[clang] aa964f1 - [HIP] Fix -mllvm option for device lld linker

[Yaxun Liu via cfe-commits]

Author: Yaxun (Sam) Liu
Date: 2023-06-30T12:54:38-04:00
New Revision: aa964f157f9b50fab3895afbfda6e0915cf6bb4a

URL: https://github.com/llvm/llvm-project/commit/aa964f157f9b50fab3895afbfda6e0915cf6bb4a
DIFF: https://github.com/llvm/llvm-project/commit/aa964f157f9b50fab3895afbfda6e0915cf6bb4a.diff

LOG: [HIP] Fix -mllvm option for device lld linker

currently clang passes -mllvm options to the device lld linker plugin
when compiling HIP. This is against default clang behavior
which is only passing -mllvm options to linker plugin specified through -Wl
options. This patch lets clang only pass -Xoffload-linker -mllvm= options
to device lld linker plugin.

Fixes: https://github.com/llvm/llvm-project/issues/63604

Reviewed by: Joseph Huber, Matt Arsenault

Differential Revision: https://reviews.llvm.org/D154145

Added: 
    

Modified: 
    clang/lib/Driver/ToolChains/HIPAMD.cpp
    clang/test/Driver/hip-toolchain-mllvm.hip

Removed: 
    


################################################################################
diff  --git a/clang/lib/Driver/ToolChains/HIPAMD.cpp b/clang/lib/Driver/ToolChains/HIPAMD.cpp
index a9afa5858b1bd..e509a01f2f977 100644
--- a/clang/lib/Driver/ToolChains/HIPAMD.cpp
+++ b/clang/lib/Driver/ToolChains/HIPAMD.cpp
@@ -142,11 +142,6 @@ void AMDGCN::Linker::constructLldCommand(Compilation &C, const JobAction &JA,
   if (IsThinLTO)
     LldArgs.push_back(Args.MakeArgString("-plugin-opt=-force-import-all"));
 
-  for (const Arg *A : Args.filtered(options::OPT_mllvm)) {
-    LldArgs.push_back(
-        Args.MakeArgString(Twine("-plugin-opt=") + A->getValue(0)));
-  }
-
   if (C.getDriver().isSaveTempsEnabled())
     LldArgs.push_back("-save-temps");
 
@@ -165,7 +160,14 @@ void AMDGCN::Linker::constructLldCommand(Compilation &C, const JobAction &JA,
   LldArgs.push_back("--whole-archive");
 
   for (auto *Arg : Args.filtered(options::OPT_Xoffload_linker)) {
-    LldArgs.push_back(Arg->getValue(1));
+    StringRef ArgVal = Arg->getValue(1);
+    auto SplitArg = ArgVal.split("-mllvm=");
+    if (!SplitArg.second.empty()) {
+      LldArgs.push_back(
+          Args.MakeArgString(Twine("-plugin-opt=") + SplitArg.second));
+    } else {
+      LldArgs.push_back(Args.MakeArgString(ArgVal));
+    }
     Arg->claim();
   }
 

diff  --git a/clang/test/Driver/hip-toolchain-mllvm.hip b/clang/test/Driver/hip-toolchain-mllvm.hip
index c7cb1f6787bc3..92954a3fc1fef 100644
--- a/clang/test/Driver/hip-toolchain-mllvm.hip
+++ b/clang/test/Driver/hip-toolchain-mllvm.hip
@@ -1,30 +1,47 @@
 // REQUIRES: x86-registered-target
 // REQUIRES: amdgpu-registered-target
 
+// Check only -Xoffload-linker -mllvm=* options are passed
+// to device lld linker.
+// -mllvm options are passed to clang only.
+
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
-// RUN:   -mllvm -amdgpu-function-calls=0 \
+// RUN:   -mllvm -unroll-count=10 \
+// RUN:   -Xoffload-linker -mllvm=-inline-threshold=100 \
 // RUN:   %s 2>&1 | FileCheck %s
 
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
-// RUN:   -fgpu-rdc -mllvm -amdgpu-function-calls=0 \
-// RUN:   %s 2>&1 | FileCheck -check-prefixes=CHECK,RDC %s
+// RUN:   -mllvm -unroll-count=10 \
+// RUN:   -Xoffload-linker -mllvm=-inline-threshold=100 \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=NEG %s
+
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -fgpu-rdc -mllvm -unroll-count=10 \
+// RUN:   -Xoffload-linker -mllvm=-inline-threshold=100 \
+// RUN:   %s 2>&1 | FileCheck %s
+
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 \
+// RUN:   -fgpu-rdc -mllvm -unroll-count=10 \
+// RUN:   -Xoffload-linker -mllvm=-inline-threshold=100 \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=NEG %s
 
 // CHECK: [[CLANG:".*clang.*"]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: {{.*}} "-target-cpu" "gfx803"
-// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
-
-// CHECK-NOT: {{".*opt"}}
-// CHECK-NOT: {{".*llc"}}
-// RDC: [[LLD:".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-function-calls=0"
+// CHECK-SAME: {{.*}} "-mllvm" "-unroll-count=10" {{.*}}
+// CHECK: [[LLD:".*lld.*"]] {{.*}}"-m" "elf64_amdgpu"{{.*}} "-plugin-opt=-inline-threshold=100"
 
 // CHECK: [[CLANG]] "-cc1" "-triple" "amdgcn-amd-amdhsa"
 // CHECK-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
 // CHECK-SAME: {{.*}} "-target-cpu" "gfx900"
-// CHECK-SAME: {{.*}} "-mllvm" "-amdgpu-function-calls=0" {{.*}}
+// CHECK-SAME: {{.*}} "-mllvm" "-unroll-count=10" {{.*}}
+// CHECK: [[LLD:".*lld.*"]] {{.*}} "-plugin-opt=-inline-threshold=100"
 
-// CHECK-NOT: {{".*opt"}}
-// CHECK-NOT: {{".*llc"}}
-// RDC: [[LLD:".*lld.*"]] {{.*}} "-plugin-opt=-amdgpu-function-calls=0"
+// NEG-NOT: {{".*opt"}}
+// NEG-NOT: {{".*llc"}}
+// NEG-NOT: "-plugin-opt=-unroll-count=10"
+// NEG-NOT: "-m" "elf_x86_64"{{.*}} "-plugin-opt=-inline-threshold=100"