[llvm] [AMDGPU] Add `.amdgpu.info` section for per-function metadata (PR #192384)

[Shilei Tian via llvm-commits]

================
@@ -6741,6 +6747,110 @@ bool AMDGPUAsmParser::ParseDirectiveAMDGPULDS() {
   return false;
 }
 
+bool AMDGPUAsmParser::ParseDirectiveAMDGPUInfo() {
+  if (getParser().checkForValidSection())
+    return true;
+
+  StringRef FuncName;
+  if (getParser().parseIdentifier(FuncName))
+    return TokError("expected symbol name after .amdgpu_info");
+
+  MCSymbol *FuncSym = getContext().getOrCreateSymbol(FuncName);
+  AMDGPU::FuncInfo FI;
+  FI.Sym = FuncSym;
+  bool HasScalarAttrs = false;
+
+  while (true) {
+    while (trySkipToken(AsmToken::EndOfStatement))
+      ;
+
+    StringRef ID;
+    SMLoc IDLoc = getLoc();
+    if (!parseId(ID, "expected directive or .end_amdgpu_info"))
+      return true;
+
+    if (ID == ".end_amdgpu_info")
+      break;
+
+    // Every per-entry directive shares the `.amdgpu_` namespace prefix; strip
+    // it once and dispatch on the distinguishing suffix below. The unstripped
+    // ID is preserved for diagnostics.
+    StringRef Dir = ID;
+    if (!Dir.consume_front(".amdgpu_"))
+      return Error(IDLoc, "unknown .amdgpu_info directive '" + ID + "'");
+
+    if (Dir == "flags") {
+      int64_t Val;
+      if (getParser().parseAbsoluteExpression(Val))
+        return true;
+      auto Flags = static_cast<AMDGPU::FuncInfoFlags>(Val);
+      FI.UsesVCC = !!(Flags & AMDGPU::FuncInfoFlags::FUNC_USES_VCC);
+      FI.UsesFlatScratch =
+          !!(Flags & AMDGPU::FuncInfoFlags::FUNC_USES_FLAT_SCRATCH);
+      FI.HasDynStack = !!(Flags & AMDGPU::FuncInfoFlags::FUNC_HAS_DYN_STACK);
+      HasScalarAttrs = true;
+    } else if (Dir == "num_sgpr") {
+      int64_t Val;
+      if (getParser().parseAbsoluteExpression(Val))
+        return true;
+      FI.NumSGPR = static_cast<uint32_t>(Val);
+      HasScalarAttrs = true;
+    } else if (Dir == "num_vgpr") {
+      int64_t Val;
+      if (getParser().parseAbsoluteExpression(Val))
+        return true;
+      FI.NumArchVGPR = static_cast<uint32_t>(Val);
----------------
shiltian wrote:

We have to defer this to the linker, because the information needs to be propagated before we can determine what is out of range. Having only partial information isn't enough to make that check.

https://github.com/llvm/llvm-project/pull/192384