[PATCH] D128206: [Clang] Allow multiple comma separated arguments to `--offload-arch=`

[Joseph Huber via Phabricator via cfe-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG21e29b6ce734: [Clang] Allow multiple comma separated 
arguments to `--offload-arch=` (authored by jhuber6).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128206/new/

https://reviews.llvm.org/D128206

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


Index: clang/test/Driver/openmp-offload-gpu-new.c
===
--- clang/test/Driver/openmp-offload-gpu-new.c
+++ 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:.*]]"
Index: clang/test/Driver/cuda-bindings.cu
===
--- clang/test/Driver/cuda-bindings.cu
+++ 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
Index: clang/lib/Driver/Driver.cpp
===
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -2977,7 +2977,7 @@
  << "--offload";
   }
 
-  // Collect all cuda_gpu_arch parameters, removing duplicates.
+  // Collect all offload arch parameters, removing duplicates.
   std::set GpuArchs;
   bool Error = false;
   for (Arg *A : Args) {
@@ -2986,21 +2986,22 @@
   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 & = getConflictOffloadArchCombination(GpuArchs);
@@ -4356,14 +4357,15 @@
   llvm::DenseSet Archs;
   for (auto  : 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 

[PATCH] D128206: [Clang] Allow multiple comma separated arguments to `--offload-arch=`

[Ye Luo via Phabricator via cfe-commits]

ye-luo accepted this revision.
ye-luo added a comment.
This revision is now accepted and ready to land.

LGTM. This allows me to write concise compile lines.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128206/new/

https://reviews.llvm.org/D128206

___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D128206: [Clang] Allow multiple comma separated arguments to `--offload-arch=`

[Joseph Huber via Phabricator via cfe-commits]

jhuber6 created this revision.
jhuber6 added reviewers: tra, yaxunl, jdoerfert, JonChesterfield, ye-luo.
Herald added a project: All.
jhuber6 requested review of this revision.
Herald added subscribers: cfe-commits, sstefan1, MaskRay.
Herald added a project: clang.

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


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D128206

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


Index: clang/test/Driver/openmp-offload-gpu-new.c
===
--- clang/test/Driver/openmp-offload-gpu-new.c
+++ 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:.*]]"
Index: clang/test/Driver/cuda-bindings.cu
===
--- clang/test/Driver/cuda-bindings.cu
+++ 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
Index: clang/lib/Driver/Driver.cpp
===
--- clang/lib/Driver/Driver.cpp
+++ clang/lib/Driver/Driver.cpp
@@ -2973,7 +2973,7 @@
  << "--offload";
   }
 
-  // Collect all cuda_gpu_arch parameters, removing duplicates.
+  // Collect all offload arch parameters, removing duplicates.
   std::set GpuArchs;
   bool Error = false;
   for (Arg *A : Args) {
@@ -2982,21 +2982,22 @@
   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 & = getConflictOffloadArchCombination(GpuArchs);
@@ -4356,14 +4357,15 @@
   llvm::DenseSet Archs;
   for (auto  : Args) {
 if (Arg->getOption().matches(options::OPT_offload_arch_EQ)) {
-  Archs.insert(