s390x/tcg: Simplify vop64_2() handling

Let's rework our macros and simplify. We still need helper functions in
most cases due to the different parameters types.

Next, we'll only have 32/128bit variants for vfi and vfsq, so special
case the others.

Note that for vfsq, the XxC and erm passed in the simd_data() will never be
set, resulting in the same behavior.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210608092337.12221-5-david@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
This commit is contained in:
David Hildenbrand 2021-06-08 11:23:15 +02:00 committed by Cornelia Huck
parent 863b9507a6
commit 21bd6ea2b3
3 changed files with 58 additions and 156 deletions

View File

@ -262,16 +262,11 @@ DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i3
DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_5(gvec_vfche64s_cc, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcdg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcdlg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
@ -282,7 +277,6 @@ DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, en
DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32)

View File

@ -2558,19 +2558,19 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o)
switch (s->fields.op2) {
case 0xc3:
fn = se ? gen_helper_gvec_vcdg64s : gen_helper_gvec_vcdg64;
fn = gen_helper_gvec_vcdg64;
break;
case 0xc1:
fn = se ? gen_helper_gvec_vcdlg64s : gen_helper_gvec_vcdlg64;
fn = gen_helper_gvec_vcdlg64;
break;
case 0xc2:
fn = se ? gen_helper_gvec_vcgd64s : gen_helper_gvec_vcgd64;
fn = gen_helper_gvec_vcgd64;
break;
case 0xc0:
fn = se ? gen_helper_gvec_vclgd64s : gen_helper_gvec_vclgd64;
fn = gen_helper_gvec_vclgd64;
break;
case 0xc7:
fn = se ? gen_helper_gvec_vfi64s : gen_helper_gvec_vfi64;
fn = gen_helper_gvec_vfi64;
break;
case 0xc5:
fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64;
@ -2681,18 +2681,14 @@ static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o)
{
const uint8_t fpf = get_field(s, m3);
const uint8_t m4 = get_field(s, m4);
gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfsq64;
if (fpf != FPF_LONG || extract32(m4, 0, 3)) {
gen_program_exception(s, PGM_SPECIFICATION);
return DISAS_NORETURN;
}
if (extract32(m4, 3, 1)) {
fn = gen_helper_gvec_vfsq64s;
}
gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env,
0, fn);
gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4,
gen_helper_gvec_vfsq64);
return DISAS_NEXT;
}

View File

@ -88,7 +88,7 @@ static void s390_vec_write_float64(S390Vector *v, uint8_t enr, float64 data)
return s390_vec_write_element64(v, enr, data);
}
typedef uint64_t (*vop64_2_fn)(uint64_t a, float_status *s);
typedef float64 (*vop64_2_fn)(float64 a, float_status *s);
static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
bool s, bool XxC, uint8_t erm, vop64_2_fn fn,
uintptr_t retaddr)
@ -99,9 +99,9 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
old_mode = s390_swap_bfp_rounding_mode(env, erm);
for (i = 0; i < 2; i++) {
const uint64_t a = s390_vec_read_element64(v2, i);
const float64 a = s390_vec_read_float64(v2, i);
s390_vec_write_element64(&tmp, i, fn(a, &env->fpu_status));
s390_vec_write_float64(&tmp, i, fn(a, &env->fpu_status));
vxc = check_ieee_exc(env, i, XxC, &vec_exc);
if (s || vxc) {
break;
@ -112,6 +112,54 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
*v1 = tmp;
}
static float64 vcdg64(float64 a, float_status *s)
{
return int64_to_float64(a, s);
}
static float64 vcdlg64(float64 a, float_status *s)
{
return uint64_to_float64(a, s);
}
static float64 vcgd64(float64 a, float_status *s)
{
const float64 tmp = float64_to_int64(a, s);
return float64_is_any_nan(a) ? INT64_MIN : tmp;
}
static float64 vclgd64(float64 a, float_status *s)
{
const float64 tmp = float64_to_uint64(a, s);
return float64_is_any_nan(a) ? 0 : tmp;
}
#define DEF_GVEC_VOP2_FN(NAME, FN, BITS) \
void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env, \
uint32_t desc) \
{ \
const uint8_t erm = extract32(simd_data(desc), 4, 4); \
const bool se = extract32(simd_data(desc), 3, 1); \
const bool XxC = extract32(simd_data(desc), 2, 1); \
\
vop##BITS##_2(v1, v2, env, se, XxC, erm, FN, GETPC()); \
}
#define DEF_GVEC_VOP2_64(NAME) \
DEF_GVEC_VOP2_FN(NAME, NAME##64, 64)
#define DEF_GVEC_VOP2(NAME, OP) \
DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64)
DEF_GVEC_VOP2_64(vcdg)
DEF_GVEC_VOP2_64(vcdlg)
DEF_GVEC_VOP2_64(vcgd)
DEF_GVEC_VOP2_64(vclgd)
DEF_GVEC_VOP2(vfi, round_to_int)
DEF_GVEC_VOP2(vfsq, sqrt)
typedef float64 (*vop64_3_fn)(float64 a, float64 b, float_status *s);
static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
CPUS390XState *env, bool s, vop64_3_fn fn,
@ -285,125 +333,6 @@ void HELPER(gvec_vfche64s_cc)(void *v1, const void *v2, const void *v3,
env->cc_op = vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC());
}
static uint64_t vcdg64(uint64_t a, float_status *s)
{
return int64_to_float64(a, s);
}
void HELPER(gvec_vcdg64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, false, XxC, erm, vcdg64, GETPC());
}
void HELPER(gvec_vcdg64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, true, XxC, erm, vcdg64, GETPC());
}
static uint64_t vcdlg64(uint64_t a, float_status *s)
{
return uint64_to_float64(a, s);
}
void HELPER(gvec_vcdlg64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, false, XxC, erm, vcdlg64, GETPC());
}
void HELPER(gvec_vcdlg64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, true, XxC, erm, vcdlg64, GETPC());
}
static uint64_t vcgd64(uint64_t a, float_status *s)
{
const uint64_t tmp = float64_to_int64(a, s);
return float64_is_any_nan(a) ? INT64_MIN : tmp;
}
void HELPER(gvec_vcgd64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, false, XxC, erm, vcgd64, GETPC());
}
void HELPER(gvec_vcgd64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, true, XxC, erm, vcgd64, GETPC());
}
static uint64_t vclgd64(uint64_t a, float_status *s)
{
const uint64_t tmp = float64_to_uint64(a, s);
return float64_is_any_nan(a) ? 0 : tmp;
}
void HELPER(gvec_vclgd64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, false, XxC, erm, vclgd64, GETPC());
}
void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC());
}
static uint64_t vfi64(uint64_t a, float_status *s)
{
return float64_round_to_int(a, s);
}
void HELPER(gvec_vfi64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, false, XxC, erm, vfi64, GETPC());
}
void HELPER(gvec_vfi64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
const uint8_t erm = extract32(simd_data(desc), 4, 4);
const bool XxC = extract32(simd_data(desc), 2, 1);
vop64_2(v1, v2, env, true, XxC, erm, vfi64, GETPC());
}
static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
bool s, uintptr_t retaddr)
{
@ -530,23 +459,6 @@ void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
}
static uint64_t vfsq64(uint64_t a, float_status *s)
{
return float64_sqrt(a, s);
}
void HELPER(gvec_vfsq64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
vop64_2(v1, v2, env, false, false, 0, vfsq64, GETPC());
}
void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
{
vop64_2(v1, v2, env, true, false, 0, vfsq64, GETPC());
}
static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env,
bool s, uint16_t i3)
{