/* fre - fre. */
uint64_t helper_fre (uint64_t arg)
{
- CPU_DoubleU fone, farg;
- fone.ll = 0x3FF0000000000000ULL; /* 1.0 */
+ CPU_DoubleU farg;
farg.ll = arg;
if (unlikely(float64_is_signaling_nan(farg.d))) {
/* sNaN reciprocal */
farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN);
} else {
- farg.d = float64_div(fone.d, farg.d, &env->fp_status);
+ farg.d = float64_div(float64_one, farg.d, &env->fp_status);
}
return farg.d;
}
/* fres - fres. */
uint64_t helper_fres (uint64_t arg)
{
- CPU_DoubleU fone, farg;
+ CPU_DoubleU farg;
float32 f32;
- fone.ll = 0x3FF0000000000000ULL; /* 1.0 */
farg.ll = arg;
if (unlikely(float64_is_signaling_nan(farg.d))) {
/* sNaN reciprocal */
farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSNAN);
} else {
- farg.d = float64_div(fone.d, farg.d, &env->fp_status);
+ farg.d = float64_div(float64_one, farg.d, &env->fp_status);
f32 = float64_to_float32(farg.d, &env->fp_status);
farg.d = float32_to_float64(f32, &env->fp_status);
}
/* frsqrte - frsqrte. */
uint64_t helper_frsqrte (uint64_t arg)
{
- CPU_DoubleU fone, farg;
+ CPU_DoubleU farg;
float32 f32;
- fone.ll = 0x3FF0000000000000ULL; /* 1.0 */
farg.ll = arg;
if (unlikely(float64_is_signaling_nan(farg.d))) {
farg.ll = fload_invalid_op_excp(POWERPC_EXCP_FP_VXSQRT);
} else {
farg.d = float64_sqrt(farg.d, &env->fp_status);
- farg.d = float64_div(fone.d, farg.d, &env->fp_status);
+ farg.d = float64_div(float64_one, farg.d, &env->fp_status);
f32 = float64_to_float32(farg.d, &env->fp_status);
farg.d = float32_to_float64(f32, &env->fp_status);
}
for (index = ARRAY_SIZE(r->element)-1; index >= 0; index--)
#endif
+/* If X is a NaN, store the corresponding QNaN into RESULT. Otherwise,
+ * execute the following block. */
+#define DO_HANDLE_NAN(result, x) \
+ if (float32_is_nan(x) || float32_is_signaling_nan(x)) { \
+ CPU_FloatU __f; \
+ __f.f = x; \
+ __f.l = __f.l | (1 << 22); /* Set QNaN bit. */ \
+ result = __f.f; \
+ } else
+
+#define HANDLE_NAN1(result, x) \
+ DO_HANDLE_NAN(result, x)
+#define HANDLE_NAN2(result, x, y) \
+ DO_HANDLE_NAN(result, x) DO_HANDLE_NAN(result, y)
+#define HANDLE_NAN3(result, x, y, z) \
+ DO_HANDLE_NAN(result, x) DO_HANDLE_NAN(result, y) DO_HANDLE_NAN(result, z)
+
/* Saturating arithmetic helpers. */
#define SATCVT(from, to, from_type, to_type, min, max, use_min, use_max) \
static always_inline to_type cvt##from##to (from_type x, int *sat) \
#undef VARITH_DO
#undef VARITH
+#define VARITHFP(suffix, func) \
+ void helper_v##suffix (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
+ { \
+ int i; \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ HANDLE_NAN2(r->f[i], a->f[i], b->f[i]) { \
+ r->f[i] = func(a->f[i], b->f[i], &env->vec_status); \
+ } \
+ } \
+ }
+VARITHFP(addfp, float32_add)
+VARITHFP(subfp, float32_sub)
+#undef VARITHFP
+
#define VARITHSAT_CASE(type, op, cvt, element) \
{ \
type result = (type)a->element[i] op (type)b->element[i]; \
#undef VAVG_DO
#undef VAVG
+#define VCF(suffix, cvt, element) \
+ void helper_vcf##suffix (ppc_avr_t *r, ppc_avr_t *b, uint32_t uim) \
+ { \
+ int i; \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ float32 t = cvt(b->element[i], &env->vec_status); \
+ r->f[i] = float32_scalbn (t, -uim, &env->vec_status); \
+ } \
+ }
+VCF(ux, uint32_to_float32, u32)
+VCF(sx, int32_to_float32, s32)
+#undef VCF
+
#define VCMP_DO(suffix, compare, element, record) \
void helper_vcmp##suffix (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
{ \
#undef VCMP_DO
#undef VCMP
+#define VCMPFP_DO(suffix, compare, order, record) \
+ void helper_vcmp##suffix (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
+ { \
+ uint32_t ones = (uint32_t)-1; \
+ uint32_t all = ones; \
+ uint32_t none = 0; \
+ int i; \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ uint32_t result; \
+ int rel = float32_compare_quiet(a->f[i], b->f[i], &env->vec_status); \
+ if (rel == float_relation_unordered) { \
+ result = 0; \
+ } else if (rel compare order) { \
+ result = ones; \
+ } else { \
+ result = 0; \
+ } \
+ r->u32[i] = result; \
+ all &= result; \
+ none |= result; \
+ } \
+ if (record) { \
+ env->crf[6] = ((all != 0) << 3) | ((none == 0) << 1); \
+ } \
+ }
+#define VCMPFP(suffix, compare, order) \
+ VCMPFP_DO(suffix, compare, order, 0) \
+ VCMPFP_DO(suffix##_dot, compare, order, 1)
+VCMPFP(eqfp, ==, float_relation_equal)
+VCMPFP(gefp, !=, float_relation_less)
+VCMPFP(gtfp, ==, float_relation_greater)
+#undef VCMPFP_DO
+#undef VCMPFP
+
+static always_inline void vcmpbfp_internal (ppc_avr_t *r, ppc_avr_t *a,
+ ppc_avr_t *b, int record)
+{
+ int i;
+ int all_in = 0;
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) {
+ int le_rel = float32_compare_quiet(a->f[i], b->f[i], &env->vec_status);
+ if (le_rel == float_relation_unordered) {
+ r->u32[i] = 0xc0000000;
+ /* ALL_IN does not need to be updated here. */
+ } else {
+ float32 bneg = float32_chs(b->f[i]);
+ int ge_rel = float32_compare_quiet(a->f[i], bneg, &env->vec_status);
+ int le = le_rel != float_relation_greater;
+ int ge = ge_rel != float_relation_less;
+ r->u32[i] = ((!le) << 31) | ((!ge) << 30);
+ all_in |= (!le | !ge);
+ }
+ }
+ if (record) {
+ env->crf[6] = (all_in == 0) << 1;
+ }
+}
+
+void helper_vcmpbfp (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+ vcmpbfp_internal(r, a, b, 0);
+}
+
+void helper_vcmpbfp_dot (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b)
+{
+ vcmpbfp_internal(r, a, b, 1);
+}
+
+#define VCT(suffix, satcvt, element) \
+ void helper_vct##suffix (ppc_avr_t *r, ppc_avr_t *b, uint32_t uim) \
+ { \
+ int i; \
+ int sat = 0; \
+ float_status s = env->vec_status; \
+ set_float_rounding_mode(float_round_to_zero, &s); \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ if (float32_is_nan(b->f[i]) || \
+ float32_is_signaling_nan(b->f[i])) { \
+ r->element[i] = 0; \
+ } else { \
+ float64 t = float32_to_float64(b->f[i], &s); \
+ int64_t j; \
+ t = float64_scalbn(t, uim, &s); \
+ j = float64_to_int64(t, &s); \
+ r->element[i] = satcvt(j, &sat); \
+ } \
+ } \
+ if (sat) { \
+ env->vscr |= (1 << VSCR_SAT); \
+ } \
+ }
+VCT(uxs, cvtsduw, u32)
+VCT(sxs, cvtsdsw, s32)
+#undef VCT
+
+void helper_vmaddfp (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) {
+ HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) {
+ /* Need to do the computation in higher precision and round
+ * once at the end. */
+ float64 af, bf, cf, t;
+ af = float32_to_float64(a->f[i], &env->vec_status);
+ bf = float32_to_float64(b->f[i], &env->vec_status);
+ cf = float32_to_float64(c->f[i], &env->vec_status);
+ t = float64_mul(af, cf, &env->vec_status);
+ t = float64_add(t, bf, &env->vec_status);
+ r->f[i] = float64_to_float32(t, &env->vec_status);
+ }
+ }
+}
+
void helper_vmhaddshs (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
{
int sat = 0;
#undef VMINMAX_DO
#undef VMINMAX
+#define VMINMAXFP(suffix, rT, rF) \
+ void helper_v##suffix (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
+ { \
+ int i; \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ HANDLE_NAN2(r->f[i], a->f[i], b->f[i]) { \
+ if (float32_lt_quiet(a->f[i], b->f[i], &env->vec_status)) { \
+ r->f[i] = rT->f[i]; \
+ } else { \
+ r->f[i] = rF->f[i]; \
+ } \
+ } \
+ } \
+ }
+VMINMAXFP(minfp, a, b)
+VMINMAXFP(maxfp, b, a)
+#undef VMINMAXFP
+
void helper_vmladduhm (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
{
int i;
#undef VMUL_DO
#undef VMUL
+void helper_vnmsubfp (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) {
+ HANDLE_NAN3(r->f[i], a->f[i], b->f[i], c->f[i]) {
+ /* Need to do the computation is higher precision and round
+ * once at the end. */
+ float64 af, bf, cf, t;
+ af = float32_to_float64(a->f[i], &env->vec_status);
+ bf = float32_to_float64(b->f[i], &env->vec_status);
+ cf = float32_to_float64(c->f[i], &env->vec_status);
+ t = float64_mul(af, cf, &env->vec_status);
+ t = float64_sub(t, bf, &env->vec_status);
+ t = float64_chs(t);
+ r->f[i] = float64_to_float32(t, &env->vec_status);
+ }
+ }
+}
+
void helper_vperm (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c)
{
ppc_avr_t result;
#undef VPK
#undef PKBIG
+#define VRFI(suffix, rounding) \
+ void helper_vrfi##suffix (ppc_avr_t *r, ppc_avr_t *b) \
+ { \
+ int i; \
+ float_status s = env->vec_status; \
+ set_float_rounding_mode(rounding, &s); \
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) { \
+ HANDLE_NAN1(r->f[i], b->f[i]) { \
+ r->f[i] = float32_round_to_int (b->f[i], &s); \
+ } \
+ } \
+ }
+VRFI(n, float_round_nearest_even)
+VRFI(m, float_round_down)
+VRFI(p, float_round_up)
+VRFI(z, float_round_to_zero)
+#undef VRFI
+
#define VROTATE(suffix, element) \
void helper_vrl##suffix (ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b) \
{ \
r->u64[1] = (a->u64[1] & ~c->u64[1]) | (b->u64[1] & c->u64[1]);
}
+void helper_vlogefp (ppc_avr_t *r, ppc_avr_t *b)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(r->f); i++) {
+ HANDLE_NAN1(r->f[i], b->f[i]) {
+ r->f[i] = float32_log2(b->f[i], &env->vec_status);
+ }
+ }
+}
+
#if defined(WORDS_BIGENDIAN)
#define LEFT 0
#define RIGHT 1
#undef UPKHI
#undef UPKLO
+#undef DO_HANDLE_NAN
+#undef HANDLE_NAN1
+#undef HANDLE_NAN2
+#undef HANDLE_NAN3
#undef VECTOR_FOR_INORDER_I
#undef HI_IDX
#undef LO_IDX
projects / qemu.git / blobdiff