diff options
| author | Uros Bizjak <ubizjak@gmail.com> | 2007-06-19 21:58:26 +0200 |
|---|---|---|
| committer | Uros Bizjak <uros@gcc.gnu.org> | 2007-06-19 21:58:26 +0200 |
| commit | 670a8526bcc1f6c3330e27cb248a2208e616fa3f (patch) | |
| tree | 0b6c75c86430e89308b379f25d73b8e2161fd3cc | |
| parent | 89a95777068068a29677510065120620abd202f1 (diff) | |
| download | gcc-670a8526bcc1f6c3330e27cb248a2208e616fa3f.zip gcc-670a8526bcc1f6c3330e27cb248a2208e616fa3f.tar.gz gcc-670a8526bcc1f6c3330e27cb248a2208e616fa3f.tar.bz2 | |
i386.c (ix86_emit_swsqrtsf): Filter out infinity result of rsqrt insn for zero input argument to avoid NaN.
* config/i386/i386.c (ix86_emit_swsqrtsf): Filter out infinity
result of rsqrt insn for zero input argument to avoid NaN.
From-SVN: r125858
| -rw-r--r-- | gcc/ChangeLog | 4 | ||||
| -rw-r--r-- | gcc/config/i386/i386.c | 26 |
2 files changed, 21 insertions, 9 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 2c19891..32754f5 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -106,8 +106,8 @@ 2007-06-19 Uros Bizjak <ubizjak@gmail.com> - * config/i386/i386.c (ix86_emit_swsqrtsf): Limit the result of - rsqrt insn to FLT_MAX to avoid NaN for zero input argument. + * config/i386/i386.c (ix86_emit_swsqrtsf): Filter out infinity + result of rsqrt insn for zero input argument to avoid NaN. 2007-06-19 Richard Guenther <rguenther@suse.de> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 204373c..1a8fa11 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -22593,7 +22593,7 @@ void ix86_emit_swdivsf (rtx res, rtx a, rtx b, enum machine_mode mode) 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); @@ -22603,29 +22603,41 @@ void ix86_emit_swsqrtsf (rtx res, rtx a, enum machine_mode 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))); |