Thursday, December 30, 2010

SSE built-in functions in GCC

int __builtin_ia32_comieq (v4sf, v4sf)
int __builtin_ia32_comineq (v4sf, v4sf)
int __builtin_ia32_comilt (v4sf, v4sf)
int __builtin_ia32_comile (v4sf, v4sf)
int __builtin_ia32_comigt (v4sf, v4sf)
int __builtin_ia32_comige (v4sf, v4sf)
int __builtin_ia32_ucomieq (v4sf, v4sf)
int __builtin_ia32_ucomineq (v4sf, v4sf)
int __builtin_ia32_ucomilt (v4sf, v4sf)
int __builtin_ia32_ucomile (v4sf, v4sf)
int __builtin_ia32_ucomigt (v4sf, v4sf)
int __builtin_ia32_ucomige (v4sf, v4sf)
v4sf __builtin_ia32_addps (v4sf, v4sf)
v4sf __builtin_ia32_subps (v4sf, v4sf)
v4sf __builtin_ia32_mulps (v4sf, v4sf)
v4sf __builtin_ia32_divps (v4sf, v4sf)
v4sf __builtin_ia32_addss (v4sf, v4sf)
v4sf __builtin_ia32_subss (v4sf, v4sf)
v4sf __builtin_ia32_mulss (v4sf, v4sf)
v4sf __builtin_ia32_divss (v4sf, v4sf)
v4si __builtin_ia32_cmpeqps (v4sf, v4sf)
v4si __builtin_ia32_cmpltps (v4sf, v4sf)
v4si __builtin_ia32_cmpleps (v4sf, v4sf)
v4si __builtin_ia32_cmpgtps (v4sf, v4sf)
v4si __builtin_ia32_cmpgeps (v4sf, v4sf)
v4si __builtin_ia32_cmpunordps (v4sf, v4sf)
v4si __builtin_ia32_cmpneqps (v4sf, v4sf)
v4si __builtin_ia32_cmpnltps (v4sf, v4sf)
v4si __builtin_ia32_cmpnleps (v4sf, v4sf)
v4si __builtin_ia32_cmpngtps (v4sf, v4sf)
v4si __builtin_ia32_cmpngeps (v4sf, v4sf)
v4si __builtin_ia32_cmpordps (v4sf, v4sf)
v4si __builtin_ia32_cmpeqss (v4sf, v4sf)
v4si __builtin_ia32_cmpltss (v4sf, v4sf)
v4si __builtin_ia32_cmpless (v4sf, v4sf)
v4si __builtin_ia32_cmpunordss (v4sf, v4sf)
v4si __builtin_ia32_cmpneqss (v4sf, v4sf)
v4si __builtin_ia32_cmpnlts (v4sf, v4sf)
v4si __builtin_ia32_cmpnless (v4sf, v4sf)
v4si __builtin_ia32_cmpordss (v4sf, v4sf)
v4sf __builtin_ia32_maxps (v4sf, v4sf)
v4sf __builtin_ia32_maxss (v4sf, v4sf)
v4sf __builtin_ia32_minps (v4sf, v4sf)
v4sf __builtin_ia32_minss (v4sf, v4sf)
v4sf __builtin_ia32_andps (v4sf, v4sf)
v4sf __builtin_ia32_andnps (v4sf, v4sf)
v4sf __builtin_ia32_orps (v4sf, v4sf)
v4sf __builtin_ia32_xorps (v4sf, v4sf)
v4sf __builtin_ia32_movss (v4sf, v4sf)
v4sf __builtin_ia32_movhlps (v4sf, v4sf)
v4sf __builtin_ia32_movlhps (v4sf, v4sf)
v4sf __builtin_ia32_unpckhps (v4sf, v4sf)
v4sf __builtin_ia32_unpcklps (v4sf, v4sf)
v4sf __builtin_ia32_cvtpi2ps (v4sf, v2si)
v4sf __builtin_ia32_cvtsi2ss (v4sf, int)
v2si __builtin_ia32_cvtps2pi (v4sf)
int __builtin_ia32_cvtss2si (v4sf)
v2si __builtin_ia32_cvttps2pi (v4sf)
int __builtin_ia32_cvttss2si (v4sf)
v4sf __builtin_ia32_rcpps (v4sf)
v4sf __builtin_ia32_rsqrtps (v4sf)
v4sf __builtin_ia32_sqrtps (v4sf)
v4sf __builtin_ia32_rcpss (v4sf)
v4sf __builtin_ia32_rsqrtss (v4sf)
v4sf __builtin_ia32_sqrtss (v4sf)
v4sf __builtin_ia32_shufps (v4sf, v4sf, int)
void __builtin_ia32_movntps (float *, v4sf)
int __builtin_ia32_movmskps (v4sf)

The following built-in functions are available when -msse is used.

v4sf __builtin_ia32_loadaps (float *)
Generates the movaps machine instruction as a load from memory. 
void __builtin_ia32_storeaps (float *, v4sf)
Generates the movaps machine instruction as a store to memory. 
v4sf __builtin_ia32_loadups (float *)
Generates the movups machine instruction as a load from memory. 
void __builtin_ia32_storeups (float *, v4sf)
Generates the movups machine instruction as a store to memory. 
v4sf __builtin_ia32_loadsss (float *)
Generates the movss machine instruction as a load from memory. 
void __builtin_ia32_storess (float *, v4sf)
Generates the movss machine instruction as a store to memory. 
v4sf __builtin_ia32_loadhps (v4sf, v2si *)
Generates the movhps machine instruction as a load from memory. 
v4sf __builtin_ia32_loadlps (v4sf, v2si *)
Generates the movlps machine instruction as a load from memory 
void __builtin_ia32_storehps (v4sf, v2si *)
Generates the movhps machine instruction as a store to memory. 
void __builtin_ia32_storelps (v4sf, v2si *)
Generates the movlps machine instruction as a store to memory.

No comments:

Post a Comment