From 4f14b80803a458209b6b11daa3ec05076b8c4973 Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun.liu@amd.com>
Date: Fri, 4 Dec 2020 17:38:57 -0500
Subject: [PATCH] [HIP] unbundle bundled preprocessor output

There is a use case that users want to emit preprocessor
output as file and compile the preprocessor output later
with -x hip-cpp-output.

Clang emits bundled preprocessor output when users
compile with -E for combined host/device compilations.
Clang should be able to compile the bundled preprocessor
output with -x hip-cpp-output. Basically clang should
unbundle the bundled preprocessor output and launch
device and host compilation actions.

Currently there is a bug in clang driver causing bundled
preprocessor output not unbundled.

This patch fixes that.

Differential Revision: https://reviews.llvm.org/D92720
---
 clang/lib/Driver/Driver.cpp                | 10 ++++++----
 clang/test/Driver/hip-unbundle-preproc.hip | 25 +++++++++++++++++++++++++
 2 files changed, 31 insertions(+), 4 deletions(-)
 create mode 100644 clang/test/Driver/hip-unbundle-preproc.hip

diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index dc9ec1b..62fba30 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2460,8 +2460,9 @@ class OffloadingActionBuilder final {
 
         // If the host input is not CUDA or HIP, we don't need to bother about
         // this input.
-        if (IA->getType() != types::TY_CUDA &&
-            IA->getType() != types::TY_HIP) {
+        if (!(IA->getType() == types::TY_CUDA ||
+              IA->getType() == types::TY_HIP ||
+              IA->getType() == types::TY_PP_HIP)) {
           // The builder will ignore this input.
           IsActive = false;
           return ABRT_Inactive;
@@ -2489,7 +2490,7 @@ class OffloadingActionBuilder final {
 
         // If -fgpu-rdc is disabled, should not unbundle since there is no
         // device code to link.
-        if (!Relocatable)
+        if (UA->getType() == types::TY_Object && !Relocatable)
           return ABRT_Inactive;
 
         CudaDeviceActions.clear();
@@ -3250,7 +3251,8 @@ public:
     // the input is not a bundle.
     if (CanUseBundler && isa<InputAction>(HostAction) &&
         InputArg->getOption().getKind() == llvm::opt::Option::InputClass &&
-        !types::isSrcFile(HostAction->getType())) {
+        (!types::isSrcFile(HostAction->getType()) ||
+         HostAction->getType() == types::TY_PP_HIP)) {
       auto UnbundlingHostAction =
           C.MakeAction<OffloadUnbundlingJobAction>(HostAction);
       UnbundlingHostAction->registerDependentActionInfo(
diff --git a/clang/test/Driver/hip-unbundle-preproc.hip b/clang/test/Driver/hip-unbundle-preproc.hip
new file mode 100644
index 0000000..1903c72
--- /dev/null
+++ b/clang/test/Driver/hip-unbundle-preproc.hip
@@ -0,0 +1,25 @@
+// REQUIRES: clang-driver, amdgpu-registered-target
+
+// RUN: %clang -### -target x86_64-unknown-linux-gnu \
+// RUN:   --offload-arch=gfx803 -nogpulib \
+// RUN:   -x hip-cpp-output %s 2>&1 | FileCheck %s
+
+// CHECK: {{".*clang-offload-bundler.*"}} {{.*}}"-outputs=[[HOST_PP:.*cui]],[[DEV_PP:.*cui]]" "-unbundle"
+// CHECK: {{".*clang.*"}} "-cc1" {{.*}}"-target-cpu" "gfx803" {{.*}}"-o" "[[DEV_O:.*o]]" {{.*}}"[[DEV_PP]]"
+// CHECK: {{".*lld.*"}} {{.*}}"-o" "[[DEV_ISA:.*]]" "[[DEV_O]]"
+// CHECK: {{".*clang-offload-bundler.*"}} {{.*}}"-inputs={{.*}},[[DEV_ISA]]" "-outputs=[[FATBIN:.*]]"
+// CHECK: {{".*clang.*"}} {{.*}}"-triple" "x86_64-unknown-linux-gnu"{{.*}} "-fcuda-include-gpubinary" "[[FATBIN]]" {{.*}}"-o" "[[HOST_O:.*o]]" {{.*}}"[[HOST_PP]]"
+// CHECK: {{".*ld.*"}} {{.*}}"[[HOST_O]]"
+
+// RUN: %clang -### -target x86_64-unknown-linux-gnu \
+// RUN:   --offload-arch=gfx803 -nogpulib -fgpu-rdc \
+// RUN:   -x hip-cpp-output %s 2>&1 | FileCheck -check-prefix=RDC %s
+
+// RDC: {{".*clang-offload-bundler.*"}} {{.*}}"-outputs=[[HOST_PP:.*cui]],[[DEV_PP:.*cui]]" "-unbundle"
+// RDC: {{".*clang.*"}} {{.*}}"-triple" "x86_64-unknown-linux-gnu"{{.*}} "-o" "[[HOST_O:.*o]]" {{.*}}"[[HOST_PP]]"
+// RDC: {{".*clang-offload-bundler.*"}} {{.*}}"-outputs=[[HOST_PP:.*cui]],[[DEV_PP:.*cui]]" "-unbundle"
+// RDC: {{".*clang.*"}} "-cc1" {{.*}}"-target-cpu" "gfx803" {{.*}}"-o" "[[DEV_BC:.*bc]]" {{.*}}"[[DEV_PP]]"
+// RDC: {{".*lld.*"}} {{.*}}"-o" "[[DEV_ISA:.*]]" "[[DEV_BC]]"
+// RDC: {{".*clang-offload-bundler.*"}} {{.*}}"-inputs={{.*}},[[DEV_ISA]]" "-outputs=[[FATBIN:.*]]"
+// RDC: {{".*llvm-mc.*"}} "-o" "[[FATBIN_O:.*o]]"
+// RDC: {{".*ld.*"}} {{.*}}"[[HOST_O]]" "[[FATBIN_O]]"
-- 
2.7.4