ABataev added inline comments.
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntime.h:499
+
+ QualType TgtAttributeStructQTy;
class OffloadEntriesInfoManagerTy {
----------------
Cab this type and corresponding functions be made AMDGCN-specific only?
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeAMDGCN.cpp:116
+ bool IsGeneric) {
+ if (!CGM.getTriple().isAMDGCN())
+ return;
----------------
Is this possible?
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeAMDGCN.cpp:119
+ int FlatAttr = 0;
+ bool flatAttrEmitted = false;
+ unsigned DefaultWorkGroupSz =
----------------
`FlatAttrEmitted`
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeAMDGCN.cpp:129
+ CGM.getTarget().getGridValue(llvm::omp::GVIDX::GV_Max_WG_Size);
+ unsigned compileTimeThreadLimit = 0;
+ // Only one of thread_limit or num_threads is used, cant do it for both
----------------
`CompileTimeThreadLimit`
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp:1390-1392
+ auto *GVMode = new llvm::GlobalVariable(
+ CGM.getModule(), CGM.Int8Ty,
+ /*isConstant=*/true, llvm::GlobalValue::WeakAnyLinkage,
----------------
Restore original formatting.
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeGPU.h:215-243
+ /// Emit outlined function specialized for the Single Program
+ /// Multiple Data programming model for applicable target directives on the
+ /// NVPTX device.
+ /// \param D Directive to emit.
+ /// \param ParentName Name of the function that encloses the target region.
+ /// \param OutlinedFn Outlined function value to be defined by this call.
+ /// \param OutlinedFnID Outlined function ID value to be defined by this
call.
----------------
Make them protected, not public if possible. Try the same for other new
functions.
================
Comment at: clang/lib/CodeGen/CGOpenMPRuntimeNVPTX.h:40-65
+ virtual llvm::GlobalVariable *
+ allocateTransferMediumGlobal(CodeGenModule &CGM, llvm::ArrayType *Ty,
+ StringRef Name) override;
+
+ /// Allocate global variable for SharedStaticRD
+ virtual llvm::GlobalVariable *
+ allocateSharedStaticRDGlobal(CodeGenModule &CGM,
----------------
No need to add `virtual`, `override` is enough
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D86097/new/
https://reviews.llvm.org/D86097
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
