From 33a6ce18373ffd1457ebd54e930b6f02fe4c39c1 Mon Sep 17 00:00:00 2001 From: "Yaxun (Sam) Liu" Date: Thu, 22 Feb 2024 13:51:31 -0500 Subject: [HIP] Allow partial linking for `-fgpu-rdc` (#81700) `-fgpu-rdc` mode allows device functions call device functions in different TU. However, currently all device objects have to be linked together since only one fat binary is supported. This is time consuming for AMDGPU backend since it only supports LTO. There are use cases that objects can be divided into groups in which device functions are self-contained but host functions are not. It is desirable to link/optimize/codegen the device code and generate a fatbin for each group, whereas partially link the host code with `ld -r` or generate a static library by using the `--emit-static-lib` option of clang. This avoids linking all device code together, therefore decreases the linking time for `-fgpu-rdc`. Previously, clang emits an external symbol `__hip_fatbin` for all objects for `-fgpu-rdc`. With this patch, clang emits an unique external symbol `__hip_fatbin_{cuid}` for the fat binary for each object. When a group of objects are linked together to generate a fatbin, the symbols are merged by alias and point to the same fat binary. Each group has its own fat binary. One executable or shared library can have multiple fat binaries. Device linking is done for undefined fab binary symbols only to avoid repeated linking. `__hip_gpubin_handle` is also uniquefied and merged to avoid repeated registering. Symbol `__hip_cuid_{cuid}` is introduced to facilitate debugging and tooling. Fixes: https://github.com/llvm/llvm-project/issues/77018 --- clang/lib/CodeGen/CodeGenModule.cpp | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'clang/lib/CodeGen/CodeGenModule.cpp') diff --git a/clang/lib/CodeGen/CodeGenModule.cpp b/clang/lib/CodeGen/CodeGenModule.cpp index 77fb3a62b356..95e457bef28e 100644 --- a/clang/lib/CodeGen/CodeGenModule.cpp +++ b/clang/lib/CodeGen/CodeGenModule.cpp @@ -915,7 +915,15 @@ void CodeGenModule::Release() { llvm::ConstantArray::get(ATy, UsedArray), "__clang_gpu_used_external"); addCompilerUsedGlobal(GV); } - + if (LangOpts.HIP) { + // Emit a unique ID so that host and device binaries from the same + // compilation unit can be associated. + auto *GV = new llvm::GlobalVariable( + getModule(), Int8Ty, false, llvm::GlobalValue::ExternalLinkage, + llvm::Constant::getNullValue(Int8Ty), + "__hip_cuid_" + getContext().getCUIDHash()); + addCompilerUsedGlobal(GV); + } emitLLVMUsed(); if (SanStats) SanStats->finish(); -- cgit v1.2.3