From b89ef3d40afc4604c279e8802bf279f6e4060f67 Mon Sep 17 00:00:00 2001
From: Pan Li <pan2.li@intel.com>
Date: Wed, 10 Jan 2024 20:57:17 +0800
Subject: [PATCH] LOOP-UNROLL: Leverage HAS_SIGNED_ZERO for var expansion
The insert_var_expansion_initialization depends on the
HONOR_SIGNED_ZEROS to initialize the unrolling variables
to +0.0f when -0.0f and no-signed-option. Unfortunately,
we should always keep the -0.0f here because:
* The -0.0f is always the correct initial value.
* We need to support the target that always honor signed zero.
Thus, we need to leverage MODE_HAS_SIGNED_ZEROS when initialize
instead of HONOR_SIGNED_ZEROS. Then the target/backend can
decide to honor the no-signed-zero or not.
We also removed the testcase pr30957-1.c, as it makes undefined behavior
whether the return value is positive or negative.
The below tests are passed for this patch:
* The riscv regression tests.
* The aarch64 regression tests.
* The x86 bootstrap and regression tests.
gcc/ChangeLog:
* loop-unroll.cc (insert_var_expansion_initialization): Leverage
MODE_HAS_SIGNED_ZEROS for expansion variable initialization.
gcc/testsuite/ChangeLog:
* gcc.dg/pr30957-1.c: Remove.
Signed-off-by: Pan Li <pan2.li@intel.com>
---
gcc/loop-unroll.cc | 4 ++--
gcc/testsuite/gcc.dg/pr30957-1.c | 36 --------------------------------
2 files changed, 2 insertions(+), 38 deletions(-)
delete mode 100644 gcc/testsuite/gcc.dg/pr30957-1.c
diff --git a/gcc/loop-unroll.cc b/gcc/loop-unroll.cc
index 4176a21e308b..bfdfe6c2bb72 100644
--- a/gcc/loop-unroll.cc
+++ b/gcc/loop-unroll.cc
@@ -1855,7 +1855,7 @@ insert_var_expansion_initialization (struct var_to_expand *ve,
rtx var, zero_init;
unsigned i;
machine_mode mode = GET_MODE (ve->reg);
- bool honor_signed_zero_p = HONOR_SIGNED_ZEROS (mode);
+ bool has_signed_zero_p = MODE_HAS_SIGNED_ZEROS (mode);
if (ve->var_expansions.length () == 0)
return;
@@ -1869,7 +1869,7 @@ insert_var_expansion_initialization (struct var_to_expand *ve,
case MINUS:
FOR_EACH_VEC_ELT (ve->var_expansions, i, var)
{
- if (honor_signed_zero_p)
+ if (has_signed_zero_p)
zero_init = simplify_gen_unary (NEG, mode, CONST0_RTX (mode), mode);
else
zero_init = CONST0_RTX (mode);
diff --git a/gcc/testsuite/gcc.dg/pr30957-1.c b/gcc/testsuite/gcc.dg/pr30957-1.c
deleted file mode 100644
index 564410913ab3..000000000000
--- a/gcc/testsuite/gcc.dg/pr30957-1.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/* { dg-do run { xfail { mmix-*-* } } } */
-/* We don't (and don't want to) perform this optimisation on soft-float targets,
- where each addition is a library call. /
-/* { dg-require-effective-target hard_float } */
-/* -fassociative-math requires -fno-trapping-math and -fno-signed-zeros. */
-/* { dg-options "-O2 -funroll-loops -fassociative-math -fno-trapping-math -fno-signed-zeros -fvariable-expansion-in-unroller -fdump-rtl-loop2_unroll" } */
-
-extern void abort (void);
-extern void exit (int);
-
-float __attribute__((noinline))
-foo (float d, int n)
-{
- unsigned i;
- float accum = d;
-
- for (i = 0; i < n; i++)
- accum += d;
-
- return accum;
-}
-
-int
-main ()
-{
- /* When compiling standard compliant we expect foo to return -0.0. But the
- variable expansion during unrolling optimization (for this testcase enabled
- by non-compliant -fassociative-math) instantiates copy(s) of the
- accumulator which it initializes with +0.0. Hence we expect that foo
- returns +0.0. */
- if (__builtin_copysignf (1.0, foo (0.0 / -5.0, 10)) != 1.0)
- abort ();
- exit (0);
-}
-
-/* { dg-final { scan-rtl-dump "Expanding Accumulator" "loop2_unroll" { xfail mmix-*-* } } } */
--
GitLab