Index: include/llvm/XRay/XRayRecord.h
===================================================================
--- include/llvm/XRay/XRayRecord.h
+++ include/llvm/XRay/XRayRecord.h
@@ -14,9 +14,9 @@
 #ifndef LLVM_XRAY_XRAY_RECORD_H
 #define LLVM_XRAY_XRAY_RECORD_H
 
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/SmallVector.h"
 #include <cstdint>
-#include <vector>
-#include <string>
 
 namespace llvm {
 namespace xray {
@@ -54,7 +54,7 @@
 /// This may or may not correspond to actual record types in the raw trace (as
 /// the loader implementation may synthesize this information in the process of
 /// of loading).
-enum class RecordTypes {
+enum class RecordTypes : uint8_t {
   ENTER,
   EXIT,
   TAIL_EXIT,
@@ -73,8 +73,8 @@
   /// the RecordType field.
   uint16_t RecordType;
 
-  /// The CPU where the thread is running. We assume number of CPUs <= 65536.
-  uint16_t CPU;
+  /// The CPU where the thread is running. We assume number of CPUs <= 255.
+  uint8_t CPU;
 
   /// Identifies the type of record.
   RecordTypes Type;
@@ -92,11 +92,14 @@
   uint32_t PId;
 
   /// The function call arguments.
-  std::vector<uint64_t> CallArgs;
+  llvm::SmallVector<uint64_t, 0> CallArgs;
 
   /// For custom and typed events, we provide the raw data from the trace.
-  std::string Data;
+  llvm::SmallString<0> Data;
 };
+static_assert(sizeof(XRayRecord) <= 56, "XRayRecord should be small");
+static_assert(sizeof(XRayRecord) % alignof(XRayRecord) == 0,
+              "Should not have any padding between two XRayRecord");
 
 } // namespace xray
 } // namespace llvm
Index: include/llvm/XRay/YAMLXRayRecord.h
===================================================================
--- include/llvm/XRay/YAMLXRayRecord.h
+++ include/llvm/XRay/YAMLXRayRecord.h
@@ -30,7 +30,7 @@
 
 struct YAMLXRayRecord {
   uint16_t RecordType;
-  uint16_t CPU;
+  uint8_t CPU;
   RecordTypes Type;
   int32_t FuncId;
   std::string Function;
Index: lib/XRay/Trace.cpp
===================================================================
--- lib/XRay/Trace.cpp
+++ lib/XRay/Trace.cpp
@@ -362,9 +362,16 @@
   Records.clear();
   std::transform(Trace.Records.begin(), Trace.Records.end(),
                  std::back_inserter(Records), [&](const YAMLXRayRecord &R) {
-                   return XRayRecord{R.RecordType, R.CPU,      R.Type,
-                                     R.FuncId,     R.TSC,      R.TId,
-                                     R.PId,        R.CallArgs, R.Data};
+                   return XRayRecord{R.RecordType,
+                                     R.CPU,
+                                     R.Type,
+                                     R.FuncId,
+                                     R.TSC,
+                                     R.TId,
+                                     R.PId,
+                                     llvm::SmallVector<uint64_t, 0>{
+                                         R.CallArgs.begin(), R.CallArgs.end()},
+                                     StringRef(R.Data)};
                  });
   return Error::success();
 }
Index: tools/llvm-xray/xray-converter.cpp
===================================================================
--- tools/llvm-xray/xray-converter.cpp
+++ tools/llvm-xray/xray-converter.cpp
@@ -87,10 +87,11 @@
                   FH.CycleFrequency};
   Trace.Records.reserve(Records.size());
   for (const auto &R : Records) {
-    Trace.Records.push_back({R.RecordType, R.CPU, R.Type, R.FuncId,
-                             Symbolize ? FuncIdHelper.SymbolOrNumber(R.FuncId)
-                                       : llvm::to_string(R.FuncId),
-                             R.TSC, R.TId, R.PId, R.CallArgs, R.Data});
+    Trace.Records.emplace_back(YAMLXRayRecord{
+        R.RecordType, R.CPU, R.Type, R.FuncId,
+        Symbolize ? FuncIdHelper.SymbolOrNumber(R.FuncId)
+                  : llvm::to_string(R.FuncId),
+        R.TSC, R.TId, R.PId, ArrayRef<uint64_t>(R.CallArgs), R.Data.str()});
   }
   Output Out(OS, nullptr, 0);
   Out.setWriteDefaultValues(false);