[clang-tools-extra] [llvm] [clang] [RISCV] Relax march string order constraint (PR #78120)

[Craig Topper via cfe-commits]

================
@@ -793,153 +887,69 @@ RISCVISAInfo::parseArchString(StringRef Arch, bool EnableExperimentalExtension,
       Minor = Version->Minor;
     }
 
-    ISAInfo->addExtension(StringRef(&Baseline, 1), {Major, Minor});
+    // Postpone AddExtension until end of this function
+    SeenExtMap[StringRef(&Baseline, 1).str()] = {Major, Minor};
   }
 
   // Consume the base ISA version number and any '_' between rvxxx and the
   // first extension
   Exts = Exts.drop_front(ConsumeLength);
   Exts.consume_front("_");
 
-  auto StdExtsItr = StdExts.begin();
-  auto StdExtsEnd = StdExts.end();
-  auto GoToNextExt = [](StringRef::iterator &I, unsigned ConsumeLength,
-                        StringRef::iterator E) {
-    I += 1 + ConsumeLength;
-    if (I != E && *I == '_')
-      ++I;
-  };
-  for (auto I = Exts.begin(), E = Exts.end(); I != E;) {
-    char C = *I;
-
-    // Check ISA extensions are specified in the canonical order.
-    while (StdExtsItr != StdExtsEnd && *StdExtsItr != C)
-      ++StdExtsItr;
-
-    if (StdExtsItr == StdExtsEnd) {
-      // Either c contains a valid extension but it was not given in
-      // canonical order or it is an invalid extension.
-      if (StdExts.contains(C)) {
-        return createStringError(
-            errc::invalid_argument,
-            "standard user-level extension not given in canonical order '%c'",
-            C);
-      }
-
-      return createStringError(errc::invalid_argument,
-                               "invalid standard user-level extension '%c'", C);
-    }
-
-    // Move to next char to prevent repeated letter.
-    ++StdExtsItr;
-
-    StringRef Next;
-    unsigned Major, Minor, ConsumeLength;
-    if (std::next(I) != E)
-      Next = StringRef(std::next(I), E - std::next(I));
-    if (auto E = getExtensionVersion(StringRef(&C, 1), Next, Major, Minor,
-                                     ConsumeLength, EnableExperimentalExtension,
-                                     ExperimentalExtensionVersionCheck)) {
-      if (IgnoreUnknown) {
-        consumeError(std::move(E));
-        GoToNextExt(I, ConsumeLength, Exts.end());
-        continue;
-      }
-      return std::move(E);
-    }
-
-    // The order is OK, then push it into features.
-    // Currently LLVM supports only "mafdcvh".
-    if (!isSupportedExtension(StringRef(&C, 1))) {
-      if (IgnoreUnknown) {
-        GoToNextExt(I, ConsumeLength, Exts.end());
-        continue;
+  std::vector<std::string> SplitedExts;
+  if (auto E = splitExtsByUnderscore(Exts, SplitedExts))
+    return std::move(E);
+
+  for (auto Ext : SplitedExts) {
+    StringRef CurrExt = Ext;
+    while (!CurrExt.empty()) {
+      if (AllStdExts.contains(CurrExt.front())) {
+        if (auto E = processSingleLetterExtension(
+                CurrExt, SeenExtMap, IgnoreUnknown, EnableExperimentalExtension,
+                ExperimentalExtensionVersionCheck))
+          return E;
+      } else if (CurrExt.front() == 'z' || CurrExt.front() == 's' ||
+                 CurrExt.front() == 'x') {
+        // Handle other types of extensions other than the standard
+        // general purpose and standard user-level extensions.
+        // Parse the ISA string containing non-standard user-level
+        // extensions, standard supervisor-level extensions and
+        // non-standard supervisor-level extensions.
+        // These extensions start with 'z', 's', 'x' prefixes, might have a
+        // version number (major, minor) and are separated by a single
+        // underscore '_'. We do not enforce a canonical order for them.
+        if (auto E = processMultiLetterExtension(
+                CurrExt, SeenExtMap, IgnoreUnknown, EnableExperimentalExtension,
+                ExperimentalExtensionVersionCheck))
+          return E;
+        // Multi-letter extension must be seperate following extension with
+        // underscore
+        break;
+      } else {
+        // FIXME: Could it be ignored by IgnoreUnknown?
+        return createStringError(errc::invalid_argument,
+                                 "invalid standard user-level extension '%c'",
+                                 CurrExt.front());
       }
-      return createStringError(errc::invalid_argument,
-                               "unsupported standard user-level extension '%c'",
-                               C);
     }
-    ISAInfo->addExtension(StringRef(&C, 1), {Major, Minor});
-
-    // Consume full extension name and version, including any optional '_'
-    // between this extension and the next
-    GoToNextExt(I, ConsumeLength, Exts.end());
   }
 
-  // Handle other types of extensions other than the standard
-  // general purpose and standard user-level extensions.
-  // Parse the ISA string containing non-standard user-level
-  // extensions, standard supervisor-level extensions and
-  // non-standard supervisor-level extensions.
-  // These extensions start with 'z', 's', 'x' prefixes, might have a version
-  // number (major, minor) and are separated by a single underscore '_'. We do
-  // not enforce a canonical order for them.
-  // Set the hardware features for the extensions that are supported.
-
-  // Multi-letter extensions are seperated by a single underscore
-  // as described in RISC-V User-Level ISA V2.2.
-  SmallVector<StringRef, 8> Split;
-  OtherExts.split(Split, '_');
-
-  SmallVector<StringRef, 8> AllExts;
-  if (Split.size() > 1 || Split[0] != "") {
-    for (StringRef Ext : Split) {
-      if (Ext.empty())
-        return createStringError(errc::invalid_argument,
-                                 "extension name missing after separator '_'");
-
-      StringRef Type = getExtensionType(Ext);
-      StringRef Desc = getExtensionTypeDesc(Ext);
-      auto Pos = findLastNonVersionCharacter(Ext) + 1;
-      StringRef Name(Ext.substr(0, Pos));
-      StringRef Vers(Ext.substr(Pos));
-
-      if (Type.empty()) {
-        if (IgnoreUnknown)
-          continue;
-        return createStringError(errc::invalid_argument,
-                                 "invalid extension prefix '" + Ext + "'");
-      }
-
-      if (!IgnoreUnknown && Name.size() == Type.size()) {
-        return createStringError(errc::invalid_argument,
-                                 "%s name missing after '%s'",
-                                 Desc.str().c_str(), Type.str().c_str());
-      }
-
-      unsigned Major, Minor, ConsumeLength;
-      if (auto E = getExtensionVersion(Name, Vers, Major, Minor, ConsumeLength,
-                                       EnableExperimentalExtension,
-                                       ExperimentalExtensionVersionCheck)) {
-        if (IgnoreUnknown) {
-          consumeError(std::move(E));
-          continue;
-        }
-        return std::move(E);
-      }
+  // Check all Extensions are supported.
+  for (auto SeenExtAndVers : SeenExtMap) {
+    std::string ExtName = SeenExtAndVers.first;
----------------
topperc wrote:

`const std::string &ExtName`

https://github.com/llvm/llvm-project/pull/78120