[CUDA] Do not embed a fatbinary when using the new driver

Previously, when using the new driver we created a fatbinary with the
PTX and Cubin output. This was mainly done in an attempt to create some
backwards compatibility with the existing CUDA support that embeds the
fatbinary in each TU. This will most likely be more work than necessary
to actually implement. The linker wrapper cannot do anything with these
embedded PTX files because we do not know how to link them, and if we
did want to include multiple files it should go through the
`clang-offload-packager` instead. Also this didn't repsect the setting
that disables embedding PTX (although it wasn't used anyway).

Reviewed By: tra

Differential Revision: https://reviews.llvm.org/D128441

Author: jhuber6

clang/lib/Driver/Driver.cpp

@@ -4459,17 +4459,6 @@ Action *Driver::BuildOffloadingActions(Compilation &C,
           OffloadAction::DeviceDependences DDep;
           DDep.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
           A = C.MakeAction<OffloadAction>(HDep, DDep);
-        } else if (isa<AssembleJobAction>(A) && Kind == Action::OFK_Cuda) {
-          // The Cuda toolchain uses fatbinary as the linker phase to bundle the
-          // PTX and Cubin output.
-          ActionList FatbinActions;
-          for (Action *A : {A, A->getInputs()[0]}) {
-            OffloadAction::DeviceDependences DDep;
-            DDep.add(*A, *TCAndArch->first, TCAndArch->second.data(), Kind);
-            FatbinActions.emplace_back(
-                C.MakeAction<OffloadAction>(DDep, A->getType()));
-          }
-          A = C.MakeAction<LinkJobAction>(FatbinActions, types::TY_CUDA_FATBIN);
         }
         ++TCAndArch;
       }

clang/lib/Driver/ToolChains/Cuda.cpp

@@ -536,8 +536,9 @@ void NVPTX::Linker::ConstructJob(Compilation &C, const JobAction &JA,
     const char *Arch = (II.getType() == types::TY_PP_Asm)
                            ? CudaArchToVirtualArchString(gpu_arch)
                            : gpu_arch_str;
-    CmdArgs.push_back(Args.MakeArgString(llvm::Twine("--image=profile=") +
-                                         Arch + ",file=" + II.getFilename()));
+    CmdArgs.push_back(
+        Args.MakeArgString(llvm::Twine("--image=profile=") + Arch +
+                           ",file=" + getToolChain().getInputFilename(II)));
   }
 
   for (const auto& A : Args.getAllArgValues(options::OPT_Xcuda_fatbinary))
@@ -695,9 +696,8 @@ CudaToolChain::CudaToolChain(const Driver &D, const llvm::Triple &Triple,
 
 std::string CudaToolChain::getInputFilename(const InputInfo &Input) const {
   // Only object files are changed, for example assembly files keep their .s
-  // extensions. CUDA also continues to use .o as they don't use nvlink but
-  // fatbinary.
-  if (!(OK == Action::OFK_OpenMP && Input.getType() == types::TY_Object))
+  // extensions. 
+  if (Input.getType() != types::TY_Object)
     return ToolChain::getInputFilename(Input);
 
   // Replace extension for object files with cubin because nvlink relies on

clang/test/Driver/cuda-openmp-driver.cu

@@ -5,13 +5,11 @@
 // RUN:        --offload-new-driver --offload-arch=sm_35 --offload-arch=sm_70 %s 2>&1 \
 // RUN: | FileCheck -check-prefix BINDINGS %s
 
-// BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX_SM_35:.+]]"
+//      BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX_SM_35:.+]]"
 // BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_SM_35]]"], output: "[[CUBIN_SM_35:.+]]"
-// BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN_SM_35]]", "[[PTX_SM_35]]"], output: "[[FATBIN_SM_35:.+]]"
 // BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]"], output: "[[PTX_SM_70:.+]]"
 // BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX_SM_70:.+]]"], output: "[[CUBIN_SM_70:.+]]"
-// BINDINGS-NEXT: "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN_SM_70]]", "[[PTX_SM_70:.+]]"], output: "[[FATBIN_SM_70:.+]]"
-// BINDINGS-NEXT: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[FATBIN_SM_35]]", "[[FATBIN_SM_70]]"], output: "[[BINARY:.+]]"
+// BINDINGS-NEXT: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[CUBIN_SM_35]]", "[[CUBIN_SM_70]]"], output: "[[BINARY:.+]]"
 // BINDINGS-NEXT: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT]]", "[[BINARY]]"], output: "[[HOST_OBJ:.+]]"
 // BINDINGS-NEXT: "x86_64-unknown-linux-gnu" - "Offload::Linker", inputs: ["[[HOST_OBJ]]"], output: "a.out"
 
@@ -31,7 +29,6 @@
 
 // BINDINGS-DEVICE: # "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT:.+]]"], output: "[[PTX:.+]]"
 // BINDINGS-DEVICE: # "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[PTX]]"], output: "[[CUBIN:.+]]"
-// BINDINGS-DEVICE: # "nvptx64-nvidia-cuda" - "NVPTX::Linker", inputs: ["[[CUBIN]]", "[[PTX]]"], output: "{{.*}}.fatbin"
 
 // RUN: %clang -### -target x86_64-linux-gnu -nocudalib --cuda-feature=+ptx61 --offload-arch=sm_70 %s 2>&1 | FileCheck -check-prefix MANUAL-FEATURE %s
 // MANUAL-FEATURE: -cc1{{.*}}-target-feature{{.*}}+ptx61

clang/test/Driver/cuda-phases.cu

@@ -232,20 +232,14 @@
 // NEW_DRIVER: 6: backend, {5}, assembler, (device-cuda, sm_52)
 // NEW_DRIVER: 7: assembler, {6}, object, (device-cuda, sm_52)
 // NEW_DRIVER: 8: offload, "device-cuda (nvptx64-nvidia-cuda:sm_52)" {7}, object
-// NEW_DRIVER: 9: offload, "device-cuda (nvptx64-nvidia-cuda:sm_52)" {6}, assembler
-// NEW_DRIVER: 10: linker, {8, 9}, cuda-fatbin, (device-cuda, sm_52)
-// NEW_DRIVER: 11: offload, "device-cuda (nvptx64-nvidia-cuda:sm_52)" {10}, cuda-fatbin
-// NEW_DRIVER: 12: input, "[[INPUT]]", cuda, (device-cuda, sm_70)
-// NEW_DRIVER: 13: preprocessor, {12}, cuda-cpp-output, (device-cuda, sm_70)
-// NEW_DRIVER: 14: compiler, {13}, ir, (device-cuda, sm_70)
-// NEW_DRIVER: 15: backend, {14}, assembler, (device-cuda, sm_70)
-// NEW_DRIVER: 16: assembler, {15}, object, (device-cuda, sm_70)
-// NEW_DRIVER: 17: offload, "device-cuda (nvptx64-nvidia-cuda:sm_70)" {16}, object
-// NEW_DRIVER: 18: offload, "device-cuda (nvptx64-nvidia-cuda:sm_70)" {15}, assembler
-// NEW_DRIVER: 19: linker, {17, 18}, cuda-fatbin, (device-cuda, sm_70)
-// NEW_DRIVER: 20: offload, "device-cuda (nvptx64-nvidia-cuda:sm_70)" {19}, cuda-fatbin
-// NEW_DRIVER: 21: clang-offload-packager, {11, 20}, image
-// NEW_DRIVER: 22: offload, " (powerpc64le-ibm-linux-gnu)" {2}, " (powerpc64le-ibm-linux-gnu)" {21}, ir
-// NEW_DRIVER: 23: backend, {22}, assembler, (host-cuda)
-// NEW_DRIVER: 24: assembler, {23}, object, (host-cuda)
-// NEW_DRIVER: 25: clang-linker-wrapper, {24}, image, (host-cuda)
+// NEW_DRIVER: 9: input, "[[INPUT]]", cuda, (device-cuda, sm_70)
+// NEW_DRIVER: 10: preprocessor, {9}, cuda-cpp-output, (device-cuda, sm_70)
+// NEW_DRIVER: 11: compiler, {10}, ir, (device-cuda, sm_70)
+// NEW_DRIVER: 12: backend, {11}, assembler, (device-cuda, sm_70)
+// NEW_DRIVER: 13: assembler, {12}, object, (device-cuda, sm_70)
+// NEW_DRIVER: 14: offload, "device-cuda (nvptx64-nvidia-cuda:sm_70)" {13}, object
+// NEW_DRIVER: 15: clang-offload-packager, {8, 14}, image
+// NEW_DRIVER: 16: offload, " (powerpc64le-ibm-linux-gnu)" {2}, " (powerpc64le-ibm-linux-gnu)" {15}, ir
+// NEW_DRIVER: 17: backend, {16}, assembler, (host-cuda)
+// NEW_DRIVER: 18: assembler, {17}, object, (host-cuda)
+// NEW_DRIVER: 19: clang-linker-wrapper, {18}, image, (host-cuda)