[V3,1/4] rs6000: build constant via li;rotldi

Hi,

If a constant is possible to be rotated to/from a positive or negative
value from "li", then "li;rotldi" can be used to build the constant.

Compare with the previous version, those one-line abstraction codes are
removed.
https://gcc.gnu.org/pipermail/gcc-patches/2023-June/621001.html

Bootstrap and regtest pass on ppc64{,le}.
Is this ok for trunk?

BR,
Jeff (Jiufu)

gcc/ChangeLog:

	* config/rs6000/rs6000.cc (can_be_built_by_li_and_rotldi): New function.
	(rs6000_emit_set_long_const): Call can_be_built_by_li_and_rotldi.

gcc/testsuite/ChangeLog:

	* gcc.target/powerpc/const-build.c: New test.
---
 gcc/config/rs6000/rs6000.cc                   | 47 +++++++++++++---
 .../gcc.target/powerpc/const-build.c          | 54 +++++++++++++++++++
 2 files changed, 95 insertions(+), 6 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/const-build.c

Hi!

On Fri, Jun 16, 2023 at 04:34:12PM +0800, Jiufu Guo wrote:
> +/* Check if value C can be built by 2 instructions: one is 'li', another is
> +   rotldi.
> +
> +   If so, *SHIFT is set to the shift operand of rotldi(rldicl), and *MASK
> +   is set to -1, and return true.  Return false otherwise.  */

Don't say "is set to -1", the point of having this is so you say "is set
to the "li" value".  Just like you describe what SHIFT is for.

> +static bool
> +can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
> +				   HOST_WIDE_INT *mask)
> +{
> +  int n;

Put shis later, like:

> +  /* Check if C can be rotated to a positive or negative value
> +      which 'li' instruction is able to load.  */
  int n;
> +  if (can_be_rotated_to_lowbits (c, 15, &n)
> +      || can_be_rotated_to_lowbits (~c, 15, &n))
> +    {
> +      *mask = HOST_WIDE_INT_M1;
> +      *shift = HOST_BITS_PER_WIDE_INT - n;
> +      return true;
> +    }

It is tricky to see ~c will always work, since what is really done is -c
instead.  Can you just use that here?

> @@ -10266,15 +10291,14 @@ static void
>  rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>  {
>    rtx temp;
> +  int shift;
> +  HOST_WIDE_INT mask;
>    HOST_WIDE_INT ud1, ud2, ud3, ud4;
>  
>    ud1 = c & 0xffff;
> -  c = c >> 16;
> -  ud2 = c & 0xffff;
> -  c = c >> 16;
> -  ud3 = c & 0xffff;
> -  c = c >> 16;
> -  ud4 = c & 0xffff;
> +  ud2 = (c >> 16) & 0xffff;
> +  ud3 = (c >> 32) & 0xffff;
> +  ud4 = (c >> 48) & 0xffff;
>  
>    if ((ud4 == 0xffff && ud3 == 0xffff && ud2 == 0xffff && (ud1 & 0x8000))
>        || (ud4 == 0 && ud3 == 0 && ud2 == 0 && ! (ud1 & 0x8000)))
> @@ -10305,6 +10329,17 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>        emit_move_insn (dest, gen_rtx_XOR (DImode, temp,
>  					 GEN_INT ((ud2 ^ 0xffff) << 16)));
>      }
> +  else if (can_be_built_by_li_and_rotldi (c, &shift, &mask))
> +    {
> +      temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
> +      unsigned HOST_WIDE_INT imm = (c | ~mask);
> +      imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
> +
> +      emit_move_insn (temp, GEN_INT (imm));
> +      if (shift != 0)
> +	temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
> +      emit_move_insn (dest, temp);
> +    }

If you would rewrite so it isn't such a run-on thing with "else if",
instead using early outs, or even some factoring, you could declare the
variable used only in a tiny scope in that tiny scope instead.

> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
> @@ -0,0 +1,54 @@
> +/* { dg-do run } */
> +/* { dg-options "-O2 -save-temps" } */
> +/* { dg-require-effective-target has_arch_ppc64 } */

Please put a tiny comment here saying what this test is *for*?  The file
name is a bit of hint already, but you can indicate much more in one or
two lines :-)

With those adjustments, okay for trunk.  Thanks!

(If -c doesn't work, it needs more explanation).


Segher

Hi!

Segher Boessenkool <segher@kernel.crashing.org> writes:

> Hi!
>
> On Fri, Jun 16, 2023 at 04:34:12PM +0800, Jiufu Guo wrote:
>> +/* Check if value C can be built by 2 instructions: one is 'li', another is
>> +   rotldi.
>> +
>> +   If so, *SHIFT is set to the shift operand of rotldi(rldicl), and *MASK
>> +   is set to -1, and return true.  Return false otherwise.  */
>
> Don't say "is set to -1", the point of having this is so you say "is set
> to the "li" value".  Just like you describe what SHIFT is for.
Yes, thanks!
>
>> +static bool
>> +can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
>> +				   HOST_WIDE_INT *mask)
>> +{
>> +  int n;
>
> Put shis later, like:
Thanks!
>
>> +  /* Check if C can be rotated to a positive or negative value
>> +      which 'li' instruction is able to load.  */
>   int n;
>> +  if (can_be_rotated_to_lowbits (c, 15, &n)
>> +      || can_be_rotated_to_lowbits (~c, 15, &n))
>> +    {
>> +      *mask = HOST_WIDE_INT_M1;
>> +      *shift = HOST_BITS_PER_WIDE_INT - n;
>> +      return true;
>> +    }
>
> It is tricky to see ~c will always work, since what is really done is -c
> instead.  Can you just use that here?

Some explanation: 
A negative value of 'li' is:
0b11..11xxx there are 49 leading '1's, and the other 15 tailing bits can
be 0 or 1. With the '~' operation, there are 49 '0's.
After the value is rotated,  there are still 49 '1's. (xxx may also be
at head/tail.) 
For the rotated value, with the '~' operation, there are still 49 '0's.

So, for a value, if there are 49 successive '1's (may cross head/tail).
It should be able to rotate to low 15 bits after the '~' operation.

It would not be enough if using the '-' operation, since '-x=~x+1' in
the bit aspect. As the below case 'li_rotldi_3': 0xffff8531ffffffffLL
(rotate left 0x8531 32bit).
The '~c' is 0x7ace00000000, this can be rotated from 0x7ace. (~0x8531).
But '-c' is 0x7ace00000001. this value is not good.

>
>> @@ -10266,15 +10291,14 @@ static void
>>  rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>>  {
>>    rtx temp;
>> +  int shift;
>> +  HOST_WIDE_INT mask;
>>    HOST_WIDE_INT ud1, ud2, ud3, ud4;
>>  
>>    ud1 = c & 0xffff;
>> -  c = c >> 16;
>> -  ud2 = c & 0xffff;
>> -  c = c >> 16;
>> -  ud3 = c & 0xffff;
>> -  c = c >> 16;
>> -  ud4 = c & 0xffff;
>> +  ud2 = (c >> 16) & 0xffff;
>> +  ud3 = (c >> 32) & 0xffff;
>> +  ud4 = (c >> 48) & 0xffff;
>>  
>>    if ((ud4 == 0xffff && ud3 == 0xffff && ud2 == 0xffff && (ud1 & 0x8000))
>>        || (ud4 == 0 && ud3 == 0 && ud2 == 0 && ! (ud1 & 0x8000)))
>> @@ -10305,6 +10329,17 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>>        emit_move_insn (dest, gen_rtx_XOR (DImode, temp,
>>  					 GEN_INT ((ud2 ^ 0xffff) << 16)));
>>      }
>> +  else if (can_be_built_by_li_and_rotldi (c, &shift, &mask))
>> +    {
>> +      temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
>> +      unsigned HOST_WIDE_INT imm = (c | ~mask);
>> +      imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
>> +
>> +      emit_move_insn (temp, GEN_INT (imm));
>> +      if (shift != 0)
>> +	temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
>> +      emit_move_insn (dest, temp);
>> +    }
>
> If you would rewrite so it isn't such a run-on thing with "else if",
> instead using early outs, or even some factoring, you could declare the
> variable used only in a tiny scope in that tiny scope instead.

Yes! Early returning is better for a lot of cases.  I would like
to have a refactor patch.

>
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
>> @@ -0,0 +1,54 @@
>> +/* { dg-do run } */
>> +/* { dg-options "-O2 -save-temps" } */
>> +/* { dg-require-effective-target has_arch_ppc64 } */
>
> Please put a tiny comment here saying what this test is *for*?  The file
> name is a bit of hint already, but you can indicate much more in one or
> two lines :-)

Oh, yes, thanks for point out this!

>
> With those adjustments, okay for trunk.  Thanks!
>
> (If -c doesn't work, it needs more explanation).

Sure, some words as above.

BR,
Jeff (Jiufu Guo)

>
>
> Segher

Hi,

Jiufu Guo via Gcc-patches <gcc-patches@gcc.gnu.org> writes:

> Hi!
>
> Segher Boessenkool <segher@kernel.crashing.org> writes:
>
>> Hi!
>>
>> On Fri, Jun 16, 2023 at 04:34:12PM +0800, Jiufu Guo wrote:
>>> +/* Check if value C can be built by 2 instructions: one is 'li', another is
>>> +   rotldi.
>>> +
>>> +   If so, *SHIFT is set to the shift operand of rotldi(rldicl), and *MASK
>>> +   is set to -1, and return true.  Return false otherwise.  */
>>
>> Don't say "is set to -1", the point of having this is so you say "is set
>> to the "li" value".  Just like you describe what SHIFT is for.
> Yes, thanks!
>>
>>> +static bool
>>> +can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
>>> +				   HOST_WIDE_INT *mask)
>>> +{
>>> +  int n;
>>
>> Put shis later, like:
> Thanks!
>>
>>> +  /* Check if C can be rotated to a positive or negative value
>>> +      which 'li' instruction is able to load.  */
>>   int n;
>>> +  if (can_be_rotated_to_lowbits (c, 15, &n)
>>> +      || can_be_rotated_to_lowbits (~c, 15, &n))
>>> +    {
>>> +      *mask = HOST_WIDE_INT_M1;
>>> +      *shift = HOST_BITS_PER_WIDE_INT - n;
>>> +      return true;
>>> +    }
>>
>> It is tricky to see ~c will always work, since what is really done is -c
>> instead.  Can you just use that here?
>
> Some explanation: 
> A negative value of 'li' is:
> 0b11..11xxx there are 49 leading '1's, and the other 15 tailing bits can
> be 0 or 1. With the '~' operation, there are 49 '0's.
> After the value is rotated,  there are still 49 '1's. (xxx may also be
> at head/tail.) 
> For the rotated value, with the '~' operation, there are still 49 '0's.
>
> So, for a value, if there are 49 successive '1's (may cross head/tail).
> It should be able to rotate to low 15 bits after the '~' operation.
>
> It would not be enough if using the '-' operation, since '-x=~x+1' in
> the bit aspect. As the below case 'li_rotldi_3': 0xffff8531ffffffffLL
> (rotate left 0x8531 32bit).
> The '~c' is 0x7ace00000000, this can be rotated from 0x7ace. (~0x8531).
> But '-c' is 0x7ace00000001. this value is not good.
>
>>
>>> @@ -10266,15 +10291,14 @@ static void
>>>  rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>>>  {
>>>    rtx temp;
>>> +  int shift;
>>> +  HOST_WIDE_INT mask;
>>>    HOST_WIDE_INT ud1, ud2, ud3, ud4;
>>>  
>>>    ud1 = c & 0xffff;
>>> -  c = c >> 16;
>>> -  ud2 = c & 0xffff;
>>> -  c = c >> 16;
>>> -  ud3 = c & 0xffff;
>>> -  c = c >> 16;
>>> -  ud4 = c & 0xffff;
>>> +  ud2 = (c >> 16) & 0xffff;
>>> +  ud3 = (c >> 32) & 0xffff;
>>> +  ud4 = (c >> 48) & 0xffff;
>>>  
>>>    if ((ud4 == 0xffff && ud3 == 0xffff && ud2 == 0xffff && (ud1 & 0x8000))
>>>        || (ud4 == 0 && ud3 == 0 && ud2 == 0 && ! (ud1 & 0x8000)))
>>> @@ -10305,6 +10329,17 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
>>>        emit_move_insn (dest, gen_rtx_XOR (DImode, temp,
>>>  					 GEN_INT ((ud2 ^ 0xffff) << 16)));
>>>      }
>>> +  else if (can_be_built_by_li_and_rotldi (c, &shift, &mask))
>>> +    {
>>> +      temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
>>> +      unsigned HOST_WIDE_INT imm = (c | ~mask);
>>> +      imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
>>> +
>>> +      emit_move_insn (temp, GEN_INT (imm));
>>> +      if (shift != 0)
>>> +	temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
>>> +      emit_move_insn (dest, temp);
>>> +    }
>>
>> If you would rewrite so it isn't such a run-on thing with "else if",
>> instead using early outs, or even some factoring, you could declare the
>> variable used only in a tiny scope in that tiny scope instead.
>
> Yes! Early returning is better for a lot of cases.  I would like
> to have a refactor patch.
>
>>
>>> --- /dev/null
>>> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
>>> @@ -0,0 +1,54 @@
>>> +/* { dg-do run } */
>>> +/* { dg-options "-O2 -save-temps" } */
>>> +/* { dg-require-effective-target has_arch_ppc64 } */
>>
>> Please put a tiny comment here saying what this test is *for*?  The file
>> name is a bit of hint already, but you can indicate much more in one or
>> two lines :-)
>
> Oh, yes, thanks for point out this!
>
>>
>> With those adjustments, okay for trunk.  Thanks!
>>
>> (If -c doesn't work, it needs more explanation).

The patch is updated, and attached below.
If ok, I would like to commit the patch accordingly.

BR,
Jeff (Jiufu Guo)


If a constant is possible to be rotated to/from a positive or negative
value from "li", then "li;rotldi" can be used to build the constant.

gcc/ChangeLog:

	* config/rs6000/rs6000.cc (can_be_built_by_li_and_rotldi): New function.
	(rs6000_emit_set_long_const): Call can_be_built_by_li_and_rotldi.

gcc/testsuite/ChangeLog:

	* gcc.target/powerpc/const-build.c: New test.

---
 gcc/config/rs6000/rs6000.cc                   | 47 +++++++++++++--
 .../gcc.target/powerpc/const-build.c          | 57 +++++++++++++++++++
 2 files changed, 98 insertions(+), 6 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/powerpc/const-build.c

diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index 42f49e4a56b..acc332acc05 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -10258,6 +10258,31 @@ rs6000_emit_set_const (rtx dest, rtx source)
   return true;
 }
 
+/* Check if value C can be built by 2 instructions: one is 'li', another is
+   rotldi.
+
+   If so, *SHIFT is set to the shift operand of rotldi(rldicl), and *MASK
+   is set to the mask operand of rotldi(rldicl), and return true.
+   Return false otherwise.  */
+
+static bool
+can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
+				   HOST_WIDE_INT *mask)
+{
+  /* If C or ~C contains at least 49 successive zeros, then C can be rotated
+     to/from a positive or negative value that 'li' is able to load.  */
+  int n;
+  if (can_be_rotated_to_lowbits (c, 15, &n)
+      || can_be_rotated_to_lowbits (~c, 15, &n))
+    {
+      *mask = HOST_WIDE_INT_M1;
+      *shift = HOST_BITS_PER_WIDE_INT - n;
+      return true;
+    }
+
+  return false;
+}
+
 /* Subroutine of rs6000_emit_set_const, handling PowerPC64 DImode.
    Output insns to set DEST equal to the constant C as a series of
    lis, ori and shl instructions.  */
@@ -10266,15 +10291,14 @@ static void
 rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
 {
   rtx temp;
+  int shift;
+  HOST_WIDE_INT mask;
   HOST_WIDE_INT ud1, ud2, ud3, ud4;
 
   ud1 = c & 0xffff;
-  c = c >> 16;
-  ud2 = c & 0xffff;
-  c = c >> 16;
-  ud3 = c & 0xffff;
-  c = c >> 16;
-  ud4 = c & 0xffff;
+  ud2 = (c >> 16) & 0xffff;
+  ud3 = (c >> 32) & 0xffff;
+  ud4 = (c >> 48) & 0xffff;
 
   if ((ud4 == 0xffff && ud3 == 0xffff && ud2 == 0xffff && (ud1 & 0x8000))
       || (ud4 == 0 && ud3 == 0 && ud2 == 0 && ! (ud1 & 0x8000)))
@@ -10305,6 +10329,17 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
       emit_move_insn (dest, gen_rtx_XOR (DImode, temp,
 					 GEN_INT ((ud2 ^ 0xffff) << 16)));
     }
+  else if (can_be_built_by_li_and_rotldi (c, &shift, &mask))
+    {
+      temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
+      unsigned HOST_WIDE_INT imm = (c | ~mask);
+      imm = (imm >> shift) | (imm << (HOST_BITS_PER_WIDE_INT - shift));
+
+      emit_move_insn (temp, GEN_INT (imm));
+      if (shift != 0)
+	temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
+      emit_move_insn (dest, temp);
+    }
   else if (ud3 == 0 && ud4 == 0)
     {
       temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
diff --git a/gcc/testsuite/gcc.target/powerpc/const-build.c b/gcc/testsuite/gcc.target/powerpc/const-build.c
new file mode 100644
index 00000000000..69b37e2bb53
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
@@ -0,0 +1,57 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -save-temps" } */
+/* { dg-require-effective-target has_arch_ppc64 } */
+
+/* Verify that two instructions are sucessfully used to build constants.
+   One insn is li or lis, another is rotate: rldicl, rldicr or rldic.  */
+
+#define NOIPA __attribute__ ((noipa))
+
+struct fun
+{
+  long long (*f) (void);
+  long long val;
+};
+
+long long NOIPA
+li_rotldi_1 (void)
+{
+  return 0x7531000000000LL;
+}
+
+long long NOIPA
+li_rotldi_2 (void)
+{
+  return 0x2100000000000064LL;
+}
+
+long long NOIPA
+li_rotldi_3 (void)
+{
+  return 0xffff8531ffffffffLL;
+}
+
+long long NOIPA
+li_rotldi_4 (void)
+{
+  return 0x21ffffffffffff94LL;
+}
+
+struct fun arr[] = {
+  {li_rotldi_1, 0x7531000000000LL},
+  {li_rotldi_2, 0x2100000000000064LL},
+  {li_rotldi_3, 0xffff8531ffffffffLL},
+  {li_rotldi_4, 0x21ffffffffffff94LL},
+};
+
+/* { dg-final { scan-assembler-times {\mrotldi\M} 4 } } */
+
+int
+main ()
+{
+  for (int i = 0; i < sizeof (arr) / sizeof (arr[0]); i++)
+    if ((*arr[i].f) () != arr[i].val)
+      __builtin_abort ();
+
+  return 0;
+}