Modify combine pattern by a pseudo AND with its nonzero bits [PR93453]

Message ID 6def3e90-2c3f-e628-8325-650969e8b8c2@linux.ibm.com
State New
Headers
Series Modify combine pattern by a pseudo AND with its nonzero bits [PR93453] |

Commit Message

HAO CHEN GUI Dec. 7, 2021, 8:28 a.m. UTC
  Hi,
  This patch modifies the combine pattern with a helper - change_pseudo_and_mask when recog fails.
The helper converts a single pseudo to the pseudo AND with a mask if the outer operator is IOR/XOR/PLUS
and the inner operator is ASHIFT/LSHIFTRT/AND. The conversion helps on shift + ior pattern.

  Not sure if the helper should be a target hook or not. Please advice.

  Bootstrapped and tested on powerpc64-linux BE and LE with no regressions. Is this okay for trunk?
Any recommendations? Thanks a lot.

ChangeLog
2021-12-07 Haochen Gui <guihaoc@linux.ibm.com>

gcc/
	* combine.c (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): Likewise.

gcc/testsuite/
	* gcc.target/powerpc/20050603-3.c: Modify dump check conditions.
	* gcc.target/powerpc/rlwimi-2.c: Likewise.

patch.diff
  

Comments

HAO CHEN GUI Jan. 10, 2022, 3:18 a.m. UTC | #1
Hi,

    Gentle ping this:
	https://gcc.gnu.org/pipermail/gcc-patches/2021-December/586304.html

Thanks

On 7/12/2021 下午 4:28, HAO CHEN GUI wrote:
> Hi,
>   This patch modifies the combine pattern with a helper - change_pseudo_and_mask when recog fails.
> The helper converts a single pseudo to the pseudo AND with a mask if the outer operator is IOR/XOR/PLUS
> and the inner operator is ASHIFT/LSHIFTRT/AND. The conversion helps on shift + ior pattern.
> 
>   Not sure if the helper should be a target hook or not. Please advice.
> 
>   Bootstrapped and tested on powerpc64-linux BE and LE with no regressions. Is this okay for trunk?
> Any recommendations? Thanks a lot.
> 
> ChangeLog
> 2021-12-07 Haochen Gui <guihaoc@linux.ibm.com>
> 
> gcc/
> 	* combine.c (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): Likewise.
> 
> gcc/testsuite/
> 	* gcc.target/powerpc/20050603-3.c: Modify dump check conditions.
> 	* gcc.target/powerpc/rlwimi-2.c: Likewise.
> 
> patch.diff
> diff --git a/gcc/combine.c b/gcc/combine.c
> index 03e9a780919..53500e8c6a0 100644
> --- a/gcc/combine.c
> +++ b/gcc/combine.c
> @@ -11539,6 +11539,36 @@ change_zero_ext (rtx pat)
>    return changed;
>  }
> 
> +/* When the outer code of set_src is IOR/XOR/PLUS and the inner code is
> +   ASHIFT/LSHIFTRT/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)) == LSHIFTRT
> +	    || 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))
> +	{
> +	  rtx x = gen_rtx_AND (mode, *reg, GEN_INT (nonzero));
> +	  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,
> @@ -11586,7 +11616,10 @@ 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 6bec2bddbde..5adbe9e9d27 100644
> --- a/gcc/config/rs6000/rs6000.md
> +++ b/gcc/config/rs6000/rs6000.md
> @@ -4149,24 +4149,6 @@ (define_insn "rotl<mode>3_insert_3"
>  }
>    [(set_attr "type" "insert")])
> 
> -(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 "*rotl<mode>3_insert_4"
>    [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
>  	(ior:GPR (and:GPR (match_operand:GPR 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/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 } } */
>
  

Patch

diff --git a/gcc/combine.c b/gcc/combine.c
index 03e9a780919..53500e8c6a0 100644
--- a/gcc/combine.c
+++ b/gcc/combine.c
@@ -11539,6 +11539,36 @@  change_zero_ext (rtx pat)
   return changed;
 }

+/* When the outer code of set_src is IOR/XOR/PLUS and the inner code is
+   ASHIFT/LSHIFTRT/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)) == LSHIFTRT
+	    || 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))
+	{
+	  rtx x = gen_rtx_AND (mode, *reg, GEN_INT (nonzero));
+	  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,
@@ -11586,7 +11616,10 @@  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 6bec2bddbde..5adbe9e9d27 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -4149,24 +4149,6 @@  (define_insn "rotl<mode>3_insert_3"
 }
   [(set_attr "type" "insert")])

-(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 "*rotl<mode>3_insert_4"
   [(set (match_operand:GPR 0 "gpc_reg_operand" "=r")
 	(ior:GPR (and:GPR (match_operand:GPR 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/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 } } */