// Computes aR * bR mod N with R = 2**64.
inline uint64_t montmul64(uint64_t a, uint64_t b, uint64_t N, uint64_t Nneginv) {
std::pair<uint64_t, uint64_t> T, mN;
uint64_t Th, Tl, m, mNh, mNl, th;
std::tie(Th, Tl) = mulu64(a, b);
m = Tl * Nneginv;
std::tie(mNh, mNl) = mulu64(m, N);
bool lc = Tl + mNl < Tl;
th = Th + mNh + lc;
bool hc = (th < Th) || (th == Th && lc);
if (hc > 0 || th >= N) th = th - N;
return th;
}
static void test_u(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(test_u_data); ++i) {
uint64_t rl, rh;
mulu64(&rl, &rh, test_u_data[i].a, test_u_data[i].b);
g_assert_cmpuint(rl, ==, test_u_data[i].rl);
g_assert_cmpuint(rh, ==, test_u_data[i].rh);
}
}
uint64_t HELPER(muluh_i64)(uint64_t arg1, uint64_t arg2)
{
uint64_t l, h;
mulu64(&l, &h, arg1, arg2);
return h;
}
static TCGArg do_constant_folding_2(TCGOpcode op, TCGArg x, TCGArg y)
{
uint64_t l64, h64;
switch (op) {
CASE_OP_32_64(add):
return x + y;
CASE_OP_32_64(sub):
return x - y;
CASE_OP_32_64(mul):
return x * y;
CASE_OP_32_64(and):
return x & y;
CASE_OP_32_64(or):
return x | y;
CASE_OP_32_64(xor):
return x ^ y;
case INDEX_op_shl_i32:
return (uint32_t)x << (y & 31);
case INDEX_op_shl_i64:
return (uint64_t)x << (y & 63);
case INDEX_op_shr_i32:
return (uint32_t)x >> (y & 31);
case INDEX_op_trunc_shr_i32:
case INDEX_op_shr_i64:
return (uint64_t)x >> (y & 63);
case INDEX_op_sar_i32:
return (int32_t)x >> (y & 31);
case INDEX_op_sar_i64:
return (int64_t)x >> (y & 63);
case INDEX_op_rotr_i32:
return ror32(x, y & 31);
case INDEX_op_rotr_i64:
return (TCGArg)ror64(x, y & 63);
case INDEX_op_rotl_i32:
return rol32(x, y & 31);
case INDEX_op_rotl_i64:
return (TCGArg)rol64(x, y & 63);
CASE_OP_32_64(not):
return ~x;
CASE_OP_32_64(neg):
return 0-x;
CASE_OP_32_64(andc):
return x & ~y;
CASE_OP_32_64(orc):
return x | ~y;
CASE_OP_32_64(eqv):
return ~(x ^ y);
CASE_OP_32_64(nand):
return ~(x & y);
CASE_OP_32_64(nor):
return ~(x | y);
CASE_OP_32_64(ext8s):
return (int8_t)x;
CASE_OP_32_64(ext16s):
return (int16_t)x;
CASE_OP_32_64(ext8u):
return (uint8_t)x;
CASE_OP_32_64(ext16u):
return (uint16_t)x;
case INDEX_op_ext32s_i64:
return (int32_t)x;
case INDEX_op_ext32u_i64:
return (uint32_t)x;
case INDEX_op_muluh_i32:
return ((uint64_t)(uint32_t)x * (uint32_t)y) >> 32;
case INDEX_op_mulsh_i32:
return ((int64_t)(int32_t)x * (int32_t)y) >> 32;
case INDEX_op_muluh_i64:
mulu64(&l64, &h64, x, y);
return (TCGArg)h64;
case INDEX_op_mulsh_i64:
muls64(&l64, &h64, x, y);
return (TCGArg)h64;
case INDEX_op_div_i32:
/* Avoid crashing on divide by zero, otherwise undefined. */
return (int32_t)x / ((int32_t)y ? (int32_t)y : 1);
case INDEX_op_divu_i32:
return (uint32_t)x / ((uint32_t)y ? (uint32_t)y : 1);
case INDEX_op_div_i64:
return (int64_t)x / ((int64_t)y ? (int64_t)y : 1);
case INDEX_op_divu_i64:
return (uint64_t)x / ((uint64_t)y ? (uint64_t)y : 1);
case INDEX_op_rem_i32:
return (int32_t)x % ((int32_t)y ? (int32_t)y : 1);
case INDEX_op_remu_i32:
return (uint32_t)x % ((uint32_t)y ? (uint32_t)y : 1);
case INDEX_op_rem_i64:
return (int64_t)x % ((int64_t)y ? (int64_t)y : 1);
case INDEX_op_remu_i64:
return (uint64_t)x % ((uint64_t)y ? (uint64_t)y : 1);
default:
fprintf(stderr,
"Unrecognized operation %d in do_constant_folding.\n", op);
tcg_abort();
}
}
