diff --git a/target-i386/ops_sse.h b/target-i386/ops_sse.h index 0d33ca1985..d109512d5b 100644 --- a/target-i386/ops_sse.h +++ b/target-i386/ops_sse.h @@ -203,12 +203,15 @@ void glue(helper_psrldq, SUFFIX)(Reg *d, Reg *s) int shift, i; shift = s->L(0); - if (shift > 16) + if (shift > 16) { shift = 16; - for(i = 0; i < 16 - shift; i++) + } + for (i = 0; i < 16 - shift; i++) { d->B(i) = d->B(i + shift); - for(i = 16 - shift; i < 16; i++) + } + for (i = 16 - shift; i < 16; i++) { d->B(i) = 0; + } } void glue(helper_pslldq, SUFFIX)(Reg *d, Reg *s) @@ -216,112 +219,119 @@ void glue(helper_pslldq, SUFFIX)(Reg *d, Reg *s) int shift, i; shift = s->L(0); - if (shift > 16) + if (shift > 16) { shift = 16; - for(i = 15; i >= shift; i--) + } + for (i = 15; i >= shift; i--) { d->B(i) = d->B(i - shift); - for(i = 0; i < shift; i++) + } + for (i = 0; i < shift; i++) { d->B(i) = 0; + } } #endif -#define SSE_HELPER_B(name, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->B(0) = F(d->B(0), s->B(0));\ - d->B(1) = F(d->B(1), s->B(1));\ - d->B(2) = F(d->B(2), s->B(2));\ - d->B(3) = F(d->B(3), s->B(3));\ - d->B(4) = F(d->B(4), s->B(4));\ - d->B(5) = F(d->B(5), s->B(5));\ - d->B(6) = F(d->B(6), s->B(6));\ - d->B(7) = F(d->B(7), s->B(7));\ - XMM_ONLY(\ - d->B(8) = F(d->B(8), s->B(8));\ - d->B(9) = F(d->B(9), s->B(9));\ - d->B(10) = F(d->B(10), s->B(10));\ - d->B(11) = F(d->B(11), s->B(11));\ - d->B(12) = F(d->B(12), s->B(12));\ - d->B(13) = F(d->B(13), s->B(13));\ - d->B(14) = F(d->B(14), s->B(14));\ - d->B(15) = F(d->B(15), s->B(15));\ - )\ -} +#define SSE_HELPER_B(name, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->B(0) = F(d->B(0), s->B(0)); \ + d->B(1) = F(d->B(1), s->B(1)); \ + d->B(2) = F(d->B(2), s->B(2)); \ + d->B(3) = F(d->B(3), s->B(3)); \ + d->B(4) = F(d->B(4), s->B(4)); \ + d->B(5) = F(d->B(5), s->B(5)); \ + d->B(6) = F(d->B(6), s->B(6)); \ + d->B(7) = F(d->B(7), s->B(7)); \ + XMM_ONLY( \ + d->B(8) = F(d->B(8), s->B(8)); \ + d->B(9) = F(d->B(9), s->B(9)); \ + d->B(10) = F(d->B(10), s->B(10)); \ + d->B(11) = F(d->B(11), s->B(11)); \ + d->B(12) = F(d->B(12), s->B(12)); \ + d->B(13) = F(d->B(13), s->B(13)); \ + d->B(14) = F(d->B(14), s->B(14)); \ + d->B(15) = F(d->B(15), s->B(15)); \ + ) \ + } -#define SSE_HELPER_W(name, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->W(0) = F(d->W(0), s->W(0));\ - d->W(1) = F(d->W(1), s->W(1));\ - d->W(2) = F(d->W(2), s->W(2));\ - d->W(3) = F(d->W(3), s->W(3));\ - XMM_ONLY(\ - d->W(4) = F(d->W(4), s->W(4));\ - d->W(5) = F(d->W(5), s->W(5));\ - d->W(6) = F(d->W(6), s->W(6));\ - d->W(7) = F(d->W(7), s->W(7));\ - )\ -} +#define SSE_HELPER_W(name, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->W(0) = F(d->W(0), s->W(0)); \ + d->W(1) = F(d->W(1), s->W(1)); \ + d->W(2) = F(d->W(2), s->W(2)); \ + d->W(3) = F(d->W(3), s->W(3)); \ + XMM_ONLY( \ + d->W(4) = F(d->W(4), s->W(4)); \ + d->W(5) = F(d->W(5), s->W(5)); \ + d->W(6) = F(d->W(6), s->W(6)); \ + d->W(7) = F(d->W(7), s->W(7)); \ + ) \ + } -#define SSE_HELPER_L(name, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->L(0) = F(d->L(0), s->L(0));\ - d->L(1) = F(d->L(1), s->L(1));\ - XMM_ONLY(\ - d->L(2) = F(d->L(2), s->L(2));\ - d->L(3) = F(d->L(3), s->L(3));\ - )\ -} +#define SSE_HELPER_L(name, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->L(0) = F(d->L(0), s->L(0)); \ + d->L(1) = F(d->L(1), s->L(1)); \ + XMM_ONLY( \ + d->L(2) = F(d->L(2), s->L(2)); \ + d->L(3) = F(d->L(3), s->L(3)); \ + ) \ + } -#define SSE_HELPER_Q(name, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->Q(0) = F(d->Q(0), s->Q(0));\ - XMM_ONLY(\ - d->Q(1) = F(d->Q(1), s->Q(1));\ - )\ -} +#define SSE_HELPER_Q(name, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->Q(0) = F(d->Q(0), s->Q(0)); \ + XMM_ONLY( \ + d->Q(1) = F(d->Q(1), s->Q(1)); \ + ) \ + } #if SHIFT == 0 static inline int satub(int x) { - if (x < 0) + if (x < 0) { return 0; - else if (x > 255) + } else if (x > 255) { return 255; - else + } else { return x; + } } static inline int satuw(int x) { - if (x < 0) + if (x < 0) { return 0; - else if (x > 65535) + } else if (x > 65535) { return 65535; - else + } else { return x; + } } static inline int satsb(int x) { - if (x < -128) + if (x < -128) { return -128; - else if (x > 127) + } else if (x > 127) { return 127; - else + } else { return x; + } } static inline int satsw(int x) { - if (x < -32768) + if (x < -32768) { return -32768; - else if (x > 32767) + } else if (x > 32767) { return 32767; - else + } else { return x; + } } #define FADD(a, b) ((a) + (b)) @@ -340,22 +350,22 @@ static inline int satsw(int x) #define FMAXUB(a, b) ((a) > (b)) ? (a) : (b) #define FMAXSW(a, b) ((int16_t)(a) > (int16_t)(b)) ? (a) : (b) -#define FAND(a, b) (a) & (b) +#define FAND(a, b) ((a) & (b)) #define FANDN(a, b) ((~(a)) & (b)) -#define FOR(a, b) (a) | (b) -#define FXOR(a, b) (a) ^ (b) +#define FOR(a, b) ((a) | (b)) +#define FXOR(a, b) ((a) ^ (b)) -#define FCMPGTB(a, b) (int8_t)(a) > (int8_t)(b) ? -1 : 0 -#define FCMPGTW(a, b) (int16_t)(a) > (int16_t)(b) ? -1 : 0 -#define FCMPGTL(a, b) (int32_t)(a) > (int32_t)(b) ? -1 : 0 -#define FCMPEQ(a, b) (a) == (b) ? -1 : 0 +#define FCMPGTB(a, b) ((int8_t)(a) > (int8_t)(b) ? -1 : 0) +#define FCMPGTW(a, b) ((int16_t)(a) > (int16_t)(b) ? -1 : 0) +#define FCMPGTL(a, b) ((int32_t)(a) > (int32_t)(b) ? -1 : 0) +#define FCMPEQ(a, b) ((a) == (b) ? -1 : 0) -#define FMULLW(a, b) (a) * (b) -#define FMULHRW(a, b) ((int16_t)(a) * (int16_t)(b) + 0x8000) >> 16 -#define FMULHUW(a, b) (a) * (b) >> 16 -#define FMULHW(a, b) (int16_t)(a) * (int16_t)(b) >> 16 +#define FMULLW(a, b) ((a) * (b)) +#define FMULHRW(a, b) (((int16_t)(a) * (int16_t)(b) + 0x8000) >> 16) +#define FMULHUW(a, b) ((a) * (b) >> 16) +#define FMULHW(a, b) ((int16_t)(a) * (int16_t)(b) >> 16) -#define FAVG(a, b) ((a) + (b) + 1) >> 1 +#define FAVG(a, b) (((a) + (b) + 1) >> 1) #endif SSE_HELPER_B(helper_paddb, FADD) @@ -407,7 +417,7 @@ SSE_HELPER_W(helper_pmulhw, FMULHW) SSE_HELPER_B(helper_pavgb, FAVG) SSE_HELPER_W(helper_pavgw, FAVG) -void glue(helper_pmuludq, SUFFIX) (Reg *d, Reg *s) +void glue(helper_pmuludq, SUFFIX)(Reg *d, Reg *s) { d->Q(0) = (uint64_t)s->L(0) * (uint64_t)d->L(0); #if SHIFT == 1 @@ -415,26 +425,27 @@ void glue(helper_pmuludq, SUFFIX) (Reg *d, Reg *s) #endif } -void glue(helper_pmaddwd, SUFFIX) (Reg *d, Reg *s) +void glue(helper_pmaddwd, SUFFIX)(Reg *d, Reg *s) { int i; - for(i = 0; i < (2 << SHIFT); i++) { - d->L(i) = (int16_t)s->W(2*i) * (int16_t)d->W(2*i) + - (int16_t)s->W(2*i+1) * (int16_t)d->W(2*i+1); + for (i = 0; i < (2 << SHIFT); i++) { + d->L(i) = (int16_t)s->W(2 * i) * (int16_t)d->W(2 * i) + + (int16_t)s->W(2 * i + 1) * (int16_t)d->W(2 * i + 1); } } #if SHIFT == 0 static inline int abs1(int a) { - if (a < 0) + if (a < 0) { return -a; - else + } else { return a; + } } #endif -void glue(helper_psadbw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_psadbw, SUFFIX)(Reg *d, Reg *s) { unsigned int val; @@ -462,16 +473,18 @@ void glue(helper_psadbw, SUFFIX) (Reg *d, Reg *s) #endif } -void glue(helper_maskmov, SUFFIX) (Reg *d, Reg *s, target_ulong a0) +void glue(helper_maskmov, SUFFIX)(Reg *d, Reg *s, target_ulong a0) { int i; - for(i = 0; i < (8 << SHIFT); i++) { - if (s->B(i) & 0x80) + + for (i = 0; i < (8 << SHIFT); i++) { + if (s->B(i) & 0x80) { stb(a0 + i, d->B(i)); + } } } -void glue(helper_movl_mm_T0, SUFFIX) (Reg *d, uint32_t val) +void glue(helper_movl_mm_T0, SUFFIX)(Reg *d, uint32_t val) { d->L(0) = val; d->L(1) = 0; @@ -481,7 +494,7 @@ void glue(helper_movl_mm_T0, SUFFIX) (Reg *d, uint32_t val) } #ifdef TARGET_X86_64 -void glue(helper_movq_mm_T0, SUFFIX) (Reg *d, uint64_t val) +void glue(helper_movq_mm_T0, SUFFIX)(Reg *d, uint64_t val) { d->Q(0) = val; #if SHIFT == 1 @@ -491,9 +504,10 @@ void glue(helper_movq_mm_T0, SUFFIX) (Reg *d, uint64_t val) #endif #if SHIFT == 0 -void glue(helper_pshufw, SUFFIX) (Reg *d, Reg *s, int order) +void glue(helper_pshufw, SUFFIX)(Reg *d, Reg *s, int order) { Reg r; + r.W(0) = s->W(order & 3); r.W(1) = s->W((order >> 2) & 3); r.W(2) = s->W((order >> 4) & 3); @@ -504,6 +518,7 @@ void glue(helper_pshufw, SUFFIX) (Reg *d, Reg *s, int order) void helper_shufps(Reg *d, Reg *s, int order) { Reg r; + r.L(0) = d->L(order & 3); r.L(1) = d->L((order >> 2) & 3); r.L(2) = s->L((order >> 4) & 3); @@ -514,14 +529,16 @@ void helper_shufps(Reg *d, Reg *s, int order) void helper_shufpd(Reg *d, Reg *s, int order) { Reg r; + r.Q(0) = d->Q(order & 1); r.Q(1) = s->Q((order >> 1) & 1); *d = r; } -void glue(helper_pshufd, SUFFIX) (Reg *d, Reg *s, int order) +void glue(helper_pshufd, SUFFIX)(Reg *d, Reg *s, int order) { Reg r; + r.L(0) = s->L(order & 3); r.L(1) = s->L((order >> 2) & 3); r.L(2) = s->L((order >> 4) & 3); @@ -529,9 +546,10 @@ void glue(helper_pshufd, SUFFIX) (Reg *d, Reg *s, int order) *d = r; } -void glue(helper_pshuflw, SUFFIX) (Reg *d, Reg *s, int order) +void glue(helper_pshuflw, SUFFIX)(Reg *d, Reg *s, int order) { Reg r; + r.W(0) = s->W(order & 3); r.W(1) = s->W((order >> 2) & 3); r.W(2) = s->W((order >> 4) & 3); @@ -540,9 +558,10 @@ void glue(helper_pshuflw, SUFFIX) (Reg *d, Reg *s, int order) *d = r; } -void glue(helper_pshufhw, SUFFIX) (Reg *d, Reg *s, int order) +void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order) { Reg r; + r.Q(0) = s->Q(0); r.W(4) = s->W(4 + (order & 3)); r.W(5) = s->W(4 + ((order >> 2) & 3)); @@ -556,29 +575,30 @@ void glue(helper_pshufhw, SUFFIX) (Reg *d, Reg *s, int order) /* FPU ops */ /* XXX: not accurate */ -#define SSE_HELPER_S(name, F)\ -void helper_ ## name ## ps (Reg *d, Reg *s)\ -{\ - d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));\ - d->XMM_S(1) = F(32, d->XMM_S(1), s->XMM_S(1));\ - d->XMM_S(2) = F(32, d->XMM_S(2), s->XMM_S(2));\ - d->XMM_S(3) = F(32, d->XMM_S(3), s->XMM_S(3));\ -}\ -\ -void helper_ ## name ## ss (Reg *d, Reg *s)\ -{\ - d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0));\ -}\ -void helper_ ## name ## pd (Reg *d, Reg *s)\ -{\ - d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));\ - d->XMM_D(1) = F(64, d->XMM_D(1), s->XMM_D(1));\ -}\ -\ -void helper_ ## name ## sd (Reg *d, Reg *s)\ -{\ - d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0));\ -} +#define SSE_HELPER_S(name, F) \ + void helper_ ## name ## ps(Reg *d, Reg *s) \ + { \ + d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0)); \ + d->XMM_S(1) = F(32, d->XMM_S(1), s->XMM_S(1)); \ + d->XMM_S(2) = F(32, d->XMM_S(2), s->XMM_S(2)); \ + d->XMM_S(3) = F(32, d->XMM_S(3), s->XMM_S(3)); \ + } \ + \ + void helper_ ## name ## ss(Reg *d, Reg *s) \ + { \ + d->XMM_S(0) = F(32, d->XMM_S(0), s->XMM_S(0)); \ + } \ + \ + void helper_ ## name ## pd(Reg *d, Reg *s) \ + { \ + d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0)); \ + d->XMM_D(1) = F(64, d->XMM_D(1), s->XMM_D(1)); \ + } \ + \ + void helper_ ## name ## sd(Reg *d, Reg *s) \ + { \ + d->XMM_D(0) = F(64, d->XMM_D(0), s->XMM_D(0)); \ + } #define FPU_ADD(size, a, b) float ## size ## _add(a, b, &env->sse_status) #define FPU_SUB(size, a, b) float ## size ## _sub(a, b, &env->sse_status) @@ -590,8 +610,10 @@ void helper_ ## name ## sd (Reg *d, Reg *s)\ * special cases right: for min and max Intel specifies that (-0,0), * (NaN, anything) and (anything, NaN) return the second argument. */ -#define FPU_MIN(size, a, b) float ## size ## _lt(a, b, &env->sse_status) ? (a) : (b) -#define FPU_MAX(size, a, b) float ## size ## _lt(b, a, &env->sse_status) ? (a) : (b) +#define FPU_MIN(size, a, b) \ + (float ## size ## _lt(a, b, &env->sse_status) ? (a) : (b)) +#define FPU_MAX(size, a, b) \ + (float ## size ## _lt(b, a, &env->sse_status) ? (a) : (b)) SSE_HELPER_S(add, FPU_ADD) SSE_HELPER_S(sub, FPU_SUB) @@ -606,6 +628,7 @@ SSE_HELPER_S(sqrt, FPU_SQRT) void helper_cvtps2pd(Reg *d, Reg *s) { float32 s0, s1; + s0 = s->XMM_S(0); s1 = s->XMM_S(1); d->XMM_D(0) = float32_to_float64(s0, &env->sse_status); @@ -641,6 +664,7 @@ void helper_cvtdq2ps(Reg *d, Reg *s) void helper_cvtdq2pd(Reg *d, Reg *s) { int32_t l0, l1; + l0 = (int32_t)s->XMM_L(0); l1 = (int32_t)s->XMM_L(1); d->XMM_D(0) = int32_to_float64(l0, &env->sse_status); @@ -864,6 +888,7 @@ void helper_insertq_i(XMMReg *d, int index, int length) void helper_haddps(XMMReg *d, XMMReg *s) { XMMReg r; + r.XMM_S(0) = float32_add(d->XMM_S(0), d->XMM_S(1), &env->sse_status); r.XMM_S(1) = float32_add(d->XMM_S(2), d->XMM_S(3), &env->sse_status); r.XMM_S(2) = float32_add(s->XMM_S(0), s->XMM_S(1), &env->sse_status); @@ -874,6 +899,7 @@ void helper_haddps(XMMReg *d, XMMReg *s) void helper_haddpd(XMMReg *d, XMMReg *s) { XMMReg r; + r.XMM_D(0) = float64_add(d->XMM_D(0), d->XMM_D(1), &env->sse_status); r.XMM_D(1) = float64_add(s->XMM_D(0), s->XMM_D(1), &env->sse_status); *d = r; @@ -882,6 +908,7 @@ void helper_haddpd(XMMReg *d, XMMReg *s) void helper_hsubps(XMMReg *d, XMMReg *s) { XMMReg r; + r.XMM_S(0) = float32_sub(d->XMM_S(0), d->XMM_S(1), &env->sse_status); r.XMM_S(1) = float32_sub(d->XMM_S(2), d->XMM_S(3), &env->sse_status); r.XMM_S(2) = float32_sub(s->XMM_S(0), s->XMM_S(1), &env->sse_status); @@ -892,6 +919,7 @@ void helper_hsubps(XMMReg *d, XMMReg *s) void helper_hsubpd(XMMReg *d, XMMReg *s) { XMMReg r; + r.XMM_D(0) = float64_sub(d->XMM_D(0), d->XMM_D(1), &env->sse_status); r.XMM_D(1) = float64_sub(s->XMM_D(0), s->XMM_D(1), &env->sse_status); *d = r; @@ -912,38 +940,47 @@ void helper_addsubpd(XMMReg *d, XMMReg *s) } /* XXX: unordered */ -#define SSE_HELPER_CMP(name, F)\ -void helper_ ## name ## ps (Reg *d, Reg *s)\ -{\ - d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0));\ - d->XMM_L(1) = F(32, d->XMM_S(1), s->XMM_S(1));\ - d->XMM_L(2) = F(32, d->XMM_S(2), s->XMM_S(2));\ - d->XMM_L(3) = F(32, d->XMM_S(3), s->XMM_S(3));\ -}\ -\ -void helper_ ## name ## ss (Reg *d, Reg *s)\ -{\ - d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0));\ -}\ -void helper_ ## name ## pd (Reg *d, Reg *s)\ -{\ - d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0));\ - d->XMM_Q(1) = F(64, d->XMM_D(1), s->XMM_D(1));\ -}\ -\ -void helper_ ## name ## sd (Reg *d, Reg *s)\ -{\ - d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0));\ -} +#define SSE_HELPER_CMP(name, F) \ + void helper_ ## name ## ps(Reg *d, Reg *s) \ + { \ + d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0)); \ + d->XMM_L(1) = F(32, d->XMM_S(1), s->XMM_S(1)); \ + d->XMM_L(2) = F(32, d->XMM_S(2), s->XMM_S(2)); \ + d->XMM_L(3) = F(32, d->XMM_S(3), s->XMM_S(3)); \ + } \ + \ + void helper_ ## name ## ss(Reg *d, Reg *s) \ + { \ + d->XMM_L(0) = F(32, d->XMM_S(0), s->XMM_S(0)); \ + } \ + \ + void helper_ ## name ## pd(Reg *d, Reg *s) \ + { \ + d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0)); \ + d->XMM_Q(1) = F(64, d->XMM_D(1), s->XMM_D(1)); \ + } \ + \ + void helper_ ## name ## sd(Reg *d, Reg *s) \ + { \ + d->XMM_Q(0) = F(64, d->XMM_D(0), s->XMM_D(0)); \ + } -#define FPU_CMPEQ(size, a, b) float ## size ## _eq_quiet(a, b, &env->sse_status) ? -1 : 0 -#define FPU_CMPLT(size, a, b) float ## size ## _lt(a, b, &env->sse_status) ? -1 : 0 -#define FPU_CMPLE(size, a, b) float ## size ## _le(a, b, &env->sse_status) ? -1 : 0 -#define FPU_CMPUNORD(size, a, b) float ## size ## _unordered_quiet(a, b, &env->sse_status) ? - 1 : 0 -#define FPU_CMPNEQ(size, a, b) float ## size ## _eq_quiet(a, b, &env->sse_status) ? 0 : -1 -#define FPU_CMPNLT(size, a, b) float ## size ## _lt(a, b, &env->sse_status) ? 0 : -1 -#define FPU_CMPNLE(size, a, b) float ## size ## _le(a, b, &env->sse_status) ? 0 : -1 -#define FPU_CMPORD(size, a, b) float ## size ## _unordered_quiet(a, b, &env->sse_status) ? 0 : -1 +#define FPU_CMPEQ(size, a, b) \ + (float ## size ## _eq_quiet(a, b, &env->sse_status) ? -1 : 0) +#define FPU_CMPLT(size, a, b) \ + (float ## size ## _lt(a, b, &env->sse_status) ? -1 : 0) +#define FPU_CMPLE(size, a, b) \ + (float ## size ## _le(a, b, &env->sse_status) ? -1 : 0) +#define FPU_CMPUNORD(size, a, b) \ + (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? -1 : 0) +#define FPU_CMPNEQ(size, a, b) \ + (float ## size ## _eq_quiet(a, b, &env->sse_status) ? 0 : -1) +#define FPU_CMPNLT(size, a, b) \ + (float ## size ## _lt(a, b, &env->sse_status) ? 0 : -1) +#define FPU_CMPNLE(size, a, b) \ + (float ## size ## _le(a, b, &env->sse_status) ? 0 : -1) +#define FPU_CMPORD(size, a, b) \ + (float ## size ## _unordered_quiet(a, b, &env->sse_status) ? 0 : -1) SSE_HELPER_CMP(cmpeq, FPU_CMPEQ) SSE_HELPER_CMP(cmplt, FPU_CMPLT) @@ -1003,6 +1040,7 @@ void helper_comisd(Reg *d, Reg *s) uint32_t helper_movmskps(Reg *s) { int b0, b1, b2, b3; + b0 = s->XMM_L(0) >> 31; b1 = s->XMM_L(1) >> 31; b2 = s->XMM_L(2) >> 31; @@ -1013,6 +1051,7 @@ uint32_t helper_movmskps(Reg *s) uint32_t helper_movmskpd(Reg *s) { int b0, b1; + b0 = s->XMM_L(1) >> 31; b1 = s->XMM_L(3) >> 31; return b0 | (b1 << 1); @@ -1023,6 +1062,7 @@ uint32_t helper_movmskpd(Reg *s) uint32_t glue(helper_pmovmskb, SUFFIX)(Reg *s) { uint32_t val; + val = 0; val |= (s->B(0) >> 7); val |= (s->B(1) >> 6) & 0x02; @@ -1045,7 +1085,7 @@ uint32_t glue(helper_pmovmskb, SUFFIX)(Reg *s) return val; } -void glue(helper_packsswb, SUFFIX) (Reg *d, Reg *s) +void glue(helper_packsswb, SUFFIX)(Reg *d, Reg *s) { Reg r; @@ -1072,7 +1112,7 @@ void glue(helper_packsswb, SUFFIX) (Reg *d, Reg *s) *d = r; } -void glue(helper_packuswb, SUFFIX) (Reg *d, Reg *s) +void glue(helper_packuswb, SUFFIX)(Reg *d, Reg *s) { Reg r; @@ -1099,7 +1139,7 @@ void glue(helper_packuswb, SUFFIX) (Reg *d, Reg *s) *d = r; } -void glue(helper_packssdw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_packssdw, SUFFIX)(Reg *d, Reg *s) { Reg r; @@ -1118,73 +1158,74 @@ void glue(helper_packssdw, SUFFIX) (Reg *d, Reg *s) *d = r; } -#define UNPCK_OP(base_name, base) \ - \ -void glue(helper_punpck ## base_name ## bw, SUFFIX) (Reg *d, Reg *s) \ -{ \ - Reg r; \ - \ - r.B(0) = d->B((base << (SHIFT + 2)) + 0); \ - r.B(1) = s->B((base << (SHIFT + 2)) + 0); \ - r.B(2) = d->B((base << (SHIFT + 2)) + 1); \ - r.B(3) = s->B((base << (SHIFT + 2)) + 1); \ - r.B(4) = d->B((base << (SHIFT + 2)) + 2); \ - r.B(5) = s->B((base << (SHIFT + 2)) + 2); \ - r.B(6) = d->B((base << (SHIFT + 2)) + 3); \ - r.B(7) = s->B((base << (SHIFT + 2)) + 3); \ -XMM_ONLY( \ - r.B(8) = d->B((base << (SHIFT + 2)) + 4); \ - r.B(9) = s->B((base << (SHIFT + 2)) + 4); \ - r.B(10) = d->B((base << (SHIFT + 2)) + 5); \ - r.B(11) = s->B((base << (SHIFT + 2)) + 5); \ - r.B(12) = d->B((base << (SHIFT + 2)) + 6); \ - r.B(13) = s->B((base << (SHIFT + 2)) + 6); \ - r.B(14) = d->B((base << (SHIFT + 2)) + 7); \ - r.B(15) = s->B((base << (SHIFT + 2)) + 7); \ -) \ - *d = r; \ -} \ - \ -void glue(helper_punpck ## base_name ## wd, SUFFIX) (Reg *d, Reg *s) \ -{ \ - Reg r; \ - \ - r.W(0) = d->W((base << (SHIFT + 1)) + 0); \ - r.W(1) = s->W((base << (SHIFT + 1)) + 0); \ - r.W(2) = d->W((base << (SHIFT + 1)) + 1); \ - r.W(3) = s->W((base << (SHIFT + 1)) + 1); \ -XMM_ONLY( \ - r.W(4) = d->W((base << (SHIFT + 1)) + 2); \ - r.W(5) = s->W((base << (SHIFT + 1)) + 2); \ - r.W(6) = d->W((base << (SHIFT + 1)) + 3); \ - r.W(7) = s->W((base << (SHIFT + 1)) + 3); \ -) \ - *d = r; \ -} \ - \ -void glue(helper_punpck ## base_name ## dq, SUFFIX) (Reg *d, Reg *s) \ -{ \ - Reg r; \ - \ - r.L(0) = d->L((base << SHIFT) + 0); \ - r.L(1) = s->L((base << SHIFT) + 0); \ -XMM_ONLY( \ - r.L(2) = d->L((base << SHIFT) + 1); \ - r.L(3) = s->L((base << SHIFT) + 1); \ -) \ - *d = r; \ -} \ - \ -XMM_ONLY( \ -void glue(helper_punpck ## base_name ## qdq, SUFFIX) (Reg *d, Reg *s) \ -{ \ - Reg r; \ - \ - r.Q(0) = d->Q(base); \ - r.Q(1) = s->Q(base); \ - *d = r; \ -} \ -) +#define UNPCK_OP(base_name, base) \ + \ + void glue(helper_punpck ## base_name ## bw, SUFFIX)(Reg *d, Reg *s) \ + { \ + Reg r; \ + \ + r.B(0) = d->B((base << (SHIFT + 2)) + 0); \ + r.B(1) = s->B((base << (SHIFT + 2)) + 0); \ + r.B(2) = d->B((base << (SHIFT + 2)) + 1); \ + r.B(3) = s->B((base << (SHIFT + 2)) + 1); \ + r.B(4) = d->B((base << (SHIFT + 2)) + 2); \ + r.B(5) = s->B((base << (SHIFT + 2)) + 2); \ + r.B(6) = d->B((base << (SHIFT + 2)) + 3); \ + r.B(7) = s->B((base << (SHIFT + 2)) + 3); \ + XMM_ONLY( \ + r.B(8) = d->B((base << (SHIFT + 2)) + 4); \ + r.B(9) = s->B((base << (SHIFT + 2)) + 4); \ + r.B(10) = d->B((base << (SHIFT + 2)) + 5); \ + r.B(11) = s->B((base << (SHIFT + 2)) + 5); \ + r.B(12) = d->B((base << (SHIFT + 2)) + 6); \ + r.B(13) = s->B((base << (SHIFT + 2)) + 6); \ + r.B(14) = d->B((base << (SHIFT + 2)) + 7); \ + r.B(15) = s->B((base << (SHIFT + 2)) + 7); \ + ) \ + *d = r; \ + } \ + \ + void glue(helper_punpck ## base_name ## wd, SUFFIX)(Reg *d, Reg *s) \ + { \ + Reg r; \ + \ + r.W(0) = d->W((base << (SHIFT + 1)) + 0); \ + r.W(1) = s->W((base << (SHIFT + 1)) + 0); \ + r.W(2) = d->W((base << (SHIFT + 1)) + 1); \ + r.W(3) = s->W((base << (SHIFT + 1)) + 1); \ + XMM_ONLY( \ + r.W(4) = d->W((base << (SHIFT + 1)) + 2); \ + r.W(5) = s->W((base << (SHIFT + 1)) + 2); \ + r.W(6) = d->W((base << (SHIFT + 1)) + 3); \ + r.W(7) = s->W((base << (SHIFT + 1)) + 3); \ + ) \ + *d = r; \ + } \ + \ + void glue(helper_punpck ## base_name ## dq, SUFFIX)(Reg *d, Reg *s) \ + { \ + Reg r; \ + \ + r.L(0) = d->L((base << SHIFT) + 0); \ + r.L(1) = s->L((base << SHIFT) + 0); \ + XMM_ONLY( \ + r.L(2) = d->L((base << SHIFT) + 1); \ + r.L(3) = s->L((base << SHIFT) + 1); \ + ) \ + *d = r; \ + } \ + \ + XMM_ONLY( \ + void glue(helper_punpck ## base_name ## qdq, SUFFIX)(Reg *d, \ + Reg *s) \ + { \ + Reg r; \ + \ + r.Q(0) = d->Q(base); \ + r.Q(1) = s->Q(base); \ + *d = r; \ + } \ + ) UNPCK_OP(l, 0) UNPCK_OP(h, 1) @@ -1211,13 +1252,16 @@ void helper_pf2id(MMXReg *d, MMXReg *s) void helper_pf2iw(MMXReg *d, MMXReg *s) { - d->MMX_L(0) = satsw(float32_to_int32_round_to_zero(s->MMX_S(0), &env->mmx_status)); - d->MMX_L(1) = satsw(float32_to_int32_round_to_zero(s->MMX_S(1), &env->mmx_status)); + d->MMX_L(0) = satsw(float32_to_int32_round_to_zero(s->MMX_S(0), + &env->mmx_status)); + d->MMX_L(1) = satsw(float32_to_int32_round_to_zero(s->MMX_S(1), + &env->mmx_status)); } void helper_pfacc(MMXReg *d, MMXReg *s) { MMXReg r; + r.MMX_S(0) = float32_add(d->MMX_S(0), d->MMX_S(1), &env->mmx_status); r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status); *d = r; @@ -1231,36 +1275,46 @@ void helper_pfadd(MMXReg *d, MMXReg *s) void helper_pfcmpeq(MMXReg *d, MMXReg *s) { - d->MMX_L(0) = float32_eq_quiet(d->MMX_S(0), s->MMX_S(0), &env->mmx_status) ? -1 : 0; - d->MMX_L(1) = float32_eq_quiet(d->MMX_S(1), s->MMX_S(1), &env->mmx_status) ? -1 : 0; + d->MMX_L(0) = float32_eq_quiet(d->MMX_S(0), s->MMX_S(0), + &env->mmx_status) ? -1 : 0; + d->MMX_L(1) = float32_eq_quiet(d->MMX_S(1), s->MMX_S(1), + &env->mmx_status) ? -1 : 0; } void helper_pfcmpge(MMXReg *d, MMXReg *s) { - d->MMX_L(0) = float32_le(s->MMX_S(0), d->MMX_S(0), &env->mmx_status) ? -1 : 0; - d->MMX_L(1) = float32_le(s->MMX_S(1), d->MMX_S(1), &env->mmx_status) ? -1 : 0; + d->MMX_L(0) = float32_le(s->MMX_S(0), d->MMX_S(0), + &env->mmx_status) ? -1 : 0; + d->MMX_L(1) = float32_le(s->MMX_S(1), d->MMX_S(1), + &env->mmx_status) ? -1 : 0; } void helper_pfcmpgt(MMXReg *d, MMXReg *s) { - d->MMX_L(0) = float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status) ? -1 : 0; - d->MMX_L(1) = float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status) ? -1 : 0; + d->MMX_L(0) = float32_lt(s->MMX_S(0), d->MMX_S(0), + &env->mmx_status) ? -1 : 0; + d->MMX_L(1) = float32_lt(s->MMX_S(1), d->MMX_S(1), + &env->mmx_status) ? -1 : 0; } void helper_pfmax(MMXReg *d, MMXReg *s) { - if (float32_lt(d->MMX_S(0), s->MMX_S(0), &env->mmx_status)) + if (float32_lt(d->MMX_S(0), s->MMX_S(0), &env->mmx_status)) { d->MMX_S(0) = s->MMX_S(0); - if (float32_lt(d->MMX_S(1), s->MMX_S(1), &env->mmx_status)) + } + if (float32_lt(d->MMX_S(1), s->MMX_S(1), &env->mmx_status)) { d->MMX_S(1) = s->MMX_S(1); + } } void helper_pfmin(MMXReg *d, MMXReg *s) { - if (float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status)) + if (float32_lt(s->MMX_S(0), d->MMX_S(0), &env->mmx_status)) { d->MMX_S(0) = s->MMX_S(0); - if (float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status)) + } + if (float32_lt(s->MMX_S(1), d->MMX_S(1), &env->mmx_status)) { d->MMX_S(1) = s->MMX_S(1); + } } void helper_pfmul(MMXReg *d, MMXReg *s) @@ -1272,6 +1326,7 @@ void helper_pfmul(MMXReg *d, MMXReg *s) void helper_pfnacc(MMXReg *d, MMXReg *s) { MMXReg r; + r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status); r.MMX_S(1) = float32_sub(s->MMX_S(0), s->MMX_S(1), &env->mmx_status); *d = r; @@ -1280,6 +1335,7 @@ void helper_pfnacc(MMXReg *d, MMXReg *s) void helper_pfpnacc(MMXReg *d, MMXReg *s) { MMXReg r; + r.MMX_S(0) = float32_sub(d->MMX_S(0), d->MMX_S(1), &env->mmx_status); r.MMX_S(1) = float32_add(s->MMX_S(0), s->MMX_S(1), &env->mmx_status); *d = r; @@ -1316,6 +1372,7 @@ void helper_pfsubr(MMXReg *d, MMXReg *s) void helper_pswapd(MMXReg *d, MMXReg *s) { MMXReg r; + r.MMX_L(0) = s->MMX_L(1); r.MMX_L(1) = s->MMX_L(0); *d = r; @@ -1323,18 +1380,19 @@ void helper_pswapd(MMXReg *d, MMXReg *s) #endif /* SSSE3 op helpers */ -void glue(helper_pshufb, SUFFIX) (Reg *d, Reg *s) +void glue(helper_pshufb, SUFFIX)(Reg *d, Reg *s) { int i; Reg r; - for (i = 0; i < (8 << SHIFT); i++) + for (i = 0; i < (8 << SHIFT); i++) { r.B(i) = (s->B(i) & 0x80) ? 0 : (d->B(s->B(i) & ((8 << SHIFT) - 1))); + } *d = r; } -void glue(helper_phaddw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phaddw, SUFFIX)(Reg *d, Reg *s) { d->W(0) = (int16_t)d->W(0) + (int16_t)d->W(1); d->W(1) = (int16_t)d->W(2) + (int16_t)d->W(3); @@ -1346,7 +1404,7 @@ void glue(helper_phaddw, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->W(7) = (int16_t)s->W(6) + (int16_t)s->W(7)); } -void glue(helper_phaddd, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phaddd, SUFFIX)(Reg *d, Reg *s) { d->L(0) = (int32_t)d->L(0) + (int32_t)d->L(1); XMM_ONLY(d->L(1) = (int32_t)d->L(2) + (int32_t)d->L(3)); @@ -1354,7 +1412,7 @@ void glue(helper_phaddd, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->L(3) = (int32_t)s->L(2) + (int32_t)s->L(3)); } -void glue(helper_phaddsw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phaddsw, SUFFIX)(Reg *d, Reg *s) { d->W(0) = satsw((int16_t)d->W(0) + (int16_t)d->W(1)); d->W(1) = satsw((int16_t)d->W(2) + (int16_t)d->W(3)); @@ -1366,19 +1424,19 @@ void glue(helper_phaddsw, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) + (int16_t)s->W(7))); } -void glue(helper_pmaddubsw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_pmaddubsw, SUFFIX)(Reg *d, Reg *s) { - d->W(0) = satsw((int8_t)s->B( 0) * (uint8_t)d->B( 0) + - (int8_t)s->B( 1) * (uint8_t)d->B( 1)); - d->W(1) = satsw((int8_t)s->B( 2) * (uint8_t)d->B( 2) + - (int8_t)s->B( 3) * (uint8_t)d->B( 3)); - d->W(2) = satsw((int8_t)s->B( 4) * (uint8_t)d->B( 4) + - (int8_t)s->B( 5) * (uint8_t)d->B( 5)); - d->W(3) = satsw((int8_t)s->B( 6) * (uint8_t)d->B( 6) + - (int8_t)s->B( 7) * (uint8_t)d->B( 7)); + d->W(0) = satsw((int8_t)s->B(0) * (uint8_t)d->B(0) + + (int8_t)s->B(1) * (uint8_t)d->B(1)); + d->W(1) = satsw((int8_t)s->B(2) * (uint8_t)d->B(2) + + (int8_t)s->B(3) * (uint8_t)d->B(3)); + d->W(2) = satsw((int8_t)s->B(4) * (uint8_t)d->B(4) + + (int8_t)s->B(5) * (uint8_t)d->B(5)); + d->W(3) = satsw((int8_t)s->B(6) * (uint8_t)d->B(6) + + (int8_t)s->B(7) * (uint8_t)d->B(7)); #if SHIFT == 1 - d->W(4) = satsw((int8_t)s->B( 8) * (uint8_t)d->B( 8) + - (int8_t)s->B( 9) * (uint8_t)d->B( 9)); + d->W(4) = satsw((int8_t)s->B(8) * (uint8_t)d->B(8) + + (int8_t)s->B(9) * (uint8_t)d->B(9)); d->W(5) = satsw((int8_t)s->B(10) * (uint8_t)d->B(10) + (int8_t)s->B(11) * (uint8_t)d->B(11)); d->W(6) = satsw((int8_t)s->B(12) * (uint8_t)d->B(12) + @@ -1388,7 +1446,7 @@ void glue(helper_pmaddubsw, SUFFIX) (Reg *d, Reg *s) #endif } -void glue(helper_phsubw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phsubw, SUFFIX)(Reg *d, Reg *s) { d->W(0) = (int16_t)d->W(0) - (int16_t)d->W(1); d->W(1) = (int16_t)d->W(2) - (int16_t)d->W(3); @@ -1400,7 +1458,7 @@ void glue(helper_phsubw, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->W(7) = (int16_t)s->W(6) - (int16_t)s->W(7)); } -void glue(helper_phsubd, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phsubd, SUFFIX)(Reg *d, Reg *s) { d->L(0) = (int32_t)d->L(0) - (int32_t)d->L(1); XMM_ONLY(d->L(1) = (int32_t)d->L(2) - (int32_t)d->L(3)); @@ -1408,7 +1466,7 @@ void glue(helper_phsubd, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->L(3) = (int32_t)s->L(2) - (int32_t)s->L(3)); } -void glue(helper_phsubsw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phsubsw, SUFFIX)(Reg *d, Reg *s) { d->W(0) = satsw((int16_t)d->W(0) - (int16_t)d->W(1)); d->W(1) = satsw((int16_t)d->W(2) - (int16_t)d->W(3)); @@ -1420,24 +1478,24 @@ void glue(helper_phsubsw, SUFFIX) (Reg *d, Reg *s) XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) - (int16_t)s->W(7))); } -#define FABSB(_, x) x > INT8_MAX ? -(int8_t ) x : x -#define FABSW(_, x) x > INT16_MAX ? -(int16_t) x : x -#define FABSL(_, x) x > INT32_MAX ? -(int32_t) x : x +#define FABSB(_, x) (x > INT8_MAX ? -(int8_t)x : x) +#define FABSW(_, x) (x > INT16_MAX ? -(int16_t)x : x) +#define FABSL(_, x) (x > INT32_MAX ? -(int32_t)x : x) SSE_HELPER_B(helper_pabsb, FABSB) SSE_HELPER_W(helper_pabsw, FABSW) SSE_HELPER_L(helper_pabsd, FABSL) -#define FMULHRSW(d, s) ((int16_t) d * (int16_t) s + 0x4000) >> 15 +#define FMULHRSW(d, s) (((int16_t) d * (int16_t)s + 0x4000) >> 15) SSE_HELPER_W(helper_pmulhrsw, FMULHRSW) -#define FSIGNB(d, s) s <= INT8_MAX ? s ? d : 0 : -(int8_t ) d -#define FSIGNW(d, s) s <= INT16_MAX ? s ? d : 0 : -(int16_t) d -#define FSIGNL(d, s) s <= INT32_MAX ? s ? d : 0 : -(int32_t) d +#define FSIGNB(d, s) (s <= INT8_MAX ? s ? d : 0 : -(int8_t)d) +#define FSIGNW(d, s) (s <= INT16_MAX ? s ? d : 0 : -(int16_t)d) +#define FSIGNL(d, s) (s <= INT32_MAX ? s ? d : 0 : -(int32_t)d) SSE_HELPER_B(helper_psignb, FSIGNB) SSE_HELPER_W(helper_psignw, FSIGNW) SSE_HELPER_L(helper_psignd, FSIGNL) -void glue(helper_palignr, SUFFIX) (Reg *d, Reg *s, int32_t shift) +void glue(helper_palignr, SUFFIX)(Reg *d, Reg *s, int32_t shift) { Reg r; @@ -1449,17 +1507,17 @@ void glue(helper_palignr, SUFFIX) (Reg *d, Reg *s, int32_t shift) shift <<= 3; #define SHR(v, i) (i < 64 && i > -64 ? i > 0 ? v >> (i) : (v << -(i)) : 0) #if SHIFT == 0 - r.Q(0) = SHR(s->Q(0), shift - 0) | - SHR(d->Q(0), shift - 64); + r.Q(0) = SHR(s->Q(0), shift - 0) | + SHR(d->Q(0), shift - 64); #else - r.Q(0) = SHR(s->Q(0), shift - 0) | - SHR(s->Q(1), shift - 64) | - SHR(d->Q(0), shift - 128) | - SHR(d->Q(1), shift - 192); - r.Q(1) = SHR(s->Q(0), shift + 64) | - SHR(s->Q(1), shift - 0) | - SHR(d->Q(0), shift - 64) | - SHR(d->Q(1), shift - 128); + r.Q(0) = SHR(s->Q(0), shift - 0) | + SHR(s->Q(1), shift - 64) | + SHR(d->Q(0), shift - 128) | + SHR(d->Q(1), shift - 192); + r.Q(1) = SHR(s->Q(0), shift + 64) | + SHR(s->Q(1), shift - 0) | + SHR(d->Q(0), shift - 64) | + SHR(d->Q(1), shift - 128); #endif #undef SHR } @@ -1467,72 +1525,78 @@ void glue(helper_palignr, SUFFIX) (Reg *d, Reg *s, int32_t shift) *d = r; } -#define XMM0 env->xmm_regs[0] +#define XMM0 (env->xmm_regs[0]) #if SHIFT == 1 -#define SSE_HELPER_V(name, elem, num, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->elem(0) = F(d->elem(0), s->elem(0), XMM0.elem(0));\ - d->elem(1) = F(d->elem(1), s->elem(1), XMM0.elem(1));\ - if (num > 2) {\ - d->elem(2) = F(d->elem(2), s->elem(2), XMM0.elem(2));\ - d->elem(3) = F(d->elem(3), s->elem(3), XMM0.elem(3));\ - if (num > 4) {\ - d->elem(4) = F(d->elem(4), s->elem(4), XMM0.elem(4));\ - d->elem(5) = F(d->elem(5), s->elem(5), XMM0.elem(5));\ - d->elem(6) = F(d->elem(6), s->elem(6), XMM0.elem(6));\ - d->elem(7) = F(d->elem(7), s->elem(7), XMM0.elem(7));\ - if (num > 8) {\ - d->elem(8) = F(d->elem(8), s->elem(8), XMM0.elem(8));\ - d->elem(9) = F(d->elem(9), s->elem(9), XMM0.elem(9));\ - d->elem(10) = F(d->elem(10), s->elem(10), XMM0.elem(10));\ - d->elem(11) = F(d->elem(11), s->elem(11), XMM0.elem(11));\ - d->elem(12) = F(d->elem(12), s->elem(12), XMM0.elem(12));\ - d->elem(13) = F(d->elem(13), s->elem(13), XMM0.elem(13));\ - d->elem(14) = F(d->elem(14), s->elem(14), XMM0.elem(14));\ - d->elem(15) = F(d->elem(15), s->elem(15), XMM0.elem(15));\ - }\ - }\ - }\ -} +#define SSE_HELPER_V(name, elem, num, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->elem(0) = F(d->elem(0), s->elem(0), XMM0.elem(0)); \ + d->elem(1) = F(d->elem(1), s->elem(1), XMM0.elem(1)); \ + if (num > 2) { \ + d->elem(2) = F(d->elem(2), s->elem(2), XMM0.elem(2)); \ + d->elem(3) = F(d->elem(3), s->elem(3), XMM0.elem(3)); \ + if (num > 4) { \ + d->elem(4) = F(d->elem(4), s->elem(4), XMM0.elem(4)); \ + d->elem(5) = F(d->elem(5), s->elem(5), XMM0.elem(5)); \ + d->elem(6) = F(d->elem(6), s->elem(6), XMM0.elem(6)); \ + d->elem(7) = F(d->elem(7), s->elem(7), XMM0.elem(7)); \ + if (num > 8) { \ + d->elem(8) = F(d->elem(8), s->elem(8), XMM0.elem(8)); \ + d->elem(9) = F(d->elem(9), s->elem(9), XMM0.elem(9)); \ + d->elem(10) = F(d->elem(10), s->elem(10), XMM0.elem(10)); \ + d->elem(11) = F(d->elem(11), s->elem(11), XMM0.elem(11)); \ + d->elem(12) = F(d->elem(12), s->elem(12), XMM0.elem(12)); \ + d->elem(13) = F(d->elem(13), s->elem(13), XMM0.elem(13)); \ + d->elem(14) = F(d->elem(14), s->elem(14), XMM0.elem(14)); \ + d->elem(15) = F(d->elem(15), s->elem(15), XMM0.elem(15)); \ + } \ + } \ + } \ + } -#define SSE_HELPER_I(name, elem, num, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s, uint32_t imm)\ -{\ - d->elem(0) = F(d->elem(0), s->elem(0), ((imm >> 0) & 1));\ - d->elem(1) = F(d->elem(1), s->elem(1), ((imm >> 1) & 1));\ - if (num > 2) {\ - d->elem(2) = F(d->elem(2), s->elem(2), ((imm >> 2) & 1));\ - d->elem(3) = F(d->elem(3), s->elem(3), ((imm >> 3) & 1));\ - if (num > 4) {\ - d->elem(4) = F(d->elem(4), s->elem(4), ((imm >> 4) & 1));\ - d->elem(5) = F(d->elem(5), s->elem(5), ((imm >> 5) & 1));\ - d->elem(6) = F(d->elem(6), s->elem(6), ((imm >> 6) & 1));\ - d->elem(7) = F(d->elem(7), s->elem(7), ((imm >> 7) & 1));\ - if (num > 8) {\ - d->elem(8) = F(d->elem(8), s->elem(8), ((imm >> 8) & 1));\ - d->elem(9) = F(d->elem(9), s->elem(9), ((imm >> 9) & 1));\ - d->elem(10) = F(d->elem(10), s->elem(10), ((imm >> 10) & 1));\ - d->elem(11) = F(d->elem(11), s->elem(11), ((imm >> 11) & 1));\ - d->elem(12) = F(d->elem(12), s->elem(12), ((imm >> 12) & 1));\ - d->elem(13) = F(d->elem(13), s->elem(13), ((imm >> 13) & 1));\ - d->elem(14) = F(d->elem(14), s->elem(14), ((imm >> 14) & 1));\ - d->elem(15) = F(d->elem(15), s->elem(15), ((imm >> 15) & 1));\ - }\ - }\ - }\ -} +#define SSE_HELPER_I(name, elem, num, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s, uint32_t imm) \ + { \ + d->elem(0) = F(d->elem(0), s->elem(0), ((imm >> 0) & 1)); \ + d->elem(1) = F(d->elem(1), s->elem(1), ((imm >> 1) & 1)); \ + if (num > 2) { \ + d->elem(2) = F(d->elem(2), s->elem(2), ((imm >> 2) & 1)); \ + d->elem(3) = F(d->elem(3), s->elem(3), ((imm >> 3) & 1)); \ + if (num > 4) { \ + d->elem(4) = F(d->elem(4), s->elem(4), ((imm >> 4) & 1)); \ + d->elem(5) = F(d->elem(5), s->elem(5), ((imm >> 5) & 1)); \ + d->elem(6) = F(d->elem(6), s->elem(6), ((imm >> 6) & 1)); \ + d->elem(7) = F(d->elem(7), s->elem(7), ((imm >> 7) & 1)); \ + if (num > 8) { \ + d->elem(8) = F(d->elem(8), s->elem(8), ((imm >> 8) & 1)); \ + d->elem(9) = F(d->elem(9), s->elem(9), ((imm >> 9) & 1)); \ + d->elem(10) = F(d->elem(10), s->elem(10), \ + ((imm >> 10) & 1)); \ + d->elem(11) = F(d->elem(11), s->elem(11), \ + ((imm >> 11) & 1)); \ + d->elem(12) = F(d->elem(12), s->elem(12), \ + ((imm >> 12) & 1)); \ + d->elem(13) = F(d->elem(13), s->elem(13), \ + ((imm >> 13) & 1)); \ + d->elem(14) = F(d->elem(14), s->elem(14), \ + ((imm >> 14) & 1)); \ + d->elem(15) = F(d->elem(15), s->elem(15), \ + ((imm >> 15) & 1)); \ + } \ + } \ + } \ + } /* SSE4.1 op helpers */ -#define FBLENDVB(d, s, m) (m & 0x80) ? s : d -#define FBLENDVPS(d, s, m) (m & 0x80000000) ? s : d -#define FBLENDVPD(d, s, m) (m & 0x8000000000000000LL) ? s : d +#define FBLENDVB(d, s, m) ((m & 0x80) ? s : d) +#define FBLENDVPS(d, s, m) ((m & 0x80000000) ? s : d) +#define FBLENDVPD(d, s, m) ((m & 0x8000000000000000LL) ? s : d) SSE_HELPER_V(helper_pblendvb, B, 16, FBLENDVB) SSE_HELPER_V(helper_blendvps, L, 4, FBLENDVPS) SSE_HELPER_V(helper_blendvpd, Q, 2, FBLENDVPD) -void glue(helper_ptest, SUFFIX) (Reg *d, Reg *s) +void glue(helper_ptest, SUFFIX)(Reg *d, Reg *s) { uint64_t zf = (s->Q(0) & d->Q(0)) | (s->Q(1) & d->Q(1)); uint64_t cf = (s->Q(0) & ~d->Q(0)) | (s->Q(1) & ~d->Q(1)); @@ -1540,22 +1604,22 @@ void glue(helper_ptest, SUFFIX) (Reg *d, Reg *s) CC_SRC = (zf ? 0 : CC_Z) | (cf ? 0 : CC_C); } -#define SSE_HELPER_F(name, elem, num, F)\ -void glue(name, SUFFIX) (Reg *d, Reg *s)\ -{\ - d->elem(0) = F(0);\ - d->elem(1) = F(1);\ - if (num > 2) {\ - d->elem(2) = F(2);\ - d->elem(3) = F(3);\ - if (num > 4) {\ - d->elem(4) = F(4);\ - d->elem(5) = F(5);\ - d->elem(6) = F(6);\ - d->elem(7) = F(7);\ - }\ - }\ -} +#define SSE_HELPER_F(name, elem, num, F) \ + void glue(name, SUFFIX)(Reg *d, Reg *s) \ + { \ + d->elem(0) = F(0); \ + d->elem(1) = F(1); \ + if (num > 2) { \ + d->elem(2) = F(2); \ + d->elem(3) = F(3); \ + if (num > 4) { \ + d->elem(4) = F(4); \ + d->elem(5) = F(5); \ + d->elem(6) = F(6); \ + d->elem(7) = F(7); \ + } \ + } \ + } SSE_HELPER_F(helper_pmovsxbw, W, 8, (int8_t) s->B) SSE_HELPER_F(helper_pmovsxbd, L, 4, (int8_t) s->B) @@ -1570,16 +1634,16 @@ SSE_HELPER_F(helper_pmovzxwd, L, 4, s->W) SSE_HELPER_F(helper_pmovzxwq, Q, 2, s->W) SSE_HELPER_F(helper_pmovzxdq, Q, 2, s->L) -void glue(helper_pmuldq, SUFFIX) (Reg *d, Reg *s) +void glue(helper_pmuldq, SUFFIX)(Reg *d, Reg *s) { - d->Q(0) = (int64_t) (int32_t) d->L(0) * (int32_t) s->L(0); - d->Q(1) = (int64_t) (int32_t) d->L(2) * (int32_t) s->L(2); + d->Q(0) = (int64_t)(int32_t) d->L(0) * (int32_t) s->L(0); + d->Q(1) = (int64_t)(int32_t) d->L(2) * (int32_t) s->L(2); } -#define FCMPEQQ(d, s) d == s ? -1 : 0 +#define FCMPEQQ(d, s) (d == s ? -1 : 0) SSE_HELPER_Q(helper_pcmpeqq, FCMPEQQ) -void glue(helper_packusdw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_packusdw, SUFFIX)(Reg *d, Reg *s) { d->W(0) = satuw((int32_t) d->L(0)); d->W(1) = satuw((int32_t) d->L(1)); @@ -1591,10 +1655,10 @@ void glue(helper_packusdw, SUFFIX) (Reg *d, Reg *s) d->W(7) = satuw((int32_t) s->L(3)); } -#define FMINSB(d, s) MIN((int8_t) d, (int8_t) s) -#define FMINSD(d, s) MIN((int32_t) d, (int32_t) s) -#define FMAXSB(d, s) MAX((int8_t) d, (int8_t) s) -#define FMAXSD(d, s) MAX((int32_t) d, (int32_t) s) +#define FMINSB(d, s) MIN((int8_t)d, (int8_t)s) +#define FMINSD(d, s) MIN((int32_t)d, (int32_t)s) +#define FMAXSB(d, s) MAX((int8_t)d, (int8_t)s) +#define FMAXSD(d, s) MAX((int32_t)d, (int32_t)s) SSE_HELPER_B(helper_pminsb, FMINSB) SSE_HELPER_L(helper_pminsd, FMINSD) SSE_HELPER_W(helper_pminuw, MIN) @@ -1604,27 +1668,34 @@ SSE_HELPER_L(helper_pmaxsd, FMAXSD) SSE_HELPER_W(helper_pmaxuw, MAX) SSE_HELPER_L(helper_pmaxud, MAX) -#define FMULLD(d, s) (int32_t) d * (int32_t) s +#define FMULLD(d, s) ((int32_t)d * (int32_t)s) SSE_HELPER_L(helper_pmulld, FMULLD) -void glue(helper_phminposuw, SUFFIX) (Reg *d, Reg *s) +void glue(helper_phminposuw, SUFFIX)(Reg *d, Reg *s) { int idx = 0; - if (s->W(1) < s->W(idx)) + if (s->W(1) < s->W(idx)) { idx = 1; - if (s->W(2) < s->W(idx)) + } + if (s->W(2) < s->W(idx)) { idx = 2; - if (s->W(3) < s->W(idx)) + } + if (s->W(3) < s->W(idx)) { idx = 3; - if (s->W(4) < s->W(idx)) + } + if (s->W(4) < s->W(idx)) { idx = 4; - if (s->W(5) < s->W(idx)) + } + if (s->W(5) < s->W(idx)) { idx = 5; - if (s->W(6) < s->W(idx)) + } + if (s->W(6) < s->W(idx)) { idx = 6; - if (s->W(7) < s->W(idx)) + } + if (s->W(7) < s->W(idx)) { idx = 7; + } d->Q(1) = 0; d->L(1) = 0; @@ -1632,12 +1703,12 @@ void glue(helper_phminposuw, SUFFIX) (Reg *d, Reg *s) d->W(0) = s->W(idx); } -void glue(helper_roundps, SUFFIX) (Reg *d, Reg *s, uint32_t mode) +void glue(helper_roundps, SUFFIX)(Reg *d, Reg *s, uint32_t mode) { signed char prev_rounding_mode; prev_rounding_mode = env->sse_status.float_rounding_mode; - if (!(mode & (1 << 2))) + if (!(mode & (1 << 2))) { switch (mode & 3) { case 0: set_float_rounding_mode(float_round_nearest_even, &env->sse_status); @@ -1652,6 +1723,7 @@ void glue(helper_roundps, SUFFIX) (Reg *d, Reg *s, uint32_t mode) set_float_rounding_mode(float_round_to_zero, &env->sse_status); break; } + } d->XMM_S(0) = float32_round_to_int(s->XMM_S(0), &env->sse_status); d->XMM_S(1) = float32_round_to_int(s->XMM_S(1), &env->sse_status); @@ -1659,21 +1731,21 @@ void glue(helper_roundps, SUFFIX) (Reg *d, Reg *s, uint32_t mode) d->XMM_S(3) = float32_round_to_int(s->XMM_S(3), &env->sse_status); #if 0 /* TODO */ - if (mode & (1 << 3)) - set_float_exception_flags( - get_float_exception_flags(&env->sse_status) & - ~float_flag_inexact, - &env->sse_status); + if (mode & (1 << 3)) { + set_float_exception_flags(get_float_exception_flags(&env->sse_status) & + ~float_flag_inexact, + &env->sse_status); + } #endif env->sse_status.float_rounding_mode = prev_rounding_mode; } -void glue(helper_roundpd, SUFFIX) (Reg *d, Reg *s, uint32_t mode) +void glue(helper_roundpd, SUFFIX)(Reg *d, Reg *s, uint32_t mode) { signed char prev_rounding_mode; prev_rounding_mode = env->sse_status.float_rounding_mode; - if (!(mode & (1 << 2))) + if (!(mode & (1 << 2))) { switch (mode & 3) { case 0: set_float_rounding_mode(float_round_nearest_even, &env->sse_status); @@ -1688,26 +1760,27 @@ void glue(helper_roundpd, SUFFIX) (Reg *d, Reg *s, uint32_t mode) set_float_rounding_mode(float_round_to_zero, &env->sse_status); break; } + } d->XMM_D(0) = float64_round_to_int(s->XMM_D(0), &env->sse_status); d->XMM_D(1) = float64_round_to_int(s->XMM_D(1), &env->sse_status); #if 0 /* TODO */ - if (mode & (1 << 3)) - set_float_exception_flags( - get_float_exception_flags(&env->sse_status) & - ~float_flag_inexact, - &env->sse_status); + if (mode & (1 << 3)) { + set_float_exception_flags(get_float_exception_flags(&env->sse_status) & + ~float_flag_inexact, + &env->sse_status); + } #endif env->sse_status.float_rounding_mode = prev_rounding_mode; } -void glue(helper_roundss, SUFFIX) (Reg *d, Reg *s, uint32_t mode) +void glue(helper_roundss, SUFFIX)(Reg *d, Reg *s, uint32_t mode) { signed char prev_rounding_mode; prev_rounding_mode = env->sse_status.float_rounding_mode; - if (!(mode & (1 << 2))) + if (!(mode & (1 << 2))) { switch (mode & 3) { case 0: set_float_rounding_mode(float_round_nearest_even, &env->sse_status); @@ -1722,25 +1795,26 @@ void glue(helper_roundss, SUFFIX) (Reg *d, Reg *s, uint32_t mode) set_float_rounding_mode(float_round_to_zero, &env->sse_status); break; } + } d->XMM_S(0) = float32_round_to_int(s->XMM_S(0), &env->sse_status); #if 0 /* TODO */ - if (mode & (1 << 3)) - set_float_exception_flags( - get_float_exception_flags(&env->sse_status) & - ~float_flag_inexact, - &env->sse_status); + if (mode & (1 << 3)) { + set_float_exception_flags(get_float_exception_flags(&env->sse_status) & + ~float_flag_inexact, + &env->sse_status); + } #endif env->sse_status.float_rounding_mode = prev_rounding_mode; } -void glue(helper_roundsd, SUFFIX) (Reg *d, Reg *s, uint32_t mode) +void glue(helper_roundsd, SUFFIX)(Reg *d, Reg *s, uint32_t mode) { signed char prev_rounding_mode; prev_rounding_mode = env->sse_status.float_rounding_mode; - if (!(mode & (1 << 2))) + if (!(mode & (1 << 2))) { switch (mode & 3) { case 0: set_float_rounding_mode(float_round_nearest_even, &env->sse_status); @@ -1755,67 +1829,80 @@ void glue(helper_roundsd, SUFFIX) (Reg *d, Reg *s, uint32_t mode) set_float_rounding_mode(float_round_to_zero, &env->sse_status); break; } + } d->XMM_D(0) = float64_round_to_int(s->XMM_D(0), &env->sse_status); #if 0 /* TODO */ - if (mode & (1 << 3)) - set_float_exception_flags( - get_float_exception_flags(&env->sse_status) & - ~float_flag_inexact, - &env->sse_status); + if (mode & (1 << 3)) { + set_float_exception_flags(get_float_exception_flags(&env->sse_status) & + ~float_flag_inexact, + &env->sse_status); + } #endif env->sse_status.float_rounding_mode = prev_rounding_mode; } -#define FBLENDP(d, s, m) m ? s : d +#define FBLENDP(d, s, m) (m ? s : d) SSE_HELPER_I(helper_blendps, L, 4, FBLENDP) SSE_HELPER_I(helper_blendpd, Q, 2, FBLENDP) SSE_HELPER_I(helper_pblendw, W, 8, FBLENDP) -void glue(helper_dpps, SUFFIX) (Reg *d, Reg *s, uint32_t mask) +void glue(helper_dpps, SUFFIX)(Reg *d, Reg *s, uint32_t mask) { float32 iresult = float32_zero; - if (mask & (1 << 4)) + if (mask & (1 << 4)) { iresult = float32_add(iresult, - float32_mul(d->XMM_S(0), s->XMM_S(0), &env->sse_status), - &env->sse_status); - if (mask & (1 << 5)) + float32_mul(d->XMM_S(0), s->XMM_S(0), + &env->sse_status), + &env->sse_status); + } + if (mask & (1 << 5)) { iresult = float32_add(iresult, - float32_mul(d->XMM_S(1), s->XMM_S(1), &env->sse_status), - &env->sse_status); - if (mask & (1 << 6)) + float32_mul(d->XMM_S(1), s->XMM_S(1), + &env->sse_status), + &env->sse_status); + } + if (mask & (1 << 6)) { iresult = float32_add(iresult, - float32_mul(d->XMM_S(2), s->XMM_S(2), &env->sse_status), - &env->sse_status); - if (mask & (1 << 7)) + float32_mul(d->XMM_S(2), s->XMM_S(2), + &env->sse_status), + &env->sse_status); + } + if (mask & (1 << 7)) { iresult = float32_add(iresult, - float32_mul(d->XMM_S(3), s->XMM_S(3), &env->sse_status), - &env->sse_status); + float32_mul(d->XMM_S(3), s->XMM_S(3), + &env->sse_status), + &env->sse_status); + } d->XMM_S(0) = (mask & (1 << 0)) ? iresult : float32_zero; d->XMM_S(1) = (mask & (1 << 1)) ? iresult : float32_zero; d->XMM_S(2) = (mask & (1 << 2)) ? iresult : float32_zero; d->XMM_S(3) = (mask & (1 << 3)) ? iresult : float32_zero; } -void glue(helper_dppd, SUFFIX) (Reg *d, Reg *s, uint32_t mask) +void glue(helper_dppd, SUFFIX)(Reg *d, Reg *s, uint32_t mask) { float64 iresult = float64_zero; - if (mask & (1 << 4)) + if (mask & (1 << 4)) { iresult = float64_add(iresult, - float64_mul(d->XMM_D(0), s->XMM_D(0), &env->sse_status), - &env->sse_status); - if (mask & (1 << 5)) + float64_mul(d->XMM_D(0), s->XMM_D(0), + &env->sse_status), + &env->sse_status); + } + if (mask & (1 << 5)) { iresult = float64_add(iresult, - float64_mul(d->XMM_D(1), s->XMM_D(1), &env->sse_status), - &env->sse_status); + float64_mul(d->XMM_D(1), s->XMM_D(1), + &env->sse_status), + &env->sse_status); + } d->XMM_D(0) = (mask & (1 << 0)) ? iresult : float64_zero; d->XMM_D(1) = (mask & (1 << 1)) ? iresult : float64_zero; } -void glue(helper_mpsadbw, SUFFIX) (Reg *d, Reg *s, uint32_t offset) +void glue(helper_mpsadbw, SUFFIX)(Reg *d, Reg *s, uint32_t offset) { int s0 = (offset & 3) << 2; int d0 = (offset & 4) << 0; @@ -1835,7 +1922,7 @@ void glue(helper_mpsadbw, SUFFIX) (Reg *d, Reg *s, uint32_t offset) /* SSE4.2 op helpers */ /* it's unclear whether signed or unsigned */ -#define FCMPGTQ(d, s) d > s ? -1 : 0 +#define FCMPGTQ(d, s) (d > s ? -1 : 0) SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ) static inline int pcmp_elen(int reg, uint32_t ctrl) @@ -1843,18 +1930,21 @@ static inline int pcmp_elen(int reg, uint32_t ctrl) int val; /* Presence of REX.W is indicated by a bit higher than 7 set */ - if (ctrl >> 8) - val = abs1((int64_t) env->regs[reg]); - else - val = abs1((int32_t) env->regs[reg]); + if (ctrl >> 8) { + val = abs1((int64_t)env->regs[reg]); + } else { + val = abs1((int32_t)env->regs[reg]); + } if (ctrl & 1) { - if (val > 8) + if (val > 8) { return 8; - } else - if (val > 16) + } + } else { + if (val > 16) { return 16; - + } + } return val; } @@ -1863,11 +1953,14 @@ static inline int pcmp_ilen(Reg *r, uint8_t ctrl) int val = 0; if (ctrl & 1) { - while (val < 8 && r->W(val)) + while (val < 8 && r->W(val)) { val++; - } else - while (val < 16 && r->B(val)) + } + } else { + while (val < 16 && r->B(val)) { val++; + } + } return val; } @@ -1880,15 +1973,15 @@ static inline int pcmp_val(Reg *r, uint8_t ctrl, int i) case 1: return r->W(i); case 2: - return (int8_t) r->B(i); + return (int8_t)r->B(i); case 3: default: - return (int16_t) r->W(i); + return (int16_t)r->W(i); } } static inline unsigned pcmpxstrx(Reg *d, Reg *s, - int8_t ctrl, int valids, int validd) + int8_t ctrl, int valids, int validd) { unsigned int res = 0; int v; @@ -1905,17 +1998,19 @@ static inline unsigned pcmpxstrx(Reg *d, Reg *s, for (j = valids; j >= 0; j--) { res <<= 1; v = pcmp_val(s, ctrl, j); - for (i = validd; i >= 0; i--) + for (i = validd; i >= 0; i--) { res |= (v == pcmp_val(d, ctrl, i)); + } } break; case 1: for (j = valids; j >= 0; j--) { res <<= 1; v = pcmp_val(s, ctrl, j); - for (i = ((validd - 1) | 1); i >= 0; i -= 2) + for (i = ((validd - 1) | 1); i >= 0; i -= 2) { res |= (pcmp_val(d, ctrl, i - 0) <= v && pcmp_val(d, ctrl, i - 1) >= v); + } } break; case 2: @@ -1931,8 +2026,9 @@ static inline unsigned pcmpxstrx(Reg *d, Reg *s, for (j = valids - validd; j >= 0; j--) { res <<= 1; res |= 1; - for (i = MIN(upper - j, validd); i >= 0; i--) + for (i = MIN(upper - j, validd); i >= 0; i--) { res &= (pcmp_val(s, ctrl, i + j) == pcmp_val(d, ctrl, i)); + } } break; } @@ -1946,10 +2042,12 @@ static inline unsigned pcmpxstrx(Reg *d, Reg *s, break; } - if (res) - CC_SRC |= CC_C; - if (res & 1) - CC_SRC |= CC_O; + if (res) { + CC_SRC |= CC_C; + } + if (res & 1) { + CC_SRC |= CC_O; + } return res; } @@ -1958,11 +2056,12 @@ static inline int rffs1(unsigned int val) { int ret = 1, hi; - for (hi = sizeof(val) * 4; hi; hi /= 2) + for (hi = sizeof(val) * 4; hi; hi /= 2) { if (val >> hi) { val >>= hi; ret += hi; } + } return ret; } @@ -1971,77 +2070,82 @@ static inline int ffs1(unsigned int val) { int ret = 1, hi; - for (hi = sizeof(val) * 4; hi; hi /= 2) + for (hi = sizeof(val) * 4; hi; hi /= 2) { if (val << hi) { val <<= hi; ret += hi; } + } return ret; } -void glue(helper_pcmpestri, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl) +void glue(helper_pcmpestri, SUFFIX)(Reg *d, Reg *s, uint32_t ctrl) { unsigned int res = pcmpxstrx(d, s, ctrl, - pcmp_elen(R_EDX, ctrl), - pcmp_elen(R_EAX, ctrl)); + pcmp_elen(R_EDX, ctrl), + pcmp_elen(R_EAX, ctrl)); - if (res) + if (res) { env->regs[R_ECX] = ((ctrl & (1 << 6)) ? rffs1 : ffs1)(res) - 1; - else + } else { env->regs[R_ECX] = 16 >> (ctrl & (1 << 0)); + } } -void glue(helper_pcmpestrm, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl) +void glue(helper_pcmpestrm, SUFFIX)(Reg *d, Reg *s, uint32_t ctrl) { int i; unsigned int res = pcmpxstrx(d, s, ctrl, - pcmp_elen(R_EDX, ctrl), - pcmp_elen(R_EAX, ctrl)); + pcmp_elen(R_EDX, ctrl), + pcmp_elen(R_EAX, ctrl)); if ((ctrl >> 6) & 1) { - if (ctrl & 1) + if (ctrl & 1) { for (i = 0; i < 8; i++, res >>= 1) { d->W(i) = (res & 1) ? ~0 : 0; } - else + } else { for (i = 0; i < 16; i++, res >>= 1) { d->B(i) = (res & 1) ? ~0 : 0; } + } } else { d->Q(1) = 0; d->Q(0) = res; } } -void glue(helper_pcmpistri, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl) +void glue(helper_pcmpistri, SUFFIX)(Reg *d, Reg *s, uint32_t ctrl) { unsigned int res = pcmpxstrx(d, s, ctrl, - pcmp_ilen(s, ctrl), - pcmp_ilen(d, ctrl)); + pcmp_ilen(s, ctrl), + pcmp_ilen(d, ctrl)); - if (res) + if (res) { env->regs[R_ECX] = ((ctrl & (1 << 6)) ? rffs1 : ffs1)(res) - 1; - else + } else { env->regs[R_ECX] = 16 >> (ctrl & (1 << 0)); + } } -void glue(helper_pcmpistrm, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl) +void glue(helper_pcmpistrm, SUFFIX)(Reg *d, Reg *s, uint32_t ctrl) { int i; unsigned int res = pcmpxstrx(d, s, ctrl, - pcmp_ilen(s, ctrl), - pcmp_ilen(d, ctrl)); + pcmp_ilen(s, ctrl), + pcmp_ilen(d, ctrl)); if ((ctrl >> 6) & 1) { - if (ctrl & 1) + if (ctrl & 1) { for (i = 0; i < 8; i++, res >>= 1) { d->W(i) = (res & 1) ? ~0 : 0; } - else + } else { for (i = 0; i < 16; i++, res >>= 1) { d->B(i) = (res & 1) ? ~0 : 0; } + } } else { d->Q(1) = 0; d->Q(0) = res; @@ -2053,16 +2157,17 @@ void glue(helper_pcmpistrm, SUFFIX) (Reg *d, Reg *s, uint32_t ctrl) target_ulong helper_crc32(uint32_t crc1, target_ulong msg, uint32_t len) { target_ulong crc = (msg & ((target_ulong) -1 >> - (TARGET_LONG_BITS - len))) ^ crc1; + (TARGET_LONG_BITS - len))) ^ crc1; - while (len--) + while (len--) { crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_BITREV : 0); + } return crc; } #define POPMASK(i) ((target_ulong) -1 / ((1LL << (1 << i)) + 1)) -#define POPCOUNT(n, i) (n & POPMASK(i)) + ((n >> (1 << i)) & POPMASK(i)) +#define POPCOUNT(n, i) ((n & POPMASK(i)) + ((n >> (1 << i)) & POPMASK(i))) target_ulong helper_popcnt(target_ulong n, uint32_t type) { CC_SRC = n ? 0 : CC_Z; @@ -2071,15 +2176,17 @@ target_ulong helper_popcnt(target_ulong n, uint32_t type) n = POPCOUNT(n, 1); n = POPCOUNT(n, 2); n = POPCOUNT(n, 3); - if (type == 1) + if (type == 1) { return n & 0xff; + } n = POPCOUNT(n, 4); #ifndef TARGET_X86_64 return n; #else - if (type == 2) + if (type == 2) { return n & 0xff; + } return POPCOUNT(n, 5); #endif