diff --git a/clang/include/clang/Driver/CC1Options.td b/clang/include/clang/Driver/CC1Options.td
--- a/clang/include/clang/Driver/CC1Options.td
+++ b/clang/include/clang/Driver/CC1Options.td
@@ -482,6 +482,10 @@
 def ast_merge : Separate<["-"], "ast-merge">,
   MetaVarName<"<ast file>">,
   HelpText<"Merge the given AST file into the translation unit being compiled.">;
+def aux_target_cpu : Separate<["-"], "aux-target-cpu">,
+  HelpText<"Target a specific auxiliary cpu type">;
+def aux_target_feature : Separate<["-"], "aux-target-feature">,
+  HelpText<"Target specific auxiliary attributes">;
 def aux_triple : Separate<["-"], "aux-triple">,
   HelpText<"Auxiliary target triple.">;
 def code_completion_at : Separate<["-"], "code-completion-at">,
diff --git a/clang/include/clang/Frontend/FrontendOptions.h b/clang/include/clang/Frontend/FrontendOptions.h
--- a/clang/include/clang/Frontend/FrontendOptions.h
+++ b/clang/include/clang/Frontend/FrontendOptions.h
@@ -426,9 +426,15 @@
   /// (in the format produced by -fdump-record-layouts).
   std::string OverrideRecordLayoutsFile;
 
-  /// Auxiliary triple for CUDA compilation.
+  /// Auxiliary triple for CUDA/HIP compilation.
   std::string AuxTriple;
 
+  /// Auxiliary target CPU for CUDA/HIP compilation.
+  Optional<std::string> AuxTargetCPU;
+
+  /// Auxiliary target features for CUDA/HIP compilation.
+  Optional<std::vector<std::string>> AuxTargetFeatures;
+
   /// Filename to write statistics to.
   std::string StatsFile;
 
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -309,7 +309,7 @@
 
 static void getTargetFeatures(const ToolChain &TC, const llvm::Triple &Triple,
                               const ArgList &Args, ArgStringList &CmdArgs,
-                              bool ForAS) {
+                              bool ForAS, bool IsAux = false) {
   const Driver &D = TC.getDriver();
   std::vector<StringRef> Features;
   switch (Triple.getArch()) {
@@ -387,7 +387,7 @@
     if (Last != I)
       continue;
 
-    CmdArgs.push_back("-target-feature");
+    CmdArgs.push_back(IsAux ? "-aux-target-feature" : "-target-feature");
     CmdArgs.push_back(Name.data());
   }
 }
@@ -4613,6 +4613,18 @@
                    AsynchronousUnwindTables))
     CmdArgs.push_back("-munwind-tables");
 
+  // Prepare `-aux-target-cpu` and `-aux-target-feature`.
+  if ((IsCuda && JA.isDeviceOffloading(Action::OFK_Cuda)) ||
+      (IsHIP && JA.isDeviceOffloading(Action::OFK_HIP))) {
+    const ArgList &HostArgs = C.getArgsForToolChain(nullptr, StringRef(), Action::OFK_None);
+    std::string HostCPU = getCPUName(HostArgs, *TC.getAuxTriple(), /*FromAs*/false);
+    if (!HostCPU.empty()) {
+      CmdArgs.push_back("-aux-target-cpu");
+      CmdArgs.push_back(Args.MakeArgString(HostCPU));
+    }
+    getTargetFeatures(TC, *TC.getAuxTriple(), HostArgs, CmdArgs, /*ForAS*/false, /*IsAux*/true);
+  }
+
   TC.addClangTargetOptions(Args, CmdArgs, JA.getOffloadingDeviceKind());
 
   // FIXME: Handle -mtune=.
diff --git a/clang/lib/Frontend/CompilerInstance.cpp b/clang/lib/Frontend/CompilerInstance.cpp
--- a/clang/lib/Frontend/CompilerInstance.cpp
+++ b/clang/lib/Frontend/CompilerInstance.cpp
@@ -923,6 +923,10 @@
       !getFrontendOpts().AuxTriple.empty()) {
     auto TO = std::make_shared<TargetOptions>();
     TO->Triple = llvm::Triple::normalize(getFrontendOpts().AuxTriple);
+    if (getFrontendOpts().AuxTargetCPU)
+      TO->CPU = getFrontendOpts().AuxTargetCPU.getValue();
+    if (getFrontendOpts().AuxTargetFeatures)
+      TO->FeaturesAsWritten = getFrontendOpts().AuxTargetFeatures.getValue();
     TO->HostTriple = getTarget().getTriple().str();
     setAuxTarget(TargetInfo::CreateTargetInfo(getDiagnostics(), TO));
   }
diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -1931,6 +1931,10 @@
   Opts.OverrideRecordLayoutsFile =
       std::string(Args.getLastArgValue(OPT_foverride_record_layout_EQ));
   Opts.AuxTriple = std::string(Args.getLastArgValue(OPT_aux_triple));
+  if (Args.hasArg(OPT_aux_target_cpu))
+    Opts.AuxTargetCPU = std::string(Args.getLastArgValue(OPT_aux_target_cpu));
+  if (Args.hasArg(OPT_aux_target_feature))
+    Opts.AuxTargetFeatures = Args.getAllArgValues(OPT_aux_target_feature);
   Opts.StatsFile = std::string(Args.getLastArgValue(OPT_stats_file));
 
   if (const Arg *A = Args.getLastArg(OPT_arcmt_check,
diff --git a/clang/test/Driver/hip-host-cpu-features.hip b/clang/test/Driver/hip-host-cpu-features.hip
new file mode 100644
--- /dev/null
+++ b/clang/test/Driver/hip-host-cpu-features.hip
@@ -0,0 +1,14 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+// RUN: %clang -### -c -target x86_64-linux-gnu -march=znver2 -x hip --cuda-gpu-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s -check-prefix=HOSTCPU
+// RUN: %clang -### -c -target x86_64-linux-gnu -msse3 -x hip --cuda-gpu-arch=gfx803 -nogpulib %s 2>&1 | FileCheck %s -check-prefix=HOSTSSE3
+
+// HOSTCPU: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// HOSTCPU-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// HOSTCPU-SAME: "-aux-target-cpu" "znver2"
+
+// HOSTSSE3: "-cc1" "-triple" "amdgcn-amd-amdhsa"
+// HOSTSSE3-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
+// HOSTSSE3-SAME: "-aux-target-feature" "+sse3"
diff --git a/clang/test/Preprocessor/hip-host-cpu-macros.cu b/clang/test/Preprocessor/hip-host-cpu-macros.cu
new file mode 100644
--- /dev/null
+++ b/clang/test/Preprocessor/hip-host-cpu-macros.cu
@@ -0,0 +1,13 @@
+// REQUIRES: clang-driver
+// REQUIRES: x86-registered-target
+// REQUIRES: amdgpu-registered-target
+
+#ifdef __HIP_DEVICE_COMPILE__
+DEVICE __SSE3__
+#else
+HOST __SSE3__
+#endif
+
+// RUN: %clang -x hip -E -target x86_64-linux-gnu -msse3 --cuda-gpu-arch=gfx803 -nogpulib -o - %s 2>&1 | FileCheck %s
+
+// CHECK-NOT: SSE3