From: Pan Li <pan2...@intel.com>
Fix the bug of the incorrect code generation for the
below code sample.
typedef unsigned short __attribute__((__vector_size__ (32))) V;
typedef unsigned short u16;
void
foo (V m, u16 *ret)
{
V v = 6 > ((V) { 2049, 8 } & m);
*ret = v[0]; // + a + b + c + d;
}
Before this patch.
addi sp,sp,-64
ld a5,0(a0)
li a4,528384
addi a4,a4,-2047
and a5,a5,a4
// slli a5,a5,48 <- eliminated by mistake
// srli a5,a5,48 <- eliminated by mistake
sltiu a5,a5,6
negw a5,a5
sh a5,0(a1)
After this patch.
addi sp,sp,-64
ld a5,0(a0)
li a4,528384
addi a4,a4,-2047
and a5,a5,a4
slli a5,a5,48
srli a5,a5,48
sltiu a5,a5,6
negw a5,a5
sh a5,0(a1)
The simplify_comparation for the AND operation will
try to simplify below RTL code from:
(and:DI (subreg:DI (reg:HI 154) 0) (const_int 0x801))
to:
(subreg:DI (and (reg:HI 154) (const_int 0x801)) 0)
If reg:HI 154 is 0x801 and reg:DI 154 is 0x80801, the RTL will
be simplified continuely to:
(subreg:DI (reg:HI 154) 0)
That will loss the chance to clean the upper bits of the
reg:DI 154, which result in the slli/srli to be eliminated. This
patch will try 2 times when simplify_gen_binary for both the
reg:HI 154 and the reg:DI 154, and only perform the operation if
the returned simplified RTX equals.
PR 109040
gcc/ChangeLog:
* combine.cc (simplify_comparison):
gcc/testsuite/ChangeLog:
* gcc.dg/pr109040.c: New test.
Signed-off-by: Pan Li <pan2...@intel.com>
Co-authored-by: Hongtao Liu <hongtao....@intel.com>
---
gcc/combine.cc | 14 +++++++++++---
gcc/testsuite/gcc.target/riscv/pr109040.c | 14 ++++++++++++++
2 files changed, 25 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/riscv/pr109040.c
diff --git a/gcc/combine.cc b/gcc/combine.cc
index 053879500b7..7a62c95ddc8 100644
--- a/gcc/combine.cc
+++ b/gcc/combine.cc
@@ -12681,10 +12681,18 @@ simplify_comparison (enum rtx_code code, rtx *pop0,
rtx *pop1)
&& c1 != mask
&& c1 != GET_MODE_MASK (tmode))
{
- op0 = simplify_gen_binary (AND, tmode,
- SUBREG_REG (XEXP (op0, 0)),
+ rtx op0_exp0 = XEXP (op0, 0);
+ machine_mode op0_exp0_mode = GET_MODE (op0_exp0);
+ rtx op0_subreg = simplify_gen_binary (AND, tmode,
+ SUBREG_REG (op0_exp0),
gen_int_mode (c1, tmode));
- op0 = gen_lowpart (mode, op0);
+ rtx op0_reg = simplify_gen_binary (AND, GET_MODE (op0_exp0),
+ op0_exp0,
+ gen_int_mode (c1, op0_exp0_mode));
+ if (!rtx_equal_p (op0_subreg, op0_reg))
+ break;
+
+ op0 = gen_lowpart (mode, op0_reg);
continue;
}
}
diff --git a/gcc/testsuite/gcc.target/riscv/pr109040.c
b/gcc/testsuite/gcc.target/riscv/pr109040.c
new file mode 100644
index 00000000000..079b2156364
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/pr109040.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64 -O2 -fno-schedule-insns
-fno-schedule-insns2" } */
+
+typedef unsigned short __attribute__((__vector_size__ (32))) V;
+typedef unsigned short u16;
+
+void
+foo (V m, u16 *ret)
+{
+ V v = 6 > ((V) { 2049, 8 } & m);
+ *ret = v[0];
+}
+
+/* { dg-final { scan-assembler-times
{slli\s+a[0-9]+,\s*a[0-9]+,\s*48\s+srli\s+a[0-9]+,\s*a[0-9]+,\s*48} 1 } } */
--
2.34.1
