void ix86_emit_swsqrtsf (rtx res, rtx a, enum machine_mode mode,
bool recip)
{
- rtx x0, e0, e1, e2, e3, three, half, bignum;
+ rtx x0, e0, e1, e2, e3, three, half, zero, mask;
x0 = gen_reg_rtx (mode);
e0 = gen_reg_rtx (mode);
three = CONST_DOUBLE_FROM_REAL_VALUE (dconst3, SFmode);
half = CONST_DOUBLE_FROM_REAL_VALUE (dconsthalf, SFmode);
- bignum = gen_lowpart (SFmode, GEN_INT (0x7f7fffff));
+
+ mask = gen_reg_rtx (mode);
if (VECTOR_MODE_P (mode))
{
three = ix86_build_const_vector (SFmode, true, three);
half = ix86_build_const_vector (SFmode, true, half);
- bignum = ix86_build_const_vector (SFmode, true, bignum);
}
three = force_reg (mode, three);
half = force_reg (mode, half);
- bignum = force_reg (mode, bignum);
+
+ zero = force_reg (mode, CONST0_RTX(mode));
/* sqrt(a) = 0.5 * a * rsqrtss(a) * (3.0 - a * rsqrtss(a) * rsqrtss(a))
1.0 / sqrt(a) = 0.5 * rsqrtss(a) * (3.0 - a * rsqrtss(a) * rsqrtss(a)) */
+ /* Compare a to zero. */
+ emit_insn (gen_rtx_SET (VOIDmode, mask,
+ gen_rtx_NE (mode, a, zero)));
+
/* x0 = 1./sqrt(a) estimate */
emit_insn (gen_rtx_SET (VOIDmode, x0,
gen_rtx_UNSPEC (mode, gen_rtvec (1, a),
UNSPEC_RSQRT)));
- emit_insn (gen_rtx_SET (VOIDmode, x0,
- gen_rtx_SMIN (mode, x0, bignum)));
-
+ /* Filter out infinity. */
+ if (VECTOR_MODE_P (mode))
+ emit_insn (gen_rtx_SET (VOIDmode, gen_lowpart (V4SFmode, x0),
+ gen_rtx_AND (mode,
+ gen_lowpart (V4SFmode, x0),
+ gen_lowpart (V4SFmode, mask))));
+ else
+ emit_insn (gen_rtx_SET (VOIDmode, x0,
+ gen_rtx_AND (mode, x0, mask)));
+
/* e0 = x0 * a */
emit_insn (gen_rtx_SET (VOIDmode, e0,
gen_rtx_MULT (mode, x0, a)));