[3/4] rs6000: build constant via li/lis;rldicl/rldicr
Checks
Commit Message
Hi,
This patch checks if a constant is possible left/right cleaned on a rotated
value from a negative value of "li/lis". If so, we can build the constant
through "li/lis ; rldicl/rldicr".
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_lis_and_rldicl): New
function.
(can_be_built_by_li_lis_and_rldicr): New function.
(rs6000_emit_set_long_const): Call can_be_built_by_li_lis_and_rldicr and
can_be_built_by_li_lis_and_rldicl.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/const-build.c: Add more tests.
---
gcc/config/rs6000/rs6000.cc | 61 ++++++++++++++++++-
.../gcc.target/powerpc/const-build.c | 44 +++++++++++++
2 files changed, 104 insertions(+), 1 deletion(-)
Comments
On Wed, Jun 7, 2023 at 9:56 PM Jiufu Guo <guojiufu@linux.ibm.com> wrote:
> Hi,
>
> This patch checks if a constant is possible left/right cleaned on a rotated
> value from a negative value of "li/lis". If so, we can build the constant
> through "li/lis ; rldicl/rldicr".
>
> 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_lis_and_rldicl): New
> function.
> (can_be_built_by_li_lis_and_rldicr): New function.
> (rs6000_emit_set_long_const): Call
> can_be_built_by_li_lis_and_rldicr and
> can_be_built_by_li_lis_and_rldicl.
>
This is okay. See below.
Thanks, David
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/powerpc/const-build.c: Add more tests.
> ---
> gcc/config/rs6000/rs6000.cc | 61 ++++++++++++++++++-
> .../gcc.target/powerpc/const-build.c | 44 +++++++++++++
> 2 files changed, 104 insertions(+), 1 deletion(-)
>
> diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
> index 03cd9d5e952..2a3fa733b45 100644
> --- a/gcc/config/rs6000/rs6000.cc
> +++ b/gcc/config/rs6000/rs6000.cc
> @@ -10332,6 +10332,61 @@ can_be_built_by_li_lis_and_rotldi (HOST_WIDE_INT
> c, int *shift,
> return false;
> }
>
> +/* Check if value C can be built by 2 instructions: one is 'li or lis',
> + another is rldicl.
> +
> + If so, *SHIFT is set to the shift operand of rldicl, and *MASK is set
> to
> + the mask operand of rldicl, and return true.
> + Return false otherwise. */
> +
> +static bool
> +can_be_built_by_li_lis_and_rldicl (HOST_WIDE_INT c, int *shift,
> + HOST_WIDE_INT *mask)
> +{
> + /* Leading zeros may be cleaned by rldicl with a mask. Change leading
> zeros
> + to ones and then recheck it. */
> + int lz = clz_hwi (c);
> + HOST_WIDE_INT unmask_c
> + = c | (HOST_WIDE_INT_M1U << (HOST_BITS_PER_WIDE_INT - lz));
> + int n;
> + if (can_be_rotated_to_negative_li (unmask_c, &n)
>
using can_be_rotated_to_lowbits (~unmask_c, 15, &n)
Maybe Segher would want the abstraction, but it seems more wasteful to me.
> + || can_be_rotated_to_negative_lis (unmask_c, &n))
> + {
> + *mask = HOST_WIDE_INT_M1U >> lz;
> + *shift = n == 0 ? 0 : HOST_BITS_PER_WIDE_INT - n;
> + return true;
> + }
> +
> + return false;
> +}
> +
> +/* Check if value C can be built by 2 instructions: one is 'li or lis',
> + another is rldicr.
> +
> + If so, *SHIFT is set to the shift operand of rldicr, and *MASK is set
> to
> + the mask operand of rldicr, and return true.
> + Return false otherwise. */
> +
> +static bool
> +can_be_built_by_li_lis_and_rldicr (HOST_WIDE_INT c, int *shift,
> + HOST_WIDE_INT *mask)
> +{
> + /* Tailing zeros may be cleaned by rldicr with a mask. Change tailing
> zeros
> + to ones and then recheck it. */
> + int tz = ctz_hwi (c);
> + HOST_WIDE_INT unmask_c = c | ((HOST_WIDE_INT_1U << tz) - 1);
> + int n;
> + if (can_be_rotated_to_negative_li (unmask_c, &n)
> + || can_be_rotated_to_negative_lis (unmask_c, &n))
> + {
> + *mask = HOST_WIDE_INT_M1U << tz;
> + *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. */
> @@ -10378,7 +10433,9 @@ 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_lis_and_rotldi (c, &shift, &mask))
> + else if (can_be_built_by_li_lis_and_rotldi (c, &shift, &mask)
> + || can_be_built_by_li_lis_and_rldicl (c, &shift, &mask)
> + || can_be_built_by_li_lis_and_rldicr (c, &shift, &mask))
> {
> temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
> unsigned HOST_WIDE_INT imm = (c | ~mask);
> @@ -10387,6 +10444,8 @@ rs6000_emit_set_long_const (rtx dest,
> HOST_WIDE_INT c)
> emit_move_insn (temp, GEN_INT (imm));
> if (shift != 0)
> temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
> + if (mask != HOST_WIDE_INT_M1)
> + temp = gen_rtx_AND (DImode, temp, GEN_INT (mask));
> emit_move_insn (dest, temp);
> }
> else if (ud3 == 0 && ud4 == 0)
> diff --git a/gcc/testsuite/gcc.target/powerpc/const-build.c
> b/gcc/testsuite/gcc.target/powerpc/const-build.c
> index c38a1dd91f2..8c209921d41 100644
> --- a/gcc/testsuite/gcc.target/powerpc/const-build.c
> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
> @@ -46,6 +46,42 @@ lis_rotldi_6 (void)
> return 0x5310000ffffffff8LL;
> }
>
> +long long NOIPA
> +li_rldicl_7 (void)
> +{
> + return 0x3ffffffa1LL;
> +}
> +
> +long long NOIPA
> +li_rldicl_8 (void)
> +{
> + return 0xff8531ffffffffLL;
> +}
> +
> +long long NOIPA
> +lis_rldicl_9 (void)
> +{
> + return 0x00ff85310000ffffLL;
> +}
> +
> +long long NOIPA
> +li_rldicr_10 (void)
> +{
> + return 0xffff8531fff00000LL;
> +}
> +
> +long long NOIPA
> +li_rldicr_11 (void)
> +{
> + return 0x21fffffffff00000LL;
> +}
> +
> +long long NOIPA
> +lis_rldicr_12 (void)
> +{
> + return 0x5310000ffffffff0LL;
> +}
> +
> struct fun arr[] = {
> {li_rotldi_1, 0x7531000000000LL},
> {li_rotldi_2, 0x2100000000000064LL},
> @@ -53,9 +89,17 @@ struct fun arr[] = {
> {li_rotldi_4, 0x21ffffffffffff94LL},
> {lis_rotldi_5, 0xffff85310000ffffLL},
> {lis_rotldi_6, 0x5310000ffffffff8LL},
> + {li_rldicl_7, 0x3ffffffa1LL},
> + {li_rldicl_8, 0xff8531ffffffffLL},
> + {lis_rldicl_9, 0x00ff85310000ffffLL},
> + {li_rldicr_10, 0xffff8531fff00000LL},
> + {li_rldicr_11, 0x21fffffffff00000LL},
> + {lis_rldicr_12, 0x5310000ffffffff0LL},
> };
>
> /* { dg-final { scan-assembler-times {\mrotldi\M} 6 } } */
> +/* { dg-final { scan-assembler-times {\mrldicl\M} 3 } } */
> +/* { dg-final { scan-assembler-times {\mrldicr\M} 3 } } */
>
> int
> main ()
> --
> 2.39.1
>
>
Hi,
David Edelsohn <dje.gcc@gmail.com> writes:
>
> On Wed, Jun 7, 2023 at 9:56 PM Jiufu Guo <guojiufu@linux.ibm.com> wrote:
>
> Hi,
>
> This patch checks if a constant is possible left/right cleaned on a rotated
> value from a negative value of "li/lis". If so, we can build the constant
> through "li/lis ; rldicl/rldicr".
>
> 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_lis_and_rldicl): New
> function.
> (can_be_built_by_li_lis_and_rldicr): New function.
> (rs6000_emit_set_long_const): Call can_be_built_by_li_lis_and_rldicr and
> can_be_built_by_li_lis_and_rldicl.
>
> This is okay. See below.
>
> Thanks, David
>
>
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/powerpc/const-build.c: Add more tests.
> ---
> gcc/config/rs6000/rs6000.cc | 61 ++++++++++++++++++-
> .../gcc.target/powerpc/const-build.c | 44 +++++++++++++
> 2 files changed, 104 insertions(+), 1 deletion(-)
>
> diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
> index 03cd9d5e952..2a3fa733b45 100644
> --- a/gcc/config/rs6000/rs6000.cc
> +++ b/gcc/config/rs6000/rs6000.cc
> @@ -10332,6 +10332,61 @@ can_be_built_by_li_lis_and_rotldi (HOST_WIDE_INT c, int *shift,
> return false;
> }
>
> +/* Check if value C can be built by 2 instructions: one is 'li or lis',
> + another is rldicl.
> +
> + If so, *SHIFT is set to the shift operand of rldicl, and *MASK is set to
> + the mask operand of rldicl, and return true.
> + Return false otherwise. */
> +
> +static bool
> +can_be_built_by_li_lis_and_rldicl (HOST_WIDE_INT c, int *shift,
> + HOST_WIDE_INT *mask)
> +{
> + /* Leading zeros may be cleaned by rldicl with a mask. Change leading zeros
> + to ones and then recheck it. */
> + int lz = clz_hwi (c);
> + HOST_WIDE_INT unmask_c
> + = c | (HOST_WIDE_INT_M1U << (HOST_BITS_PER_WIDE_INT - lz));
> + int n;
> + if (can_be_rotated_to_negative_li (unmask_c, &n)
>
> using can_be_rotated_to_lowbits (~unmask_c, 15, &n)
>
> Maybe Segher would want the abstraction, but it seems more wasteful to
> me.
Thanks! I would update accordingly :)
BR,
Jeff (Jiufu) Guo
>
> + || can_be_rotated_to_negative_lis (unmask_c, &n))
> + {
> + *mask = HOST_WIDE_INT_M1U >> lz;
> + *shift = n == 0 ? 0 : HOST_BITS_PER_WIDE_INT - n;
> + return true;
> + }
> +
> + return false;
> +}
> +
> +/* Check if value C can be built by 2 instructions: one is 'li or lis',
> + another is rldicr.
> +
> + If so, *SHIFT is set to the shift operand of rldicr, and *MASK is set to
> + the mask operand of rldicr, and return true.
> + Return false otherwise. */
> +
> +static bool
> +can_be_built_by_li_lis_and_rldicr (HOST_WIDE_INT c, int *shift,
> + HOST_WIDE_INT *mask)
> +{
> + /* Tailing zeros may be cleaned by rldicr with a mask. Change tailing zeros
> + to ones and then recheck it. */
> + int tz = ctz_hwi (c);
> + HOST_WIDE_INT unmask_c = c | ((HOST_WIDE_INT_1U << tz) - 1);
> + int n;
> + if (can_be_rotated_to_negative_li (unmask_c, &n)
> + || can_be_rotated_to_negative_lis (unmask_c, &n))
> + {
> + *mask = HOST_WIDE_INT_M1U << tz;
> + *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. */
> @@ -10378,7 +10433,9 @@ 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_lis_and_rotldi (c, &shift, &mask))
> + else if (can_be_built_by_li_lis_and_rotldi (c, &shift, &mask)
> + || can_be_built_by_li_lis_and_rldicl (c, &shift, &mask)
> + || can_be_built_by_li_lis_and_rldicr (c, &shift, &mask))
> {
> temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
> unsigned HOST_WIDE_INT imm = (c | ~mask);
> @@ -10387,6 +10444,8 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
> emit_move_insn (temp, GEN_INT (imm));
> if (shift != 0)
> temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
> + if (mask != HOST_WIDE_INT_M1)
> + temp = gen_rtx_AND (DImode, temp, GEN_INT (mask));
> emit_move_insn (dest, temp);
> }
> else if (ud3 == 0 && ud4 == 0)
> diff --git a/gcc/testsuite/gcc.target/powerpc/const-build.c b/gcc/testsuite/gcc.target/powerpc/const-build.c
> index c38a1dd91f2..8c209921d41 100644
> --- a/gcc/testsuite/gcc.target/powerpc/const-build.c
> +++ b/gcc/testsuite/gcc.target/powerpc/const-build.c
> @@ -46,6 +46,42 @@ lis_rotldi_6 (void)
> return 0x5310000ffffffff8LL;
> }
>
> +long long NOIPA
> +li_rldicl_7 (void)
> +{
> + return 0x3ffffffa1LL;
> +}
> +
> +long long NOIPA
> +li_rldicl_8 (void)
> +{
> + return 0xff8531ffffffffLL;
> +}
> +
> +long long NOIPA
> +lis_rldicl_9 (void)
> +{
> + return 0x00ff85310000ffffLL;
> +}
> +
> +long long NOIPA
> +li_rldicr_10 (void)
> +{
> + return 0xffff8531fff00000LL;
> +}
> +
> +long long NOIPA
> +li_rldicr_11 (void)
> +{
> + return 0x21fffffffff00000LL;
> +}
> +
> +long long NOIPA
> +lis_rldicr_12 (void)
> +{
> + return 0x5310000ffffffff0LL;
> +}
> +
> struct fun arr[] = {
> {li_rotldi_1, 0x7531000000000LL},
> {li_rotldi_2, 0x2100000000000064LL},
> @@ -53,9 +89,17 @@ struct fun arr[] = {
> {li_rotldi_4, 0x21ffffffffffff94LL},
> {lis_rotldi_5, 0xffff85310000ffffLL},
> {lis_rotldi_6, 0x5310000ffffffff8LL},
> + {li_rldicl_7, 0x3ffffffa1LL},
> + {li_rldicl_8, 0xff8531ffffffffLL},
> + {lis_rldicl_9, 0x00ff85310000ffffLL},
> + {li_rldicr_10, 0xffff8531fff00000LL},
> + {li_rldicr_11, 0x21fffffffff00000LL},
> + {lis_rldicr_12, 0x5310000ffffffff0LL},
> };
>
> /* { dg-final { scan-assembler-times {\mrotldi\M} 6 } } */
> +/* { dg-final { scan-assembler-times {\mrldicl\M} 3 } } */
> +/* { dg-final { scan-assembler-times {\mrldicr\M} 3 } } */
>
> int
> main ()
> --
> 2.39.1
@@ -10332,6 +10332,61 @@ can_be_built_by_li_lis_and_rotldi (HOST_WIDE_INT c, int *shift,
return false;
}
+/* Check if value C can be built by 2 instructions: one is 'li or lis',
+ another is rldicl.
+
+ If so, *SHIFT is set to the shift operand of rldicl, and *MASK is set to
+ the mask operand of rldicl, and return true.
+ Return false otherwise. */
+
+static bool
+can_be_built_by_li_lis_and_rldicl (HOST_WIDE_INT c, int *shift,
+ HOST_WIDE_INT *mask)
+{
+ /* Leading zeros may be cleaned by rldicl with a mask. Change leading zeros
+ to ones and then recheck it. */
+ int lz = clz_hwi (c);
+ HOST_WIDE_INT unmask_c
+ = c | (HOST_WIDE_INT_M1U << (HOST_BITS_PER_WIDE_INT - lz));
+ int n;
+ if (can_be_rotated_to_negative_li (unmask_c, &n)
+ || can_be_rotated_to_negative_lis (unmask_c, &n))
+ {
+ *mask = HOST_WIDE_INT_M1U >> lz;
+ *shift = n == 0 ? 0 : HOST_BITS_PER_WIDE_INT - n;
+ return true;
+ }
+
+ return false;
+}
+
+/* Check if value C can be built by 2 instructions: one is 'li or lis',
+ another is rldicr.
+
+ If so, *SHIFT is set to the shift operand of rldicr, and *MASK is set to
+ the mask operand of rldicr, and return true.
+ Return false otherwise. */
+
+static bool
+can_be_built_by_li_lis_and_rldicr (HOST_WIDE_INT c, int *shift,
+ HOST_WIDE_INT *mask)
+{
+ /* Tailing zeros may be cleaned by rldicr with a mask. Change tailing zeros
+ to ones and then recheck it. */
+ int tz = ctz_hwi (c);
+ HOST_WIDE_INT unmask_c = c | ((HOST_WIDE_INT_1U << tz) - 1);
+ int n;
+ if (can_be_rotated_to_negative_li (unmask_c, &n)
+ || can_be_rotated_to_negative_lis (unmask_c, &n))
+ {
+ *mask = HOST_WIDE_INT_M1U << tz;
+ *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. */
@@ -10378,7 +10433,9 @@ 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_lis_and_rotldi (c, &shift, &mask))
+ else if (can_be_built_by_li_lis_and_rotldi (c, &shift, &mask)
+ || can_be_built_by_li_lis_and_rldicl (c, &shift, &mask)
+ || can_be_built_by_li_lis_and_rldicr (c, &shift, &mask))
{
temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
unsigned HOST_WIDE_INT imm = (c | ~mask);
@@ -10387,6 +10444,8 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
emit_move_insn (temp, GEN_INT (imm));
if (shift != 0)
temp = gen_rtx_ROTATE (DImode, temp, GEN_INT (shift));
+ if (mask != HOST_WIDE_INT_M1)
+ temp = gen_rtx_AND (DImode, temp, GEN_INT (mask));
emit_move_insn (dest, temp);
}
else if (ud3 == 0 && ud4 == 0)
@@ -46,6 +46,42 @@ lis_rotldi_6 (void)
return 0x5310000ffffffff8LL;
}
+long long NOIPA
+li_rldicl_7 (void)
+{
+ return 0x3ffffffa1LL;
+}
+
+long long NOIPA
+li_rldicl_8 (void)
+{
+ return 0xff8531ffffffffLL;
+}
+
+long long NOIPA
+lis_rldicl_9 (void)
+{
+ return 0x00ff85310000ffffLL;
+}
+
+long long NOIPA
+li_rldicr_10 (void)
+{
+ return 0xffff8531fff00000LL;
+}
+
+long long NOIPA
+li_rldicr_11 (void)
+{
+ return 0x21fffffffff00000LL;
+}
+
+long long NOIPA
+lis_rldicr_12 (void)
+{
+ return 0x5310000ffffffff0LL;
+}
+
struct fun arr[] = {
{li_rotldi_1, 0x7531000000000LL},
{li_rotldi_2, 0x2100000000000064LL},
@@ -53,9 +89,17 @@ struct fun arr[] = {
{li_rotldi_4, 0x21ffffffffffff94LL},
{lis_rotldi_5, 0xffff85310000ffffLL},
{lis_rotldi_6, 0x5310000ffffffff8LL},
+ {li_rldicl_7, 0x3ffffffa1LL},
+ {li_rldicl_8, 0xff8531ffffffffLL},
+ {lis_rldicl_9, 0x00ff85310000ffffLL},
+ {li_rldicr_10, 0xffff8531fff00000LL},
+ {li_rldicr_11, 0x21fffffffff00000LL},
+ {lis_rldicr_12, 0x5310000ffffffff0LL},
};
/* { dg-final { scan-assembler-times {\mrotldi\M} 6 } } */
+/* { dg-final { scan-assembler-times {\mrldicl\M} 3 } } */
+/* { dg-final { scan-assembler-times {\mrldicr\M} 3 } } */
int
main ()