[Offload][SYCL] Refactor OffloadKind implementation (#135809)

Following are the changes:

1. Make OffloadKind enum values to be powers of two so we can use them
like a bitfield
2. Include OFK_SYCL enum value
3. Modify ActiveOffloadKinds support in clang-linker-wrapper to use
bitfields instead of a vector.

Thanks

---------

Signed-off-by: Arvind Sudarsanam <arvind.sudarsanam@intel.com>

4 files changed, 24 insertions, 21 deletions

diff --git a/clang/test/CodeGenCUDA/offloading-entries.cu b/clang/test/CodeGenCUDA/offloading-entries.cu
index c053cf5..ac0680f 100644
--- a/clang/test/CodeGenCUDA/offloading-entries.cu
+++ b/clang/test/CodeGenCUDA/offloading-entries.cu
@@ -34,17 +34,17 @@
 // HIP: @managed.managed = global i32 0, align 4
 // HIP: @managed = externally_initialized global ptr null
 // HIP: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
+// HIP: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
 // HIP: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
+// HIP: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries"
 // HIP: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
+// HIP: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries"
 // HIP: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries"
+// HIP: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries"
 // HIP: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
+// HIP: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
 // HIP: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
-// HIP: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
+// HIP: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries"
 //.
 // CUDA-COFF: @managed = dso_local global i32 undef, align 4
 // CUDA-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
@@ -63,17 +63,17 @@
 // HIP-COFF: @managed.managed = dso_local global i32 0, align 4
 // HIP-COFF: @managed = dso_local externally_initialized global ptr null
 // HIP-COFF: @.offloading.entry_name = internal unnamed_addr constant [8 x i8] c"_Z3foov\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry._Z3foov = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z3foov, ptr @.offloading.entry_name, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
 // HIP-COFF: @.offloading.entry_name.1 = internal unnamed_addr constant [11 x i8] c"_Z6kernelv\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry._Z6kernelv = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @_Z6kernelv, ptr @.offloading.entry_name.1, i64 0, i64 0, ptr null }, section "llvm_offload_entries$OE"
 // HIP-COFF: @.offloading.entry_name.2 = internal unnamed_addr constant [4 x i8] c"var\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry.var = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 0, ptr @var, ptr @.offloading.entry_name.2, i64 4, i64 0, ptr null }, section "llvm_offload_entries$OE"
 // HIP-COFF: @.offloading.entry_name.3 = internal unnamed_addr constant [8 x i8] c"managed\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry.managed = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 1, ptr @managed.managed, ptr @.offloading.entry_name.3, i64 4, i64 4, ptr @managed }, section "llvm_offload_entries$OE"
 // HIP-COFF: @.offloading.entry_name.4 = internal unnamed_addr constant [5 x i8] c"surf\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry.surf = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 2, ptr @surf, ptr @.offloading.entry_name.4, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
 // HIP-COFF: @.offloading.entry_name.5 = internal unnamed_addr constant [4 x i8] c"tex\00", section ".llvm.rodata.offloading"
-// HIP-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 3, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
+// HIP-COFF: @.offloading.entry.tex = weak constant %struct.__tgt_offload_entry { i64 0, i16 1, i16 4, i32 3, ptr @tex, ptr @.offloading.entry_name.5, i64 4, i64 1, ptr null }, section "llvm_offload_entries$OE"
 //.
 // CUDA-LABEL: @_Z18__device_stub__foov(
 // CUDA-NEXT:  entry:
diff --git a/clang/test/Driver/linker-wrapper-image.c b/clang/test/Driver/linker-wrapper-image.c
index 7753851..c0de56d 100644
--- a/clang/test/Driver/linker-wrapper-image.c
+++ b/clang/test/Driver/linker-wrapper-image.c
@@ -220,7 +220,7 @@
 // HIP-NEXT:   %constant = lshr i32 %11, 4
 // HIP-NEXT:   %12 = and i32 %flags, 32
 // HIP-NEXT:   %normalized = lshr i32 %12, 5
-// HIP-NEXT:   %13 = icmp eq i16 %kind, 3
+// HIP-NEXT:   %13 = icmp eq i16 %kind, 4
 // HIP-NEXT:   br i1 %13, label %if.kind, label %if.end
 //
 //      HIP: if.kind:
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 52d922a..082355e 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -923,10 +923,9 @@ Expected<SmallVector<StringRef>> linkAndWrapDeviceFiles(
         });
     auto LinkerArgs = getLinkerArgs(Input, BaseArgs);
 
-    DenseSet<OffloadKind> ActiveOffloadKinds;
+    uint16_t ActiveOffloadKindMask = 0u;
     for (const auto &File : Input)
-      if (File.getBinary()->getOffloadKind() != OFK_None)
-        ActiveOffloadKinds.insert(File.getBinary()->getOffloadKind());
+      ActiveOffloadKindMask |= File.getBinary()->getOffloadKind();
 
     // Write any remaining device inputs to an output file.
     SmallVector<StringRef> InputFiles;
@@ -943,7 +942,10 @@ Expected<SmallVector<StringRef>> linkAndWrapDeviceFiles(
       return OutputOrErr.takeError();
 
     // Store the offloading image for each linked output file.
-    for (OffloadKind Kind : ActiveOffloadKinds) {
+    for (OffloadKind Kind = OFK_OpenMP; Kind != OFK_LAST;
+         Kind = static_cast<OffloadKind>((uint16_t)(Kind) << 1)) {
+      if ((ActiveOffloadKindMask & Kind) == 0)
+        continue;
       llvm::ErrorOr<std::unique_ptr<llvm::MemoryBuffer>> FileOrErr =
           llvm::MemoryBuffer::getFileOrSTDIN(*OutputOrErr);
       if (std::error_code EC = FileOrErr.getError()) {
diff --git a/llvm/include/llvm/Object/OffloadBinary.h b/llvm/include/llvm/Object/OffloadBinary.h
index c02aec8..a3b78b8ec 100644
--- a/llvm/include/llvm/Object/OffloadBinary.h
+++ b/llvm/include/llvm/Object/OffloadBinary.h
@@ -32,10 +32,11 @@ namespace object {
 /// The producer of the associated offloading image.
 enum OffloadKind : uint16_t {
   OFK_None = 0,
-  OFK_OpenMP,
-  OFK_Cuda,
-  OFK_HIP,
-  OFK_LAST,
+  OFK_OpenMP = (1 << 0),
+  OFK_Cuda = (1 << 1),
+  OFK_HIP = (1 << 2),
+  OFK_SYCL = (1 << 3),
+  OFK_LAST = (1 << 4),
 };
 
 /// The type of contents the offloading image contains.