diff --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp --- a/clang/lib/Driver/Driver.cpp +++ b/clang/lib/Driver/Driver.cpp @@ -3086,8 +3086,16 @@ } // By default, we produce an action for each device arch. - for (Action *&A : OpenMPDeviceActions) + for (unsigned I = 0; I < ToolChains.size(); ++I) { + Action *&A = OpenMPDeviceActions[I]; + // AMDGPU does not support linking of object files, so we skip + // assemble and backend actions to produce LLVM IR. + if (ToolChains[I]->getTriple().isAMDGCN() && + (CurPhase == phases::Assemble || CurPhase == phases::Backend)) + continue; + A = C.getDriver().ConstructPhaseAction(C, Args, CurPhase, A); + } return ABRT_Success; } diff --git a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp --- a/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp +++ b/clang/lib/Driver/ToolChains/AMDGPUOpenMP.cpp @@ -161,6 +161,11 @@ // Each command outputs different files. const char *LLVMLinkCommand = constructLLVMLinkCommand(C, JA, Inputs, Args, GPUArch, Prefix); + + // Produce readable assembly if save-temps is enabled. + if (C.getDriver().isSaveTempsEnabled()) + constructLlcCommand(C, JA, Inputs, Args, GPUArch, Prefix, LLVMLinkCommand, + /*OutputIsAsm=*/true); const char *LlcCommand = constructLlcCommand(C, JA, Inputs, Args, GPUArch, Prefix, LLVMLinkCommand); constructLldCommand(C, JA, Inputs, Output, Args, LlcCommand); @@ -189,7 +194,6 @@ CC1Args.push_back("-target-cpu"); CC1Args.push_back(DriverArgs.MakeArgStringRef(GpuArch)); CC1Args.push_back("-fcuda-is-device"); - CC1Args.push_back("-emit-llvm-bc"); if (DriverArgs.hasArg(options::OPT_nogpulib)) return; diff --git a/clang/test/Driver/amdgpu-openmp-toolchain.c b/clang/test/Driver/amdgpu-openmp-toolchain.c --- a/clang/test/Driver/amdgpu-openmp-toolchain.c +++ b/clang/test/Driver/amdgpu-openmp-toolchain.c @@ -1,3 +1,4 @@ +// REQUIRES: x86-registered-target // REQUIRES: amdgpu-registered-target // RUN: env LIBRARY_PATH=%S/Inputs/hip_dev_lib %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 %s 2>&1 \ // RUN: | FileCheck %s @@ -5,7 +6,7 @@ // verify the tools invocations // CHECK: clang{{.*}}"-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-x" "c"{{.*}} // CHECK: clang{{.*}}"-cc1" "-triple" "x86_64-unknown-linux-gnu"{{.*}}"-x" "ir"{{.*}} -// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx906" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx906.bc"{{.*}} +// CHECK: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx906" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx906.bc"{{.*}} // CHECK: llvm-link{{.*}}"-o" "{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked-{{.*}}.bc" // CHECK: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked-{{.*}}.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=obj" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-{{.*}}.o" // CHECK: lld{{.*}}"-flavor" "gnu" "--no-undefined" "-shared" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}.out" "{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-{{.*}}.o" @@ -25,18 +26,35 @@ // CHECK-PHASES: 6: preprocessor, {5}, cpp-output, (device-openmp) // CHECK-PHASES: 7: compiler, {6}, ir, (device-openmp) // CHECK-PHASES: 8: offload, "host-openmp (x86_64-unknown-linux-gnu)" {2}, "device-openmp (amdgcn-amd-amdhsa)" {7}, ir -// CHECK-PHASES: 9: backend, {8}, assembler, (device-openmp) -// CHECK-PHASES: 10: assembler, {9}, object, (device-openmp) -// CHECK-PHASES: 11: linker, {10}, image, (device-openmp) -// CHECK-PHASES: 12: offload, "device-openmp (amdgcn-amd-amdhsa)" {11}, image -// CHECK-PHASES: 13: clang-offload-wrapper, {12}, ir, (host-openmp) -// CHECK-PHASES: 14: backend, {13}, assembler, (host-openmp) -// CHECK-PHASES: 15: assembler, {14}, object, (host-openmp) -// CHECK-PHASES: 16: linker, {4, 15}, image, (host-openmp) +// CHECK-PHASES: 9: linker, {8}, image, (device-openmp) +// CHECK-PHASES: 10: offload, "device-openmp (amdgcn-amd-amdhsa)" {9}, image +// CHECK-PHASES: 11: clang-offload-wrapper, {10}, ir, (host-openmp) +// CHECK-PHASES: 12: backend, {11}, assembler, (host-openmp) +// CHECK-PHASES: 13: assembler, {12}, object, (host-openmp) +// CHECK-PHASES: 14: linker, {4, 13}, image, (host-openmp) // handling of --libomptarget-amdgcn-bc-path // RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 --libomptarget-amdgcn-bc-path=%S/Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc %s 2>&1 | FileCheck %s --check-prefix=CHECK-LIBOMPTARGET -// CHECK-LIBOMPTARGET: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc"{{.*}} +// CHECK-LIBOMPTARGET: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}Inputs/hip_dev_lib/libomptarget-amdgcn-gfx803.bc"{{.*}} // RUN: %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-NOGPULIB -// CHECK-NOGPULIB-NOT: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-emit-llvm-bc" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx803.bc"{{.*}} +// CHECK-NOGPULIB-NOT: clang{{.*}}"-cc1"{{.*}}"-triple" "amdgcn-amd-amdhsa"{{.*}}"-target-cpu" "gfx803" "-fcuda-is-device" "-mlink-builtin-bitcode"{{.*}}libomptarget-amdgcn-gfx803.bc"{{.*}} + +// RUN: %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -save-temps -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx803 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-PRINT-BINDINGS +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang",{{.*}} output: "[[HOST_BC:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]"], output: "[[HOST_S:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang::as", inputs: ["[[HOST_S]]"], output: "[[HOST_O:.*]]" +// CHECK-PRINT-BINDINGS: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[INPUT]]"], output: "[[DEVICE_I:.*]]" +// CHECK-PRINT-BINDINGS: "amdgcn-amd-amdhsa" - "clang", inputs: ["[[DEVICE_I]]", "[[HOST_BC]]"], output: "[[DEVICE_BC:.*]]" +// CHECK-PRINT-BINDINGS: "amdgcn-amd-amdhsa" - "AMDGCN::OpenMPLinker", inputs: ["[[DEVICE_BC]]"], output: "[[DEVICE_OUT:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "offload wrapper", inputs: ["[[DEVICE_OUT]]"], output: "[[OFFLOAD_WRAPPER:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[OFFLOAD_WRAPPER]]"], output: "[[OFFLOAD_S:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "clang::as", inputs: ["[[OFFLOAD_S]]"], output: "[[OFFLOAD_O:.*]]" +// CHECK-PRINT-BINDINGS: "x86_64-unknown-linux-gnu" - "GNU::Linker", inputs: ["[[HOST_O]]", "[[OFFLOAD_O]]"], output: + +// verify the llc is invoked for textual assembly output +// RUN: env LIBRARY_PATH=%S/Inputs/hip_dev_lib %clang -### --target=x86_64-unknown-linux-gnu -fopenmp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx906 -save-temps %s 2>&1 \ +// RUN: | FileCheck %s --check-prefix=CHECK-SAVE-ASM +// CHECK-SAVE-ASM: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=asm" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906.s" +// CHECK-SAVE-ASM: llc{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906-linked.bc" "-mtriple=amdgcn-amd-amdhsa" "-mcpu=gfx906" "-filetype=obj" "-o"{{.*}}amdgpu-openmp-toolchain-{{.*}}-gfx906.o"