From: Pan Li <pan2...@intel.com>
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.
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: Adjust tests cases for different scenarios.
Signed-off-by: Pan Li <pan2...@intel.com>
---
gcc/loop-unroll.cc | 4 +--
gcc/testsuite/gcc.dg/pr30957-1.c | 48 ++++++++++++++++++++++++++++----
2 files changed, 44 insertions(+), 8 deletions(-)
diff --git a/gcc/loop-unroll.cc b/gcc/loop-unroll.cc
index 4176a21e308..bfdfe6c2bb7 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
index 564410913ab..6a9d3d87932 100644
--- a/gcc/testsuite/gcc.dg/pr30957-1.c
+++ b/gcc/testsuite/gcc.dg/pr30957-1.c
@@ -20,16 +20,52 @@ foo (float d, int n)
return accum;
}
+float __attribute__((noinline))
+get_minus_zero()
+{
+ return 0.0 / -5.0;
+}
+
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)
+ /* The variable expansion in unroll requires option unsafe-math-optimizations
+ (aka -fno-signed-zeros, -fno-trapping-math, -fassociative-math
+ and -freciprocal-math).
+
+ When loop like above will have expansion after unrolling as below:
+
+ accum_1 += d_1;
+ accum_2 += d_2;
+ accum_3 += d_3;
+ ...
+
+ The accum_1, accum_2 and accum_3 need to be initialized. Given the
+ floating-point we have
+ +0.0f + -0.0f = +0.0f.
+
+ Thus, we should initialize the accum_* to -0.0 for correctness. But
+ the things become more complicated when no-signed-zeros, as well as VLA
+ vectorizer mode which doesn't trigger variable expansion. Then we have:
+
+ Case 1: Trigger variable expansion but target doesn't honor
no-signed-zero.
+ minus_zero will be -0.0f and foo (minus_zero, 10) will be -0.0f.
+ Case 2: Trigger variable expansion but target does honor no-signed-zero.
+ minus_zero will be +0.0f and foo (minus_zero, 10) will be +0.0f.
+ Case 3: No variable expansion but target doesn't honor no-signed-zero.
+ minus_zero will be -0.0f and foo (minus_zero, 10) will be -0.0f.
+ Case 4: No variable expansion but target does honor no-signed-zero.
+ minus_zero will be +0.0f and foo (minus_zero, 10) will be +0.0f.
+
+ The test case covers above 4 cases for running.
+ */
+ float minus_zero = get_minus_zero ();
+ float a = __builtin_copysignf (1.0, minus_zero);
+ float b = __builtin_copysignf (1.0, foo (minus_zero, 10));
+
+ if (a != b)
abort ();
+
exit (0);
}
--
2.34.1
