From a.beregalov@gmail.com Tue Mar 17 15:54:49 2009 From: Alexander Beregalov Date: Thu, 12 Mar 2009 03:32:45 +0300 Subject: Staging: echo cleanup To: Greg Kroah-Hartman , Steve Underwood , David Rowe Message-ID: <20090312003245.GA12794@orion> Content-Disposition: inline before: errors lines of code errors/KLOC drivers/staging/echo/ 213 1701 125.2 after: errors lines of code errors/KLOC drivers/staging/echo/ 8 1685 4.7 Compile tested. Signed-off-by: Alexander Beregalov Signed-off-by: Greg Kroah-Hartman --- drivers/staging/echo/bit_operations.h | 30 +- drivers/staging/echo/echo.c | 42 +-- drivers/staging/echo/echo.h | 2 drivers/staging/echo/fir.h | 28 +- drivers/staging/echo/mmx.h | 410 +++++++++++++++++----------------- 5 files changed, 248 insertions(+), 264 deletions(-) --- a/drivers/staging/echo/bit_operations.h +++ b/drivers/staging/echo/bit_operations.h @@ -21,8 +21,6 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * $Id: bit_operations.h,v 1.11 2006/11/28 15:37:03 steveu Exp $ */ /*! \file */ @@ -34,7 +32,7 @@ /*! \brief Find the bit position of the highest set bit in a word \param bits The word to be searched \return The bit number of the highest set bit, or -1 if the word is zero. */ -static __inline__ int top_bit(unsigned int bits) +static inline int top_bit(unsigned int bits) { int res; @@ -50,7 +48,7 @@ static __inline__ int top_bit(unsigned i /*! \brief Find the bit position of the lowest set bit in a word \param bits The word to be searched \return The bit number of the lowest set bit, or -1 if the word is zero. */ -static __inline__ int bottom_bit(unsigned int bits) +static inline int bottom_bit(unsigned int bits) { int res; @@ -63,7 +61,7 @@ static __inline__ int bottom_bit(unsigne return res; } #else -static __inline__ int top_bit(unsigned int bits) +static inline int top_bit(unsigned int bits) { int i; @@ -93,7 +91,7 @@ static __inline__ int top_bit(unsigned i return i; } -static __inline__ int bottom_bit(unsigned int bits) +static inline int bottom_bit(unsigned int bits) { int i; @@ -127,7 +125,7 @@ static __inline__ int bottom_bit(unsigne /*! \brief Bit reverse a byte. \param data The byte to be reversed. \return The bit reversed version of data. */ -static __inline__ uint8_t bit_reverse8(uint8_t x) +static inline uint8_t bit_reverse8(uint8_t x) { #if defined(__i386__) || defined(__x86_64__) /* If multiply is fast */ @@ -172,32 +170,32 @@ uint32_t make_mask32(uint32_t x); uint16_t make_mask16(uint16_t x); /*! \brief Find the least significant one in a word, and return a word - with just that bit set. + with just that bit set. \param x The word to be searched. \return The word with the single set bit. */ -static __inline__ uint32_t least_significant_one32(uint32_t x) +static inline uint32_t least_significant_one32(uint32_t x) { - return (x & (-(int32_t) x)); + return x & (-(int32_t) x); } /*! \brief Find the most significant one in a word, and return a word - with just that bit set. + with just that bit set. \param x The word to be searched. \return The word with the single set bit. */ -static __inline__ uint32_t most_significant_one32(uint32_t x) +static inline uint32_t most_significant_one32(uint32_t x) { #if defined(__i386__) || defined(__x86_64__) return 1 << top_bit(x); #else x = make_mask32(x); - return (x ^ (x >> 1)); + return x ^ (x >> 1); #endif } /*! \brief Find the parity of a byte. \param x The byte to be checked. \return 1 for odd, or 0 for even. */ -static __inline__ int parity8(uint8_t x) +static inline int parity8(uint8_t x) { x = (x ^ (x >> 4)) & 0x0F; return (0x6996 >> x) & 1; @@ -206,7 +204,7 @@ static __inline__ int parity8(uint8_t x) /*! \brief Find the parity of a 16 bit word. \param x The word to be checked. \return 1 for odd, or 0 for even. */ -static __inline__ int parity16(uint16_t x) +static inline int parity16(uint16_t x) { x ^= (x >> 8); x = (x ^ (x >> 4)) & 0x0F; @@ -216,7 +214,7 @@ static __inline__ int parity16(uint16_t /*! \brief Find the parity of a 32 bit word. \param x The word to be checked. \return 1 for odd, or 0 for even. */ -static __inline__ int parity32(uint32_t x) +static inline int parity32(uint32_t x) { x ^= (x >> 16); x ^= (x >> 8); --- a/drivers/staging/echo/echo.c +++ b/drivers/staging/echo/echo.c @@ -27,8 +27,6 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * $Id: echo.c,v 1.20 2006/12/01 18:00:48 steveu Exp $ */ /*! \file */ @@ -113,17 +111,17 @@ #define MIN_TX_POWER_FOR_ADAPTION 64 #define MIN_RX_POWER_FOR_ADAPTION 64 -#define DTD_HANGOVER 600 /* 600 samples, or 75ms */ -#define DC_LOG2BETA 3 /* log2() of DC filter Beta */ +#define DTD_HANGOVER 600 /* 600 samples, or 75ms */ +#define DC_LOG2BETA 3 /* log2() of DC filter Beta */ /*-----------------------------------------------------------------------*\ - FUNCTIONS + FUNCTIONS \*-----------------------------------------------------------------------*/ /* adapting coeffs using the traditional stochastic descent (N)LMS algorithm */ #ifdef __bfin__ -static void __inline__ lms_adapt_bg(struct oslec_state *ec, int clean, +static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift) { int i, j; @@ -147,13 +145,13 @@ static void __inline__ lms_adapt_bg(stru /* st: and en: help us locate the assembler in echo.s */ - //asm("st:"); + /* asm("st:"); */ n = ec->taps; for (i = 0, j = offset2; i < n; i++, j++) { exp = *phist++ * factor; ec->fir_taps16[1][i] += (int16_t) ((exp + (1 << 14)) >> 15); } - //asm("en:"); + /* asm("en:"); */ /* Note the asm for the inner loop above generated by Blackfin gcc 4.1.1 is pretty good (note even parallel instructions used): @@ -195,7 +193,7 @@ static void __inline__ lms_adapt_bg(stru */ #else -static __inline__ void lms_adapt_bg(struct oslec_state *ec, int clean, +static inline void lms_adapt_bg(struct oslec_state *ec, int clean, int shift) { int i; @@ -249,9 +247,8 @@ struct oslec_state *oslec_create(int len fir16_create(&ec->fir_state, ec->fir_taps16[0], ec->taps); fir16_create(&ec->fir_state_bg, ec->fir_taps16[1], ec->taps); - for (i = 0; i < 5; i++) { + for (i = 0; i < 5; i++) ec->xvtx[i] = ec->yvtx[i] = ec->xvrx[i] = ec->yvrx[i] = 0; - } ec->cng_level = 1000; oslec_adaption_mode(ec, adaption_mode); @@ -271,14 +268,13 @@ struct oslec_state *oslec_create(int len return ec; - error_oom: +error_oom: for (i = 0; i < 2; i++) kfree(ec->fir_taps16[i]); kfree(ec); return NULL; } - EXPORT_SYMBOL_GPL(oslec_create); void oslec_free(struct oslec_state *ec) @@ -292,14 +288,12 @@ void oslec_free(struct oslec_state *ec) kfree(ec->snapshot); kfree(ec); } - EXPORT_SYMBOL_GPL(oslec_free); void oslec_adaption_mode(struct oslec_state *ec, int adaption_mode) { ec->adaption_mode = adaption_mode; } - EXPORT_SYMBOL_GPL(oslec_adaption_mode); void oslec_flush(struct oslec_state *ec) @@ -326,14 +320,12 @@ void oslec_flush(struct oslec_state *ec) ec->curr_pos = ec->taps - 1; ec->Pstates = 0; } - EXPORT_SYMBOL_GPL(oslec_flush); void oslec_snapshot(struct oslec_state *ec) { memcpy(ec->snapshot, ec->fir_taps16[0], ec->taps * sizeof(int16_t)); } - EXPORT_SYMBOL_GPL(oslec_snapshot); /* Dual Path Echo Canceller ------------------------------------------------*/ @@ -399,7 +391,7 @@ int16_t oslec_update(struct oslec_state /* efficient "out with the old and in with the new" algorithm so we don't have to recalculate over the whole block of samples. */ - new = (int)tx *(int)tx; + new = (int)tx * (int)tx; old = (int)ec->fir_state.history[ec->fir_state.curr_pos] * (int)ec->fir_state.history[ec->fir_state.curr_pos]; ec->Pstates += @@ -498,15 +490,15 @@ int16_t oslec_update(struct oslec_state if ((ec->adaption_mode & ECHO_CAN_USE_ADAPTION) && (ec->nonupdate_dwell == 0) && - (8 * ec->Lclean_bg < - 7 * ec->Lclean) /* (ec->Lclean_bg < 0.875*ec->Lclean) */ && - (8 * ec->Lclean_bg < - ec->Ltx) /* (ec->Lclean_bg < 0.125*ec->Ltx) */ ) { + /* (ec->Lclean_bg < 0.875*ec->Lclean) */ + (8 * ec->Lclean_bg < 7 * ec->Lclean) && + /* (ec->Lclean_bg < 0.125*ec->Ltx) */ + (8 * ec->Lclean_bg < ec->Ltx)) { if (ec->cond_met == 6) { /* BG filter has had better results for 6 consecutive samples */ ec->adapt = 1; memcpy(ec->fir_taps16[0], ec->fir_taps16[1], - ec->taps * sizeof(int16_t)); + ec->taps * sizeof(int16_t)); } else ec->cond_met++; } else @@ -580,7 +572,6 @@ int16_t oslec_update(struct oslec_state return (int16_t) ec->clean_nlp << 1; } - EXPORT_SYMBOL_GPL(oslec_update); /* This function is seperated from the echo canceller is it is usually called @@ -604,7 +595,7 @@ EXPORT_SYMBOL_GPL(oslec_update); precision, which noise shapes things, giving very clean DC removal. */ -int16_t oslec_hpf_tx(struct oslec_state * ec, int16_t tx) +int16_t oslec_hpf_tx(struct oslec_state *ec, int16_t tx) { int tmp, tmp1; @@ -629,7 +620,6 @@ int16_t oslec_hpf_tx(struct oslec_state return tx; } - EXPORT_SYMBOL_GPL(oslec_hpf_tx); MODULE_LICENSE("GPL"); --- a/drivers/staging/echo/echo.h +++ b/drivers/staging/echo/echo.h @@ -23,8 +23,6 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * $Id: echo.h,v 1.9 2006/10/24 13:45:28 steveu Exp $ */ #ifndef __ECHO_H --- a/drivers/staging/echo/fir.h +++ b/drivers/staging/echo/fir.h @@ -21,8 +21,6 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * $Id: fir.h,v 1.8 2006/10/24 13:45:28 steveu Exp $ */ /*! \page fir_page FIR filtering @@ -102,8 +100,8 @@ struct fir_float_state_t { float *history; }; -static __inline__ const int16_t *fir16_create(struct fir16_state_t *fir, - const int16_t * coeffs, int taps) +static inline const int16_t *fir16_create(struct fir16_state_t *fir, + const int16_t *coeffs, int taps) { fir->taps = taps; fir->curr_pos = taps - 1; @@ -116,7 +114,7 @@ static __inline__ const int16_t *fir16_c return fir->history; } -static __inline__ void fir16_flush(struct fir16_state_t *fir) +static inline void fir16_flush(struct fir16_state_t *fir) { #if defined(USE_MMX) || defined(USE_SSE2) || defined(__bfin__) memset(fir->history, 0, 2 * fir->taps * sizeof(int16_t)); @@ -125,7 +123,7 @@ static __inline__ void fir16_flush(struc #endif } -static __inline__ void fir16_free(struct fir16_state_t *fir) +static inline void fir16_free(struct fir16_state_t *fir) { kfree(fir->history); } @@ -148,16 +146,16 @@ static inline int32_t dot_asm(short *x, "A0 += R0.L*R1.L (IS);\n\t" "R0 = A0;\n\t" "%0 = R0;\n\t" - :"=&d"(dot) - :"a"(x), "a"(y), "a"(len) - :"I0", "I1", "A1", "A0", "R0", "R1" + : "=&d"(dot) + : "a"(x), "a"(y), "a"(len) + : "I0", "I1", "A1", "A0", "R0", "R1" ); return dot; } #endif -static __inline__ int16_t fir16(struct fir16_state_t *fir, int16_t sample) +static inline int16_t fir16(struct fir16_state_t *fir, int16_t sample) { int32_t y; #if defined(USE_MMX) @@ -250,8 +248,8 @@ static __inline__ int16_t fir16(struct f return (int16_t) (y >> 15); } -static __inline__ const int16_t *fir32_create(struct fir32_state_t *fir, - const int32_t * coeffs, int taps) +static inline const int16_t *fir32_create(struct fir32_state_t *fir, + const int32_t *coeffs, int taps) { fir->taps = taps; fir->curr_pos = taps - 1; @@ -260,17 +258,17 @@ static __inline__ const int16_t *fir32_c return fir->history; } -static __inline__ void fir32_flush(struct fir32_state_t *fir) +static inline void fir32_flush(struct fir32_state_t *fir) { memset(fir->history, 0, fir->taps * sizeof(int16_t)); } -static __inline__ void fir32_free(struct fir32_state_t *fir) +static inline void fir32_free(struct fir32_state_t *fir) { kfree(fir->history); } -static __inline__ int16_t fir32(struct fir32_state_t *fir, int16_t sample) +static inline int16_t fir32(struct fir32_state_t *fir, int16_t sample) { int i; int32_t y; --- a/drivers/staging/echo/mmx.h +++ b/drivers/staging/echo/mmx.h @@ -44,238 +44,238 @@ union xmm_t { char b[16]; }; -#define mmx_i2r(op,imm,reg) \ - __asm__ __volatile__ (#op " %0, %%" #reg \ - : /* nothing */ \ - : "i" (imm) ) - -#define mmx_m2r(op,mem,reg) \ - __asm__ __volatile__ (#op " %0, %%" #reg \ - : /* nothing */ \ - : "m" (mem)) - -#define mmx_r2m(op,reg,mem) \ - __asm__ __volatile__ (#op " %%" #reg ", %0" \ - : "=m" (mem) \ - : /* nothing */ ) - -#define mmx_r2r(op,regs,regd) \ - __asm__ __volatile__ (#op " %" #regs ", %" #regd) - -#define emms() __asm__ __volatile__ ("emms") - -#define movd_m2r(var,reg) mmx_m2r (movd, var, reg) -#define movd_r2m(reg,var) mmx_r2m (movd, reg, var) -#define movd_r2r(regs,regd) mmx_r2r (movd, regs, regd) - -#define movq_m2r(var,reg) mmx_m2r (movq, var, reg) -#define movq_r2m(reg,var) mmx_r2m (movq, reg, var) -#define movq_r2r(regs,regd) mmx_r2r (movq, regs, regd) - -#define packssdw_m2r(var,reg) mmx_m2r (packssdw, var, reg) -#define packssdw_r2r(regs,regd) mmx_r2r (packssdw, regs, regd) -#define packsswb_m2r(var,reg) mmx_m2r (packsswb, var, reg) -#define packsswb_r2r(regs,regd) mmx_r2r (packsswb, regs, regd) - -#define packuswb_m2r(var,reg) mmx_m2r (packuswb, var, reg) -#define packuswb_r2r(regs,regd) mmx_r2r (packuswb, regs, regd) - -#define paddb_m2r(var,reg) mmx_m2r (paddb, var, reg) -#define paddb_r2r(regs,regd) mmx_r2r (paddb, regs, regd) -#define paddd_m2r(var,reg) mmx_m2r (paddd, var, reg) -#define paddd_r2r(regs,regd) mmx_r2r (paddd, regs, regd) -#define paddw_m2r(var,reg) mmx_m2r (paddw, var, reg) -#define paddw_r2r(regs,regd) mmx_r2r (paddw, regs, regd) - -#define paddsb_m2r(var,reg) mmx_m2r (paddsb, var, reg) -#define paddsb_r2r(regs,regd) mmx_r2r (paddsb, regs, regd) -#define paddsw_m2r(var,reg) mmx_m2r (paddsw, var, reg) -#define paddsw_r2r(regs,regd) mmx_r2r (paddsw, regs, regd) - -#define paddusb_m2r(var,reg) mmx_m2r (paddusb, var, reg) -#define paddusb_r2r(regs,regd) mmx_r2r (paddusb, regs, regd) -#define paddusw_m2r(var,reg) mmx_m2r (paddusw, var, reg) -#define paddusw_r2r(regs,regd) mmx_r2r (paddusw, regs, regd) - -#define pand_m2r(var,reg) mmx_m2r (pand, var, reg) -#define pand_r2r(regs,regd) mmx_r2r (pand, regs, regd) - -#define pandn_m2r(var,reg) mmx_m2r (pandn, var, reg) -#define pandn_r2r(regs,regd) mmx_r2r (pandn, regs, regd) - -#define pcmpeqb_m2r(var,reg) mmx_m2r (pcmpeqb, var, reg) -#define pcmpeqb_r2r(regs,regd) mmx_r2r (pcmpeqb, regs, regd) -#define pcmpeqd_m2r(var,reg) mmx_m2r (pcmpeqd, var, reg) -#define pcmpeqd_r2r(regs,regd) mmx_r2r (pcmpeqd, regs, regd) -#define pcmpeqw_m2r(var,reg) mmx_m2r (pcmpeqw, var, reg) -#define pcmpeqw_r2r(regs,regd) mmx_r2r (pcmpeqw, regs, regd) - -#define pcmpgtb_m2r(var,reg) mmx_m2r (pcmpgtb, var, reg) -#define pcmpgtb_r2r(regs,regd) mmx_r2r (pcmpgtb, regs, regd) -#define pcmpgtd_m2r(var,reg) mmx_m2r (pcmpgtd, var, reg) -#define pcmpgtd_r2r(regs,regd) mmx_r2r (pcmpgtd, regs, regd) -#define pcmpgtw_m2r(var,reg) mmx_m2r (pcmpgtw, var, reg) -#define pcmpgtw_r2r(regs,regd) mmx_r2r (pcmpgtw, regs, regd) - -#define pmaddwd_m2r(var,reg) mmx_m2r (pmaddwd, var, reg) -#define pmaddwd_r2r(regs,regd) mmx_r2r (pmaddwd, regs, regd) - -#define pmulhw_m2r(var,reg) mmx_m2r (pmulhw, var, reg) -#define pmulhw_r2r(regs,regd) mmx_r2r (pmulhw, regs, regd) - -#define pmullw_m2r(var,reg) mmx_m2r (pmullw, var, reg) -#define pmullw_r2r(regs,regd) mmx_r2r (pmullw, regs, regd) - -#define por_m2r(var,reg) mmx_m2r (por, var, reg) -#define por_r2r(regs,regd) mmx_r2r (por, regs, regd) - -#define pslld_i2r(imm,reg) mmx_i2r (pslld, imm, reg) -#define pslld_m2r(var,reg) mmx_m2r (pslld, var, reg) -#define pslld_r2r(regs,regd) mmx_r2r (pslld, regs, regd) -#define psllq_i2r(imm,reg) mmx_i2r (psllq, imm, reg) -#define psllq_m2r(var,reg) mmx_m2r (psllq, var, reg) -#define psllq_r2r(regs,regd) mmx_r2r (psllq, regs, regd) -#define psllw_i2r(imm,reg) mmx_i2r (psllw, imm, reg) -#define psllw_m2r(var,reg) mmx_m2r (psllw, var, reg) -#define psllw_r2r(regs,regd) mmx_r2r (psllw, regs, regd) - -#define psrad_i2r(imm,reg) mmx_i2r (psrad, imm, reg) -#define psrad_m2r(var,reg) mmx_m2r (psrad, var, reg) -#define psrad_r2r(regs,regd) mmx_r2r (psrad, regs, regd) -#define psraw_i2r(imm,reg) mmx_i2r (psraw, imm, reg) -#define psraw_m2r(var,reg) mmx_m2r (psraw, var, reg) -#define psraw_r2r(regs,regd) mmx_r2r (psraw, regs, regd) - -#define psrld_i2r(imm,reg) mmx_i2r (psrld, imm, reg) -#define psrld_m2r(var,reg) mmx_m2r (psrld, var, reg) -#define psrld_r2r(regs,regd) mmx_r2r (psrld, regs, regd) -#define psrlq_i2r(imm,reg) mmx_i2r (psrlq, imm, reg) -#define psrlq_m2r(var,reg) mmx_m2r (psrlq, var, reg) -#define psrlq_r2r(regs,regd) mmx_r2r (psrlq, regs, regd) -#define psrlw_i2r(imm,reg) mmx_i2r (psrlw, imm, reg) -#define psrlw_m2r(var,reg) mmx_m2r (psrlw, var, reg) -#define psrlw_r2r(regs,regd) mmx_r2r (psrlw, regs, regd) - -#define psubb_m2r(var,reg) mmx_m2r (psubb, var, reg) -#define psubb_r2r(regs,regd) mmx_r2r (psubb, regs, regd) -#define psubd_m2r(var,reg) mmx_m2r (psubd, var, reg) -#define psubd_r2r(regs,regd) mmx_r2r (psubd, regs, regd) -#define psubw_m2r(var,reg) mmx_m2r (psubw, var, reg) -#define psubw_r2r(regs,regd) mmx_r2r (psubw, regs, regd) - -#define psubsb_m2r(var,reg) mmx_m2r (psubsb, var, reg) -#define psubsb_r2r(regs,regd) mmx_r2r (psubsb, regs, regd) -#define psubsw_m2r(var,reg) mmx_m2r (psubsw, var, reg) -#define psubsw_r2r(regs,regd) mmx_r2r (psubsw, regs, regd) - -#define psubusb_m2r(var,reg) mmx_m2r (psubusb, var, reg) -#define psubusb_r2r(regs,regd) mmx_r2r (psubusb, regs, regd) -#define psubusw_m2r(var,reg) mmx_m2r (psubusw, var, reg) -#define psubusw_r2r(regs,regd) mmx_r2r (psubusw, regs, regd) - -#define punpckhbw_m2r(var,reg) mmx_m2r (punpckhbw, var, reg) -#define punpckhbw_r2r(regs,regd) mmx_r2r (punpckhbw, regs, regd) -#define punpckhdq_m2r(var,reg) mmx_m2r (punpckhdq, var, reg) -#define punpckhdq_r2r(regs,regd) mmx_r2r (punpckhdq, regs, regd) -#define punpckhwd_m2r(var,reg) mmx_m2r (punpckhwd, var, reg) -#define punpckhwd_r2r(regs,regd) mmx_r2r (punpckhwd, regs, regd) - -#define punpcklbw_m2r(var,reg) mmx_m2r (punpcklbw, var, reg) -#define punpcklbw_r2r(regs,regd) mmx_r2r (punpcklbw, regs, regd) -#define punpckldq_m2r(var,reg) mmx_m2r (punpckldq, var, reg) -#define punpckldq_r2r(regs,regd) mmx_r2r (punpckldq, regs, regd) -#define punpcklwd_m2r(var,reg) mmx_m2r (punpcklwd, var, reg) -#define punpcklwd_r2r(regs,regd) mmx_r2r (punpcklwd, regs, regd) +#define mmx_i2r(op, imm, reg) \ + __asm__ __volatile__ (#op " %0, %%" #reg \ + : /* nothing */ \ + : "i" (imm)) + +#define mmx_m2r(op, mem, reg) \ + __asm__ __volatile__ (#op " %0, %%" #reg \ + : /* nothing */ \ + : "m" (mem)) + +#define mmx_r2m(op, reg, mem) \ + __asm__ __volatile__ (#op " %%" #reg ", %0" \ + : "=m" (mem) \ + : /* nothing */) + +#define mmx_r2r(op, regs, regd) \ + __asm__ __volatile__ (#op " %" #regs ", %" #regd) + +#define emms() __asm__ __volatile__ ("emms") + +#define movd_m2r(var, reg) mmx_m2r(movd, var, reg) +#define movd_r2m(reg, var) mmx_r2m(movd, reg, var) +#define movd_r2r(regs, regd) mmx_r2r(movd, regs, regd) + +#define movq_m2r(var, reg) mmx_m2r(movq, var, reg) +#define movq_r2m(reg, var) mmx_r2m(movq, reg, var) +#define movq_r2r(regs, regd) mmx_r2r(movq, regs, regd) + +#define packssdw_m2r(var, reg) mmx_m2r(packssdw, var, reg) +#define packssdw_r2r(regs, regd) mmx_r2r(packssdw, regs, regd) +#define packsswb_m2r(var, reg) mmx_m2r(packsswb, var, reg) +#define packsswb_r2r(regs, regd) mmx_r2r(packsswb, regs, regd) + +#define packuswb_m2r(var, reg) mmx_m2r(packuswb, var, reg) +#define packuswb_r2r(regs, regd) mmx_r2r(packuswb, regs, regd) + +#define paddb_m2r(var, reg) mmx_m2r(paddb, var, reg) +#define paddb_r2r(regs, regd) mmx_r2r(paddb, regs, regd) +#define paddd_m2r(var, reg) mmx_m2r(paddd, var, reg) +#define paddd_r2r(regs, regd) mmx_r2r(paddd, regs, regd) +#define paddw_m2r(var, reg) mmx_m2r(paddw, var, reg) +#define paddw_r2r(regs, regd) mmx_r2r(paddw, regs, regd) + +#define paddsb_m2r(var, reg) mmx_m2r(paddsb, var, reg) +#define paddsb_r2r(regs, regd) mmx_r2r(paddsb, regs, regd) +#define paddsw_m2r(var, reg) mmx_m2r(paddsw, var, reg) +#define paddsw_r2r(regs, regd) mmx_r2r(paddsw, regs, regd) + +#define paddusb_m2r(var, reg) mmx_m2r(paddusb, var, reg) +#define paddusb_r2r(regs, regd) mmx_r2r(paddusb, regs, regd) +#define paddusw_m2r(var, reg) mmx_m2r(paddusw, var, reg) +#define paddusw_r2r(regs, regd) mmx_r2r(paddusw, regs, regd) + +#define pand_m2r(var, reg) mmx_m2r(pand, var, reg) +#define pand_r2r(regs, regd) mmx_r2r(pand, regs, regd) + +#define pandn_m2r(var, reg) mmx_m2r(pandn, var, reg) +#define pandn_r2r(regs, regd) mmx_r2r(pandn, regs, regd) + +#define pcmpeqb_m2r(var, reg) mmx_m2r(pcmpeqb, var, reg) +#define pcmpeqb_r2r(regs, regd) mmx_r2r(pcmpeqb, regs, regd) +#define pcmpeqd_m2r(var, reg) mmx_m2r(pcmpeqd, var, reg) +#define pcmpeqd_r2r(regs, regd) mmx_r2r(pcmpeqd, regs, regd) +#define pcmpeqw_m2r(var, reg) mmx_m2r(pcmpeqw, var, reg) +#define pcmpeqw_r2r(regs, regd) mmx_r2r(pcmpeqw, regs, regd) + +#define pcmpgtb_m2r(var, reg) mmx_m2r(pcmpgtb, var, reg) +#define pcmpgtb_r2r(regs, regd) mmx_r2r(pcmpgtb, regs, regd) +#define pcmpgtd_m2r(var, reg) mmx_m2r(pcmpgtd, var, reg) +#define pcmpgtd_r2r(regs, regd) mmx_r2r(pcmpgtd, regs, regd) +#define pcmpgtw_m2r(var, reg) mmx_m2r(pcmpgtw, var, reg) +#define pcmpgtw_r2r(regs, regd) mmx_r2r(pcmpgtw, regs, regd) + +#define pmaddwd_m2r(var, reg) mmx_m2r(pmaddwd, var, reg) +#define pmaddwd_r2r(regs, regd) mmx_r2r(pmaddwd, regs, regd) + +#define pmulhw_m2r(var, reg) mmx_m2r(pmulhw, var, reg) +#define pmulhw_r2r(regs, regd) mmx_r2r(pmulhw, regs, regd) + +#define pmullw_m2r(var, reg) mmx_m2r(pmullw, var, reg) +#define pmullw_r2r(regs, regd) mmx_r2r(pmullw, regs, regd) + +#define por_m2r(var, reg) mmx_m2r(por, var, reg) +#define por_r2r(regs, regd) mmx_r2r(por, regs, regd) + +#define pslld_i2r(imm, reg) mmx_i2r(pslld, imm, reg) +#define pslld_m2r(var, reg) mmx_m2r(pslld, var, reg) +#define pslld_r2r(regs, regd) mmx_r2r(pslld, regs, regd) +#define psllq_i2r(imm, reg) mmx_i2r(psllq, imm, reg) +#define psllq_m2r(var, reg) mmx_m2r(psllq, var, reg) +#define psllq_r2r(regs, regd) mmx_r2r(psllq, regs, regd) +#define psllw_i2r(imm, reg) mmx_i2r(psllw, imm, reg) +#define psllw_m2r(var, reg) mmx_m2r(psllw, var, reg) +#define psllw_r2r(regs, regd) mmx_r2r(psllw, regs, regd) + +#define psrad_i2r(imm, reg) mmx_i2r(psrad, imm, reg) +#define psrad_m2r(var, reg) mmx_m2r(psrad, var, reg) +#define psrad_r2r(regs, regd) mmx_r2r(psrad, regs, regd) +#define psraw_i2r(imm, reg) mmx_i2r(psraw, imm, reg) +#define psraw_m2r(var, reg) mmx_m2r(psraw, var, reg) +#define psraw_r2r(regs, regd) mmx_r2r(psraw, regs, regd) + +#define psrld_i2r(imm, reg) mmx_i2r(psrld, imm, reg) +#define psrld_m2r(var, reg) mmx_m2r(psrld, var, reg) +#define psrld_r2r(regs, regd) mmx_r2r(psrld, regs, regd) +#define psrlq_i2r(imm, reg) mmx_i2r(psrlq, imm, reg) +#define psrlq_m2r(var, reg) mmx_m2r(psrlq, var, reg) +#define psrlq_r2r(regs, regd) mmx_r2r(psrlq, regs, regd) +#define psrlw_i2r(imm, reg) mmx_i2r(psrlw, imm, reg) +#define psrlw_m2r(var, reg) mmx_m2r(psrlw, var, reg) +#define psrlw_r2r(regs, regd) mmx_r2r(psrlw, regs, regd) + +#define psubb_m2r(var, reg) mmx_m2r(psubb, var, reg) +#define psubb_r2r(regs, regd) mmx_r2r(psubb, regs, regd) +#define psubd_m2r(var, reg) mmx_m2r(psubd, var, reg) +#define psubd_r2r(regs, regd) mmx_r2r(psubd, regs, regd) +#define psubw_m2r(var, reg) mmx_m2r(psubw, var, reg) +#define psubw_r2r(regs, regd) mmx_r2r(psubw, regs, regd) + +#define psubsb_m2r(var, reg) mmx_m2r(psubsb, var, reg) +#define psubsb_r2r(regs, regd) mmx_r2r(psubsb, regs, regd) +#define psubsw_m2r(var, reg) mmx_m2r(psubsw, var, reg) +#define psubsw_r2r(regs, regd) mmx_r2r(psubsw, regs, regd) + +#define psubusb_m2r(var, reg) mmx_m2r(psubusb, var, reg) +#define psubusb_r2r(regs, regd) mmx_r2r(psubusb, regs, regd) +#define psubusw_m2r(var, reg) mmx_m2r(psubusw, var, reg) +#define psubusw_r2r(regs, regd) mmx_r2r(psubusw, regs, regd) + +#define punpckhbw_m2r(var, reg) mmx_m2r(punpckhbw, var, reg) +#define punpckhbw_r2r(regs, regd) mmx_r2r(punpckhbw, regs, regd) +#define punpckhdq_m2r(var, reg) mmx_m2r(punpckhdq, var, reg) +#define punpckhdq_r2r(regs, regd) mmx_r2r(punpckhdq, regs, regd) +#define punpckhwd_m2r(var, reg) mmx_m2r(punpckhwd, var, reg) +#define punpckhwd_r2r(regs, regd) mmx_r2r(punpckhwd, regs, regd) + +#define punpcklbw_m2r(var, reg) mmx_m2r(punpcklbw, var, reg) +#define punpcklbw_r2r(regs, regd) mmx_r2r(punpcklbw, regs, regd) +#define punpckldq_m2r(var, reg) mmx_m2r(punpckldq, var, reg) +#define punpckldq_r2r(regs, regd) mmx_r2r(punpckldq, regs, regd) +#define punpcklwd_m2r(var, reg) mmx_m2r(punpcklwd, var, reg) +#define punpcklwd_r2r(regs, regd) mmx_r2r(punpcklwd, regs, regd) -#define pxor_m2r(var,reg) mmx_m2r (pxor, var, reg) -#define pxor_r2r(regs,regd) mmx_r2r (pxor, regs, regd) +#define pxor_m2r(var, reg) mmx_m2r(pxor, var, reg) +#define pxor_r2r(regs, regd) mmx_r2r(pxor, regs, regd) /* 3DNOW extensions */ -#define pavgusb_m2r(var,reg) mmx_m2r (pavgusb, var, reg) -#define pavgusb_r2r(regs,regd) mmx_r2r (pavgusb, regs, regd) +#define pavgusb_m2r(var, reg) mmx_m2r(pavgusb, var, reg) +#define pavgusb_r2r(regs, regd) mmx_r2r(pavgusb, regs, regd) /* AMD MMX extensions - also available in intel SSE */ -#define mmx_m2ri(op,mem,reg,imm) \ - __asm__ __volatile__ (#op " %1, %0, %%" #reg \ - : /* nothing */ \ - : "m" (mem), "i" (imm)) -#define mmx_r2ri(op,regs,regd,imm) \ - __asm__ __volatile__ (#op " %0, %%" #regs ", %%" #regd \ - : /* nothing */ \ - : "i" (imm) ) +#define mmx_m2ri(op, mem, reg, imm) \ + __asm__ __volatile__ (#op " %1, %0, %%" #reg \ + : /* nothing */ \ + : "m" (mem), "i" (imm)) +#define mmx_r2ri(op, regs, regd, imm) \ + __asm__ __volatile__ (#op " %0, %%" #regs ", %%" #regd \ + : /* nothing */ \ + : "i" (imm)) -#define mmx_fetch(mem,hint) \ - __asm__ __volatile__ ("prefetch" #hint " %0" \ - : /* nothing */ \ - : "m" (mem)) +#define mmx_fetch(mem, hint) \ + __asm__ __volatile__ ("prefetch" #hint " %0" \ + : /* nothing */ \ + : "m" (mem)) -#define maskmovq(regs,maskreg) mmx_r2ri (maskmovq, regs, maskreg) +#define maskmovq(regs, maskreg) mmx_r2ri(maskmovq, regs, maskreg) -#define movntq_r2m(mmreg,var) mmx_r2m (movntq, mmreg, var) +#define movntq_r2m(mmreg, var) mmx_r2m(movntq, mmreg, var) -#define pavgb_m2r(var,reg) mmx_m2r (pavgb, var, reg) -#define pavgb_r2r(regs,regd) mmx_r2r (pavgb, regs, regd) -#define pavgw_m2r(var,reg) mmx_m2r (pavgw, var, reg) -#define pavgw_r2r(regs,regd) mmx_r2r (pavgw, regs, regd) +#define pavgb_m2r(var, reg) mmx_m2r(pavgb, var, reg) +#define pavgb_r2r(regs, regd) mmx_r2r(pavgb, regs, regd) +#define pavgw_m2r(var, reg) mmx_m2r(pavgw, var, reg) +#define pavgw_r2r(regs, regd) mmx_r2r(pavgw, regs, regd) -#define pextrw_r2r(mmreg,reg,imm) mmx_r2ri (pextrw, mmreg, reg, imm) +#define pextrw_r2r(mmreg, reg, imm) mmx_r2ri(pextrw, mmreg, reg, imm) -#define pinsrw_r2r(reg,mmreg,imm) mmx_r2ri (pinsrw, reg, mmreg, imm) +#define pinsrw_r2r(reg, mmreg, imm) mmx_r2ri(pinsrw, reg, mmreg, imm) -#define pmaxsw_m2r(var,reg) mmx_m2r (pmaxsw, var, reg) -#define pmaxsw_r2r(regs,regd) mmx_r2r (pmaxsw, regs, regd) +#define pmaxsw_m2r(var, reg) mmx_m2r(pmaxsw, var, reg) +#define pmaxsw_r2r(regs, regd) mmx_r2r(pmaxsw, regs, regd) -#define pmaxub_m2r(var,reg) mmx_m2r (pmaxub, var, reg) -#define pmaxub_r2r(regs,regd) mmx_r2r (pmaxub, regs, regd) +#define pmaxub_m2r(var, reg) mmx_m2r(pmaxub, var, reg) +#define pmaxub_r2r(regs, regd) mmx_r2r(pmaxub, regs, regd) -#define pminsw_m2r(var,reg) mmx_m2r (pminsw, var, reg) -#define pminsw_r2r(regs,regd) mmx_r2r (pminsw, regs, regd) +#define pminsw_m2r(var, reg) mmx_m2r(pminsw, var, reg) +#define pminsw_r2r(regs, regd) mmx_r2r(pminsw, regs, regd) -#define pminub_m2r(var,reg) mmx_m2r (pminub, var, reg) -#define pminub_r2r(regs,regd) mmx_r2r (pminub, regs, regd) +#define pminub_m2r(var, reg) mmx_m2r(pminub, var, reg) +#define pminub_r2r(regs, regd) mmx_r2r(pminub, regs, regd) -#define pmovmskb(mmreg,reg) \ - __asm__ __volatile__ ("movmskps %" #mmreg ", %" #reg) +#define pmovmskb(mmreg, reg) \ + __asm__ __volatile__ ("movmskps %" #mmreg ", %" #reg) -#define pmulhuw_m2r(var,reg) mmx_m2r (pmulhuw, var, reg) -#define pmulhuw_r2r(regs,regd) mmx_r2r (pmulhuw, regs, regd) +#define pmulhuw_m2r(var, reg) mmx_m2r(pmulhuw, var, reg) +#define pmulhuw_r2r(regs, regd) mmx_r2r(pmulhuw, regs, regd) -#define prefetcht0(mem) mmx_fetch (mem, t0) -#define prefetcht1(mem) mmx_fetch (mem, t1) -#define prefetcht2(mem) mmx_fetch (mem, t2) -#define prefetchnta(mem) mmx_fetch (mem, nta) +#define prefetcht0(mem) mmx_fetch(mem, t0) +#define prefetcht1(mem) mmx_fetch(mem, t1) +#define prefetcht2(mem) mmx_fetch(mem, t2) +#define prefetchnta(mem) mmx_fetch(mem, nta) -#define psadbw_m2r(var,reg) mmx_m2r (psadbw, var, reg) -#define psadbw_r2r(regs,regd) mmx_r2r (psadbw, regs, regd) +#define psadbw_m2r(var, reg) mmx_m2r(psadbw, var, reg) +#define psadbw_r2r(regs, regd) mmx_r2r(psadbw, regs, regd) -#define pshufw_m2r(var,reg,imm) mmx_m2ri(pshufw, var, reg, imm) -#define pshufw_r2r(regs,regd,imm) mmx_r2ri(pshufw, regs, regd, imm) +#define pshufw_m2r(var, reg, imm) mmx_m2ri(pshufw, var, reg, imm) +#define pshufw_r2r(regs, regd, imm) mmx_r2ri(pshufw, regs, regd, imm) -#define sfence() __asm__ __volatile__ ("sfence\n\t") +#define sfence() __asm__ __volatile__ ("sfence\n\t") /* SSE2 */ -#define pshufhw_m2r(var,reg,imm) mmx_m2ri(pshufhw, var, reg, imm) -#define pshufhw_r2r(regs,regd,imm) mmx_r2ri(pshufhw, regs, regd, imm) -#define pshuflw_m2r(var,reg,imm) mmx_m2ri(pshuflw, var, reg, imm) -#define pshuflw_r2r(regs,regd,imm) mmx_r2ri(pshuflw, regs, regd, imm) - -#define pshufd_r2r(regs,regd,imm) mmx_r2ri(pshufd, regs, regd, imm) - -#define movdqa_m2r(var,reg) mmx_m2r (movdqa, var, reg) -#define movdqa_r2m(reg,var) mmx_r2m (movdqa, reg, var) -#define movdqa_r2r(regs,regd) mmx_r2r (movdqa, regs, regd) -#define movdqu_m2r(var,reg) mmx_m2r (movdqu, var, reg) -#define movdqu_r2m(reg,var) mmx_r2m (movdqu, reg, var) -#define movdqu_r2r(regs,regd) mmx_r2r (movdqu, regs, regd) +#define pshufhw_m2r(var, reg, imm) mmx_m2ri(pshufhw, var, reg, imm) +#define pshufhw_r2r(regs, regd, imm) mmx_r2ri(pshufhw, regs, regd, imm) +#define pshuflw_m2r(var, reg, imm) mmx_m2ri(pshuflw, var, reg, imm) +#define pshuflw_r2r(regs, regd, imm) mmx_r2ri(pshuflw, regs, regd, imm) + +#define pshufd_r2r(regs, regd, imm) mmx_r2ri(pshufd, regs, regd, imm) + +#define movdqa_m2r(var, reg) mmx_m2r(movdqa, var, reg) +#define movdqa_r2m(reg, var) mmx_r2m(movdqa, reg, var) +#define movdqa_r2r(regs, regd) mmx_r2r(movdqa, regs, regd) +#define movdqu_m2r(var, reg) mmx_m2r(movdqu, var, reg) +#define movdqu_r2m(reg, var) mmx_r2m(movdqu, reg, var) +#define movdqu_r2r(regs, regd) mmx_r2r(movdqu, regs, regd) -#define pmullw_r2m(reg,var) mmx_r2m (pmullw, reg, var) +#define pmullw_r2m(reg, var) mmx_r2m(pmullw, reg, var) -#define pslldq_i2r(imm,reg) mmx_i2r (pslldq, imm, reg) -#define psrldq_i2r(imm,reg) mmx_i2r (psrldq, imm, reg) +#define pslldq_i2r(imm, reg) mmx_i2r(pslldq, imm, reg) +#define psrldq_i2r(imm, reg) mmx_i2r(psrldq, imm, reg) -#define punpcklqdq_r2r(regs,regd) mmx_r2r (punpcklqdq, regs, regd) -#define punpckhqdq_r2r(regs,regd) mmx_r2r (punpckhqdq, regs, regd) +#define punpcklqdq_r2r(regs, regd) mmx_r2r(punpcklqdq, regs, regd) +#define punpckhqdq_r2r(regs, regd) mmx_r2r(punpckhqdq, regs, regd) #endif /* AVCODEC_I386MMX_H */