/*
    Copyright 2005-2013 Intel Corporation.  All Rights Reserved.

    The source code contained or described herein and all documents related
    to the source code ("Material") are owned by Intel Corporation or its
    suppliers or licensors.  Title to the Material remains with Intel
    Corporation or its suppliers and licensors.  The Material is protected
    by worldwide copyright laws and treaty provisions.  No part of the
    Material may be used, copied, reproduced, modified, published, uploaded,
    posted, transmitted, distributed, or disclosed in any way without
    Intel's prior express written permission.

    No license under any patent, copyright, trade secret or other
    intellectual property right is granted to or conferred upon you by
    disclosure or delivery of the Materials, either expressly, by
    implication, inducement, estoppel or otherwise.  Any license under such
    intellectual property rights must be express and approved by Intel in
    writing.
*/

#if !defined(__TBB_machine_H) || defined(__TBB_machine_windows_ia32_H)
#error Do not #include this internal file directly; use public TBB headers instead.
#endif

#define __TBB_machine_windows_ia32_H

#include "msvc_ia32_common.h"

#define __TBB_WORDSIZE 4
#define __TBB_ENDIANNESS __TBB_ENDIAN_LITTLE

#if __INTEL_COMPILER && (__INTEL_COMPILER < 1100)
    #define __TBB_compiler_fence()    __asm { __asm nop }
    #define __TBB_full_memory_fence() __asm { __asm mfence }
#elif _MSC_VER >= 1300 || __INTEL_COMPILER
    #pragma intrinsic(_ReadWriteBarrier)
    #pragma intrinsic(_mm_mfence)
    #define __TBB_compiler_fence()    _ReadWriteBarrier()
    #define __TBB_full_memory_fence() _mm_mfence()
#else
    #error Unsupported compiler - need to define __TBB_{control,acquire,release}_consistency_helper to support it
#endif

#define __TBB_control_consistency_helper() __TBB_compiler_fence()
#define __TBB_acquire_consistency_helper() __TBB_compiler_fence()
#define __TBB_release_consistency_helper() __TBB_compiler_fence()

#if defined(_MSC_VER) && !defined(__INTEL_COMPILER)
    // Workaround for overzealous compiler warnings in /Wp64 mode
    #pragma warning (push)
    #pragma warning (disable: 4244 4267)
#endif

extern "C" {
    __int64 __TBB_EXPORTED_FUNC __TBB_machine_cmpswp8 (volatile void *ptr, __int64 value, __int64 comparand );
    __int64 __TBB_EXPORTED_FUNC __TBB_machine_fetchadd8 (volatile void *ptr, __int64 addend );
    __int64 __TBB_EXPORTED_FUNC __TBB_machine_fetchstore8 (volatile void *ptr, __int64 value );
    void __TBB_EXPORTED_FUNC __TBB_machine_store8 (volatile void *ptr, __int64 value );
    __int64 __TBB_EXPORTED_FUNC __TBB_machine_load8 (const volatile void *ptr);
}

//TODO: use _InterlockedXXX intrinsics as they available since VC 2005
#define __TBB_MACHINE_DEFINE_ATOMICS(S,T,U,A,C) \
static inline T __TBB_machine_cmpswp##S ( volatile void * ptr, U value, U comparand ) { \
    T result; \
    volatile T *p = (T *)ptr; \
    __asm \
    { \
       __asm mov edx, p \
       __asm mov C , value \
       __asm mov A , comparand \
       __asm lock cmpxchg [edx], C \
       __asm mov result, A \
    } \
    return result; \
} \
\
static inline T __TBB_machine_fetchadd##S ( volatile void * ptr, U addend ) { \
    T result; \
    volatile T *p = (T *)ptr; \
    __asm \
    { \
        __asm mov edx, p \
        __asm mov A, addend \
        __asm lock xadd [edx], A \
        __asm mov result, A \
    } \
    return result; \
}\
\
static inline T __TBB_machine_fetchstore##S ( volatile void * ptr, U value ) { \
    T result; \
    volatile T *p = (T *)ptr; \
    __asm \
    { \
        __asm mov edx, p \
        __asm mov A, value \
        __asm lock xchg [edx], A \
        __asm mov result, A \
    } \
    return result; \
}


__TBB_MACHINE_DEFINE_ATOMICS(1, __int8, __int8, al, cl)
__TBB_MACHINE_DEFINE_ATOMICS(2, __int16, __int16, ax, cx)
__TBB_MACHINE_DEFINE_ATOMICS(4, ptrdiff_t, ptrdiff_t, eax, ecx)

#undef __TBB_MACHINE_DEFINE_ATOMICS

static inline void __TBB_machine_OR( volatile void *operand, __int32 addend ) {
   __asm 
   {
       mov eax, addend
       mov edx, [operand]
       lock or [edx], eax
   }
}

static inline void __TBB_machine_AND( volatile void *operand, __int32 addend ) {
   __asm 
   {
       mov eax, addend
       mov edx, [operand]
       lock and [edx], eax
   }
}

#define __TBB_AtomicOR(P,V) __TBB_machine_OR(P,V)
#define __TBB_AtomicAND(P,V) __TBB_machine_AND(P,V)

//TODO: Check if it possible and profitable for IA-32 architecture on (Linux and Windows)
//to use of 64-bit load/store via floating point registers together with full fence
//for sequentially consistent load/store, instead of CAS.
#define __TBB_USE_FETCHSTORE_AS_FULL_FENCED_STORE           1
#define __TBB_USE_GENERIC_HALF_FENCED_LOAD_STORE            1
#define __TBB_USE_GENERIC_RELAXED_LOAD_STORE                1
#define __TBB_USE_GENERIC_SEQUENTIAL_CONSISTENCY_LOAD_STORE 1


#if defined(_MSC_VER) && !defined(__INTEL_COMPILER)
    #pragma warning (pop)
#endif // warnings 4244, 4267 are back