Part 1 (Clang): Reland "[HIP] Support compressing device binary"

Original PR: llvm#67162

The commit was reverted due to UB detected by santizer:

https://lab.llvm.org/buildbot/#/builders/238/builds/5955

clang/lib/Driver/OffloadBundler.cpp:1012:25: runtime error:
 load of misaligned address 0xaaaae2d90e7c for type
 'const uint64_t' (aka 'const unsigned long'), which
 requires 8 byte alignment

It was fixed by using memcpy instead of dereferencing int*
casted from unaligned char*.

Note from committer:
The original patch is splitted into two parts, one only for clang, and
the other only for LLVM. This is to allow easier packaging for Nix.

Signed-off-by: Gavin Zhao <git@gzgz.dev>

clang/include/clang/Driver/OffloadBundler.h

@@ -19,18 +19,23 @@
 
 #include "llvm/Support/Error.h"
 #include "llvm/TargetParser/Triple.h"
+#include <llvm/Support/MemoryBuffer.h>
 #include <string>
 #include <vector>
 
 namespace clang {
 
 class OffloadBundlerConfig {
 public:
+  OffloadBundlerConfig();
+
   bool AllowNoHost = false;
   bool AllowMissingBundles = false;
   bool CheckInputArchive = false;
   bool PrintExternalCommands = false;
   bool HipOpenmpCompatible = false;
+  bool Compress = false;
+  bool Verbose = false;
 
   unsigned BundleAlignment = 1;
   unsigned HostInputIndex = ~0u;
@@ -82,6 +87,38 @@ struct OffloadTargetInfo {
   std::string str() const;
 };
 
+// CompressedOffloadBundle represents the format for the compressed offload
+// bundles.
+//
+// The format is as follows:
+// - Magic Number (4 bytes) - A constant "CCOB".
+// - Version (2 bytes)
+// - Compression Method (2 bytes) - Uses the values from
+// llvm::compression::Format.
+// - Uncompressed Size (4 bytes).
+// - Truncated MD5 Hash (8 bytes).
+// - Compressed Data (variable length).
+
+class CompressedOffloadBundle {
+private:
+  static inline const size_t MagicSize = 4;
+  static inline const size_t VersionFieldSize = sizeof(uint16_t);
+  static inline const size_t MethodFieldSize = sizeof(uint16_t);
+  static inline const size_t SizeFieldSize = sizeof(uint32_t);
+  static inline const size_t HashFieldSize = 8;
+  static inline const size_t HeaderSize = MagicSize + VersionFieldSize +
+                                          MethodFieldSize + SizeFieldSize +
+                                          HashFieldSize;
+  static inline const llvm::StringRef MagicNumber = "CCOB";
+  static inline const uint16_t Version = 1;
+
+public:
+  static llvm::Expected<std::unique_ptr<llvm::MemoryBuffer>>
+  compress(const llvm::MemoryBuffer &Input, bool Verbose = false);
+  static llvm::Expected<std::unique_ptr<llvm::MemoryBuffer>>
+  decompress(const llvm::MemoryBuffer &Input, bool Verbose = false);
+};
+
 } // namespace clang
 
 #endif // LLVM_CLANG_DRIVER_OFFLOADBUNDLER_H

clang/include/clang/Driver/Options.td

@@ -1254,6 +1254,10 @@ def static_libsan : Flag<["-"], "static-libsan">,
 def : Flag<["-"], "shared-libasan">, Alias<shared_libsan>;
 def fasm : Flag<["-"], "fasm">, Group<f_Group>;
 
+def offload_compress : Flag<["--"], "offload-compress">,
+  HelpText<"Compress offload device binaries (HIP only)">;
+def no_offload_compress : Flag<["--"], "no-offload-compress">;
+
 def fassume_sane_operator_new : Flag<["-"], "fassume-sane-operator-new">, Group<f_Group>;
 def fastcp : Flag<["-"], "fastcp">, Group<f_Group>;
 def fastf : Flag<["-"], "fastf">, Group<f_Group>;