uint64_t val_n1 = aarch64_get_vec_u64 (cpu, vn, 0);
uint64_t val_n2 = aarch64_get_vec_u64 (cpu, vn, 1);
- uint64_t val1 = 0;
- uint64_t val2 = 0;
+ uint64_t val1;
+ uint64_t val2;
- uint64_t input1 = upper ? val_n1 : val_m1;
- uint64_t input2 = upper ? val_n2 : val_m2;
- unsigned i;
+ uint64_t input2 = full ? val_n2 : val_m1;
NYI_assert (29, 24, 0x0E);
NYI_assert (21, 21, 0);
NYI_assert (13, 10, 6);
TRACE_DECODE (cpu, "emulated at line %d", __LINE__);
- switch (INSTR (23, 23))
+ switch (INSTR (23, 22))
{
case 0:
- for (i = 0; i < 8; i++)
+ val1 = (val_n1 >> (upper * 8)) & 0xFFULL;
+ val1 |= (val_n1 >> ((upper * 8) + 8)) & 0xFF00ULL;
+ val1 |= (val_n1 >> ((upper * 8) + 16)) & 0xFF0000ULL;
+ val1 |= (val_n1 >> ((upper * 8) + 24)) & 0xFF000000ULL;
+
+ val1 |= (input2 << (32 - (upper * 8))) & 0xFF00000000ULL;
+ val1 |= (input2 << (24 - (upper * 8))) & 0xFF0000000000ULL;
+ val1 |= (input2 << (16 - (upper * 8))) & 0xFF000000000000ULL;
+ val1 |= (input2 << (8 - (upper * 8))) & 0xFF00000000000000ULL;
+
+ if (full)
{
- val1 |= (input1 >> (i * 8)) & (0xFFULL << (i * 8));
- val2 |= (input2 >> (i * 8)) & (0xFFULL << (i * 8));
+ val2 = (val_m1 >> (upper * 8)) & 0xFFULL;
+ val2 |= (val_m1 >> ((upper * 8) + 8)) & 0xFF00ULL;
+ val2 |= (val_m1 >> ((upper * 8) + 16)) & 0xFF0000ULL;
+ val2 |= (val_m1 >> ((upper * 8) + 24)) & 0xFF000000ULL;
+
+ val2 |= (val_m2 << (32 - (upper * 8))) & 0xFF00000000ULL;
+ val2 |= (val_m2 << (24 - (upper * 8))) & 0xFF0000000000ULL;
+ val2 |= (val_m2 << (16 - (upper * 8))) & 0xFF000000000000ULL;
+ val2 |= (val_m2 << (8 - (upper * 8))) & 0xFF00000000000000ULL;
}
break;
case 1:
- for (i = 0; i < 4; i++)
+ val1 = (val_n1 >> (upper * 16)) & 0xFFFFULL;
+ val1 |= (val_n1 >> ((upper * 16) + 16)) & 0xFFFF0000ULL;
+
+ val1 |= (input2 << (32 - (upper * 16))) & 0xFFFF00000000ULL;;
+ val1 |= (input2 << (16 - (upper * 16))) & 0xFFFF000000000000ULL;
+
+ if (full)
{
- val1 |= (input1 >> (i * 16)) & (0xFFFFULL << (i * 16));
- val2 |= (input2 >> (i * 16)) & (0xFFFFULL << (i * 16));
+ val2 = (val_m1 >> (upper * 16)) & 0xFFFFULL;
+ val2 |= (val_m1 >> ((upper * 16) + 16)) & 0xFFFF0000ULL;
+
+ val2 |= (val_m2 << (32 - (upper * 16))) & 0xFFFF00000000ULL;
+ val2 |= (val_m2 << (16 - (upper * 16))) & 0xFFFF000000000000ULL;
}
break;
case 2:
- val1 = ((input1 & 0xFFFFFFFF) | ((input1 >> 32) & 0xFFFFFFFF00000000ULL));
- val2 = ((input2 & 0xFFFFFFFF) | ((input2 >> 32) & 0xFFFFFFFF00000000ULL));
+ val1 = (val_n1 >> (upper * 32)) & 0xFFFFFFFF;
+ val1 |= (input2 << (32 - (upper * 32))) & 0xFFFFFFFF00000000ULL;
+
+ if (full)
+ {
+ val2 = (val_m1 >> (upper * 32)) & 0xFFFFFFFF;
+ val2 |= (val_m2 << (32 - (upper * 32))) & 0xFFFFFFFF00000000ULL;
+ }
+ break;
case 3:
- val1 = input1;
- val2 = input2;
- break;
+ if (! full)
+ HALT_UNALLOC;
+
+ val1 = upper ? val_n2 : val_n1;
+ val2 = upper ? val_m2 : val_m1;
+ break;
}
aarch64_set_vec_u64 (cpu, vd, 0, val1);
case 0x8: /* 16-bit, no shift. */
for (i = 0; i < (full ? 8 : 4); i++)
aarch64_set_vec_u16 (cpu, vd, i, val);
- /* Fall through. */
+ break;
+
case 0xd: /* 32-bit, mask shift by 16. */
val <<= 8;
val |= 0xFF;
case 0:
for (i = 0; i < (full ? 16 : 8); i++)
val += aarch64_get_vec_u8 (cpu, vm, i);
- aarch64_set_reg_u64 (cpu, rd, NO_SP, val);
+ aarch64_set_vec_u64 (cpu, rd, 0, val);
return;
case 1:
for (i = 0; i < (full ? 8 : 4); i++)
val += aarch64_get_vec_u16 (cpu, vm, i);
- aarch64_set_reg_u64 (cpu, rd, NO_SP, val);
+ aarch64_set_vec_u64 (cpu, rd, 0, val);
return;
case 2:
- for (i = 0; i < (full ? 4 : 2); i++)
+ if (! full)
+ HALT_UNALLOC;
+ for (i = 0; i < 4; i++)
val += aarch64_get_vec_u32 (cpu, vm, i);
- aarch64_set_reg_u64 (cpu, rd, NO_SP, val);
+ aarch64_set_vec_u64 (cpu, rd, 0, val);
return;
case 3:
- if (! full)
- HALT_UNALLOC;
- val = aarch64_get_vec_u64 (cpu, vm, 0);
- val += aarch64_get_vec_u64 (cpu, vm, 1);
- aarch64_set_reg_u64 (cpu, rd, NO_SP, val);
- return;
+ HALT_UNALLOC;
}
}
switch (INSTR (23, 22))
{
case 0:
- DO_VEC_WIDENING_MUL (full ? 16 : 8, uint16_t, u8, u16);
+ DO_VEC_WIDENING_MUL (full ? 16 : 8, uint8_t, u8, u8);
return;
case 1:
- DO_VEC_WIDENING_MUL (full ? 8 : 4, uint32_t, u16, u32);
+ DO_VEC_WIDENING_MUL (full ? 8 : 4, uint16_t, u16, u16);
return;
case 2:
- DO_VEC_WIDENING_MUL (full ? 4 : 2, uint64_t, u32, u64);
+ DO_VEC_WIDENING_MUL (full ? 4 : 2, uint32_t, u32, u32);
return;
case 3:
static float
fmaxnm (float a, float b)
{
- if (fpclassify (a) == FP_NORMAL)
+ if (! isnan (a))
{
- if (fpclassify (b) == FP_NORMAL)
+ if (! isnan (b))
return a > b ? a : b;
return a;
}
- else if (fpclassify (b) == FP_NORMAL)
+ else if (! isnan (b))
return b;
return a;
}
static float
fminnm (float a, float b)
{
- if (fpclassify (a) == FP_NORMAL)
+ if (! isnan (a))
{
- if (fpclassify (b) == FP_NORMAL)
+ if (! isnan (b))
return a < b ? a : b;
return a;
}
- else if (fpclassify (b) == FP_NORMAL)
+ else if (! isnan (b))
return b;
return a;
}
static double
dmaxnm (double a, double b)
{
- if (fpclassify (a) == FP_NORMAL)
+ if (! isnan (a))
{
- if (fpclassify (b) == FP_NORMAL)
+ if (! isnan (b))
return a > b ? a : b;
return a;
}
- else if (fpclassify (b) == FP_NORMAL)
+ else if (! isnan (b))
return b;
return a;
}
static double
dminnm (double a, double b)
{
- if (fpclassify (a) == FP_NORMAL)
+ if (! isnan (a))
{
- if (fpclassify (b) == FP_NORMAL)
+ if (! isnan (b))
return a < b ? a : b;
return a;
}
- else if (fpclassify (b) == FP_NORMAL)
+ else if (! isnan (b))
return b;
return a;
}
switch (INSTR (23, 22))
{
case 0:
- if (bias)
- for (i = 0; i < 8; i++)
- aarch64_set_vec_u8 (cpu, vd, i + 8,
- aarch64_get_vec_u16 (cpu, vs, i) >> 8);
- else
- for (i = 0; i < 8; i++)
- aarch64_set_vec_u8 (cpu, vd, i, aarch64_get_vec_u16 (cpu, vs, i));
+ for (i = 0; i < 8; i++)
+ aarch64_set_vec_u8 (cpu, vd, i + (bias * 8),
+ aarch64_get_vec_u16 (cpu, vs, i));
return;
case 1:
- if (bias)
- for (i = 0; i < 4; i++)
- aarch64_set_vec_u16 (cpu, vd, i + 4,
- aarch64_get_vec_u32 (cpu, vs, i) >> 16);
- else
- for (i = 0; i < 4; i++)
- aarch64_set_vec_u16 (cpu, vd, i, aarch64_get_vec_u32 (cpu, vs, i));
+ for (i = 0; i < 4; i++)
+ aarch64_set_vec_u16 (cpu, vd, i + (bias * 4),
+ aarch64_get_vec_u32 (cpu, vs, i));
return;
case 2:
- if (bias)
- for (i = 0; i < 2; i++)
- aarch64_set_vec_u32 (cpu, vd, i + 4,
- aarch64_get_vec_u64 (cpu, vs, i) >> 32);
- else
- for (i = 0; i < 2; i++)
- aarch64_set_vec_u32 (cpu, vd, i, aarch64_get_vec_u64 (cpu, vs, i));
+ for (i = 0; i < 2; i++)
+ aarch64_set_vec_u32 (cpu, vd, i + (bias * 2),
+ aarch64_get_vec_u64 (cpu, vs, i));
return;
}
}
case 0:
for (i = 0; i < (full ? 16 : 8); i++)
aarch64_set_vec_u8 (cpu, vd, i,
- (aarch64_get_vec_u8 (cpu, vn, i)
- * aarch64_get_vec_u8 (cpu, vm, i))
- - aarch64_get_vec_u8 (cpu, vd, i));
+ aarch64_get_vec_u8 (cpu, vd, i)
+ - (aarch64_get_vec_u8 (cpu, vn, i)
+ * aarch64_get_vec_u8 (cpu, vm, i)));
return;
case 1:
for (i = 0; i < (full ? 8 : 4); i++)
aarch64_set_vec_u16 (cpu, vd, i,
- (aarch64_get_vec_u16 (cpu, vn, i)
- * aarch64_get_vec_u16 (cpu, vm, i))
- - aarch64_get_vec_u16 (cpu, vd, i));
+ aarch64_get_vec_u16 (cpu, vd, i)
+ - (aarch64_get_vec_u16 (cpu, vn, i)
+ * aarch64_get_vec_u16 (cpu, vm, i)));
return;
case 2:
for (i = 0; i < (full ? 4 : 2); i++)
aarch64_set_vec_u32 (cpu, vd, i,
- (aarch64_get_vec_u32 (cpu, vn, i)
- * aarch64_get_vec_u32 (cpu, vm, i))
- - aarch64_get_vec_u32 (cpu, vd, i));
+ aarch64_get_vec_u32 (cpu, vd, i)
+ - (aarch64_get_vec_u32 (cpu, vn, i)
+ * aarch64_get_vec_u32 (cpu, vm, i)));
return;
default:
TRACE_DECODE (cpu, "emulated at line %d", __LINE__);
if (INSTR (22, 22))
- aarch64_set_FP_double (cpu, sd, set ? sn : sm);
+ aarch64_set_FP_double (cpu, sd, (set ? aarch64_get_FP_double (cpu, sn)
+ : aarch64_get_FP_double (cpu, sm)));
else
- aarch64_set_FP_float (cpu, sd, set ? sn : sm);
+ aarch64_set_FP_float (cpu, sd, (set ? aarch64_get_FP_float (cpu, sn)
+ : aarch64_get_FP_float (cpu, sm)));
}
/* Store 32 bit unscaled signed 9 bit. */
static const double DOUBLE_LONG_MAX = (double) LONG_MAX;
static const double DOUBLE_LONG_MIN = (double) LONG_MIN;
+#define UINT_MIN 0
+#define ULONG_MIN 0
+static const float FLOAT_UINT_MAX = (float) UINT_MAX;
+static const float FLOAT_UINT_MIN = (float) UINT_MIN;
+static const double DOUBLE_UINT_MAX = (double) UINT_MAX;
+static const double DOUBLE_UINT_MIN = (double) UINT_MIN;
+static const float FLOAT_ULONG_MAX = (float) ULONG_MAX;
+static const float FLOAT_ULONG_MIN = (float) ULONG_MIN;
+static const double DOUBLE_ULONG_MAX = (double) ULONG_MAX;
+static const double DOUBLE_ULONG_MIN = (double) ULONG_MIN;
+
/* Check for FP exception conditions:
NaN raises IO
Infinity raises IO
/* Do not raise an exception if we have reached ULONG_MAX. */
if (value != (1UL << 63))
- RAISE_EXCEPTIONS (d, value, DOUBLE, LONG);
+ RAISE_EXCEPTIONS (d, value, DOUBLE, ULONG);
aarch64_set_reg_u64 (cpu, rd, NO_SP, value);
}
/* Do not raise an exception if we have reached ULONG_MAX. */
if (value != (1UL << 63))
- RAISE_EXCEPTIONS (f, value, FLOAT, LONG);
+ RAISE_EXCEPTIONS (f, value, FLOAT, ULONG);
aarch64_set_reg_u64 (cpu, rd, NO_SP, value);
}
value = (uint32_t) d;
/* Do not raise an exception if we have reached UINT_MAX. */
if (value != (1UL << 31))
- RAISE_EXCEPTIONS (d, value, DOUBLE, INT);
+ RAISE_EXCEPTIONS (d, value, DOUBLE, UINT);
}
else
{
value = (uint32_t) f;
/* Do not raise an exception if we have reached UINT_MAX. */
if (value != (1UL << 31))
- RAISE_EXCEPTIONS (f, value, FLOAT, INT);
+ RAISE_EXCEPTIONS (f, value, FLOAT, UINT);
}
aarch64_set_reg_u64 (cpu, rd, NO_SP, value);