[clang] 21e29b6 - [Clang] Allow multiple comma separated arguments to `--offload-arch=`

[Joseph Huber via cfe-commits]

Author: Joseph Huber
Date: 2022-06-22T09:25:04-04:00
New Revision: 21e29b6ce734cca1557aa801740078d98c3ff447

URL: https://github.com/llvm/llvm-project/commit/21e29b6ce734cca1557aa801740078d98c3ff447
DIFF: https://github.com/llvm/llvm-project/commit/21e29b6ce734cca1557aa801740078d98c3ff447.diff

LOG: [Clang] Allow multiple comma separated arguments to `--offload-arch=`

This patch updates the `--[no-]offload-arch` command line arguments to
allow the user to pass in many architectures in a single argument rather
than specifying it multiple times. This means that the following command
line,
```
clang foo.cu --offload-arch=sm_70 --offload-arch=sm_80
```
can become:
```
clang foo.cu --offload-arch=sm_70,sm_80
```

Reviewed By: ye-luo

Differential Revision: https://reviews.llvm.org/D128206

Added: 
    

Modified: 
    clang/lib/Driver/Driver.cpp
    clang/test/Driver/cuda-bindings.cu
    clang/test/Driver/openmp-offload-gpu-new.c

Removed: 
    


################################################################################
diff  --git a/clang/lib/Driver/Driver.cpp b/clang/lib/Driver/Driver.cpp
index 385c194cdeb7..67bcb418a52e 100644
--- a/clang/lib/Driver/Driver.cpp
+++ b/clang/lib/Driver/Driver.cpp
@@ -2977,7 +2977,7 @@ class OffloadingActionBuilder final {
                                                              << "--offload";
       }
 
-      // Collect all cuda_gpu_arch parameters, removing duplicates.
+      // Collect all offload arch parameters, removing duplicates.
       std::set<StringRef> GpuArchs;
       bool Error = false;
       for (Arg *A : Args) {
@@ -2986,21 +2986,22 @@ class OffloadingActionBuilder final {
           continue;
         A->claim();
 
-        StringRef ArchStr = A->getValue();
-        if (A->getOption().matches(options::OPT_no_offload_arch_EQ) &&
-            ArchStr == "all") {
-          GpuArchs.clear();
-          continue;
+        for (StringRef ArchStr : llvm::split(A->getValue(), ",")) {
+          if (A->getOption().matches(options::OPT_no_offload_arch_EQ) &&
+              ArchStr == "all") {
+            GpuArchs.clear();
+          } else {
+            ArchStr = getCanonicalOffloadArch(ArchStr);
+            if (ArchStr.empty()) {
+              Error = true;
+            } else if (A->getOption().matches(options::OPT_offload_arch_EQ))
+              GpuArchs.insert(ArchStr);
+            else if (A->getOption().matches(options::OPT_no_offload_arch_EQ))
+              GpuArchs.erase(ArchStr);
+            else
+              llvm_unreachable("Unexpected option.");
+          }
         }
-        ArchStr = getCanonicalOffloadArch(ArchStr);
-        if (ArchStr.empty()) {
-          Error = true;
-        } else if (A->getOption().matches(options::OPT_offload_arch_EQ))
-          GpuArchs.insert(ArchStr);
-        else if (A->getOption().matches(options::OPT_no_offload_arch_EQ))
-          GpuArchs.erase(ArchStr);
-        else
-          llvm_unreachable("Unexpected option.");
       }
 
       auto &&ConflictingArchs = getConflictOffloadArchCombination(GpuArchs);
@@ -4356,14 +4357,15 @@ Driver::getOffloadArchs(Compilation &C, const llvm::opt::DerivedArgList &Args,
   llvm::DenseSet<StringRef> Archs;
   for (auto &Arg : Args) {
     if (Arg->getOption().matches(options::OPT_offload_arch_EQ)) {
-      Archs.insert(
-          getCanonicalArchString(C, Args, Arg->getValue(), TC->getTriple()));
+      for (StringRef Arch : llvm::split(Arg->getValue(), ","))
+        Archs.insert(getCanonicalArchString(C, Args, Arch, TC->getTriple()));
     } else if (Arg->getOption().matches(options::OPT_no_offload_arch_EQ)) {
-      if (Arg->getValue() == StringRef("all"))
-        Archs.clear();
-      else
-        Archs.erase(
-            getCanonicalArchString(C, Args, Arg->getValue(), TC->getTriple()));
+      for (StringRef Arch : llvm::split(Arg->getValue(), ",")) {
+        if (Arch == StringRef("all"))
+          Archs.clear();
+        else
+          Archs.erase(getCanonicalArchString(C, Args, Arch, TC->getTriple()));
+      }
     }
   }
 

diff  --git a/clang/test/Driver/cuda-bindings.cu b/clang/test/Driver/cuda-bindings.cu
index 178db31a2905..6cc21251bfdd 100644
--- a/clang/test/Driver/cuda-bindings.cu
+++ b/clang/test/Driver/cuda-bindings.cu
@@ -40,6 +40,7 @@
 // Test two gpu architectures with complete compilation.
 //
 // RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --cuda-gpu-arch=sm_30 --cuda-gpu-arch=sm_35 %s 2>&1 \
+// RUN: %clang -target powerpc64le-ibm-linux-gnu -ccc-print-bindings --offload-arch=sm_30,sm_35 %s 2>&1 \
 // RUN: | FileCheck -check-prefix=BIN2 %s
 // BIN2: # "nvptx64-nvidia-cuda" - "clang",{{.*}} output:
 // BIN2-NOT: cuda-bindings-device-cuda-nvptx64

diff  --git a/clang/test/Driver/openmp-offload-gpu-new.c b/clang/test/Driver/openmp-offload-gpu-new.c
index 8eb197af1fd4..4c2748515cf0 100644
--- a/clang/test/Driver/openmp-offload-gpu-new.c
+++ b/clang/test/Driver/openmp-offload-gpu-new.c
@@ -51,6 +51,8 @@
 // CHECK-TEMP-BINDINGS: "x86_64-unknown-linux-gnu" - "Offload::Packager", inputs: ["[[DEVICE_OBJ:.+]]"], output: "[[BINARY:.+.out]]"
 
 // RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52 --offload-arch=sm_70 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52,sm_70 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
+// RUN:   %clang -### --target=x86_64-unknown-linux-gnu -ccc-print-bindings -fopenmp -fopenmp-targets=nvptx64-nvidia-cuda --offload-arch=sm_52,sm_70,sm_35,sm_80 --no-offload-arch=sm_35,sm_80 -nogpulib %s 2>&1 | FileCheck %s --check-prefix=CHECK-ARCH-BINDINGS
 // CHECK-ARCH-BINDINGS: "x86_64-unknown-linux-gnu" - "clang", inputs: ["[[INPUT:.*]]"], output: "[[HOST_BC:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[INPUT]]", "[[HOST_BC]]"], output: "[[DEVICE_BC_SM_52:.*]]"
 // CHECK-ARCH-BINDINGS: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_BC_SM_52]]"], output: "[[DEVICE_OBJ_SM_52:.*]]"