[PATCH] D116543: [OpenMP] Embed device files into the host IR

[Joseph Huber via Phabricator via cfe-commits]

jhuber6 updated this revision to Diff 404030.
jhuber6 added a comment.

Adding test for multiple input files to embed.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D116543/new/

https://reviews.llvm.org/D116543

Files:
  clang/lib/Driver/ToolChains/Clang.cpp
  clang/test/Driver/openmp-offload-gpu.c
  clang/test/Frontend/embed-object.ll


Index: clang/test/Frontend/embed-object.ll
===================================================================
--- clang/test/Frontend/embed-object.ll
+++ clang/test/Frontend/embed-object.ll
@@ -1,9 +1,11 @@
 ; RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm \
-; RUN:    -fembed-offload-object=%S/Inputs/empty.h,section -x ir %s -o - \
+; RUN:    -fembed-offload-object=%S/Inputs/empty.h,section1 \
+; RUN:    -fembed-offload-object=%S/Inputs/empty.h,section2 -x ir %s -o - \
 ; RUN:    | FileCheck %s -check-prefix=CHECK
 
-; CHECK: @llvm.embedded.object = private constant [0 x i8] zeroinitializer, section ".llvm.offloading.section"
-; CHECK: @llvm.compiler.used = appending global [2 x i8*] [i8* @x, i8* getelementptr inbounds ([0 x i8], [0 x i8]* @llvm.embedded.object, i32 0, i32 0)], section "llvm.metadata"
+; CHECK: @[[OBJECT1:.+]] = private constant [0 x i8] zeroinitializer, section ".llvm.offloading.section1"
+; CHECK: @[[OBJECT2:.+]] = private constant [0 x i8] zeroinitializer, section ".llvm.offloading.section2"
+; CHECK: @llvm.compiler.used = appending global [3 x i8*] [i8* @x, i8* getelementptr inbounds ([0 x i8], [0 x i8]* @[[OBJECT1]], i32 0, i32 0), i8* getelementptr inbounds ([0 x i8], [0 x i8]* @[[OBJECT2]], i32 0, i32 0)], section "llvm.metadata"
 
 @x = private constant i8 1
 @llvm.compiler.used = appending global [1 x i8*] [i8* @x], section "llvm.metadata"
Index: clang/test/Driver/openmp-offload-gpu.c
===================================================================
--- clang/test/Driver/openmp-offload-gpu.c
+++ clang/test/Driver/openmp-offload-gpu.c
@@ -353,3 +353,10 @@
 // NEW_DRIVER: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_ASM]]"], output: "[[DEVICE_OBJ:.+]]" 
 // NEW_DRIVER: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[HOST_BC]]", "[[DEVICE_OBJ]]"], output: "[[HOST_OBJ:.+]]" 
 // NEW_DRIVER: "x86_64-unknown-linux-gnu" - "[[LINKER:.+]]", inputs: ["[[HOST_OBJ]]"], output: "openmp-offload-gpu"
+
+// RUN:   %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvida-cuda -march=sm_70 \
+// RUN:          --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc \
+// RUN:          -fopenmp-new-driver -no-canonical-prefixes %s -o openmp-offload-gpu 2>&1 \
+// RUN:   | FileCheck -check-prefix=NEW_DRIVER_EMBEDDING %s
+
+// NEW_DRIVER_EMBEDDING: -fembed-offload-object=[[CUBIN:.*\.cubin]],nvptx64-nvidia-cuda.sm_70
Index: clang/lib/Driver/ToolChains/Clang.cpp
===================================================================
--- clang/lib/Driver/ToolChains/Clang.cpp
+++ clang/lib/Driver/ToolChains/Clang.cpp
@@ -4366,9 +4366,9 @@
       IsHeaderModulePrecompile ? HeaderModuleInput : Inputs[0];
 
   InputInfoList ModuleHeaderInputs;
+  InputInfoList OpenMPHostInputs;
   const InputInfo *CudaDeviceInput = nullptr;
   const InputInfo *OpenMPDeviceInput = nullptr;
-  const InputInfo *OpenMPHostInput = nullptr;
   for (const InputInfo &I : Inputs) {
     if (&I == &Input) {
       // This is the primary input.
@@ -4385,8 +4385,8 @@
       CudaDeviceInput = &I;
     } else if (IsOpenMPDevice && !OpenMPDeviceInput) {
       OpenMPDeviceInput = &I;
-    } else if (IsOpenMPHost && !OpenMPHostInput) {
-      OpenMPHostInput = &I;
+    } else if (IsOpenMPHost) {
+      OpenMPHostInputs.push_back(I);
     } else {
       llvm_unreachable("unexpectedly given multiple inputs");
     }
@@ -6894,6 +6894,24 @@
     }
   }
 
+  // Host-side OpenMP offloading recieves the device object files and embeds it
+  // in a named section including the associated target triple and architecture.
+  if (IsOpenMPHost && !OpenMPHostInputs.empty()) {
+    auto InputFile = OpenMPHostInputs.begin();
+    auto OpenMPTCs = C.getOffloadToolChains<Action::OFK_OpenMP>();
+    for (auto TI = OpenMPTCs.first, TE = OpenMPTCs.second; TI != TE;
+         ++TI, ++InputFile) {
+      const ToolChain *TC = TI->second;
+      const ArgList &TCArgs = C.getArgsForToolChain(TC, "", Action::OFK_OpenMP);
+      StringRef File =
+          C.getArgs().MakeArgString(TC->getInputFilename(*InputFile));
+
+      CmdArgs.push_back(Args.MakeArgString(
+          "-fembed-offload-object=" + File + "," + TC->getTripleString() + "." +
+          TCArgs.getLastArgValue(options::OPT_march_EQ)));
+    }
+  }
+
   if (Triple.isAMDGPU()) {
     handleAMDGPUCodeObjectVersionOptions(D, Args, CmdArgs);
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D116543.404030.patch
Type: text/x-patch
Size: 4421 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20220128/790a914b/attachment.bin>