From e8fd998e6194d8749b83b30813e3cb74e5261770 Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun.liu@amd.com>
Date: Mon, 12 Dec 2022 15:50:44 -0500
Subject: [PATCH] [HIP] support --offload-arch=native

This patch detects system GPU and use them
in --offload-arch if 'native' is specified. If system GPU
cannot be detected clang will fall back to the default GPU arch.

Reviewed by: Artem Belevich

Differential Revision: https://reviews.llvm.org/D139045
---
 clang/lib/Driver/Driver.cpp          | 11 +++++++++++
 clang/lib/Driver/ToolChains/AMDGPU.h |  5 +++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 969d385..c7efe60 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -3067,6 +3067,17 @@ class OffloadingActionBuilder final {
           if (A->getOption().matches(options::OPT_no_offload_arch_EQ) &&
               ArchStr == "all") {
             GpuArchs.clear();
+          } else if (ArchStr == "native" &&
+                     ToolChains.front()->getTriple().isAMDGPU()) {
+            auto *TC = static_cast<const toolchains::HIPAMDToolChain *>(
+                ToolChains.front());
+            SmallVector<std::string, 1> GPUs;
+            auto Err = TC->detectSystemGPUs(Args, GPUs);
+            if (!Err) {
+              for (auto GPU : GPUs)
+                GpuArchs.insert(Args.MakeArgString(GPU));
+            } else
+              llvm::consumeError(std::move(Err));
           } else {
             ArchStr = getCanonicalOffloadArch(ArchStr);
             if (ArchStr.empty()) {
diff --git a/clang/lib/Driver/ToolChains/AMDGPU.h b/clang/lib/Driver/ToolChains/AMDGPU.h
index 0ac13ec..3f5461a 100644
--- a/clang/lib/Driver/ToolChains/AMDGPU.h
+++ b/clang/lib/Driver/ToolChains/AMDGPU.h
@@ -107,6 +107,9 @@ public:
   llvm::Error getSystemGPUArch(const llvm::opt::ArgList &Args,
                                std::string &GPUArch) const;
 
+  llvm::Error detectSystemGPUs(const llvm::opt::ArgList &Args,
+                               SmallVector<std::string, 1> &GPUArchs) const;
+
 protected:
   /// Check and diagnose invalid target ID specified by -mcpu.
   virtual void checkTargetID(const llvm::opt::ArgList &DriverArgs) const;
@@ -126,8 +129,6 @@ protected:
   /// Get GPU arch from -mcpu without checking.
   StringRef getGPUArch(const llvm::opt::ArgList &DriverArgs) const;
 
-  llvm::Error detectSystemGPUs(const llvm::opt::ArgList &Args,
-                               SmallVector<std::string, 1> &GPUArchs) const;
 };
 
 class LLVM_LIBRARY_VISIBILITY ROCMToolChain : public AMDGPUToolChain {
-- 
2.7.4