Commit 2e19adc8 by Richard Earnshaw Committed by Richard Earnshaw

[AArch64] Fix for gcc-7 regression PR 80530


This patch fixes the regression caused by the changes to add square root
estimation when compiling for xgene-1 or exynos-m1 targets.

The issue is that the expand path for the reciprocal estimate square
root pattern assumes that pattern cannot fail once it has been decided
that this expansion path is available, but because the logic deep inside
aarch64_emit_approx_sqrt() differs from use_rsqrt_p() the two disagree
as to what is safe.

This patch refactors the logic to ensure that we cannot unknowingly make
different choices here.

	PR target/80530
	* config/aarch64/aarch64.c (aarch64_emit_approx_sqrt): Ensure
	that the logic for permitting reciprocal estimates matches that
	in use_rsqrt_p.

From-SVN: r247340
parent a96eb6f2
2017-04-27 Richard Earnshaw <rearnsha@arm.com>
PR target/80530
* config/aarch64/aarch64.c (aarch64_emit_approx_sqrt): Ensure
that the logic for permitting reciprocal estimates matches that
in use_rsqrt_p.
2017-04-27 Jakub Jelinek <jakub@redhat.com>
PR c++/80534
......
......@@ -7925,33 +7925,40 @@ aarch64_emit_approx_sqrt (rtx dst, rtx src, bool recp)
machine_mode mode = GET_MODE (dst);
if (GET_MODE_INNER (mode) == HFmode)
return false;
{
gcc_assert (!recp);
return false;
}
machine_mode mmsk = mode_for_vector
(int_mode_for_mode (GET_MODE_INNER (mode)),
GET_MODE_NUNITS (mode));
bool use_approx_sqrt_p = (!recp
&& (flag_mlow_precision_sqrt
|| (aarch64_tune_params.approx_modes->sqrt
& AARCH64_APPROX_MODE (mode))));
bool use_approx_rsqrt_p = (recp
&& (flag_mrecip_low_precision_sqrt
|| (aarch64_tune_params.approx_modes->recip_sqrt
& AARCH64_APPROX_MODE (mode))));
machine_mode mmsk
= mode_for_vector (int_mode_for_mode (GET_MODE_INNER (mode)),
GET_MODE_NUNITS (mode));
if (!recp)
{
if (!(flag_mlow_precision_sqrt
|| (aarch64_tune_params.approx_modes->sqrt
& AARCH64_APPROX_MODE (mode))))
return false;
if (flag_finite_math_only
|| flag_trapping_math
|| !flag_unsafe_math_optimizations
|| optimize_function_for_size_p (cfun))
return false;
}
else
/* Caller assumes we cannot fail. */
gcc_assert (use_rsqrt_p (mode));
if (!flag_finite_math_only
|| flag_trapping_math
|| !flag_unsafe_math_optimizations
|| !(use_approx_sqrt_p || use_approx_rsqrt_p)
|| optimize_function_for_size_p (cfun))
return false;
rtx xmsk = gen_reg_rtx (mmsk);
if (!recp)
/* When calculating the approximate square root, compare the argument with
0.0 and create a mask. */
emit_insn (gen_rtx_SET (xmsk, gen_rtx_NEG (mmsk, gen_rtx_EQ (mmsk, src,
CONST0_RTX (mode)))));
/* When calculating the approximate square root, compare the
argument with 0.0 and create a mask. */
emit_insn (gen_rtx_SET (xmsk,
gen_rtx_NEG (mmsk,
gen_rtx_EQ (mmsk, src,
CONST0_RTX (mode)))));
/* Estimate the approximate reciprocal square root. */
rtx xdst = gen_reg_rtx (mode);
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment