Merge remote-tracking branch 'origin/master' into hw

common/TracyAlloc.hpp

@@ -4,15 +4,28 @@
 #include <stdlib.h>
 
 #ifdef TRACY_ENABLE
+#  include "TracyApi.h"
+#  include "TracyForceInline.hpp"
 #  include "../client/tracy_rpmalloc.hpp"
 #endif
 
 namespace tracy
 {
 
+#ifdef TRACY_ENABLE
+extern thread_local bool RpThreadInitDone;
+TRACY_API void InitRpmallocPlumbing();
+
+static tracy_force_inline void InitRpmalloc()
+{
+    if( !RpThreadInitDone ) InitRpmallocPlumbing();
+}
+#endif
+
 static inline void* tracy_malloc( size_t size )
 {
 #ifdef TRACY_ENABLE
+    InitRpmalloc();
     return rpmalloc( size );
 #else
     return malloc( size );
@@ -22,6 +35,7 @@ static inline void* tracy_malloc( size_t size )
 static inline void tracy_free( void* ptr )
 {
 #ifdef TRACY_ENABLE
+    InitRpmalloc();
     rpfree( ptr );
 #else
     free( ptr );
@@ -31,6 +45,7 @@ static inline void tracy_free( void* ptr )
 static inline void* tracy_realloc( void* ptr, size_t size )
 {
 #ifdef TRACY_ENABLE
+    InitRpmalloc();
     return rprealloc( ptr, size );
 #else
     return realloc( ptr, size );

common/TracySystem.cpp

@@ -96,7 +96,6 @@ struct ThreadNameData
     ThreadNameData* next;
 };
 std::atomic<ThreadNameData*>& GetThreadNameData();
-TRACY_API void InitRPMallocThread();
 #endif
 
 #ifdef _MSC_VER
@@ -161,7 +160,6 @@ TRACY_API void SetThreadName( const char* name )
 #endif
 #ifdef TRACY_ENABLE
     {
-        InitRPMallocThread();
         const auto sz = strlen( name );
         char* buf = (char*)tracy_malloc( sz+1 );
         memcpy( buf, name, sz );

common/TracyYield.hpp

@@ -0,0 +1,26 @@
+#ifndef __TRACYYIELD_HPP__
+#define __TRACYYIELD_HPP__
+
+#if defined __SSE2__ || defined _M_AMD64 || _M_IX86_FP == 2
+#  include <emmintrin.h>
+#else
+#  include <thread>
+#endif
+
+#include "TracyForceInline.hpp"
+
+namespace tracy
+{
+
+static tracy_force_inline void YieldThread()
+{
+#if defined __SSE2__ || defined _M_AMD64 || _M_IX86_FP == 2
+    _mm_pause();
+#else
+    std::this_thread::yield();
+#endif
+}
+
+}
+
+#endif