[clangd] Make categorical features 64 bit in DecisionForest Model.

CodeCompletionContext::Kind has 36 Kinds. The completion model used to
support categorical features of 32 cardinality.
Due to this clangd tests were failing asan tests due to overflow.

This patch makes the completion model support 64 cardinality of
categorical features by storing ENUM Features as uint64_t instead of
uint32_t.

Verified that this fixes the asan failures.

Latency: 6.7ms (old) VS 6.8ms (new) per 1000 predictions.

Differential Revision: https://reviews.llvm.org/D97770

Author: usx95

clang-tools-extra/clangd/benchmarks/CompletionModel/DecisionForestBenchmark.cpp

@@ -51,7 +51,7 @@ std::vector<Example> generateRandomDataset(int NumExamples) {
                       : RandInt(20));
     E.setSemaSaysInScope(FlipCoin(0.5));      // Boolean.
     E.setScope(RandInt(4));                   // 4 Scopes.
-    E.setContextKind(RandInt(32));            // 32 Context kinds.
+    E.setContextKind(RandInt(36));            // 36 Context kinds.
     E.setIsInstanceMember(FlipCoin(0.5));     // Boolean.
     E.setHadContextType(FlipCoin(0.6));       // Boolean.
     E.setHadSymbolType(FlipCoin(0.6));        // Boolean.

clang-tools-extra/clangd/quality/CompletionModelCodegen.py

@@ -131,18 +131,19 @@ class can be used to represent a code completion candidate.
                     feature, feature))
         elif f["kind"] == "ENUM":
             setters.append(
-                "void set%s(unsigned V) { %s = 1 << V; }" % (feature, feature))
+                "void set%s(unsigned V) { %s = 1LL << V; }" % (feature, feature))
         else:
             raise ValueError("Unhandled feature type.", f["kind"])
 
     # Class members represent all the features of the Example.
     class_members = [
-        "uint32_t %s = 0;" % f['name']
+        "uint%d_t %s = 0;"
+        % (64 if f["kind"] == "ENUM" else 32, f['name'])
         for f in features_json
     ]
     getters = [
-        "LLVM_ATTRIBUTE_ALWAYS_INLINE uint32_t get%s() const { return %s; }"
-        % (f['name'], f['name'])
+        "LLVM_ATTRIBUTE_ALWAYS_INLINE uint%d_t get%s() const { return %s; }"
+        % (64 if f["kind"] == "ENUM" else 32, f['name'], f['name'])
         for f in features_json
     ]
     nline = "\n  "
@@ -245,7 +246,7 @@ def gen_cpp_code(forest_json, features_json, filename, cpp_class):
 
 %s
 
-#define BIT(X) (1 << X)
+#define BIT(X) (1LL << X)
 
 %s