+#include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+
+namespace llvm {
+class DominatorTree;
+class Function;
+
+/// Data structure holding function info for kernels.
+class KernelInfo {
+  void updateForBB(const BasicBlock &BB, int64_t Direction,
+                   OptimizationRemarkEmitter &ORE);
+
+public:
+  static KernelInfo getKernelInfo(Function &F, FunctionAnalysisManager &FAM);
+
+  bool operator==(const KernelInfo &FPI) const {
+    return std::memcmp(this, &FPI, sizeof(KernelInfo)) == 0;
+  }
+
+  bool operator!=(const KernelInfo &FPI) const { return !(*this == FPI); }
+
+  /// Whether the function has external linkage and is not a kernel function.
+  bool ExternalNotKernel = false;
+
+  /// OpenMP Launch bounds.
+  ///@{
+  std::optional<int64_t> OmpTargetNumTeams;
+  std::optional<int64_t> OmpTargetThreadLimit;
+  ///@}
+
+  /// AMDGPU launch bounds.
+  ///@{
+  std::optional<int64_t> AmdgpuMaxNumWorkgroupsX;
+  std::optional<int64_t> AmdgpuMaxNumWorkgroupsY;
+  std::optional<int64_t> AmdgpuMaxNumWorkgroupsZ;
+  std::optional<int64_t> AmdgpuFlatWorkGroupSizeMin;
+  std::optional<int64_t> AmdgpuFlatWorkGroupSizeMax;
+  std::optional<int64_t> AmdgpuWavesPerEuMin;
+  std::optional<int64_t> AmdgpuWavesPerEuMax;
----------------
arsenm wrote:

Just because there isn't an explicit attribute doesn't mean the value doesn't exist (actually the attributes can be used to specify impossible values, which then need to be logically clamped). The logical values always exist.

For reference, AMDGPUAttributor queries the logical values for these when doing the propagation: https://github.com/llvm/llvm-project/blob/f668708796b981733a5816f2efed0d5195af923d/llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp#L186

https://github.com/llvm/llvm-project/pull/102944