[2/4] rs6000: build constant via lis;rotldi
Checks
Commit Message
Hi,
This patch checks if a constant is possible to be rotated to/from a negative
value from "lis". If so, we could use "lis;rotldi" to build it.
The positive value of "lis" does not need to be analyzed. Because if a
constant can be rotated from the positive value of "lis", it also can be
rotated from a positive value of "li".
Bootstrap and regtest pass on ppc64{,le}.
Is this ok for trunk?
BR,
Jeff (Jiufu)
gcc/ChangeLog:
* config/rs6000/rs6000.cc (can_be_rotated_to_negative_lis): New
function.
(can_be_built_by_li_and_rotldi): Rename to ...
(can_be_built_by_li_lis_and_rotldi): ... this function.
(rs6000_emit_set_long_const): Call can_be_built_by_li_lis_and_rotldi.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/const-build.c: Add more tests.
---
gcc/config/rs6000/rs6000.cc | 42 ++++++++++++++++---
.../gcc.target/powerpc/const-build.c | 16 ++++++-
2 files changed, 52 insertions(+), 6 deletions(-)
Comments
On Wed, Jun 7, 2023 at 9:55 PM Jiufu Guo <guojiufu@linux.ibm.com> wrote:
> Hi,
>
> This patch checks if a constant is possible to be rotated to/from a
> negative
> value from "lis". If so, we could use "lis;rotldi" to build it.
> The positive value of "lis" does not need to be analyzed. Because if a
> constant can be rotated from the positive value of "lis", it also can be
> rotated from a positive value of "li".
>
> Bootstrap and regtest pass on ppc64{,le}.
> Is this ok for trunk?
>
> BR,
> Jeff (Jiufu)
>
> gcc/ChangeLog:
>
> * config/rs6000/rs6000.cc (can_be_rotated_to_negative_lis): New
> function.
> (can_be_built_by_li_and_rotldi): Rename to ...
> (can_be_built_by_li_lis_and_rotldi): ... this function.
> (rs6000_emit_set_long_const): Call
> can_be_built_by_li_lis_and_rotldi.
>
This patch is okay.
Thanks, David
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/powerpc/const-build.c: Add more tests.
> ---
> gcc/config/rs6000/rs6000.cc | 42 ++++++++++++++++---
> .../gcc.target/powerpc/const-build.c | 16 ++++++-
> 2 files changed, 52 insertions(+), 6 deletions(-)
>
> diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
> index 1dd0072350a..03cd9d5e952 100644
> --- a/gcc/config/rs6000/rs6000.cc
> +++ b/gcc/config/rs6000/rs6000.cc
> @@ -10278,19 +10278,51 @@ can_be_rotated_to_negative_li (HOST_WIDE_INT c,
> int *rot)
> return can_be_rotated_to_lowbits (~c, 15, rot);
> }
>
> -/* Check if value C can be built by 2 instructions: one is 'li', another
> is
> - rotldi.
> +/* Check if C can be rotated to a negative value which 'lis' instruction
> is
> + able to load: 1..1xx0..0. If so, set *ROT to the number by which C is
> + rotated, and return true. Return false otherwise. */
> +
> +static bool
> +can_be_rotated_to_negative_lis (HOST_WIDE_INT c, int *rot)
> +{
> + /* case a. 1..1xxx0..01..1: up to 15 x's, at least 16 0's. */
> + int leading_ones = clz_hwi (~c);
> + int tailing_ones = ctz_hwi (~c);
> + int middle_zeros = ctz_hwi (c >> tailing_ones);
> + if (middle_zeros >= 16 && leading_ones + tailing_ones >= 33)
> + {
> + *rot = HOST_BITS_PER_WIDE_INT - tailing_ones;
> + return true;
> + }
> +
> + /* case b. xx0..01..1xx: some of 15 x's (and some of 16 0's) are
> + rotated over the highest bit. */
> + int pos_one = clz_hwi ((c << 16) >> 16);
> + middle_zeros = ctz_hwi (c >> (HOST_BITS_PER_WIDE_INT - pos_one));
> + int middle_ones = clz_hwi (~(c << pos_one));
> + if (middle_zeros >= 16 && middle_ones >= 33)
> + {
> + *rot = pos_one;
> + return true;
> + }
> +
> + return false;
> +}
> +
> +/* Check if value C can be built by 2 instructions: one is 'li or lis',
> + 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. */
>
> static bool
> -can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
> +can_be_built_by_li_lis_and_rotldi (HOST_WIDE_INT c, int *shift,
> HOST_WIDE_INT *mask)
> {
> int n;
> if (can_be_rotated_to_positive_li (c, &n)
> - || can_be_rotated_to_negative_li (c, &n))
> + || can_be_rotated_to_negative_li (c, &n)
> + || can_be_rotated_to_negative_lis (c, &n))
> {
> *mask = HOST_WIDE_INT_M1;
> *shift = HOST_BITS_PER_WIDE_INT - n;
> @@ -10346,7 +10378,7 @@ 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))
> + else if (can_be_built_by_li_lis_and_rotldi (c, &shift, &mask))
> {
> temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
> unsigned HOST_WIDE_INT imm = (c | ~mask);
> diff --git a/gcc/testsuite/gcc.target/powerpc/const-build.c
> b/gcc/testsuite/gcc.target/powerpc/const-build.c
> index 70f095f6bf2..c38a1dd91f2 100644
> --- a/gcc/testsuite/gcc.target/powerpc/const-build.c
> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
> @@ -34,14 +34,28 @@ li_rotldi_4 (void)
> return 0x21ffffffffffff94LL;
> }
>
> +long long NOIPA
> +lis_rotldi_5 (void)
> +{
> + return 0xffff85310000ffffLL;
> +}
> +
> +long long NOIPA
> +lis_rotldi_6 (void)
> +{
> + return 0x5310000ffffffff8LL;
> +}
> +
> struct fun arr[] = {
> {li_rotldi_1, 0x7531000000000LL},
> {li_rotldi_2, 0x2100000000000064LL},
> {li_rotldi_3, 0xffff8531ffffffffLL},
> {li_rotldi_4, 0x21ffffffffffff94LL},
> + {lis_rotldi_5, 0xffff85310000ffffLL},
> + {lis_rotldi_6, 0x5310000ffffffff8LL},
> };
>
> -/* { dg-final { scan-assembler-times {\mrotldi\M} 4 } } */
> +/* { dg-final { scan-assembler-times {\mrotldi\M} 6 } } */
>
> int
> main ()
> --
> 2.39.1
>
>
@@ -10278,19 +10278,51 @@ can_be_rotated_to_negative_li (HOST_WIDE_INT c, int *rot)
return can_be_rotated_to_lowbits (~c, 15, rot);
}
-/* Check if value C can be built by 2 instructions: one is 'li', another is
- rotldi.
+/* Check if C can be rotated to a negative value which 'lis' instruction is
+ able to load: 1..1xx0..0. If so, set *ROT to the number by which C is
+ rotated, and return true. Return false otherwise. */
+
+static bool
+can_be_rotated_to_negative_lis (HOST_WIDE_INT c, int *rot)
+{
+ /* case a. 1..1xxx0..01..1: up to 15 x's, at least 16 0's. */
+ int leading_ones = clz_hwi (~c);
+ int tailing_ones = ctz_hwi (~c);
+ int middle_zeros = ctz_hwi (c >> tailing_ones);
+ if (middle_zeros >= 16 && leading_ones + tailing_ones >= 33)
+ {
+ *rot = HOST_BITS_PER_WIDE_INT - tailing_ones;
+ return true;
+ }
+
+ /* case b. xx0..01..1xx: some of 15 x's (and some of 16 0's) are
+ rotated over the highest bit. */
+ int pos_one = clz_hwi ((c << 16) >> 16);
+ middle_zeros = ctz_hwi (c >> (HOST_BITS_PER_WIDE_INT - pos_one));
+ int middle_ones = clz_hwi (~(c << pos_one));
+ if (middle_zeros >= 16 && middle_ones >= 33)
+ {
+ *rot = pos_one;
+ return true;
+ }
+
+ return false;
+}
+
+/* Check if value C can be built by 2 instructions: one is 'li or lis',
+ 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. */
static bool
-can_be_built_by_li_and_rotldi (HOST_WIDE_INT c, int *shift,
+can_be_built_by_li_lis_and_rotldi (HOST_WIDE_INT c, int *shift,
HOST_WIDE_INT *mask)
{
int n;
if (can_be_rotated_to_positive_li (c, &n)
- || can_be_rotated_to_negative_li (c, &n))
+ || can_be_rotated_to_negative_li (c, &n)
+ || can_be_rotated_to_negative_lis (c, &n))
{
*mask = HOST_WIDE_INT_M1;
*shift = HOST_BITS_PER_WIDE_INT - n;
@@ -10346,7 +10378,7 @@ 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))
+ else if (can_be_built_by_li_lis_and_rotldi (c, &shift, &mask))
{
temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
unsigned HOST_WIDE_INT imm = (c | ~mask);
@@ -34,14 +34,28 @@ li_rotldi_4 (void)
return 0x21ffffffffffff94LL;
}
+long long NOIPA
+lis_rotldi_5 (void)
+{
+ return 0xffff85310000ffffLL;
+}
+
+long long NOIPA
+lis_rotldi_6 (void)
+{
+ return 0x5310000ffffffff8LL;
+}
+
struct fun arr[] = {
{li_rotldi_1, 0x7531000000000LL},
{li_rotldi_2, 0x2100000000000064LL},
{li_rotldi_3, 0xffff8531ffffffffLL},
{li_rotldi_4, 0x21ffffffffffff94LL},
+ {lis_rotldi_5, 0xffff85310000ffffLL},
+ {lis_rotldi_6, 0x5310000ffffffff8LL},
};
-/* { dg-final { scan-assembler-times {\mrotldi\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mrotldi\M} 6 } } */
int
main ()