OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

target-ppc: use the softfloat float32_muladd function

Browse Source 
Use the new softfloat float32_muladd() function to implement the vmaddfp
and vnmsubfp instructions. As a bonus we can get rid of the call to the
HANDLE_NAN3 macro, as the NaN handling is directly done at the softfloat
level.

Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Alexander Graf <agraf@suse.de>
This commit is contained in:
Aurelien Jarno 2012-09-11 08:47:12 +00:00 committed by Alexander Graf
parent db1babb8db
commit 2f93c23fe7
1 changed files with 14 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
target-ppc/int_helper.c
View File

@ -418,6 +418,20 @@ VARITHFP(minfp, float32_min)
VARITHFP(maxfp, float32_max) VARITHFP(maxfp, float32_max)
#undef VARITHFP #undef VARITHFP
#define VARITHFPFMA(suffix, type) \
void helper_v##suffix(CPUPPCState *env, 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++) { \
r->f[i] = float32_muladd(a->f[i], c->f[i], b->f[i], \
type, &env->vec_status); \
} \
}
VARITHFPFMA(maddfp, 0);
VARITHFPFMA(nmsubfp, float_muladd_negate_result | float_muladd_negate_c);
#undef VARITHFPFMA
#define VARITHSAT_CASE(type, op, cvt, element) \ #define VARITHSAT_CASE(type, op, cvt, element) \
{ \ { \
type result = (type)a->element[i] op (type)b->element[i]; \ type result = (type)a->element[i] op (type)b->element[i]; \
@ -649,27 +663,6 @@ VCT(uxs, cvtsduw, u32)
VCT(sxs, cvtsdsw, s32) VCT(sxs, cvtsdsw, s32)
#undef VCT #undef VCT
void helper_vmaddfp(CPUPPCState *env, 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(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, void helper_vmhaddshs(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a,
ppc_avr_t *b, ppc_avr_t *c) ppc_avr_t *b, ppc_avr_t *c)
{ {
@ -909,28 +902,6 @@ VMUL(uh, u16, u32)
#undef VMUL_DO #undef VMUL_DO
#undef VMUL #undef VMUL
void helper_vnmsubfp(CPUPPCState *env, 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(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, void helper_vperm(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b,
ppc_avr_t *c) ppc_avr_t *c)
{ {