On Mon, Oct 31, 2022 at 5:22 PM Uros Bizjak <ubiz...@gmail.com> wrote:
>
> On Mon, Oct 31, 2022 at 2:10 AM liuhongt <hongtao....@intel.com> wrote:
> >
> > >You have a couple of other patterns where operand 1 is matched to
> > >produce vmovddup insn. These are *avx512f_unpcklpd512<mask_name> and
> > >avx_unpcklpd256<mask_name>. You can also remove expander in both
> > >cases.
> >
> > Yes, changed in V2 patch.
> >
> > Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
> > Ok for trunk?
> >
> >
> > Matching constraints are used in these circumstances. More precisely,
> > the two operands that match must include one input-only operand and
> > one output-only operand. Moreover, the digit must be a smaller number
> > than the number of the operand that uses it in the constraint.
> >
> > In pr107057, the 2 operands in the pattern are both input operands.
> >
> > gcc/ChangeLog:
> >
> > PR target/107057
> > * config/i386/sse.md (*vec_interleave_highv2df): Remove
> > constraint 1.
> > (*vec_interleave_lowv2df): Ditto.
> > (vec_concatv2df): Ditto.
> > (*avx512f_unpcklpd512<mask_name>): Ditto and renamed to ..
> > (avx512f_unpcklpd512<mask_name>): .. this.
> > (avx512f_movddup512<mask_name>): Change to define_insn.
> > (avx_movddup256<mask_name>): Ditto.
> > (*avx_unpcklpd256<mask_name>): Remove constraint 1 and renamed
> > to ..
> > (avx_unpcklpd256<mask_name>): .. this.
> > * config/i386/i386.cc (ix86_vec_interleave_v2df_operator_ok):
> > Disallow MEM_P (op1) && MEM_P (op2).
> >
> > gcc/testsuite/ChangeLog:
> >
> > * gcc.target/i386/pr107057.c: New test.
> OK with two small adjustments.
Changed and committed.
>
> Thanks,
> Uros.
>
> > ---
> > gcc/config/i386/i386.cc | 2 +-
> > gcc/config/i386/sse.md | 140 +++++++++--------------
> > gcc/testsuite/gcc.target/i386/pr107057.c | 19 +++
> > 3 files changed, 77 insertions(+), 84 deletions(-)
> > create mode 100644 gcc/testsuite/gcc.target/i386/pr107057.c
> >
> > diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> > index aeea26ef4be..e3b7bea0d68 100644
> > --- a/gcc/config/i386/i386.cc
> > +++ b/gcc/config/i386/i386.cc
> > @@ -15652,7 +15652,7 @@ ix86_vec_interleave_v2df_operator_ok (rtx
> > operands[3], bool high)
> > if (MEM_P (operands[0]))
> > return rtx_equal_p (operands[0], operands[1 + high]);
> > if (MEM_P (operands[1]) && MEM_P (operands[2]))
> > - return TARGET_SSE3 && rtx_equal_p (operands[1], operands[2]);
> > + return false;
> > return true;
> > }
> >
> > diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> > index f4b5506703f..b7922521734 100644
> > --- a/gcc/config/i386/sse.md
> > +++ b/gcc/config/i386/sse.md
> > @@ -12170,107 +12170,88 @@ (define_expand "vec_interleave_highv2df"
> > })
> >
> > (define_insn "*vec_interleave_highv2df"
> > - [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,v,v,x,v,m")
> > + [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,v,x,v,m")
> > (vec_select:V2DF
> > (vec_concat:V4DF
> > - (match_operand:V2DF 1 "nonimmediate_operand" " 0,v,o,o,o,v")
> > - (match_operand:V2DF 2 "nonimmediate_operand" " x,v,1,0,v,0"))
> > + (match_operand:V2DF 1 "nonimmediate_operand" " 0,v,o,o,v")
> > + (match_operand:V2DF 2 "nonimmediate_operand" " x,v,0,v,0"))
> > (parallel [(const_int 1)
> > (const_int 3)])))]
> > "TARGET_SSE2 && ix86_vec_interleave_v2df_operator_ok (operands, 1)"
> > "@
> > unpckhpd\t{%2, %0|%0, %2}
> > vunpckhpd\t{%2, %1, %0|%0, %1, %2}
> > - %vmovddup\t{%H1, %0|%0, %H1}
> > movlpd\t{%H1, %0|%0, %H1}
> > vmovlpd\t{%H1, %2, %0|%0, %2, %H1}
> > %vmovhpd\t{%1, %0|%q0, %1}"
> > - [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
> > - (set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
> > + [(set_attr "isa" "noavx,avx,noavx,avx,*")
> > + (set_attr "type" "sselog,sselog,ssemov,ssemov,ssemov")
> > (set (attr "prefix_data16")
> > - (if_then_else (eq_attr "alternative" "3,5")
> > + (if_then_else (eq_attr "alternative" "2,4")
> > (const_string "1")
> > (const_string "*")))
> > - (set_attr "prefix"
> > "orig,maybe_evex,maybe_vex,orig,maybe_evex,maybe_vex")
> > - (set_attr "mode" "V2DF,V2DF,DF,V1DF,V1DF,V1DF")])
> > + (set_attr "prefix" "orig,maybe_evex,orig,maybe_evex,maybe_vex")
> > + (set_attr "mode" "V2DF,V2DF,V1DF,V1DF,V1DF")])
> >
> > -(define_expand "avx512f_movddup512<mask_name>"
> > - [(set (match_operand:V8DF 0 "register_operand")
> > +(define_insn "avx512f_movddup512<mask_name>"
> > + [(set (match_operand:V8DF 0 "register_operand" "=v")
> > (vec_select:V8DF
> > (vec_concat:V16DF
> > - (match_operand:V8DF 1 "nonimmediate_operand")
> > + (match_operand:V8DF 1 "memory_operand" "m")
>
> I think you should leave nonimmediate_operand here with "m" predicate.
> Reload is able to move the register to the memory, and it is
> beneficial to allow registers for possible combine opportunities.
>
> > (match_dup 1))
> > (parallel [(const_int 0) (const_int 8)
> > (const_int 2) (const_int 10)
> > (const_int 4) (const_int 12)
> > (const_int 6) (const_int 14)])))]
> > - "TARGET_AVX512F")
> > -
> > -(define_expand "avx512f_unpcklpd512<mask_name>"
> > - [(set (match_operand:V8DF 0 "register_operand")
> > - (vec_select:V8DF
> > - (vec_concat:V16DF
> > - (match_operand:V8DF 1 "register_operand")
> > - (match_operand:V8DF 2 "nonimmediate_operand"))
> > - (parallel [(const_int 0) (const_int 8)
> > - (const_int 2) (const_int 10)
> > - (const_int 4) (const_int 12)
> > - (const_int 6) (const_int 14)])))]
> > - "TARGET_AVX512F")
> > + "TARGET_AVX512F"
> > + "vmovddup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
> > + [(set_attr "type" "sselog")
> > + (set_attr "prefix" "evex")
> > + (set_attr "mode" "V8DF")])
> >
> > -(define_insn "*avx512f_unpcklpd512<mask_name>"
> > - [(set (match_operand:V8DF 0 "register_operand" "=v,v")
> > +(define_insn "avx512f_unpcklpd512<mask_name>"
> > + [(set (match_operand:V8DF 0 "register_operand" "=v")
> > (vec_select:V8DF
> > (vec_concat:V16DF
> > - (match_operand:V8DF 1 "nonimmediate_operand" "vm, v")
> > - (match_operand:V8DF 2 "nonimmediate_operand" "1 ,vm"))
> > + (match_operand:V8DF 1 "register_operand" "v")
> > + (match_operand:V8DF 2 "nonimmediate_operand" "vm"))
> > (parallel [(const_int 0) (const_int 8)
> > (const_int 2) (const_int 10)
> > (const_int 4) (const_int 12)
> > (const_int 6) (const_int 14)])))]
> > "TARGET_AVX512F"
> > - "@
> > - vmovddup\t{%1, %0<mask_operand3>|%0<mask_operand3>, %1}
> > - vunpcklpd\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
> > + "vunpcklpd\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
> > [(set_attr "type" "sselog")
> > (set_attr "prefix" "evex")
> > (set_attr "mode" "V8DF")])
> >
> > ;; Recall that the 256-bit unpck insns only shuffle within their lanes.
> > -(define_expand "avx_movddup256<mask_name>"
> > - [(set (match_operand:V4DF 0 "register_operand")
> > +(define_insn "avx_movddup256<mask_name>"
> > + [(set (match_operand:V4DF 0 "register_operand" "=v")
> > (vec_select:V4DF
> > (vec_concat:V8DF
> > - (match_operand:V4DF 1 "nonimmediate_operand")
> > + (match_operand:V4DF 1 "memory_operand" "m")
>
> Also here, leave nonimmediate_operand.
>
> > (match_dup 1))
> > (parallel [(const_int 0) (const_int 4)
> > (const_int 2) (const_int 6)])))]
> > - "TARGET_AVX && <mask_avx512vl_condition>")
> > -
> > -(define_expand "avx_unpcklpd256<mask_name>"
> > - [(set (match_operand:V4DF 0 "register_operand")
> > - (vec_select:V4DF
> > - (vec_concat:V8DF
> > - (match_operand:V4DF 1 "register_operand")
> > - (match_operand:V4DF 2 "nonimmediate_operand"))
> > - (parallel [(const_int 0) (const_int 4)
> > - (const_int 2) (const_int 6)])))]
> > - "TARGET_AVX && <mask_avx512vl_condition>")
> > + "TARGET_AVX && <mask_avx512vl_condition>"
> > + "vmovddup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
> > + [(set_attr "type" "sselog")
> > + (set_attr "prefix" "<mask_prefix>")
> > + (set_attr "mode" "V4DF")])
> >
> > -(define_insn "*avx_unpcklpd256<mask_name>"
> > - [(set (match_operand:V4DF 0 "register_operand" "=v,v")
> > +(define_insn "avx_unpcklpd256<mask_name>"
> > + [(set (match_operand:V4DF 0 "register_operand" "=v")
> > (vec_select:V4DF
> > (vec_concat:V8DF
> > - (match_operand:V4DF 1 "nonimmediate_operand" " v,m")
> > - (match_operand:V4DF 2 "nonimmediate_operand" "vm,1"))
> > + (match_operand:V4DF 1 "register_operand" " v")
> > + (match_operand:V4DF 2 "nonimmediate_operand" "vm"))
> > (parallel [(const_int 0) (const_int 4)
> > (const_int 2) (const_int 6)])))]
> > "TARGET_AVX && <mask_avx512vl_condition>"
> > - "@
> > - vunpcklpd\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}
> > - vmovddup\t{%1, %0<mask_operand3>|%0<mask_operand3>, %1}"
> > + "vunpcklpd\t{%2, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2}"
> > [(set_attr "type" "sselog")
> > - (set_attr "prefix" "vex")
> > + (set_attr "prefix" "<mask_prefix>")
> > (set_attr "mode" "V4DF")])
> >
> > (define_expand "vec_interleave_lowv4df"
> > @@ -12332,29 +12313,28 @@ (define_expand "vec_interleave_lowv2df"
> > })
> >
> > (define_insn "*vec_interleave_lowv2df"
> > - [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,v,v,x,v,o")
> > + [(set (match_operand:V2DF 0 "nonimmediate_operand" "=x,v,x,v,o")
> > (vec_select:V2DF
> > (vec_concat:V4DF
> > - (match_operand:V2DF 1 "nonimmediate_operand" " 0,v,m,0,v,0")
> > - (match_operand:V2DF 2 "nonimmediate_operand" " x,v,1,m,m,v"))
> > + (match_operand:V2DF 1 "nonimmediate_operand" " 0,v,0,v,0")
> > + (match_operand:V2DF 2 "nonimmediate_operand" " x,v,m,m,v"))
> > (parallel [(const_int 0)
> > (const_int 2)])))]
> > "TARGET_SSE2 && ix86_vec_interleave_v2df_operator_ok (operands, 0)"
> > "@
> > unpcklpd\t{%2, %0|%0, %2}
> > vunpcklpd\t{%2, %1, %0|%0, %1, %2}
> > - %vmovddup\t{%1, %0|%0, %q1}
> > movhpd\t{%2, %0|%0, %q2}
> > vmovhpd\t{%2, %1, %0|%0, %1, %q2}
> > %vmovlpd\t{%2, %H0|%H0, %2}"
> > - [(set_attr "isa" "noavx,avx,sse3,noavx,avx,*")
> > - (set_attr "type" "sselog,sselog,sselog,ssemov,ssemov,ssemov")
> > + [(set_attr "isa" "noavx,avx,noavx,avx,*")
> > + (set_attr "type" "sselog,sselog,ssemov,ssemov,ssemov")
> > (set (attr "prefix_data16")
> > - (if_then_else (eq_attr "alternative" "3,5")
> > + (if_then_else (eq_attr "alternative" "2,4")
> > (const_string "1")
> > (const_string "*")))
> > - (set_attr "prefix"
> > "orig,maybe_evex,maybe_vex,orig,maybe_evex,maybe_vex")
> > - (set_attr "mode" "V2DF,V2DF,DF,V1DF,V1DF,V1DF")])
> > + (set_attr "prefix" "orig,maybe_evex,orig,maybe_evex,maybe_vex")
> > + (set_attr "mode" "V2DF,V2DF,V1DF,V1DF,V1DF")])
> >
> > (define_split
> > [(set (match_operand:V2DF 0 "memory_operand")
> > @@ -13560,56 +13540,50 @@ (define_insn "vec_dupv2df<mask_name>"
> > (set_attr "mode" "V2DF,DF,DF")])
> >
> > (define_insn "vec_concatv2df"
> > - [(set (match_operand:V2DF 0 "register_operand" "=x,x,v,x,v,x,x,
> > v,x,x")
> > + [(set (match_operand:V2DF 0 "register_operand" "=x,x,v,x,x, v,x,x")
> > (vec_concat:V2DF
> > - (match_operand:DF 1 "nonimmediate_operand" "
> > 0,x,v,m,m,0,x,vm,0,0")
> > - (match_operand:DF 2 "nonimm_or_0_operand" " x,x,v,1,1,m,m,
> > C,x,m")))]
> > - "TARGET_SSE
> > - && (!(MEM_P (operands[1]) && MEM_P (operands[2]))
> > - || (TARGET_SSE3 && rtx_equal_p (operands[1], operands[2])))"
> > + (match_operand:DF 1 "nonimmediate_operand" " 0,x,v,0,x,vm,0,0")
> > + (match_operand:DF 2 "nonimm_or_0_operand" " x,x,v,m,m, C,x,m")))]
> > + "TARGET_SSE && !(MEM_P (operands[1]) && MEM_P (operands[2]))"
> > "@
> > unpcklpd\t{%2, %0|%0, %2}
> > vunpcklpd\t{%2, %1, %0|%0, %1, %2}
> > vunpcklpd\t{%2, %1, %0|%0, %1, %2}
> > - %vmovddup\t{%1, %0|%0, %1}
> > - vmovddup\t{%1, %0|%0, %1}
> > movhpd\t{%2, %0|%0, %2}
> > vmovhpd\t{%2, %1, %0|%0, %1, %2}
> > %vmovq\t{%1, %0|%0, %1}
> > movlhps\t{%2, %0|%0, %2}
> > movhps\t{%2, %0|%0, %2}"
> > [(set (attr "isa")
> > - (cond [(eq_attr "alternative" "0,5")
> > + (cond [(eq_attr "alternative" "0,3")
> > (const_string "sse2_noavx")
> > - (eq_attr "alternative" "1,6")
> > + (eq_attr "alternative" "1,4")
> > (const_string "avx")
> > - (eq_attr "alternative" "2,4")
> > + (eq_attr "alternative" "2")
> > (const_string "avx512vl")
> > - (eq_attr "alternative" "3")
> > - (const_string "sse3")
> > - (eq_attr "alternative" "7")
> > + (eq_attr "alternative" "5")
> > (const_string "sse2")
> > ]
> > (const_string "noavx")))
> > (set (attr "type")
> > (if_then_else
> > - (eq_attr "alternative" "0,1,2,3,4")
> > + (eq_attr "alternative" "0,1,2")
> > (const_string "sselog")
> > (const_string "ssemov")))
> > (set (attr "prefix_data16")
> > - (if_then_else (eq_attr "alternative" "5")
> > + (if_then_else (eq_attr "alternative" "3")
> > (const_string "1")
> > (const_string "*")))
> > (set (attr "prefix")
> > - (cond [(eq_attr "alternative" "1,6")
> > + (cond [(eq_attr "alternative" "1,4")
> > (const_string "vex")
> > - (eq_attr "alternative" "2,4")
> > + (eq_attr "alternative" "2")
> > (const_string "evex")
> > - (eq_attr "alternative" "3,7")
> > + (eq_attr "alternative" "5")
> > (const_string "maybe_vex")
> > ]
> > (const_string "orig")))
> > - (set_attr "mode" "V2DF,V2DF,V2DF, DF, DF, V1DF,V1DF,DF,V4SF,V2SF")])
> > + (set_attr "mode" "V2DF,V2DF,V2DF,V1DF,V1DF,DF,V4SF,V2SF")])
> >
> > ;; vmovq clears also the higher bits.
> > (define_insn "vec_set<mode>_0"
> > diff --git a/gcc/testsuite/gcc.target/i386/pr107057.c
> > b/gcc/testsuite/gcc.target/i386/pr107057.c
> > new file mode 100644
> > index 00000000000..40b49ac21ec
> > --- /dev/null
> > +++ b/gcc/testsuite/gcc.target/i386/pr107057.c
> > @@ -0,0 +1,19 @@
> > +/* { dg-do compile { target { ! ia32 } } } */
> > +/* { dg-options "-mavx -mcmodel=large -O3" } */
> > +
> > +typedef double v2df __attribute__ ((vector_size (16)));
> > +v2df f (double a, double b)
> > +{
> > + v2df v;
> > + double *c = (double *)&v;
> > + *c = a;
> > + *(c+1) = b;
> > + return v;
> > +}
> > +void g ()
> > +{
> > + v2df x = f (1.0, 1.0);
> > + v2df y = f (2.0, 2.0);
> > + for (;*(double *)&x<=8; x+=y)
> > + g ();
> > +}
> > --
> > 2.27.0
> >
--
BR,
Hongtao
