Hi Kewen,
Thanks for your review on this patch!
"Kewen.Lin" <li...@linux.ibm.com> writes:
> Hi Jeff,
>
> Sorry for the late review.
>
> on 2022/9/15 16:30, Jiufu Guo wrote:
>> Hi,
>>
>> For a complicate 64bit constant, blow is one instruction-sequence to
>> build:
>> lis 9,0x800a
>> ori 9,9,0xabcd
>> sldi 9,9,32
>> oris 9,9,0xc167
>> ori 9,9,0xfa16
>>
>> while we can also use below sequence to build:
>> lis 9,0xc167
>> lis 10,0x800a
>> ori 9,9,0xfa16
>> ori 10,10,0xabcd
>> rldimi 9,10,32,0
>> This sequence is using 2 registers to build high and low part firstly,
>> and then merge them.
>> In parallel aspect, this sequence would be faster. (Ofcause, using 1 more
>> register with potential register pressure).
>>
>> Bootstrap and regtest pass on ppc64le.
>> Is this ok for trunk?
>>
>>
>> BR,
>> Jeff(Jiufu)
>>
>>
>> gcc/ChangeLog:
>>
>> * config/rs6000/rs6000.cc (rs6000_emit_set_long_const): Update 64bit
>> constant build.
>>
>> gcc/testsuite/ChangeLog:
>>
>> * gcc.target/powerpc/parall_5insn_const.c: New test.
>>
>> ---
>> gcc/config/rs6000/rs6000.cc | 45 +++++++++++--------
>> .../gcc.target/powerpc/parall_5insn_const.c | 27 +++++++++++
>> 2 files changed, 53 insertions(+), 19 deletions(-)
>> create mode 100644 gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
>>
>> diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
>> index a656cb32a47..759c6309677 100644
>> --- a/gcc/config/rs6000/rs6000.cc
>> +++ b/gcc/config/rs6000/rs6000.cc
>> @@ -10180,26 +10180,33 @@ rs6000_emit_set_long_const (rtx dest,
>> HOST_WIDE_INT c)
>> }
>> else
>> {
>> - temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
>> -
>> - emit_move_insn (copy_rtx (temp),
>> - GEN_INT (((ud4 << 16) ^ 0x80000000) - 0x80000000));
>> - if (ud3 != 0)
>> - emit_move_insn (copy_rtx (temp),
>> - gen_rtx_IOR (DImode, copy_rtx (temp),
>> - GEN_INT (ud3)));
>> + if (can_create_pseudo_p ())
>> + {
>> + /* lis A,U4; ori A,U3; lis B,U2; ori B,U1; rldimi A,B,32,0. */
>
> Nit: A, B are supposed to be H, L?
Yes, thanks for this catch! It should be
/* lis H,U4; ori H,U3; lis L,U2; ori L,U1; rldimi L,H,32,0. */
>
>> + rtx H = gen_reg_rtx (DImode);
>> + rtx L = gen_reg_rtx (DImode);
>> + HOST_WIDE_INT num = (ud2 << 16) | ud1;
>> + rs6000_emit_set_long_const (L, (num ^ 0x80000000) - 0x80000000);
>> + num = (ud4 << 16) | ud3;
>> + rs6000_emit_set_long_const (H, (num ^ 0x80000000) - 0x80000000);
>> + emit_insn (gen_rotldi3_insert_3 (dest, H, GEN_INT (32), L,
>> + GEN_INT (0xffffffff)));
>> + }
>> + else
>> + {
>> + /* lis A, U4; ori A,U3; rotl A,32; oris A,U2; ori A,U1. */
> ~~~ unexpected space?
Thanks for the catch!
>
>> + emit_move_insn (dest,
>> + GEN_INT (((ud4 << 16) ^ 0x80000000) - 0x80000000));
>> + if (ud3 != 0)
>> + emit_move_insn (dest, gen_rtx_IOR (DImode, dest, GEN_INT (ud3)));
>>
>> - emit_move_insn (ud2 != 0 || ud1 != 0 ? copy_rtx (temp) : dest,
>> - gen_rtx_ASHIFT (DImode, copy_rtx (temp),
>> - GEN_INT (32)));
>> - if (ud2 != 0)
>> - emit_move_insn (ud1 != 0 ? copy_rtx (temp) : dest,
>> - gen_rtx_IOR (DImode, copy_rtx (temp),
>> - GEN_INT (ud2 << 16)));
>> - if (ud1 != 0)
>> - emit_move_insn (dest,
>> - gen_rtx_IOR (DImode, copy_rtx (temp),
>> - GEN_INT (ud1)));
>> + emit_move_insn (dest, gen_rtx_ASHIFT (DImode, dest, GEN_INT (32)));
>> + if (ud2 != 0)
>> + emit_move_insn (dest,
>> + gen_rtx_IOR (DImode, dest, GEN_INT (ud2 << 16)));
>> + if (ud1 != 0)
>> + emit_move_insn (dest, gen_rtx_IOR (DImode, dest, GEN_INT (ud1)));
>> + }
>> }
>> }
>>
>> diff --git a/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
>> b/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
>> new file mode 100644
>> index 00000000000..ed8ccc73378
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
>> @@ -0,0 +1,27 @@
>> +/* { dg-do run } */
>> +/* { dg-options "-O2 -mdejagnu-cpu=power7 -save-temps" } */
>
> Why do we need power7 here?
power8/9 are also ok for this case. Actually, O just want to
avoid to use new p10 instruction, like "pli", and then selected
an old arch option.
>
>> +/* { dg-require-effective-target has_arch_ppc64 } */
>> +
>> +/* { dg-final { scan-assembler-times {\mlis\M} 4 } } */
>> +/* { dg-final { scan-assembler-times {\mori\M} 4 } } */
>> +/* { dg-final { scan-assembler-times {\mrldimi\M} 2 } } */
>> +
>> +void __attribute__ ((noinline)) foo (unsigned long long *a)
>> +{
>> + /* 2lis+2ori+1rldimi for each constant. */
>
> Nit: seems better to read with "/* 2 lis + 2 ori + 1 rldimi for ..."
Thanks for your sugguestion!
BR,
Jeff (Jiufu)
I updated it as below:
gcc/ChangeLog:
* config/rs6000/rs6000.cc (rs6000_emit_set_long_const): Update 64bit
constant build.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/parall_5insn_const.c: New test.
---
gcc/config/rs6000/rs6000.cc | 45 +++++++++++--------
.../gcc.target/powerpc/parall_5insn_const.c | 27 +++++++++++
2 files changed, 53 insertions(+), 19 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index a656cb32a47..759c6309677 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -10180,26 +10180,33 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT c)
}
else
{
- temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode);
-
- emit_move_insn (copy_rtx (temp),
- GEN_INT (((ud4 << 16) ^ 0x80000000) - 0x80000000));
- if (ud3 != 0)
- emit_move_insn (copy_rtx (temp),
- gen_rtx_IOR (DImode, copy_rtx (temp),
- GEN_INT (ud3)));
+ if (can_create_pseudo_p ())
+ {
+ /* lis H,U4; ori H,U3; lis L,U2; ori L,U1; rldimi L,H,32,0. */
+ rtx H = gen_reg_rtx (DImode);
+ rtx L = gen_reg_rtx (DImode);
+ HOST_WIDE_INT num = (ud2 << 16) | ud1;
+ rs6000_emit_set_long_const (L, (num ^ 0x80000000) - 0x80000000);
+ num = (ud4 << 16) | ud3;
+ rs6000_emit_set_long_const (H, (num ^ 0x80000000) - 0x80000000);
+ emit_insn (gen_rotldi3_insert_3 (dest, H, GEN_INT (32), L,
+ GEN_INT (0xffffffff)));
+ }
+ else
+ {
+ /* lis A,U4; ori A,U3; rotl A,32; oris A,U2; ori A,U1. */
+ emit_move_insn (dest,
+ GEN_INT (((ud4 << 16) ^ 0x80000000) - 0x80000000));
+ if (ud3 != 0)
+ emit_move_insn (dest, gen_rtx_IOR (DImode, dest, GEN_INT (ud3)));
- emit_move_insn (ud2 != 0 || ud1 != 0 ? copy_rtx (temp) : dest,
- gen_rtx_ASHIFT (DImode, copy_rtx (temp),
- GEN_INT (32)));
- if (ud2 != 0)
- emit_move_insn (ud1 != 0 ? copy_rtx (temp) : dest,
- gen_rtx_IOR (DImode, copy_rtx (temp),
- GEN_INT (ud2 << 16)));
- if (ud1 != 0)
- emit_move_insn (dest,
- gen_rtx_IOR (DImode, copy_rtx (temp),
- GEN_INT (ud1)));
+ emit_move_insn (dest, gen_rtx_ASHIFT (DImode, dest, GEN_INT (32)));
+ if (ud2 != 0)
+ emit_move_insn (dest,
+ gen_rtx_IOR (DImode, dest, GEN_INT (ud2 << 16)));
+ if (ud1 != 0)
+ emit_move_insn (dest, gen_rtx_IOR (DImode, dest, GEN_INT (ud1)));
+ }
}
}
diff --git a/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
b/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
new file mode 100644
index 00000000000..ed8ccc73378
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/parall_5insn_const.c
@@ -0,1 +1,27 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -mdejagnu-cpu=power8 -save-temps" } */
+/* { dg-require-effective-target has_arch_ppc64 } */
+
+/* { dg-final { scan-assembler-times {\mlis\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mori\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mrldimi\M} 2 } } */
+
+void __attribute__ ((noinline)) foo (unsigned long long *a)
+{
+ /* 2 lis + 2 ori + 1 rldimi for each constant. */
+ *a++ = 0x800aabcdc167fa16ULL;
+ *a++ = 0x7543a876867f616ULL;
+}
+
+long long A[] = {0x800aabcdc167fa16ULL, 0x7543a876867f616ULL};
+int
+main ()
+{
+ long long res[2];
+
+ foo (res);
+ if (__builtin_memcmp (res, A, sizeof (res)) != 0)
+ __builtin_abort ();
+
+ return 0;
+}
--
2.17.1
>
> BR,
> Kewen
