Hi,
This patch modifies the combine pattern after recog fails. With a helper
- change_pseudo_and_mask, it converts a single pseudo to the pseudo AND with
a mask when the outer operator is IOR/XOR/PLUS and inner operator is ASHIFT
or AND. The conversion helps pattern to match rotate and mask insn on some
targets.
For test case rlwimi-2.c, current trunk fails on
"scan-assembler-times (?n)^\\s+[a-z]". It reports 21305 times. So my patch
reduces the total number of insns from 21305 to 21279.
Bootstrapped and tested on powerpc64-linux BE and LE with no regressions.
Is this okay for trunk? Any recommendations? Thanks a lot.
ChangeLog
2022-07-07 Haochen Gui <guih...@linux.ibm.com>
gcc/
PR target/93453
* combine.cc (change_pseudo_and_mask): New.
(recog_for_combine): If recog fails, try again with the pattern
modified by change_pseudo_and_mask.
* config/rs6000/rs6000.md (plus_ior_xor): Removed.
(anonymous split pattern for plus_ior_xor): Removed.
gcc/testsuite/
PR target/93453
* gcc.target/powerpc/20050603-3.c: Modify dump check conditions.
* gcc.target/powerpc/rlwimi-2.c: Likewise.
* gcc.target/powerpc/pr93453-2.c: New.
patch.diff
diff --git a/gcc/combine.cc b/gcc/combine.cc
index a5fabf397f7..3cd7b2b652b 100644
--- a/gcc/combine.cc
+++ b/gcc/combine.cc
@@ -11599,6 +11599,47 @@ change_zero_ext (rtx pat)
return changed;
}
+/* When the outer code of set_src is IOR/XOR/PLUS and the inner code is
+ ASHIFT/AND, convert a pseudo to psuedo AND with a mask if its nonzero_bits
+ is less than its mode mask. The nonzero_bits in other pass doesn't return
+ the same value as it does in combine pass. */
+static bool
+change_pseudo_and_mask (rtx pat)
+{
+ rtx src = SET_SRC (pat);
+ if ((GET_CODE (src) == IOR
+ || GET_CODE (src) == XOR
+ || GET_CODE (src) == PLUS)
+ && (((GET_CODE (XEXP (src, 0)) == ASHIFT
+ || GET_CODE (XEXP (src, 0)) == AND)
+ && REG_P (XEXP (src, 1)))))
+ {
+ rtx *reg = &XEXP (SET_SRC (pat), 1);
+ machine_mode mode = GET_MODE (*reg);
+ unsigned HOST_WIDE_INT nonzero = nonzero_bits (*reg, mode);
+ if (nonzero < GET_MODE_MASK (mode))
+ {
+ int shift;
+
+ if (GET_CODE (XEXP (src, 0)) == ASHIFT)
+ shift = INTVAL (XEXP (XEXP (src, 0), 1));
+ else
+ shift = ctz_hwi (INTVAL (XEXP (XEXP (src, 0), 1)));
+
+ if (shift > 0
+ && ((HOST_WIDE_INT_1U << shift) - 1) >= nonzero)
+ {
+ unsigned HOST_WIDE_INT mask = (HOST_WIDE_INT_1U << shift) - 1;
+ rtx x = gen_rtx_AND (mode, *reg, GEN_INT (mask));
+ SUBST (*reg, x);
+ maybe_swap_commutative_operands (SET_SRC (pat));
+ return true;
+ }
+ }
+ }
+ return false;
+}
+
/* Like recog, but we receive the address of a pointer to a new pattern.
We try to match the rtx that the pointer points to.
If that fails, we may try to modify or replace the pattern,
@@ -11646,7 +11687,10 @@ recog_for_combine (rtx *pnewpat, rtx_insn *insn, rtx
*pnotes)
}
}
else
- changed = change_zero_ext (pat);
+ {
+ changed = change_pseudo_and_mask (pat);
+ changed |= change_zero_ext (pat);
+ }
}
else if (GET_CODE (pat) == PARALLEL)
{
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 1367a2cb779..2bd6bd5f908 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -4207,24 +4207,6 @@ (define_insn_and_split "*rotl<mode>3_insert_3_<code>"
(ior:GPR (and:GPR (match_dup 3) (match_dup 4))
(ashift:GPR (match_dup 1) (match_dup 2))))])
-(define_code_iterator plus_ior_xor [plus ior xor])
-
-(define_split
- [(set (match_operand:GPR 0 "gpc_reg_operand")
- (plus_ior_xor:GPR (ashift:GPR (match_operand:GPR 1 "gpc_reg_operand")
- (match_operand:SI 2 "const_int_operand"))
- (match_operand:GPR 3 "gpc_reg_operand")))]
- "nonzero_bits (operands[3], <MODE>mode)
- < HOST_WIDE_INT_1U << INTVAL (operands[2])"
- [(set (match_dup 0)
- (ior:GPR (and:GPR (match_dup 3)
- (match_dup 4))
- (ashift:GPR (match_dup 1)
- (match_dup 2))))]
-{
- operands[4] = GEN_INT ((HOST_WIDE_INT_1U << INTVAL (operands[2])) - 1);
-})
-
(define_insn "*rotlsi3_insert_4"
[(set (match_operand:SI 0 "gpc_reg_operand" "=r")
(ior:SI (and:SI (match_operand:SI 3 "gpc_reg_operand" "0")
diff --git a/gcc/testsuite/gcc.target/powerpc/20050603-3.c
b/gcc/testsuite/gcc.target/powerpc/20050603-3.c
index 4017d34f429..e628be11532 100644
--- a/gcc/testsuite/gcc.target/powerpc/20050603-3.c
+++ b/gcc/testsuite/gcc.target/powerpc/20050603-3.c
@@ -12,7 +12,7 @@ void rotins (unsigned int x)
b.y = (x<<12) | (x>>20);
}
-/* { dg-final { scan-assembler-not {\mrlwinm} } } */
+/* { dg-final { scan-assembler-not {\mrlwinm} { target ilp32 } } } */
/* { dg-final { scan-assembler-not {\mrldic} } } */
/* { dg-final { scan-assembler-not {\mrot[lr]} } } */
/* { dg-final { scan-assembler-not {\ms[lr][wd]} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/pr93453-2.c
b/gcc/testsuite/gcc.target/powerpc/pr93453-2.c
new file mode 100644
index 00000000000..34b7834af8d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr93453-2.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+long foo (char a, long b)
+{
+ long c = a;
+ c = c | (b << 12);
+ return c;
+}
+
+long bar (long b, char a)
+{
+ long c = a;
+ long m = -4096;
+ c = c | (b & m);
+ return c;
+}
+
+/* { dg-final { scan-assembler-times {\mrlwimi\M} 2 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times {\mrldimi\M} 2 { target lp64 } } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/rlwimi-2.c
b/gcc/testsuite/gcc.target/powerpc/rlwimi-2.c
index bafa371db73..ffb5f9e450f 100644
--- a/gcc/testsuite/gcc.target/powerpc/rlwimi-2.c
+++ b/gcc/testsuite/gcc.target/powerpc/rlwimi-2.c
@@ -2,14 +2,14 @@
/* { dg-options "-O2" } */
/* { dg-final { scan-assembler-times {(?n)^\s+[a-z]} 14121 { target ilp32 } }
} */
-/* { dg-final { scan-assembler-times {(?n)^\s+[a-z]} 20217 { target lp64 } } }
*/
+/* { dg-final { scan-assembler-times {(?n)^\s+[a-z]} 21279 { target lp64 } } }
*/
/* { dg-final { scan-assembler-times {(?n)^\s+blr} 6750 } } */
/* { dg-final { scan-assembler-times {(?n)^\s+mr} 643 { target ilp32 } } } */
/* { dg-final { scan-assembler-times {(?n)^\s+mr} 11 { target lp64 } } } */
/* { dg-final { scan-assembler-times {(?n)^\s+rldicl} 7790 { target lp64 } } }
*/
/* { dg-final { scan-assembler-times {(?n)^\s+rlwimi} 1692 { target ilp32 } }
} */
-/* { dg-final { scan-assembler-times {(?n)^\s+rlwimi} 1666 { target lp64 } } }
*/
+/* { dg-final { scan-assembler-times {(?n)^\s+rlwimi} 1692 { target lp64 } } }
*/
/* { dg-final { scan-assembler-times {(?n)^\s+mulli} 5036 } } */
