Hi Kewen,
Thanks a lot for your insight comments! "Kewen.Lin" <li...@linux.ibm.com> writes: > Hi Jeff, > > Sorry for the late reply. > > on 2022/10/26 19:40, Jiufu Guo wrote: >> Hi, >> >> PR106708 constaint some constants which can be support by li/lis + >> oris/xoris. > ~~~~~~~~ typo? Oh, typo! > > for "li/lis + oris/xoris", I interpreted it into four combinations: > > li + oris, lis + oris, li + xoris, lis + xoris. > > not sure just me interpreting like that, but the actual combinations > which this patch adopts are: > > li + oris, li + xoris, lis + xoris. > > It's a bit off, but not a big deal, up to you to reword it or not. :) Oh, thanks! I will update to use "li/lis + xoris" or "li + oris" to avoid confuse. > >> >> For constant C: >> if '(c & 0xFFFFFFFF80008000ULL) == 0x80000000ULL' or say: >> 32(0) || 1(1) || 15(x) || 1(0) || 15(x), we could use li+oris to >> build constant 'C'. >> Here N(M) means N continuous bit M, x for M means it is ok for either >> 1 or 0; '||' means concatenation. >> >> if '(c & 0xFFFFFFFF00008000ULL) == 0xFFFFFFFF00008000ULL' or say: >> 32(1) || 16(x) || 1(1) || 15(x), using li+xoris would be ok. >> >> if '(c & 0xFFFFFFFF0000FFFFULL) == 0xFFFFFFFF00000000' or say: >> 32(1) || 1(0) || 15(x) || 16(0), using lis+xoris would be ok. >> >> This patch update rs6000_emit_set_long_const to support these forms. >> Bootstrap and regtest pass on ppc64 and ppc64le. >> >> Is this ok for trunk? > > This updated version looks good to me, but I'd leave it to Segher for the > final say. Thanks! Thanks! BR, Jeff (Jiufu) > > BR, > Kewen > >> >> BR, >> Jeff(Jiufu) >> >> >> PR target/106708 >> >> gcc/ChangeLog: >> >> * config/rs6000/rs6000.cc (rs6000_emit_set_long_const): Support >> constants which can be built with li + oris or li/lis + xoris. >> >> gcc/testsuite/ChangeLog: >> >> * gcc.target/powerpc/pr106708-run.c: New test. >> * gcc.target/powerpc/pr106708.c: New test. >> * gcc.target/powerpc/pr106708.h: New file. >> >> --- >> gcc/config/rs6000/rs6000.cc | 41 ++++++++++++++----- >> .../gcc.target/powerpc/pr106708-run.c | 17 ++++++++ >> gcc/testsuite/gcc.target/powerpc/pr106708.c | 12 ++++++ >> gcc/testsuite/gcc.target/powerpc/pr106708.h | 9 ++++ >> 4 files changed, 69 insertions(+), 10 deletions(-) >> create mode 100644 gcc/testsuite/gcc.target/powerpc/pr106708-run.c >> create mode 100644 gcc/testsuite/gcc.target/powerpc/pr106708.c >> create mode 100644 gcc/testsuite/gcc.target/powerpc/pr106708.h >> >> diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc >> index d2743f7bce6..9b7a51f052d 100644 >> --- a/gcc/config/rs6000/rs6000.cc >> +++ b/gcc/config/rs6000/rs6000.cc >> @@ -10228,6 +10228,7 @@ rs6000_emit_set_long_const (rtx dest, HOST_WIDE_INT >> c) >> { >> rtx temp; >> HOST_WIDE_INT ud1, ud2, ud3, ud4; >> + HOST_WIDE_INT orig_c = c; >> >> ud1 = c & 0xffff; >> c = c >> 16; >> @@ -10253,21 +10254,41 @@ rs6000_emit_set_long_const (rtx dest, >> HOST_WIDE_INT c) >> gen_rtx_IOR (DImode, copy_rtx (temp), >> GEN_INT (ud1))); >> } >> + else if ((ud4 == 0xffff && ud3 == 0xffff) >> + && ((ud1 & 0x8000) || (ud1 == 0 && !(ud2 & 0x8000)))) >> + { >> + temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode); >> + >> + HOST_WIDE_INT imm = (ud1 & 0x8000) ? ((ud1 ^ 0x8000) - 0x8000) >> + : ((ud2 << 16) - 0x80000000); >> + /* li/lis + xoris */ >> + emit_move_insn (temp, GEN_INT (imm)); >> + emit_move_insn (dest, gen_rtx_XOR (DImode, temp, >> + GEN_INT (orig_c ^ imm))); >> + } >> else if (ud3 == 0 && ud4 == 0) >> { >> temp = !can_create_pseudo_p () ? dest : gen_reg_rtx (DImode); >> >> gcc_assert (ud2 & 0x8000); >> - emit_move_insn (copy_rtx (temp), >> - GEN_INT (((ud2 << 16) ^ 0x80000000) - 0x80000000)); >> - if (ud1 != 0) >> - emit_move_insn (copy_rtx (temp), >> - gen_rtx_IOR (DImode, copy_rtx (temp), >> - GEN_INT (ud1))); >> - emit_move_insn (dest, >> - gen_rtx_ZERO_EXTEND (DImode, >> - gen_lowpart (SImode, >> - copy_rtx (temp)))); >> + >> + if (!(ud1 & 0x8000)) >> + { >> + /* li+oris */ >> + emit_move_insn (temp, GEN_INT (ud1)); >> + emit_move_insn (dest, >> + gen_rtx_IOR (DImode, temp, GEN_INT (ud2 << 16))); >> + } >> + else >> + { >> + emit_move_insn (temp, >> + GEN_INT (((ud2 << 16) ^ 0x80000000) - 0x80000000)); >> + if (ud1 != 0) >> + emit_move_insn (temp, gen_rtx_IOR (DImode, temp, GEN_INT (ud1))); >> + emit_move_insn (dest, >> + gen_rtx_ZERO_EXTEND (DImode, >> + gen_lowpart (SImode, temp))); >> + } >> } >> else if (ud1 == ud3 && ud2 == ud4) >> { >> diff --git a/gcc/testsuite/gcc.target/powerpc/pr106708-run.c >> b/gcc/testsuite/gcc.target/powerpc/pr106708-run.c >> new file mode 100644 >> index 00000000000..df65c321f6b >> --- /dev/null >> +++ b/gcc/testsuite/gcc.target/powerpc/pr106708-run.c >> @@ -0,0 +1,17 @@ >> +/* PR target/106708 */ >> +/* { dg-do run } */ >> +/* { dg-options "-O2" } */ >> + >> +#include "pr106708.h" >> + >> +long long arr[] = {0x98765432ULL, 0xffffffff7cdeab55ULL, >> 0xffffffff65430000ULL}; >> +int >> +main () >> +{ >> + long long a[3]; >> + >> + foo (a); >> + if (__builtin_memcmp (a, arr, sizeof (arr)) != 0) >> + __builtin_abort (); >> + return 0; >> +} >> diff --git a/gcc/testsuite/gcc.target/powerpc/pr106708.c >> b/gcc/testsuite/gcc.target/powerpc/pr106708.c >> new file mode 100644 >> index 00000000000..ebd9ea88993 >> --- /dev/null >> +++ b/gcc/testsuite/gcc.target/powerpc/pr106708.c >> @@ -0,0 +1,12 @@ >> +/* PR target/106708 */ >> +/* { dg-do compile } } */ >> +/* { dg-options "-O2 -mdejagnu-cpu=power8" } */ >> +/* { dg-require-effective-target has_arch_ppc64 } */ >> + >> + >> +#include "pr106708.h" >> + >> +/* { dg-final { scan-assembler-times {\mli\M} 2 } } */ >> +/* { dg-final { scan-assembler-times {\mlis\M} 1 } } */ >> +/* { dg-final { scan-assembler-times {\moris\M} 1 } } */ >> +/* { dg-final { scan-assembler-times {\mxoris\M} 2 } } */ >> diff --git a/gcc/testsuite/gcc.target/powerpc/pr106708.h >> b/gcc/testsuite/gcc.target/powerpc/pr106708.h >> new file mode 100644 >> index 00000000000..42526a70892 >> --- /dev/null >> +++ b/gcc/testsuite/gcc.target/powerpc/pr106708.h >> @@ -0,0 +1,9 @@ >> +/* Test constants which can be built by li/lis + oris/xoris */ >> +void __attribute__ ((__noinline__, __noclone__)) foo (long long *arg) >> +{ >> + *arg++ = 0x98765432ULL; >> + *arg++ = 0xffffffff7cdeab55ULL; >> + *arg++ = 0xffffffff65430000ULL; >> +} >> + >> +