diff --git a/TracyLua.hpp b/TracyLua.hpp
index 441662a1..a544856c 100644
--- a/TracyLua.hpp
+++ b/TracyLua.hpp
@@ -145,7 +145,7 @@ static inline int LuaZoneBegin( lua_State* L )
     auto& tail = token->get_tail_index();
     auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
     MemWrite( &item->hdr.type, QueueType::ZoneBeginAllocSrcLoc );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
     MemWrite( &item->zoneBegin.time, Profiler::GetTime( item->zoneBegin.cpu ) );
 #else
     uint32_t cpu;
@@ -196,7 +196,7 @@ static inline int LuaZoneBeginN( lua_State* L )
     auto& tail = token->get_tail_index();
     auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
     MemWrite( &item->hdr.type, QueueType::ZoneBeginAllocSrcLoc );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
     MemWrite( &item->zoneBegin.time, Profiler::GetTime( item->zoneBegin.cpu ) );
 #else
     uint32_t cpu;
@@ -216,7 +216,7 @@ static inline int LuaZoneEnd( lua_State* L )
     auto& tail = token->get_tail_index();
     auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
     MemWrite( &item->hdr.type, QueueType::ZoneEnd );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
     MemWrite( &item->zoneEnd.time, Profiler::GetTime( item->zoneEnd.cpu ) );
 #else
     uint32_t cpu;
diff --git a/client/TracyProfiler.cpp b/client/TracyProfiler.cpp
index d1d063b0..6496f975 100644
--- a/client/TracyProfiler.cpp
+++ b/client/TracyProfiler.cpp
@@ -620,7 +620,7 @@ void Profiler::CalibrateDelay()
             auto item = ptoken->enqueue_begin<moodycamel::CanAlloc>( magic );
             MemWrite( &item->hdr.type, QueueType::ZoneBegin );
             MemWrite( &item->zoneBegin.thread, GetThreadHandle() );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
             MemWrite( &item->zoneBegin.time, Profiler::GetTime( item->zoneBegin.cpu ) );
 #else
             uint32_t cpu;
@@ -636,7 +636,7 @@ void Profiler::CalibrateDelay()
             auto item = ptoken->enqueue_begin<moodycamel::CanAlloc>( magic );
             MemWrite( &item->hdr.type, QueueType::ZoneEnd );
             MemWrite( &item->zoneEnd.thread, uint64_t( 0 ) );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
             MemWrite( &item->zoneEnd.time, GetTime( item->zoneEnd.cpu ) );
 #else
             uint32_t cpu;
@@ -662,7 +662,7 @@ void Profiler::CalibrateDelay()
             auto item = ptoken->enqueue_begin<moodycamel::CanAlloc>( magic );
             MemWrite( &item->hdr.type, QueueType::ZoneBegin );
             MemWrite( &item->zoneBegin.thread, GetThreadHandle() );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
             MemWrite( &item->zoneBegin.time, Profiler::GetTime( item->zoneBegin.cpu ) );
 #else
             uint32_t cpu;
@@ -678,7 +678,7 @@ void Profiler::CalibrateDelay()
             auto item = ptoken->enqueue_begin<moodycamel::CanAlloc>( magic );
             MemWrite( &item->hdr.type, QueueType::ZoneEnd );
             MemWrite( &item->zoneEnd.thread, uint64_t( 0 ) );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
             MemWrite( &item->zoneEnd.time, GetTime( item->zoneEnd.cpu ) );
 #else
             uint32_t cpu;
diff --git a/client/TracyProfiler.hpp b/client/TracyProfiler.hpp
index fdfaa62d..4feee0e9 100644
--- a/client/TracyProfiler.hpp
+++ b/client/TracyProfiler.hpp
@@ -21,6 +21,11 @@
 
 #if defined _MSC_VER || defined __CYGWIN__ || ( ( defined __i386 || defined _M_IX86 || defined __x86_64__ || defined _M_X64 ) && !defined __ANDROID__ ) || __ARM_ARCH >= 6
 #  define TRACY_HW_TIMER
+#  if defined _MSC_VER || defined __CYGWIN__
+     // Enable optimization for MSVC __rdtscp() intrin, saving one LHS of a cpu value on the stack.
+     // This comes at the cost of an unaligned memory write.
+#    define TRACY_RDTSCP_OPT
+#  endif
 #endif
 
 namespace tracy
diff --git a/client/TracyScoped.hpp b/client/TracyScoped.hpp
index fcaafd2f..3c5b76a8 100644
--- a/client/TracyScoped.hpp
+++ b/client/TracyScoped.hpp
@@ -24,7 +24,7 @@ public:
         auto& tail = token->get_tail_index();
         auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
         MemWrite( &item->hdr.type, QueueType::ZoneBegin );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
         MemWrite( &item->zoneBegin.time, Profiler::GetTime( item->zoneBegin.cpu ) );
 #else
         uint32_t cpu;
@@ -43,7 +43,7 @@ public:
         auto& tail = token->get_tail_index();
         auto item = token->enqueue_begin<moodycamel::CanAlloc>( magic );
         MemWrite( &item->hdr.type, QueueType::ZoneEnd );
-#ifdef TRACY_HW_TIMER
+#ifdef TRACY_RDTSCP_OPT
         MemWrite( &item->zoneEnd.time, Profiler::GetTime( item->zoneEnd.cpu ) );
 #else
         uint32_t cpu;