diff options
Diffstat (limited to 'target/i386/ops_sse.h')
| -rw-r--r-- | target/i386/ops_sse.h | 116 |
1 files changed, 60 insertions, 56 deletions
diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h index d35fc15c65..3cbc36a59d 100644 --- a/target/i386/ops_sse.h +++ b/target/i386/ops_sse.h @@ -586,6 +586,35 @@ void glue(helper_cvtpd2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) } } +#if SHIFT >= 1 +void glue(helper_cvtph2ps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s) +{ + int i; + + for (i = 2 << SHIFT; --i >= 0; ) { + d->ZMM_S(i) = float16_to_float32(s->ZMM_H(i), true, &env->sse_status); + } +} + +void glue(helper_cvtps2ph, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, int mode) +{ + int i; + FloatRoundMode prev_rounding_mode = env->sse_status.float_rounding_mode; + if (!(mode & (1 << 2))) { + set_x86_rounding_mode(mode & 3, &env->sse_status); + } + + for (i = 0; i < 2 << SHIFT; i++) { + d->ZMM_H(i) = float32_to_float16(s->ZMM_S(i), true, &env->sse_status); + } + for (i >>= 2; i < 1 << SHIFT; i++) { + d->Q(i) = 0; + } + + env->sse_status.float_rounding_mode = prev_rounding_mode; +} +#endif + #if SHIFT == 1 void helper_cvtss2sd(CPUX86State *env, Reg *d, Reg *v, Reg *s) { @@ -1684,20 +1713,7 @@ void glue(helper_roundps, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, prev_rounding_mode = env->sse_status.float_rounding_mode; if (!(mode & (1 << 2))) { - switch (mode & 3) { - case 0: - set_float_rounding_mode(float_round_nearest_even, &env->sse_status); - break; - case 1: - set_float_rounding_mode(float_round_down, &env->sse_status); - break; - case 2: - set_float_rounding_mode(float_round_up, &env->sse_status); - break; - case 3: - set_float_rounding_mode(float_round_to_zero, &env->sse_status); - break; - } + set_x86_rounding_mode(mode & 3, &env->sse_status); } for (i = 0; i < 2 << SHIFT; i++) { @@ -1721,20 +1737,7 @@ void glue(helper_roundpd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s, prev_rounding_mode = env->sse_status.float_rounding_mode; if (!(mode & (1 << 2))) { - switch (mode & 3) { - case 0: - set_float_rounding_mode(float_round_nearest_even, &env->sse_status); - break; - case 1: - set_float_rounding_mode(float_round_down, &env->sse_status); - break; - case 2: - set_float_rounding_mode(float_round_up, &env->sse_status); - break; - case 3: - set_float_rounding_mode(float_round_to_zero, &env->sse_status); - break; - } + set_x86_rounding_mode(mode & 3, &env->sse_status); } for (i = 0; i < 1 << SHIFT; i++) { @@ -1759,20 +1762,7 @@ void glue(helper_roundss, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s, prev_rounding_mode = env->sse_status.float_rounding_mode; if (!(mode & (1 << 2))) { - switch (mode & 3) { - case 0: - set_float_rounding_mode(float_round_nearest_even, &env->sse_status); - break; - case 1: - set_float_rounding_mode(float_round_down, &env->sse_status); - break; - case 2: - set_float_rounding_mode(float_round_up, &env->sse_status); - break; - case 3: - set_float_rounding_mode(float_round_to_zero, &env->sse_status); - break; - } + set_x86_rounding_mode(mode & 3, &env->sse_status); } d->ZMM_S(0) = float32_round_to_int(s->ZMM_S(0), &env->sse_status); @@ -1797,20 +1787,7 @@ void glue(helper_roundsd, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s, prev_rounding_mode = env->sse_status.float_rounding_mode; if (!(mode & (1 << 2))) { - switch (mode & 3) { - case 0: - set_float_rounding_mode(float_round_nearest_even, &env->sse_status); - break; - case 1: - set_float_rounding_mode(float_round_down, &env->sse_status); - break; - case 2: - set_float_rounding_mode(float_round_up, &env->sse_status); - break; - case 3: - set_float_rounding_mode(float_round_to_zero, &env->sse_status); - break; - } + set_x86_rounding_mode(mode & 3, &env->sse_status); } d->ZMM_D(0) = float64_round_to_int(s->ZMM_D(0), &env->sse_status); @@ -2545,6 +2522,33 @@ void helper_vpermd_ymm(Reg *d, Reg *v, Reg *s) } #endif +/* FMA3 op helpers */ +#if SHIFT == 1 +#define SSE_HELPER_FMAS(name, elem, F) \ + void name(CPUX86State *env, Reg *d, Reg *a, Reg *b, Reg *c, int flags) \ + { \ + d->elem(0) = F(a->elem(0), b->elem(0), c->elem(0), flags, &env->sse_status); \ + } +#define SSE_HELPER_FMAP(name, elem, num, F) \ + void glue(name, SUFFIX)(CPUX86State *env, Reg *d, Reg *a, Reg *b, Reg *c, \ + int flags, int flip) \ + { \ + int i; \ + for (i = 0; i < num; i++) { \ + d->elem(i) = F(a->elem(i), b->elem(i), c->elem(i), flags, &env->sse_status); \ + flags ^= flip; \ + } \ + } + +SSE_HELPER_FMAS(helper_fma4ss, ZMM_S, float32_muladd) +SSE_HELPER_FMAS(helper_fma4sd, ZMM_D, float64_muladd) +#endif + +#if SHIFT >= 1 +SSE_HELPER_FMAP(helper_fma4ps, ZMM_S, 2 << SHIFT, float32_muladd) +SSE_HELPER_FMAP(helper_fma4pd, ZMM_D, 1 << SHIFT, float64_muladd) +#endif + #undef SSE_HELPER_S #undef LANE_WIDTH |