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

[usaxena95]

Summary

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.

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

E.setFileProximityDistanceCost(
         FlipCoin(0.1) ? 999999 // Sometimes file distance is not available.
                       : RandInt(20));
     E.setSemaFileProximityScore(RandFloat(1)); // Float in range [0,1].
     E.setSymbolScopeDistanceCost(
         FlipCoin(0.1) ? 999999 // Sometimes scope distance is not available.
                       : 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.
     E.setTypeMatchesPreferred(FlipCoin(0.5)); // Boolean.
     Examples.push_back(E);
   }
   return Examples;
 }

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

for f in features_json:
 
         if f["kind"] == "NUMBER":
             # Floats are order-encoded to integers for faster comparison.
             setters.append(
                 "void set%s(float V) { %s = OrderEncode(V); }" % (
                     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  "
     guard = header_guard(filename)
     return """#ifndef %s
 #define %s
 #include <cstdint>
 #include "llvm/Support/Compiler.h"
using_decls = "\n".join("using %s_type = %s;" % (
         feature['name'], feature['type'])
         for feature in features_json
         if feature["kind"] == "ENUM")
     nl = "\n"
     return """%s
 
 %s
 
-#define BIT(X) (1 << X)
+#define BIT(X) (1LL << X)
 
 %s
 
 %s
 
 uint32_t %s::OrderEncode(float F) {
   static_assert(std::numeric_limits<float>::is_iec559, "");
   constexpr uint32_t TopBit = ~(~uint32_t{0} >> 1);