* [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 [not found] <20220831064846.1305576-1-lingling.kong@intel.com> @ 2022-08-31 6:52 ` Kong, Lingling 2022-08-31 6:52 ` Kong, Lingling 2022-08-31 9:55 ` Hongtao Liu 0 siblings, 2 replies; 5+ messages in thread From: Kong, Lingling @ 2022-08-31 6:52 UTC (permalink / raw) To: Liu, Hongtao, gcc-patches; +Cc: Kong, Lingling Hi, Handle E_V8BFmode in expand_vec_perm_broadcast_1 and ix86_expand_vector_init_duplicate. Ok for trunk? gcc/ChangeLog: PR target/106742 * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): Handle V8BF mode. (expand_vec_perm_broadcast_1): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/pr106742.c: New test. --- gcc/config/i386/i386-expand.cc | 17 ++++++++++++----- gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr106742.c diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 4b216308a18..a08222fe1b6 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -15030,11 +15030,15 @@ ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, dperm.op0 = dperm.op1 = gen_reg_rtx (mode); dperm.one_operand_p = true; - if (mode == V8HFmode) + if (mode == V8HFmode || mode == V8BFmode) { - tmp1 = force_reg (HFmode, val); + rtx (*gen_vec_set_0) (rtx, rtx, rtx) = NULL; + tmp1 = mode == V8HFmode ? force_reg (HFmode, val) + : force_reg (BFmode, val); tmp2 = gen_reg_rtx (mode); - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); + gen_vec_set_0 = mode == V8HFmode ? gen_vec_setv8hf_0 + : gen_vec_setv8bf_0; + emit_insn (gen_vec_set_0 (tmp2, CONST0_RTX (mode), tmp1)); tmp1 = gen_lowpart (mode, tmp2); } else @@ -21822,17 +21826,20 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d) return true; case E_V8HFmode: + case E_V8BFmode: /* This can be implemented via interleave and pshufd. */ if (d->testing_p) return true; if (elt >= nelt2) { - gen = gen_vec_interleave_highv8hf; + gen = vmode == V8HFmode ? gen_vec_interleave_highv8hf + : gen_vec_interleave_highv8bf; elt -= nelt2; } else - gen = gen_vec_interleave_lowv8hf; + gen = vmode == V8HFmode ? gen_vec_interleave_lowv8hf + : gen_vec_interleave_lowv8bf; nelt2 /= 2; dest = gen_reg_rtx (vmode); diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c b/gcc/testsuite/gcc.target/i386/pr106742.c new file mode 100644 index 00000000000..4a53cd49902 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr106742.c @@ -0,0 +1,10 @@ +/* { dg-do compile } */ +/* { dg-options " -msse2 -mno-avx2 -O1" } */ +typedef __bf16 v8bf __attribute__ ((__vector_size__ (16))); + +v8bf +vec_init_dup_v8bf (__bf16 a1) +{ + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } +/* { dg-final { scan-assembler-times "punpcklwd" 1} } */ -- 2.18.2 ^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 2022-08-31 6:52 ` [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 Kong, Lingling @ 2022-08-31 6:52 ` Kong, Lingling 2022-08-31 9:55 ` Hongtao Liu 1 sibling, 0 replies; 5+ messages in thread From: Kong, Lingling @ 2022-08-31 6:52 UTC (permalink / raw) To: Liu, Hongtao, gcc-patches Hi, Handle E_V8BFmode in expand_vec_perm_broadcast_1 and ix86_expand_vector_init_duplicate. Ok for trunk? gcc/ChangeLog: PR target/106742 * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): Handle V8BF mode. (expand_vec_perm_broadcast_1): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/pr106742.c: New test. --- gcc/config/i386/i386-expand.cc | 17 ++++++++++++----- gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr106742.c diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 4b216308a18..a08222fe1b6 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -15030,11 +15030,15 @@ ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, dperm.op0 = dperm.op1 = gen_reg_rtx (mode); dperm.one_operand_p = true; - if (mode == V8HFmode) + if (mode == V8HFmode || mode == V8BFmode) { - tmp1 = force_reg (HFmode, val); + rtx (*gen_vec_set_0) (rtx, rtx, rtx) = NULL; + tmp1 = mode == V8HFmode ? force_reg (HFmode, val) + : force_reg (BFmode, val); tmp2 = gen_reg_rtx (mode); - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); + gen_vec_set_0 = mode == V8HFmode ? gen_vec_setv8hf_0 + : gen_vec_setv8bf_0; + emit_insn (gen_vec_set_0 (tmp2, CONST0_RTX (mode), tmp1)); tmp1 = gen_lowpart (mode, tmp2); } else @@ -21822,17 +21826,20 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d) return true; case E_V8HFmode: + case E_V8BFmode: /* This can be implemented via interleave and pshufd. */ if (d->testing_p) return true; if (elt >= nelt2) { - gen = gen_vec_interleave_highv8hf; + gen = vmode == V8HFmode ? gen_vec_interleave_highv8hf + : gen_vec_interleave_highv8bf; elt -= nelt2; } else - gen = gen_vec_interleave_lowv8hf; + gen = vmode == V8HFmode ? gen_vec_interleave_lowv8hf + : gen_vec_interleave_lowv8bf; nelt2 /= 2; dest = gen_reg_rtx (vmode); diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c b/gcc/testsuite/gcc.target/i386/pr106742.c new file mode 100644 index 00000000000..4a53cd49902 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr106742.c @@ -0,0 +1,10 @@ +/* { dg-do compile } */ +/* { dg-options " -msse2 -mno-avx2 -O1" } */ +typedef __bf16 v8bf __attribute__ ((__vector_size__ (16))); + +v8bf +vec_init_dup_v8bf (__bf16 a1) +{ + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } +/* { dg-final { scan-assembler-times "punpcklwd" 1} } */ -- 2.18.2 ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 2022-08-31 6:52 ` [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 Kong, Lingling 2022-08-31 6:52 ` Kong, Lingling @ 2022-08-31 9:55 ` Hongtao Liu 2022-09-02 8:08 ` Kong, Lingling 1 sibling, 1 reply; 5+ messages in thread From: Hongtao Liu @ 2022-08-31 9:55 UTC (permalink / raw) To: Kong, Lingling; +Cc: Liu, Hongtao, gcc-patches On Wed, Aug 31, 2022 at 2:52 PM Kong, Lingling via Gcc-patches <gcc-patches@gcc.gnu.org> wrote: > > Hi, > > Handle E_V8BFmode in expand_vec_perm_broadcast_1 and ix86_expand_vector_init_duplicate. > Ok for trunk? > > gcc/ChangeLog: > > PR target/106742 > * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): > Handle V8BF mode. > (expand_vec_perm_broadcast_1): Ditto. > > gcc/testsuite/ChangeLog: > > * gcc.target/i386/pr106742.c: New test. > --- > gcc/config/i386/i386-expand.cc | 17 ++++++++++++----- > gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ > 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr106742.c > > diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 4b216308a18..a08222fe1b6 100644 > --- a/gcc/config/i386/i386-expand.cc > +++ b/gcc/config/i386/i386-expand.cc > @@ -15030,11 +15030,15 @@ ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, > dperm.op0 = dperm.op1 = gen_reg_rtx (mode); > dperm.one_operand_p = true; > > - if (mode == V8HFmode) > + if (mode == V8HFmode || mode == V8BFmode) > { > - tmp1 = force_reg (HFmode, val); > + rtx (*gen_vec_set_0) (rtx, rtx, rtx) = NULL; > + tmp1 = mode == V8HFmode ? force_reg (HFmode, val) > + : force_reg (BFmode, val); tmp1 = force_reg (GET_MODE_INNER (mode), val); > tmp2 = gen_reg_rtx (mode); > - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); > + gen_vec_set_0 = mode == V8HFmode ? gen_vec_setv8hf_0 > + : gen_vec_setv8bf_0; add @ to vec_set<mode>_0 as (define_insn "@vec_set<mode>_0" and pass mode to vec_set_0 as emit_insn (gen_vec_set_0 (mode, tmp2, CONST0_RTX (mode), tmp1)); > + emit_insn (gen_vec_set_0 (tmp2, CONST0_RTX (mode), tmp1)); > tmp1 = gen_lowpart (mode, tmp2); > } > else > @@ -21822,17 +21826,20 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d) > return true; > > case E_V8HFmode: > + case E_V8BFmode: > /* This can be implemented via interleave and pshufd. */ > if (d->testing_p) > return true; > > if (elt >= nelt2) > { > - gen = gen_vec_interleave_highv8hf; > + gen = vmode == V8HFmode ? gen_vec_interleave_highv8hf > + : gen_vec_interleave_highv8bf; Similar, add @ to define_insn and pass gen_vec_interleave. > elt -= nelt2; > } > else > - gen = gen_vec_interleave_lowv8hf; > + gen = vmode == V8HFmode ? gen_vec_interleave_lowv8hf > + : gen_vec_interleave_lowv8bf; > nelt2 /= 2; > > dest = gen_reg_rtx (vmode); > diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c b/gcc/testsuite/gcc.target/i386/pr106742.c > new file mode 100644 > index 00000000000..4a53cd49902 > --- /dev/null > +++ b/gcc/testsuite/gcc.target/i386/pr106742.c > @@ -0,0 +1,10 @@ > +/* { dg-do compile } */ > +/* { dg-options " -msse2 -mno-avx2 -O1" } */ > +typedef __bf16 v8bf __attribute__ ((__vector_size__ (16))); > + > +v8bf > +vec_init_dup_v8bf (__bf16 a1) > +{ > + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } > +/* { dg-final { scan-assembler-times "punpcklwd" 1} } */ > -- > 2.18.2 > -- BR, Hongtao ^ permalink raw reply [flat|nested] 5+ messages in thread
* RE: [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 2022-08-31 9:55 ` Hongtao Liu @ 2022-09-02 8:08 ` Kong, Lingling 2022-09-05 0:59 ` Hongtao Liu 0 siblings, 1 reply; 5+ messages in thread From: Kong, Lingling @ 2022-09-02 8:08 UTC (permalink / raw) To: Hongtao Liu; +Cc: Liu, Hongtao, gcc-patches [-- Attachment #1: Type: text/plain, Size: 3898 bytes --] Hi, I fixed it in a new patch. And added BF vector mode in SUBST_V and avx512fmaskhalfmode for @vec_interleave_high<mode><mask_name>. Ok for trunk ? > > Hi, > > > > Handle E_V8BFmode in expand_vec_perm_broadcast_1 and > ix86_expand_vector_init_duplicate. > > Ok for trunk? > > > > gcc/ChangeLog: > > > > PR target/106742 > > * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): > > Handle V8BF mode. > > (expand_vec_perm_broadcast_1): Ditto. > > > > gcc/testsuite/ChangeLog: > > > > * gcc.target/i386/pr106742.c: New test. > > --- > > gcc/config/i386/i386-expand.cc | 17 ++++++++++++----- > > gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ > > 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 > > gcc/testsuite/gcc.target/i386/pr106742.c > > > > diff --git a/gcc/config/i386/i386-expand.cc > > b/gcc/config/i386/i386-expand.cc index 4b216308a18..a08222fe1b6 100644 > > --- a/gcc/config/i386/i386-expand.cc > > +++ b/gcc/config/i386/i386-expand.cc > > @@ -15030,11 +15030,15 @@ ix86_expand_vector_init_duplicate (bool > mmx_ok, machine_mode mode, > > dperm.op0 = dperm.op1 = gen_reg_rtx (mode); > > dperm.one_operand_p = true; > > > > - if (mode == V8HFmode) > > + if (mode == V8HFmode || mode == V8BFmode) > > { > > - tmp1 = force_reg (HFmode, val); > > + rtx (*gen_vec_set_0) (rtx, rtx, rtx) = NULL; > > + tmp1 = mode == V8HFmode ? force_reg (HFmode, val) > > + : force_reg (BFmode, val); > tmp1 = force_reg (GET_MODE_INNER (mode), val); > > tmp2 = gen_reg_rtx (mode); > > - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); > > + gen_vec_set_0 = mode == V8HFmode ? gen_vec_setv8hf_0 > > + : gen_vec_setv8bf_0; > add @ to vec_set<mode>_0 as (define_insn "@vec_set<mode>_0" and pass > mode to vec_set_0 as emit_insn (gen_vec_set_0 (mode, tmp2, CONST0_RTX > (mode), tmp1)); > > + emit_insn (gen_vec_set_0 (tmp2, CONST0_RTX (mode), > > + tmp1)); > > > tmp1 = gen_lowpart (mode, tmp2); > > } > > else > > @@ -21822,17 +21826,20 @@ expand_vec_perm_broadcast_1 (struct > expand_vec_perm_d *d) > > return true; > > > > case E_V8HFmode: > > + case E_V8BFmode: > > /* This can be implemented via interleave and pshufd. */ > > if (d->testing_p) > > return true; > > > > if (elt >= nelt2) > > { > > - gen = gen_vec_interleave_highv8hf; > > + gen = vmode == V8HFmode ? gen_vec_interleave_highv8hf > > + : gen_vec_interleave_highv8bf; > Similar, add @ to define_insn and pass gen_vec_interleave. > > elt -= nelt2; > > } > > else > > - gen = gen_vec_interleave_lowv8hf; > > + gen = vmode == V8HFmode ? gen_vec_interleave_lowv8hf > > + : gen_vec_interleave_lowv8bf; > > nelt2 /= 2; > > > > dest = gen_reg_rtx (vmode); > > diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c > > b/gcc/testsuite/gcc.target/i386/pr106742.c > > new file mode 100644 > > index 00000000000..4a53cd49902 > > --- /dev/null > > +++ b/gcc/testsuite/gcc.target/i386/pr106742.c > > @@ -0,0 +1,10 @@ > > +/* { dg-do compile } */ > > +/* { dg-options " -msse2 -mno-avx2 -O1" } */ typedef __bf16 v8bf > > +__attribute__ ((__vector_size__ (16))); > > + > > +v8bf > > +vec_init_dup_v8bf (__bf16 a1) > > +{ > > + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } > > +/* { dg-final { scan-assembler-times "punpcklwd" 1} } */ > > -- > > 2.18.2 > > > > > -- > BR, > Hongtao [-- Attachment #2: 0001-x86-Handle-V8BF-in-expand_vec_perm_broadcast_1.patch --] [-- Type: application/octet-stream, Size: 4788 bytes --] gcc/ChangeLog: PR target/106742 * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): Handle V8BF mode. (expand_vec_perm_broadcast_1): Ditto. * config/i386/sse.md (avx512fmaskhalfmode): Add BF vector mode. (vec_set<mode>_0): Add @ to it. (@vec_set<mode>_0): Ditto. (vec_interleave_high<mode><mask_name>): Ditto. (@vec_interleave_high<mode><mask_name>): Ditto. (vec_interleave_low<mode><mask_name>): Ditto. (@vec_interleave_low<mode><mask_name>): Ditto. * config/i386/subst.md (SUBST_V): Add BF vector mode. gcc/testsuite/ChangeLog: * gcc.target/i386/pr106742.c: New test. --- gcc/config/i386/i386-expand.cc | 15 +++++++++------ gcc/config/i386/sse.md | 7 ++++--- gcc/config/i386/subst.md | 1 + gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ 4 files changed, 24 insertions(+), 9 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr106742.c diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 836ebc82d67..d7b49c99dc8 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -15034,11 +15034,12 @@ ix86_expand_vector_init_duplicate (bool mmx_ok, machine_mode mode, dperm.op0 = dperm.op1 = gen_reg_rtx (mode); dperm.one_operand_p = true; - if (mode == V8HFmode) + if (mode == V8HFmode || mode == V8BFmode) { - tmp1 = force_reg (HFmode, val); + tmp1 = force_reg (GET_MODE_INNER (mode), val); tmp2 = gen_reg_rtx (mode); - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); + emit_insn (maybe_gen_vec_set_0 (mode, tmp2, + CONST0_RTX (mode), tmp1)); tmp1 = gen_lowpart (mode, tmp2); } else @@ -21826,21 +21827,23 @@ expand_vec_perm_broadcast_1 (struct expand_vec_perm_d *d) return true; case E_V8HFmode: + case E_V8BFmode: /* This can be implemented via interleave and pshufd. */ if (d->testing_p) return true; + rtx (*maybe_gen) (machine_mode, int, rtx, rtx, rtx); if (elt >= nelt2) { - gen = gen_vec_interleave_highv8hf; + maybe_gen = maybe_gen_vec_interleave_high; elt -= nelt2; } else - gen = gen_vec_interleave_lowv8hf; + maybe_gen = maybe_gen_vec_interleave_low; nelt2 /= 2; dest = gen_reg_rtx (vmode); - emit_insn (gen (dest, op0, op0)); + emit_insn (maybe_gen (vmode, 1, dest, op0, op0)); vmode = V4SImode; op0 = gen_lowpart (vmode, dest); diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 259048481b6..72acf0b3e23 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -984,6 +984,7 @@ (V16SI "QI") (V8SI "QI") (V4SI "QI") (V8DI "QI") (V4DI "QI") (V2DI "QI") (V32HF "HI") (V16HF "QI") (V8HF "QI") + (V32BF "HI") (V16BF "QI") (V8BF "QI") (V16SF "QI") (V8SF "QI") (V4SF "QI") (V8DF "QI") (V4DF "QI") (V2DF "QI")]) @@ -10712,7 +10713,7 @@ ] (symbol_ref "true")))]) -(define_insn "vec_set<mode>_0" +(define_insn "@vec_set<mode>_0" [(set (match_operand:V8_128 0 "register_operand" "=v,v,v,x,x,Yr,*x,x,x,x,v,v") (vec_merge:V8_128 @@ -17895,7 +17896,7 @@ (set_attr "prefix" "maybe_evex") (set_attr "mode" "OI")]) -(define_insn "vec_interleave_high<mode><mask_name>" +(define_insn "@vec_interleave_high<mode><mask_name>" [(set (match_operand:V8_128 0 "register_operand" "=x,Yw") (vec_select:V8_128 (vec_concat:<ssedoublevecmode> @@ -17963,7 +17964,7 @@ (set_attr "prefix" "maybe_evex") (set_attr "mode" "OI")]) -(define_insn "vec_interleave_low<mode><mask_name>" +(define_insn "@vec_interleave_low<mode><mask_name>" [(set (match_operand:V8_128 0 "register_operand" "=x,Yw") (vec_select:V8_128 (vec_concat:<ssedoublevecmode> diff --git a/gcc/config/i386/subst.md b/gcc/config/i386/subst.md index 0b7588237fe..e169282fbbc 100644 --- a/gcc/config/i386/subst.md +++ b/gcc/config/i386/subst.md @@ -25,6 +25,7 @@ V16SI V8SI V4SI V8DI V4DI V2DI V32HF V16HF V8HF + V32BF V16BF V8BF V16SF V8SF V4SF V8DF V4DF V2DF]) diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c b/gcc/testsuite/gcc.target/i386/pr106742.c new file mode 100644 index 00000000000..36ac93c9623 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr106742.c @@ -0,0 +1,10 @@ +/* { dg-do compile } */ +/* { dg-options "-msse2 -mno-sse4 -O1" } */ typedef __bf16 v8bf +__attribute__ ((__vector_size__ (16))); + +v8bf +vec_init_dup_v8bf (__bf16 a1) +{ + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } +/* { dg-final { scan-assembler-times "pinsrw" 1} } */ -- 2.18.2 ^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 2022-09-02 8:08 ` Kong, Lingling @ 2022-09-05 0:59 ` Hongtao Liu 0 siblings, 0 replies; 5+ messages in thread From: Hongtao Liu @ 2022-09-05 0:59 UTC (permalink / raw) To: Kong, Lingling; +Cc: Liu, Hongtao, gcc-patches On Fri, Sep 2, 2022 at 4:08 PM Kong, Lingling <lingling.kong@intel.com> wrote: > > Hi, > > I fixed it in a new patch. And added BF vector mode in SUBST_V and avx512fmaskhalfmode for @vec_interleave_high<mode><mask_name>. > Ok for trunk ? Ok. > > > > Hi, > > > > > > Handle E_V8BFmode in expand_vec_perm_broadcast_1 and > > ix86_expand_vector_init_duplicate. > > > Ok for trunk? > > > > > > gcc/ChangeLog: > > > > > > PR target/106742 > > > * config/i386/i386-expand.cc (ix86_expand_vector_init_duplicate): > > > Handle V8BF mode. > > > (expand_vec_perm_broadcast_1): Ditto. > > > > > > gcc/testsuite/ChangeLog: > > > > > > * gcc.target/i386/pr106742.c: New test. > > > --- > > > gcc/config/i386/i386-expand.cc | 17 ++++++++++++----- > > > gcc/testsuite/gcc.target/i386/pr106742.c | 10 ++++++++++ > > > 2 files changed, 22 insertions(+), 5 deletions(-) create mode 100644 > > > gcc/testsuite/gcc.target/i386/pr106742.c > > > > > > diff --git a/gcc/config/i386/i386-expand.cc > > > b/gcc/config/i386/i386-expand.cc index 4b216308a18..a08222fe1b6 100644 > > > --- a/gcc/config/i386/i386-expand.cc > > > +++ b/gcc/config/i386/i386-expand.cc > > > @@ -15030,11 +15030,15 @@ ix86_expand_vector_init_duplicate (bool > > mmx_ok, machine_mode mode, > > > dperm.op0 = dperm.op1 = gen_reg_rtx (mode); > > > dperm.one_operand_p = true; > > > > > > - if (mode == V8HFmode) > > > + if (mode == V8HFmode || mode == V8BFmode) > > > { > > > - tmp1 = force_reg (HFmode, val); > > > + rtx (*gen_vec_set_0) (rtx, rtx, rtx) = NULL; > > > + tmp1 = mode == V8HFmode ? force_reg (HFmode, val) > > > + : force_reg (BFmode, val); > > tmp1 = force_reg (GET_MODE_INNER (mode), val); > > > tmp2 = gen_reg_rtx (mode); > > > - emit_insn (gen_vec_setv8hf_0 (tmp2, CONST0_RTX (mode), tmp1)); > > > + gen_vec_set_0 = mode == V8HFmode ? gen_vec_setv8hf_0 > > > + : gen_vec_setv8bf_0; > > add @ to vec_set<mode>_0 as (define_insn "@vec_set<mode>_0" and pass > > mode to vec_set_0 as emit_insn (gen_vec_set_0 (mode, tmp2, CONST0_RTX > > (mode), tmp1)); > > > + emit_insn (gen_vec_set_0 (tmp2, CONST0_RTX (mode), > > > + tmp1)); > > > > > tmp1 = gen_lowpart (mode, tmp2); > > > } > > > else > > > @@ -21822,17 +21826,20 @@ expand_vec_perm_broadcast_1 (struct > > expand_vec_perm_d *d) > > > return true; > > > > > > case E_V8HFmode: > > > + case E_V8BFmode: > > > /* This can be implemented via interleave and pshufd. */ > > > if (d->testing_p) > > > return true; > > > > > > if (elt >= nelt2) > > > { > > > - gen = gen_vec_interleave_highv8hf; > > > + gen = vmode == V8HFmode ? gen_vec_interleave_highv8hf > > > + : gen_vec_interleave_highv8bf; > > Similar, add @ to define_insn and pass gen_vec_interleave. > > > elt -= nelt2; > > > } > > > else > > > - gen = gen_vec_interleave_lowv8hf; > > > + gen = vmode == V8HFmode ? gen_vec_interleave_lowv8hf > > > + : gen_vec_interleave_lowv8bf; > > > nelt2 /= 2; > > > > > > dest = gen_reg_rtx (vmode); > > > diff --git a/gcc/testsuite/gcc.target/i386/pr106742.c > > > b/gcc/testsuite/gcc.target/i386/pr106742.c > > > new file mode 100644 > > > index 00000000000..4a53cd49902 > > > --- /dev/null > > > +++ b/gcc/testsuite/gcc.target/i386/pr106742.c > > > @@ -0,0 +1,10 @@ > > > +/* { dg-do compile } */ > > > +/* { dg-options " -msse2 -mno-avx2 -O1" } */ typedef __bf16 v8bf > > > +__attribute__ ((__vector_size__ (16))); > > > + > > > +v8bf > > > +vec_init_dup_v8bf (__bf16 a1) > > > +{ > > > + return __extension__ (v8bf) { a1, a1, a1, a1, a1, a1, a1, a1 }; } > > > +/* { dg-final { scan-assembler-times "punpcklwd" 1} } */ > > > -- > > > 2.18.2 > > > > > > > > > -- > > BR, > > Hongtao -- BR, Hongtao ^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2022-09-05 0:59 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <20220831064846.1305576-1-lingling.kong@intel.com>
2022-08-31 6:52 ` [PATCH] x86: Handle V8BF in expand_vec_perm_broadcast_1 Kong, Lingling
2022-08-31 6:52 ` Kong, Lingling
2022-08-31 9:55 ` Hongtao Liu
2022-09-02 8:08 ` Kong, Lingling
2022-09-05 0:59 ` Hongtao Liu
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).