================
@@ -478,4 +481,70 @@ bool isClobberedInFunction(const LoadInst *Load, MemorySSA
*MSSA,
return false;
}
+static constexpr SIAtomicAddrSpace LLVMToSIAtomicAddrSpaceMapping[] = {
+ SIAtomicAddrSpace::FLAT, //< AMDGPUAS::FLAT_ADDRESS
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::GLOBAL_ADDRESS
+ SIAtomicAddrSpace::GDS, //< AMDGPUAS::REGION_ADDRESS
+ SIAtomicAddrSpace::LDS, //< AMDGPUAS::LOCAL_ADDRESS
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::CONSTANT_ADDRESS
+ SIAtomicAddrSpace::SCRATCH, //< AMDGPUAS::PRIVATE_ADDRESS
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::CONSTANT_ADDRESS_32BIT
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::BUFFER_FAT_POINTER
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::BUFFER_RESOURCE
+ SIAtomicAddrSpace::GLOBAL, //< AMDGPUAS::BUFFER_STRIDED_POINTER
+};
+
+SIAtomicAddrSpace toSIAtomicAddrSpace(unsigned LLVMAddrSpace) {
+ constexpr unsigned SizeOfLLVMToSIAtomicAddrSpaceMapping =
+ sizeof(LLVMToSIAtomicAddrSpaceMapping) /
+ sizeof(LLVMToSIAtomicAddrSpaceMapping[0]);
+ if (LLVMAddrSpace > AMDGPUAS::MAX_AMDGPU_ADDRESS)
+ return SIAtomicAddrSpace::GLOBAL;
+ if (LLVMAddrSpace < SizeOfLLVMToSIAtomicAddrSpaceMapping)
+ return LLVMToSIAtomicAddrSpaceMapping[LLVMAddrSpace];
+ return SIAtomicAddrSpace::OTHER;
+}
+
+static const StringMap<SIAtomicAddrSpace> ASNames = {{
+ {"global", SIAtomicAddrSpace::GLOBAL},
+ {"local", SIAtomicAddrSpace::LDS},
+}};
+
+std::optional<SIAtomicAddrSpace>
+getSynchronizeAddrSpace(const MMRAMetadata &MMRA, const Function *DiagFn,
+ const DebugLoc &DL) {
+ static constexpr StringLiteral FenceASPrefix = "amdgpu-synchronize-as";
+
+ if (!MMRA)
+ return std::nullopt;
+
+ SIAtomicAddrSpace Result = SIAtomicAddrSpace::NONE;
+ for (const auto &[Prefix, Suffix] : MMRA) {
+ if (Prefix != FenceASPrefix)
+ continue;
+
+ if (auto It = ASNames.find(Suffix); It != ASNames.end()) {
+ Result |= It->second;
+ } else if (DiagFn) {
+ SmallString<128> Str;
+ raw_svector_ostream OS(Str);
+ OS << "unknown address space '" << Suffix << "'; expected one of ";
+ ListSeparator LS;
+ for (const auto &[Name, Val] : ASNames)
+ OS << LS << '\'' << Name << '\'';
+ DiagFn->getContext().diagnose(
+ DiagnosticInfoUnsupported(*DiagFn, Str, DL, DS_Warning));
+ }
+ }
+
+ if (Result == SIAtomicAddrSpace::NONE)
+ return std::nullopt;
----------------
ritter-x2a wrote:
We currently define all synchronization to only affect at most
`SIAtomicAddrSpace::ATOMIC`, as can be seen from the returns in
[SIMemOpAccess::toSIAtomicScope](https://github.com/llvm/llvm-project/blob/9f0c2f993640bcafb3e2722f1fe68d564b537276/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp#L789-L826),
where the second tuple value is always `ATOMIC` (for non-one-as syncscopes) or
`ATOMIC` intersected with something (for one-as syncscopes).
We'd [issue
diagnostics](https://github.com/llvm/llvm-project/blob/14a8bae5a7664333dcb7618a1e3e30b9e07e4ce3/llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp#L918-L923)
if something including `SIAtomicAddrSpace::OTHER` was involved.
So, with the way this is set up and used right now, I'd argue that `ATOMIC` is
the right choice here.
But yes, that's odd. Acquire/release without restrictions should affect all
memory accesses. One specific point that I see where this gives us (at least
theoretical) trouble is the BARRIER address space, 15, which falls under
`OTHER`. The "fence-release; s_barrier; fence-acquire" pattern relies on the
fences pairing with operations in the BARRIER AS (that's the reason why one-as
fences don't work for this pattern, they also restrict what operations the
fences pair with).
I'd really like to not put these refactors (including the renaming of
`SIAtomicAddrSpace` to `AMDGPU::MemoryApertureSet`) on the critical path for
landing the correctness fix in #219991, though.
https://github.com/llvm/llvm-project/pull/231854
_______________________________________________
llvm-branch-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits