forked from OSchip/llvm-project
68d133a3e8
Summary: Memory globalization is required to maintain OpenMP standard semantics for data sharing between worker and master threads. The GPU cannot share data between its threads so must allocate global or shared memory to store the data in. Currently this is implemented fully in the frontend using the `__kmpc_data_sharing_push_stack` and __kmpc_data_sharing_pop_stack` functions to emulate standard CPU stack sharing. The front-end scans the target region for variables that escape the region and must be shared between the threads. Each variable then has a field created for it in a global record type. This patch replaces this functinality with a single allocation command, effectively mimicing an alloca instruction for the variables that must be shared between the threads. This will be much slower than the current solution, but makes it much easier to optimize as we can analyze each variable independently and determine if it is not captured. In the future, we can replace these calls with an `alloca` and small allocations can be pushed to shared memory. Reviewed By: tianshilei1992 Differential Revision: https://reviews.llvm.org/D97680 |
||
|---|---|---|
| .. | ||
| ABIInfo.h | ||
| Address.h | ||
| BackendUtil.cpp | ||
| CGAtomic.cpp | ||
| CGBlocks.cpp | ||
| CGBlocks.h | ||
| CGBuilder.h | ||
| CGBuiltin.cpp | ||
| CGCUDANV.cpp | ||
| CGCUDARuntime.cpp | ||
| CGCUDARuntime.h | ||
| CGCXX.cpp | ||
| CGCXXABI.cpp | ||
| CGCXXABI.h | ||
| CGCall.cpp | ||
| CGCall.h | ||
| CGClass.cpp | ||
| CGCleanup.cpp | ||
| CGCleanup.h | ||
| CGCoroutine.cpp | ||
| CGDebugInfo.cpp | ||
| CGDebugInfo.h | ||
| CGDecl.cpp | ||
| CGDeclCXX.cpp | ||
| CGException.cpp | ||
| CGExpr.cpp | ||
| CGExprAgg.cpp | ||
| CGExprCXX.cpp | ||
| CGExprComplex.cpp | ||
| CGExprConstant.cpp | ||
| CGExprScalar.cpp | ||
| CGGPUBuiltin.cpp | ||
| CGLoopInfo.cpp | ||
| CGLoopInfo.h | ||
| CGNonTrivialStruct.cpp | ||
| CGObjC.cpp | ||
| CGObjCGNU.cpp | ||
| CGObjCMac.cpp | ||
| CGObjCRuntime.cpp | ||
| CGObjCRuntime.h | ||
| CGOpenCLRuntime.cpp | ||
| CGOpenCLRuntime.h | ||
| CGOpenMPRuntime.cpp | ||
| CGOpenMPRuntime.h | ||
| CGOpenMPRuntimeAMDGCN.cpp | ||
| CGOpenMPRuntimeAMDGCN.h | ||
| CGOpenMPRuntimeGPU.cpp | ||
| CGOpenMPRuntimeGPU.h | ||
| CGOpenMPRuntimeNVPTX.cpp | ||
| CGOpenMPRuntimeNVPTX.h | ||
| CGRecordLayout.h | ||
| CGRecordLayoutBuilder.cpp | ||
| CGStmt.cpp | ||
| CGStmtOpenMP.cpp | ||
| CGVTT.cpp | ||
| CGVTables.cpp | ||
| CGVTables.h | ||
| CGValue.h | ||
| CMakeLists.txt | ||
| CodeGenABITypes.cpp | ||
| CodeGenAction.cpp | ||
| CodeGenFunction.cpp | ||
| CodeGenFunction.h | ||
| CodeGenModule.cpp | ||
| CodeGenModule.h | ||
| CodeGenPGO.cpp | ||
| CodeGenPGO.h | ||
| CodeGenTBAA.cpp | ||
| CodeGenTBAA.h | ||
| CodeGenTypeCache.h | ||
| CodeGenTypes.cpp | ||
| CodeGenTypes.h | ||
| ConstantEmitter.h | ||
| ConstantInitBuilder.cpp | ||
| CoverageMappingGen.cpp | ||
| CoverageMappingGen.h | ||
| EHScopeStack.h | ||
| ItaniumCXXABI.cpp | ||
| MacroPPCallbacks.cpp | ||
| MacroPPCallbacks.h | ||
| MicrosoftCXXABI.cpp | ||
| ModuleBuilder.cpp | ||
| ObjectFilePCHContainerOperations.cpp | ||
| PatternInit.cpp | ||
| PatternInit.h | ||
| README.txt | ||
| SanitizerMetadata.cpp | ||
| SanitizerMetadata.h | ||
| SwiftCallingConv.cpp | ||
| TargetInfo.cpp | ||
| TargetInfo.h | ||
| VarBypassDetector.cpp | ||
| VarBypassDetector.h | ||
README.txt
IRgen optimization opportunities. //===---------------------------------------------------------------------===// The common pattern of -- short x; // or char, etc (x == 10) -- generates an zext/sext of x which can easily be avoided. //===---------------------------------------------------------------------===// Bitfields accesses can be shifted to simplify masking and sign extension. For example, if the bitfield width is 8 and it is appropriately aligned then is is a lot shorter to just load the char directly. //===---------------------------------------------------------------------===// It may be worth avoiding creation of alloca's for formal arguments for the common situation where the argument is never written to or has its address taken. The idea would be to begin generating code by using the argument directly and if its address is taken or it is stored to then generate the alloca and patch up the existing code. In theory, the same optimization could be a win for block local variables as long as the declaration dominates all statements in the block. NOTE: The main case we care about this for is for -O0 -g compile time performance, and in that scenario we will need to emit the alloca anyway currently to emit proper debug info. So this is blocked by being able to emit debug information which refers to an LLVM temporary, not an alloca. //===---------------------------------------------------------------------===// We should try and avoid generating basic blocks which only contain jumps. At -O0, this penalizes us all the way from IRgen (malloc & instruction overhead), all the way down through code generation and assembly time. On 176.gcc:expr.ll, it looks like over 12% of basic blocks are just direct branches! //===---------------------------------------------------------------------===//