[HIP] Ignore host linker flags for device-only

[scchan]

Summary

When compiling in device only mode (e.g. --offload-device-only), the
host linker phase would not happen and therefore, the driver should
ignore all the host linker flags.

[yaxunl]

clang/lib/Driver/Driver.cpp

4153

The --hip-link -fgpu-rdc --offload-device-only case needs to add the linker inputs e.g. archive of bundled bitcodes. Need a test to make sure that still works.

Also you need to use Driver::offloadDeviceOnly() to check whether it is device compilation only

[scchan]

addressed comments from yaxunl, rebased

[yaxunl]

clang/test/Driver/hip-phases.hip

276

need to check RELOC-NOT: host

304

need to check RELOC2-NOT: host

425

need to check RL2-DEV-NOT: host

[scchan]

added extra checks for not host, rebased

[yaxunl]

LGTM. Thanks.

[scchan]

minor formatting fixes, rebased

clang/lib/Driver/Driver.cpp

for (phases::ID Phase : PL) {
         Current = OffloadBuilder->addDeviceDependencesToHostAction(
             Current, InputArg, Phase, PL.back(), FullPL);
       if (!Current)
         break;
 
       // Queue linker inputs.
       if (Phase == phases::Link) {
         assert(Phase == PL.back() && "linking must be final compilation step.");
-        // We don't need to generate additional link commands if emitting AMD bitcode
+        // We don't need to generate additional link commands if emitting AMD
+        // bitcode or compiling only for the offload device
         if (!(C.getInputArgs().hasArg(options::OPT_hip_link) &&
-             (C.getInputArgs().hasArg(options::OPT_emit_llvm))))
+              (C.getInputArgs().hasArg(options::OPT_emit_llvm))) &&
+            !offloadDeviceOnly())
           LinkerInputs.push_back(Current);
         Current = nullptr;
         break;
       }
 
       // TODO: Consider removing this because the merged may not end up being
       // the final Phase in the pipeline. Perhaps the merged could just merge
       // and then pass an artifact of some sort to the Link Phase.

clang/test/Driver/hip-phases.hip

 
 //
 // Test single gpu architecture with complete compilation in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only 2>&1 \
 // RUN: | FileCheck -check-prefixes=DBIN %s
+//
+// Test single gpu architecture with complete compilation in device-only
+// compilation mode with an unused host linker flag.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only -Wl,--disable-new-dtags 2>&1 \
+// RUN: | FileCheck -check-prefixes=DBIN %s
+
 // DBIN-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DBIN-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
 // DBIN-DAG: [[P6:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P5]]}, image
 // DBIN-DAG: [[P7:[0-9]+]]: linker, {[[P6]]}, hip-fatbin, (device-hip, )
 // DBIN-DAG: [[P8:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:)" {[[P7]]}, hip-fatbin
 // DBIN-NOT: host
+
 //
 // Test single gpu architecture up to the assemble phase in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only -S --no-gpu-bundle-output 2>&1 \
 // RUN: | FileCheck -check-prefixes=DASM %s
 // DASM-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DASM-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DASM-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
 // DASM-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
 // DASM-DAG: [[P4:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P3]]}, assembler
 // DASM-NOT: clang-offload-bundler
 // DASM-NOT: host
 
 //
 // Test single gpu architecture with compile to relocatable in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only -fhip-emit-relocatable 2>&1 \
 // RUN: | FileCheck -check-prefixes=RELOC %s
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 %s --cuda-device-only -fhip-emit-relocatable -Wl,--disable-new-dtags \
+// RUN: 2>&1 | FileCheck -check-prefixes=RELOC %s
+//
 // RELOC-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // RELOC-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // RELOC-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
 // RELOC-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
 // RELOC-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
 // RELOC-NOT: linker
 // RELOC-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
+// RELOC-NOT: host
 
 //
 // Test two gpu architectures with compile to relocatable in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only -fhip-emit-relocatable 2>&1 \
 // RUN: | FileCheck -check-prefixes=RELOC2 %s
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only -fhip-emit-relocatable \
+// RUN: -Wl,--disable-new-dtags 2>&1 | FileCheck -check-prefixes=RELOC2 %s
+//
 // RELOC2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // RELOC2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // RELOC2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
 // RELOC2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
 // RELOC2-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
 // RELOC2-NOT: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
 // RELOC2-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P4]]}, object
 // RELOC2-DAG: [[P6:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH2:gfx900]])
 // RELOC2-DAG: [[P7:[0-9]+]]: preprocessor, {[[P6]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
 // RELOC2-DAG: [[P8:[0-9]+]]: compiler, {[[P7]]}, ir, (device-[[T]], [[ARCH2]])
 // RELOC2-DAG: [[P9:[0-9]+]]: backend, {[[P8]]}, assembler, (device-[[T]], [[ARCH2]])
 // RELOC2-DAG: [[P10:[0-9]+]]: assembler, {[[P9]]}, object, (device-[[T]], [[ARCH2]])
 // RELOC2-NOT: linker
 // RELOC2-DAG: [[P11:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P10]]}, object
+// RELOC2-NOT: host
 
 //
 // Test two gpu architectures with complete compilation in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
 // RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only \
 // RUN: 2>&1 | FileCheck -check-prefixes=DBIN2 %s
+//
+// Test two gpu architectures with complete compilation in device-only
+// compilation mode with an unused host linker flag.
+//
+// RUN: %clang -x hip --target=x86_64-unknown-linux-gnu -ccc-print-phases \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s --cuda-device-only \
+// RUN: -Wl,--disable-new-dtags 2>&1 | FileCheck -check-prefixes=DBIN2 %s
+
 // DBIN2-DAG: [[P0:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T:hip]], (device-[[T]], [[ARCH:gfx803]])
 // DBIN2-DAG: [[P1:[0-9]+]]: preprocessor, {[[P0]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P2:[0-9]+]]: compiler, {[[P1]]}, ir, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P3:[0-9]+]]: backend, {[[P2]]}, assembler, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P4:[0-9]+]]: assembler, {[[P3]]}, object, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P5:[0-9]+]]: linker, {[[P4]]}, image, (device-[[T]], [[ARCH]])
 // DBIN2-DAG: [[P6:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH]])" {[[P5]]}, image
 // DBIN2-DAG: [[P7:[0-9]+]]: input, "{{.*}}hip-phases.hip", [[T]], (device-[[T]], [[ARCH2:gfx900]])
 // DBIN2-DAG: [[P8:[0-9]+]]: preprocessor, {[[P7]]}, [[T]]-cpp-output, (device-[[T]], [[ARCH2]])
 // DBIN2-DAG: [[P9:[0-9]+]]: compiler, {[[P8]]}, ir, (device-[[T]], [[ARCH2]])
 // DBIN2-DAG: [[P10:[0-9]+]]: backend, {[[P9]]}, assembler, (device-[[T]], [[ARCH2]])
 // DBIN2-DAG: [[P11:[0-9]+]]: assembler, {[[P10]]}, object, (device-[[T]], [[ARCH2]])
 // DBIN2-DAG: [[P12:[0-9]+]]: linker, {[[P11]]}, image, (device-[[T]], [[ARCH2]])
 // DBIN2-DAG: [[P13:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P12]]}, image
 // DBIN2-DAG: [[P14:[0-9]+]]: linker, {[[P6]], [[P13]]}, hip-fatbin, (device-hip, )
 // DBIN2-DAG: [[P15:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:)" {[[P14]]}, hip-fatbin
 // DBIN2-NOT: host
+
 //
 // Test two gpu architectures up to the assemble phase in device-only
 // compilation mode.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu \
 // RUN: -ccc-print-phases --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %s \
 // RUN: --cuda-device-only -S -o %t.s 2>&1 \
 // RUN: | FileCheck -check-prefixes=DASM2,DASM2-NOBUNDLE %s

 // RUN: -fgpu-rdc 2>&1 | FileCheck -check-prefixes=L2,RL2,RL2-EM %s
 //
 // RUN: %clang --target=x86_64-unknown-linux-gnu -ccc-print-phases --hip-link \
 // RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t/obj1.o %t/obj2.o \
 // RUN: -fgpu-rdc --cuda-device-only 2>&1 | FileCheck -check-prefixes=L2,RL2,RL2-DEV %s
 
 // RUN: %clang --target=x86_64-unknown-linux-gnu -ccc-print-phases --hip-link \
 // RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t/obj1.o %t/obj2.o \
+// RUN: -fgpu-rdc --cuda-device-only -Wl,--disable-new-dtags 2>&1 \
+// RUN: | FileCheck -check-prefixes=L2,RL2,RL2-DEV %s
+
+// RUN: %clang --target=x86_64-unknown-linux-gnu -ccc-print-phases --hip-link \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t/obj1.o %t/obj2.o \
 // RUN: -fgpu-rdc --cuda-device-only --no-gpu-bundle-output 2>&1 \
 // RUN: | FileCheck -check-prefixes=L2,RL2,RL2-NB %s
 
+// RUN: %clang --target=x86_64-unknown-linux-gnu -ccc-print-phases --hip-link \
+// RUN: --cuda-gpu-arch=gfx803 --cuda-gpu-arch=gfx900 %t/obj1.o %t/obj2.o \
+// RUN: -fgpu-rdc --cuda-device-only --no-gpu-bundle-output -Wl,--disable-new-dtags 2>&1 \
+// RUN: | FileCheck -check-prefixes=L2,RL2,RL2-NB %s
+
 // L2-DAG: [[P0:[0-9]+]]: input, "{{.*}}obj1.o", object
 // RL2-DAG: [[P1:[0-9]+]]: clang-offload-unbundler, {[[P0]]}, object
 // L2-DAG: [[P2:[0-9]+]]: input, "{{.*}}obj2.o", object
 // RL2-DAG: [[P3:[0-9]+]]: clang-offload-unbundler, {[[P2]]}, object
 
 // RL2-DAG: [[P4:[0-9]+]]: linker, {[[P1]], [[P3]]}, image, (device-[[T:hip]], [[ARCH1:gfx803]])
 // RL2-DAG: [[P5:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH1]])" {[[P4]]}, image
 // RL2-DAG: [[P6:[0-9]+]]: linker, {[[P1]], [[P3]]}, image, (device-[[T]], [[ARCH2:gfx900]])
 // RL2-DAG: [[P7:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa:[[ARCH2]])" {[[P6]]}, image
 // RL2-DEV-DAG: [[P8:[0-9]+]]: linker, {[[P5]], [[P7]]}, hip-fatbin, (device-[[T]])
 // RL2-DEV-DAG: [[P9:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)" {[[P8]]}, hip-fatbin
 // RL2-EM-DAG: [[P8:[0-9]+]]: linker, {[[P5]], [[P7]]}, object, (device-[[T]])
 // RL2-EM-DAG: [[P9:[0-9]+]]: offload, "device-[[T]] (amdgcn-amd-amdhsa)" {[[P8]]}, object
 // RL2-NB-NOT: linker
 // RL2-NB-NOT: offload
 
 // NL2-DAG: [[P4:[0-9]+]]: linker, {[[P0]], [[P2]]}, image
 // RL2-EM-DAG: [[P4:[0-9]+]]: linker, {[[P1]], [[P3]], [[P9]]}, image, (host-[[T]])
 // RL2-DEV-NOT: linker
+// RL2-NB-NOT: host
 
 // Test one gpu architectures up to the preprocessor expansion output phase in device-only
 // compilation mode. no bundle.
 //
 // RUN: %clang -x hip --target=x86_64-unknown-linux-gnu \
 // RUN: -ccc-print-phases --cuda-gpu-arch=gfx803 %s \
 // RUN: --cuda-device-only -E 2>&1 \
 // RUN: | FileCheck -check-prefixes=PPE,PPEN %s