Prepare the "easy" floating point vector helpers for AVX No functional changes to existing helpers.
Signed-off-by: Paul Brook <p...@nowt.org> --- target/i386/ops_sse.h | 144 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 119 insertions(+), 25 deletions(-) diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h index fc8fd57aa5..d308a1ec40 100644 --- a/target/i386/ops_sse.h +++ b/target/i386/ops_sse.h @@ -762,40 +762,66 @@ void glue(helper_pshufhw, SUFFIX)(Reg *d, Reg *s, int order) } #endif -#if SHIFT == 1 +#if SHIFT >= 1 /* FPU ops */ /* XXX: not accurate */ -#define SSE_HELPER_S(name, F) \ - void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\ +#define SSE_HELPER_P(name, F) \ + void glue(helper_ ## name ## ps, SUFFIX)(CPUX86State *env, \ + Reg *d, Reg *s) \ { \ - d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \ - d->ZMM_S(1) = F(32, d->ZMM_S(1), s->ZMM_S(1)); \ - d->ZMM_S(2) = F(32, d->ZMM_S(2), s->ZMM_S(2)); \ - d->ZMM_S(3) = F(32, d->ZMM_S(3), s->ZMM_S(3)); \ + Reg *v = d; \ + d->ZMM_S(0) = F(32, v->ZMM_S(0), s->ZMM_S(0)); \ + d->ZMM_S(1) = F(32, v->ZMM_S(1), s->ZMM_S(1)); \ + d->ZMM_S(2) = F(32, v->ZMM_S(2), s->ZMM_S(2)); \ + d->ZMM_S(3) = F(32, v->ZMM_S(3), s->ZMM_S(3)); \ + YMM_ONLY( \ + d->ZMM_S(4) = F(32, v->ZMM_S(4), s->ZMM_S(4)); \ + d->ZMM_S(5) = F(32, v->ZMM_S(5), s->ZMM_S(5)); \ + d->ZMM_S(6) = F(32, v->ZMM_S(6), s->ZMM_S(6)); \ + d->ZMM_S(7) = F(32, v->ZMM_S(7), s->ZMM_S(7)); \ + ) \ } \ \ - void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s) \ + void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, \ + Reg *d, Reg *s) \ { \ - d->ZMM_S(0) = F(32, d->ZMM_S(0), s->ZMM_S(0)); \ - } \ + Reg *v = d; \ + d->ZMM_D(0) = F(64, v->ZMM_D(0), s->ZMM_D(0)); \ + d->ZMM_D(1) = F(64, v->ZMM_D(1), s->ZMM_D(1)); \ + YMM_ONLY( \ + d->ZMM_D(2) = F(64, v->ZMM_D(2), s->ZMM_D(2)); \ + d->ZMM_D(3) = F(64, v->ZMM_D(3), s->ZMM_D(3)); \ + ) \ + } + +#if SHIFT == 1 + +#define SSE_HELPER_S(name, F) \ + SSE_HELPER_P(name, F) \ \ - void glue(helper_ ## name ## pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)\ + void helper_ ## name ## ss(CPUX86State *env, Reg *d, Reg *s)\ { \ - d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \ - d->ZMM_D(1) = F(64, d->ZMM_D(1), s->ZMM_D(1)); \ + Reg *v = d; \ + d->ZMM_S(0) = F(32, v->ZMM_S(0), s->ZMM_S(0)); \ } \ \ - void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s) \ + void helper_ ## name ## sd(CPUX86State *env, Reg *d, Reg *s)\ { \ - d->ZMM_D(0) = F(64, d->ZMM_D(0), s->ZMM_D(0)); \ + Reg *v = d; \ + d->ZMM_D(0) = F(64, v->ZMM_D(0), s->ZMM_D(0)); \ } +#else + +#define SSE_HELPER_S(name, F) SSE_HELPER_P(name, F) + +#endif + #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) #define FPU_MUL(size, a, b) float ## size ## _mul(a, b, &env->sse_status) #define FPU_DIV(size, a, b) float ## size ## _div(a, b, &env->sse_status) -#define FPU_SQRT(size, a, b) float ## size ## _sqrt(b, &env->sse_status) /* Note that the choice of comparison op here is important to get the * special cases right: for min and max Intel specifies that (-0,0), @@ -812,8 +838,42 @@ SSE_HELPER_S(mul, FPU_MUL) SSE_HELPER_S(div, FPU_DIV) SSE_HELPER_S(min, FPU_MIN) SSE_HELPER_S(max, FPU_MAX) -SSE_HELPER_S(sqrt, FPU_SQRT) +void glue(helper_sqrtps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) +{ + d->ZMM_S(0) = float32_sqrt(s->ZMM_S(0), &env->sse_status); + d->ZMM_S(1) = float32_sqrt(s->ZMM_S(1), &env->sse_status); + d->ZMM_S(2) = float32_sqrt(s->ZMM_S(2), &env->sse_status); + d->ZMM_S(3) = float32_sqrt(s->ZMM_S(3), &env->sse_status); +#if SHIFT == 2 + d->ZMM_S(4) = float32_sqrt(s->ZMM_S(4), &env->sse_status); + d->ZMM_S(5) = float32_sqrt(s->ZMM_S(5), &env->sse_status); + d->ZMM_S(6) = float32_sqrt(s->ZMM_S(6), &env->sse_status); + d->ZMM_S(7) = float32_sqrt(s->ZMM_S(7), &env->sse_status); +#endif +} + +void glue(helper_sqrtpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) +{ + d->ZMM_D(0) = float64_sqrt(s->ZMM_D(0), &env->sse_status); + d->ZMM_D(1) = float64_sqrt(s->ZMM_D(1), &env->sse_status); +#if SHIFT == 2 + d->ZMM_D(2) = float64_sqrt(s->ZMM_D(2), &env->sse_status); + d->ZMM_D(3) = float64_sqrt(s->ZMM_D(3), &env->sse_status); +#endif +} + +#if SHIFT == 1 +void helper_sqrtss(CPUX86State *env, Reg *d, Reg *s) +{ + d->ZMM_S(0) = float32_sqrt(s->ZMM_S(0), &env->sse_status); +} + +void helper_sqrtsd(CPUX86State *env, Reg *d, Reg *s) +{ + d->ZMM_D(0) = float64_sqrt(s->ZMM_D(0), &env->sse_status); +} +#endif /* float to float conversions */ void glue(helper_cvtps2pd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) @@ -1043,6 +1103,20 @@ void glue(helper_rsqrtps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s) d->ZMM_S(3) = float32_div(float32_one, float32_sqrt(s->ZMM_S(3), &env->sse_status), &env->sse_status); +#if SHIFT == 2 + d->ZMM_S(4) = float32_div(float32_one, + float32_sqrt(s->ZMM_S(4), &env->sse_status), + &env->sse_status); + d->ZMM_S(5) = float32_div(float32_one, + float32_sqrt(s->ZMM_S(5), &env->sse_status), + &env->sse_status); + d->ZMM_S(6) = float32_div(float32_one, + float32_sqrt(s->ZMM_S(6), &env->sse_status), + &env->sse_status); + d->ZMM_S(7) = float32_div(float32_one, + float32_sqrt(s->ZMM_S(7), &env->sse_status), + &env->sse_status); +#endif set_float_exception_flags(old_flags, &env->sse_status); } @@ -1062,6 +1136,12 @@ void glue(helper_rcpps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s) d->ZMM_S(1) = float32_div(float32_one, s->ZMM_S(1), &env->sse_status); d->ZMM_S(2) = float32_div(float32_one, s->ZMM_S(2), &env->sse_status); d->ZMM_S(3) = float32_div(float32_one, s->ZMM_S(3), &env->sse_status); +#if SHIFT == 2 + d->ZMM_S(4) = float32_div(float32_one, s->ZMM_S(4), &env->sse_status); + d->ZMM_S(5) = float32_div(float32_one, s->ZMM_S(5), &env->sse_status); + d->ZMM_S(6) = float32_div(float32_one, s->ZMM_S(6), &env->sse_status); + d->ZMM_S(7) = float32_div(float32_one, s->ZMM_S(7), &env->sse_status); +#endif set_float_exception_flags(old_flags, &env->sse_status); } @@ -1156,18 +1236,30 @@ void glue(helper_hsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s) MOVE(*d, r); } -void glue(helper_addsubps, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s) +void glue(helper_addsubps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) { - d->ZMM_S(0) = float32_sub(d->ZMM_S(0), s->ZMM_S(0), &env->sse_status); - d->ZMM_S(1) = float32_add(d->ZMM_S(1), s->ZMM_S(1), &env->sse_status); - d->ZMM_S(2) = float32_sub(d->ZMM_S(2), s->ZMM_S(2), &env->sse_status); - d->ZMM_S(3) = float32_add(d->ZMM_S(3), s->ZMM_S(3), &env->sse_status); + Reg *v = d; + d->ZMM_S(0) = float32_sub(v->ZMM_S(0), s->ZMM_S(0), &env->sse_status); + d->ZMM_S(1) = float32_add(v->ZMM_S(1), s->ZMM_S(1), &env->sse_status); + d->ZMM_S(2) = float32_sub(v->ZMM_S(2), s->ZMM_S(2), &env->sse_status); + d->ZMM_S(3) = float32_add(v->ZMM_S(3), s->ZMM_S(3), &env->sse_status); +#if SHIFT == 2 + d->ZMM_S(4) = float32_sub(v->ZMM_S(4), s->ZMM_S(4), &env->sse_status); + d->ZMM_S(5) = float32_add(v->ZMM_S(5), s->ZMM_S(5), &env->sse_status); + d->ZMM_S(6) = float32_sub(v->ZMM_S(6), s->ZMM_S(6), &env->sse_status); + d->ZMM_S(7) = float32_add(v->ZMM_S(7), s->ZMM_S(7), &env->sse_status); +#endif } -void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, ZMMReg *d, ZMMReg *s) +void glue(helper_addsubpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) { - d->ZMM_D(0) = float64_sub(d->ZMM_D(0), s->ZMM_D(0), &env->sse_status); - d->ZMM_D(1) = float64_add(d->ZMM_D(1), s->ZMM_D(1), &env->sse_status); + Reg *v = d; + d->ZMM_D(0) = float64_sub(v->ZMM_D(0), s->ZMM_D(0), &env->sse_status); + d->ZMM_D(1) = float64_add(v->ZMM_D(1), s->ZMM_D(1), &env->sse_status); +#if SHIFT == 2 + d->ZMM_D(2) = float64_sub(v->ZMM_D(2), s->ZMM_D(2), &env->sse_status); + d->ZMM_D(3) = float64_add(v->ZMM_D(3), s->ZMM_D(3), &env->sse_status); +#endif } /* XXX: unordered */ @@ -2694,6 +2786,8 @@ void glue(helper_aeskeygenassist, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, } #endif +#undef SSE_HELPER_S + #undef SHIFT #undef XMM_ONLY #undef YMM_ONLY -- 2.36.0