This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCH] i386: Use scalar operand in SF/DF/SI/DI vec_dup patterns
- From: Uros Bizjak <ubizjak at gmail dot com>
- To: "H. J. Lu" <hjl dot tools at gmail dot com>
- Cc: "gcc-patches at gcc dot gnu dot org" <gcc-patches at gcc dot gnu dot org>
- Date: Mon, 29 Oct 2018 22:02:32 +0100
- Subject: Re: [PATCH] i386: Use scalar operand in SF/DF/SI/DI vec_dup patterns
- References: <20181027055846.1682-1-hjl.tools@gmail.com>
On Sat, Oct 27, 2018 at 8:03 AM H.J. Lu <hjl.tools@gmail.com> wrote:
>
> Use scalar operand in SF/DF/SI/DI vec_dup patterns which enables combiner
> to generate
>
> (set (reg:V8SF 84)
> (vec_duplicate:V8SF (mem/c:SF (symbol_ref:DI ("y")))))
>
> const_vector_duplicate_operand is added for constant vector broadcast.
> We split
>
> (set (reg:V16SF 86)
> (const_vector:V16SF
> [(const_double:SF 2.0e+0 [0x0.8p+2]) repeated x16])
>
> to
>
> (set (reg:V16SF 86)
> (vec_duplicate:V16SF (mem/u/c:SF (symbol_ref/u:DI ("*.LC1")))))
Why not at the expand time? Rewrite vector constant as vec_duplicate
from memory and combine will do the stuff for you. We do have _bcst
instruction patterns.
BTW: We have similar stuff at compress_float_constant.
> before IRA so tha IRA can turn
>
> (set (reg:V16SF 86)
> (vec_duplicate:V16SF (mem/u/c:SF (symbol_ref/u:DI ("*.LC1")))))
> (set (reg:V16SF 90)
> (plus:V16SF (reg/v:V16SF 85 [ x ])
> (reg:V16SF 86)))
>
> into
>
> (set (reg:V16SF 90)
> (plus:V16SF
> (vec_duplicate:V16SF (mem/u/c:SF (symbol_ref/u:DI ("*.LC1"))))
> (reg/v:V16SF 85 [ x ])))
>
> For AVX512 broadcast instructions from integer register operand, we only
> need to broadcast integer to integer vectors.
>
> pic_reg_initialized is added to machine_function to indicate that IRA
> has started since *<avx512>_const_vec_dup<mode> is valid only before
> IRA.
I stopped reading the patch here.
Uros.
> gcc/
>
> PR target/87537
> PR target/87767
> * config/i386/i386-builtin-types.def: Replace
> CODE_FOR_avx2_vec_dupv4sf, CODE_FOR_avx2_vec_dupv8sf and
> CODE_FOR_avx2_vec_dupv4df with CODE_FOR_vec_dupv4sf,
> CODE_FOR_vec_dupv8sf and CODE_FOR_vec_dupv4df, respectively.
> * config/i386/i386.c (ix86_init_pic_reg): Set pic_reg_initialized.
> (expand_vec_perm_1): Replace gen_avx512f_vec_dupv16sf_1,
> gen_avx2_vec_dupv8sf_1 and gen_avx512f_vec_dupv8df_1 with
> gen_avx512f_vec_dupv16sf, gen_vec_dupv8sf and
> gen_avx512f_vec_dupv8df, respectively. Duplicate them from
> scalar operand.
> * config/i386/i386.h (machine_function): Add pic_reg_initialized.
> * config/i386/i386.md (SF to DF splitter): Replace
> gen_avx512f_vec_dupv16sf_1 with gen_avx512f_vec_dupv16sf.
> * config/i386/predicates.md (const_vector_duplicate_operand): New.
> * config/i386/sse.md (VF48_AVX512VL): New.
> (avx2_vec_dup<mode>): Removed.
> (avx2_vec_dupv8sf_1): Likewise.
> (avx512f_vec_dup<mode>_1): Likewise.
> (avx2_vec_dupv4df): Likewise.
> (<avx512>_vec_dup<mode><mask_name>:V48_AVX512VL): Likewise.
> (<avx512>_vec_dup<mode><mask_name>:VF48_AVX512VL): New.
> (*<avx512>_const_vec_dup<mode>): Likewise.
> (<avx512>_vec_dup<mode><mask_name>:VI48_AVX512VL): Likewise.
> (<mask_codefor><avx512>_vec_dup_gpr<mode><mask_name>): Replace
> V48_AVX512VL with VI48_AVX512VL.
> (*avx_vperm_broadcast_<mode>): Replace gen_avx2_vec_dupv8sf with
> gen_vec_dupv8sf.
>
> gcc/testsuite/
>
> PR target/87537
> PR target/87767
> * gcc.target/i386/avx2-vbroadcastss_ps256-1.c: Updated.
> * gcc.target/i386/avx512vl-vbroadcast-3.c: Likewise.
> * gcc.target/i386/avx512-binop-7.h: New file.
> * gcc.target/i386/avx512f-add-sf-zmm-7.c: Likewise.
> * gcc.target/i386/avx512f-add-si-zmm-7.c: Likewise.
> * gcc.target/i386/avx512vl-add-di-xmm-7.c: Likewise.
> * gcc.target/i386/avx512vl-add-sf-xmm-7.c: Likewise.
> * gcc.target/i386/avx512vl-add-sf-ymm-7.c: Likewise.
> * gcc.target/i386/avx512vl-add-si-xmm-7.c: Likewise.
> * gcc.target/i386/avx512vl-add-si-ymm-7.c: Likewise.
> * gcc.target/i386/pr87537-2.c: Likewise.
> * gcc.target/i386/pr87537-3.c: Likewise.
> * gcc.target/i386/pr87537-4.c: Likewise.
> * gcc.target/i386/pr87537-5.c: Likewise.
> * gcc.target/i386/pr87537-6.c: Likewise.
> * gcc.target/i386/pr87537-7.c: Likewise.
> * gcc.target/i386/pr87537-8.c: Likewise.
> * gcc.target/i386/pr87537-9.c: Likewise.
> ---
> gcc/config/i386/i386-builtin.def | 6 +-
> gcc/config/i386/i386.c | 30 +++++-
> gcc/config/i386/i386.h | 3 +
> gcc/config/i386/i386.md | 2 +-
> gcc/config/i386/predicates.md | 13 +++
> gcc/config/i386/sse.md | 98 ++++++++-----------
> .../i386/avx2-vbroadcastss_ps256-1.c | 3 +-
> .../gcc.target/i386/avx512-binop-7.h | 12 +++
> .../gcc.target/i386/avx512f-add-sf-zmm-7.c | 14 +++
> .../gcc.target/i386/avx512f-add-si-zmm-7.c | 12 +++
> .../gcc.target/i386/avx512vl-add-di-xmm-7.c | 13 +++
> .../gcc.target/i386/avx512vl-add-sf-xmm-7.c | 13 +++
> .../gcc.target/i386/avx512vl-add-sf-ymm-7.c | 13 +++
> .../gcc.target/i386/avx512vl-add-si-xmm-7.c | 13 +++
> .../gcc.target/i386/avx512vl-add-si-ymm-7.c | 13 +++
> .../gcc.target/i386/avx512vl-vbroadcast-3.c | 5 +-
> gcc/testsuite/gcc.target/i386/pr87537-2.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-3.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-4.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-5.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-6.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-7.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-8.c | 12 +++
> gcc/testsuite/gcc.target/i386/pr87537-9.c | 12 +++
> 24 files changed, 289 insertions(+), 70 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512-binop-7.h
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-add-sf-zmm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512f-add-si-zmm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-add-di-xmm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-add-sf-xmm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-add-sf-ymm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-add-si-xmm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-add-si-ymm-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-2.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-3.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-4.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-5.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-6.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-7.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-8.c
> create mode 100644 gcc/testsuite/gcc.target/i386/pr87537-9.c
>
> diff --git a/gcc/config/i386/i386-builtin.def b/gcc/config/i386/i386-builtin.def
> index df0f7e975ac..d217add8ee2 100644
> --- a/gcc/config/i386/i386-builtin.def
> +++ b/gcc/config/i386/i386-builtin.def
> @@ -1194,9 +1194,9 @@ BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_interleave_lowv16hi, "__builtin_ia32_
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_interleave_lowv8si, "__builtin_ia32_punpckldq256", IX86_BUILTIN_PUNPCKLDQ256, UNKNOWN, (int) V8SI_FTYPE_V8SI_V8SI)
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_interleave_lowv4di, "__builtin_ia32_punpcklqdq256", IX86_BUILTIN_PUNPCKLQDQ256, UNKNOWN, (int) V4DI_FTYPE_V4DI_V4DI)
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_xorv4di3, "__builtin_ia32_pxor256", IX86_BUILTIN_PXOR256, UNKNOWN, (int) V4DI_FTYPE_V4DI_V4DI)
> -BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_vec_dupv4sf, "__builtin_ia32_vbroadcastss_ps", IX86_BUILTIN_VBROADCASTSS_PS, UNKNOWN, (int) V4SF_FTYPE_V4SF)
> -BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_vec_dupv8sf, "__builtin_ia32_vbroadcastss_ps256", IX86_BUILTIN_VBROADCASTSS_PS256, UNKNOWN, (int) V8SF_FTYPE_V4SF)
> -BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_vec_dupv4df, "__builtin_ia32_vbroadcastsd_pd256", IX86_BUILTIN_VBROADCASTSD_PD256, UNKNOWN, (int) V4DF_FTYPE_V2DF)
> +BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_vec_dupv4sf, "__builtin_ia32_vbroadcastss_ps", IX86_BUILTIN_VBROADCASTSS_PS, UNKNOWN, (int) V4SF_FTYPE_V4SF)
> +BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_vec_dupv8sf, "__builtin_ia32_vbroadcastss_ps256", IX86_BUILTIN_VBROADCASTSS_PS256, UNKNOWN, (int) V8SF_FTYPE_V4SF)
> +BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_vec_dupv4df, "__builtin_ia32_vbroadcastsd_pd256", IX86_BUILTIN_VBROADCASTSD_PD256, UNKNOWN, (int) V4DF_FTYPE_V2DF)
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_vbroadcasti128_v4di, "__builtin_ia32_vbroadcastsi256", IX86_BUILTIN_VBROADCASTSI256, UNKNOWN, (int) V4DI_FTYPE_V2DI)
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_pblenddv4si, "__builtin_ia32_pblendd128", IX86_BUILTIN_PBLENDD128, UNKNOWN, (int) V4SI_FTYPE_V4SI_V4SI_INT)
> BDESC (OPTION_MASK_ISA_AVX2, CODE_FOR_avx2_pblenddv8si, "__builtin_ia32_pblendd256", IX86_BUILTIN_PBLENDD256, UNKNOWN, (int) V8SI_FTYPE_V8SI_V8SI_INT)
> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
> index 963c7fcbb34..293a523fe7e 100644
> --- a/gcc/config/i386/i386.c
> +++ b/gcc/config/i386/i386.c
> @@ -6951,6 +6951,8 @@ ix86_init_pic_reg (void)
> edge entry_edge;
> rtx_insn *seq;
>
> + cfun->machine->pic_reg_initialized = true;
> +
> if (!ix86_use_pseudo_pic_reg ())
> return;
>
> @@ -45963,6 +45965,7 @@ expand_vec_perm_1 (struct expand_vec_perm_d *d)
> {
> /* Use vpbroadcast{b,w,d}. */
> rtx (*gen) (rtx, rtx) = NULL;
> + machine_mode scalar_mode = VOIDmode;
> switch (d->vmode)
> {
> case E_V64QImode:
> @@ -45993,15 +45996,18 @@ expand_vec_perm_1 (struct expand_vec_perm_d *d)
> gen = gen_avx2_pbroadcastv8hi;
> break;
> case E_V16SFmode:
> + scalar_mode = SFmode;
> if (TARGET_AVX512F)
> - gen = gen_avx512f_vec_dupv16sf_1;
> + gen = gen_avx512f_vec_dupv16sf;
> break;
> case E_V8SFmode:
> - gen = gen_avx2_vec_dupv8sf_1;
> + scalar_mode = SFmode;
> + gen = gen_vec_dupv8sf;
> break;
> case E_V8DFmode:
> + scalar_mode = DFmode;
> if (TARGET_AVX512F)
> - gen = gen_avx512f_vec_dupv8df_1;
> + gen = gen_avx512f_vec_dupv8df;
> break;
> case E_V8DImode:
> if (TARGET_AVX512F)
> @@ -46013,7 +46019,23 @@ expand_vec_perm_1 (struct expand_vec_perm_d *d)
> if (gen != NULL)
> {
> if (!d->testing_p)
> - emit_insn (gen (d->target, d->op0));
> + {
> + if (scalar_mode == VOIDmode)
> + emit_insn (gen (d->target, d->op0));
> + else
> + {
> + rtx op = d->op0;
> + unsigned int oppos = 0;
> + if (SUBREG_P (op))
> + {
> + op = SUBREG_REG (op);
> + oppos = SUBREG_BYTE (op);
> + }
> + emit_insn (gen (d->target,
> + gen_rtx_SUBREG (scalar_mode,
> + op, oppos)));
> + }
> + }
> return true;
> }
> }
> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> index b0d2f249db7..8880d25d282 100644
> --- a/gcc/config/i386/i386.h
> +++ b/gcc/config/i386/i386.h
> @@ -2744,6 +2744,9 @@ struct GTY(()) machine_function {
> /* If true, ENDBR is queued at function entrance. */
> BOOL_BITFIELD endbr_queued_at_entrance : 1;
>
> + /* If true, PIC register has been initialized. */
> + BOOL_BITFIELD pic_reg_initialized : 1;
> +
> /* The largest alignment, in bytes, of stack slot actually used. */
> unsigned int max_used_stack_alignment;
>
> diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
> index 7fb2b144f47..4a6fa077db5 100644
> --- a/gcc/config/i386/i386.md
> +++ b/gcc/config/i386/i386.md
> @@ -4399,7 +4399,7 @@
> else
> {
> rtx tmp = lowpart_subreg (V16SFmode, operands[3], V4SFmode);
> - emit_insn (gen_avx512f_vec_dupv16sf_1 (tmp, tmp));
> + emit_insn (gen_avx512f_vec_dupv16sf (tmp, tmp));
> }
> }
> else
> diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
> index bd262d77c6b..1d80de0634f 100644
> --- a/gcc/config/i386/predicates.md
> +++ b/gcc/config/i386/predicates.md
> @@ -1048,6 +1048,19 @@
> (ior (match_operand 0 "nonimmediate_operand")
> (match_code "const_vector")))
>
> +;; Return true when OP is CONST_VECTOR which can be represented by
> +;; VEC_DUPLICATE.
> +(define_predicate "const_vector_duplicate_operand"
> + (and (match_code "const_vector")
> + (match_test "!standard_sse_constant_p (op, mode)"))
> +{
> + int i, nunits = GET_MODE_NUNITS (mode);
> + for (i = 1; i < nunits; i++)
> + if (CONST_VECTOR_ELT (op, i) != CONST_VECTOR_ELT (op, 0))
> + return false;
> + return true;
> +})
> +
> ;; Return true when OP is nonimmediate or standard SSE constant.
> (define_predicate "nonimmediate_or_sse_const_operand"
> (ior (match_operand 0 "nonimmediate_operand")
> diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
> index ee73e1fdf80..27b0ef7f440 100644
> --- a/gcc/config/i386/sse.md
> +++ b/gcc/config/i386/sse.md
> @@ -304,6 +304,10 @@
> (define_mode_iterator VF_512
> [V16SF V8DF])
>
> +(define_mode_iterator VF48_AVX512VL
> + [V16SF (V8SF "TARGET_AVX512VL") (V4SF "TARGET_AVX512VL")
> + V8DF (V4DF "TARGET_AVX512VL") (V2DF "TARGET_AVX512VL")])
> +
> (define_mode_iterator VI48_AVX512VL
> [V16SI (V8SI "TARGET_AVX512VL") (V4SI "TARGET_AVX512VL")
> V8DI (V4DI "TARGET_AVX512VL") (V2DI "TARGET_AVX512VL")])
> @@ -7117,42 +7121,6 @@
> (set_attr "prefix" "orig,maybe_evex")
> (set_attr "mode" "SF")])
>
> -(define_insn "avx2_vec_dup<mode>"
> - [(set (match_operand:VF1_128_256 0 "register_operand" "=v")
> - (vec_duplicate:VF1_128_256
> - (vec_select:SF
> - (match_operand:V4SF 1 "register_operand" "v")
> - (parallel [(const_int 0)]))))]
> - "TARGET_AVX2"
> - "vbroadcastss\t{%1, %0|%0, %1}"
> - [(set_attr "type" "sselog1")
> - (set_attr "prefix" "maybe_evex")
> - (set_attr "mode" "<MODE>")])
> -
> -(define_insn "avx2_vec_dupv8sf_1"
> - [(set (match_operand:V8SF 0 "register_operand" "=v")
> - (vec_duplicate:V8SF
> - (vec_select:SF
> - (match_operand:V8SF 1 "register_operand" "v")
> - (parallel [(const_int 0)]))))]
> - "TARGET_AVX2"
> - "vbroadcastss\t{%x1, %0|%0, %x1}"
> - [(set_attr "type" "sselog1")
> - (set_attr "prefix" "maybe_evex")
> - (set_attr "mode" "V8SF")])
> -
> -(define_insn "avx512f_vec_dup<mode>_1"
> - [(set (match_operand:VF_512 0 "register_operand" "=v")
> - (vec_duplicate:VF_512
> - (vec_select:<ssescalarmode>
> - (match_operand:VF_512 1 "register_operand" "v")
> - (parallel [(const_int 0)]))))]
> - "TARGET_AVX512F"
> - "vbroadcast<bcstscalarsuff>\t{%x1, %0|%0, %x1}"
> - [(set_attr "type" "sselog1")
> - (set_attr "prefix" "evex")
> - (set_attr "mode" "<MODE>")])
> -
> ;; Although insertps takes register source, we prefer
> ;; unpcklps with register source since it is shorter.
> (define_insn "*vec_concatv2sf_sse4_1"
> @@ -18111,18 +18079,6 @@
> (set_attr "prefix" "vex")
> (set_attr "mode" "OI")])
>
> -(define_insn "avx2_vec_dupv4df"
> - [(set (match_operand:V4DF 0 "register_operand" "=v")
> - (vec_duplicate:V4DF
> - (vec_select:DF
> - (match_operand:V2DF 1 "register_operand" "v")
> - (parallel [(const_int 0)]))))]
> - "TARGET_AVX2"
> - "vbroadcastsd\t{%1, %0|%0, %1}"
> - [(set_attr "type" "sselog1")
> - (set_attr "prefix" "maybe_evex")
> - (set_attr "mode" "V4DF")])
> -
> (define_insn "<avx512>_vec_dup<mode>_1"
> [(set (match_operand:VI_AVX512BW 0 "register_operand" "=v,v")
> (vec_duplicate:VI_AVX512BW
> @@ -18138,11 +18094,9 @@
> (set_attr "mode" "<sseinsnmode>")])
>
> (define_insn "<avx512>_vec_dup<mode><mask_name>"
> - [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v")
> - (vec_duplicate:V48_AVX512VL
> - (vec_select:<ssescalarmode>
> - (match_operand:<ssexmmmode> 1 "nonimmediate_operand" "vm")
> - (parallel [(const_int 0)]))))]
> + [(set (match_operand:VF48_AVX512VL 0 "register_operand" "=v")
> + (vec_duplicate:VF48_AVX512VL
> + (match_operand:<ssescalarmode> 1 "nonimmediate_operand" "vm")))]
> "TARGET_AVX512F"
> {
> /* There is no DF broadcast (in AVX-512*) to 128b register.
> @@ -18156,6 +18110,34 @@
> (set_attr "prefix" "evex")
> (set_attr "mode" "<sseinsnmode>")])
>
> +;; NB: This is valid only before IRA. pic_reg_initialized is set at
> +;; the IRA entry.
> +(define_insn_and_split "*<avx512>_const_vec_dup<mode>"
> + [(set (match_operand:V48_AVX512VL 0 "register_operand")
> + (match_operand:V48_AVX512VL 1 "const_vector_duplicate_operand"))]
> + "TARGET_AVX512F && !cfun->machine->pic_reg_initialized"
> + "#"
> + "&& 1"
> + [(set (match_dup 0) (match_dup 1))]
> +{
> + rtx val = CONST_VECTOR_ELT (operands[1], 0);
> + machine_mode scalar_mode = GET_MODE_INNER (<MODE>mode);
> + val = validize_mem (force_const_mem (scalar_mode, val));
> + operands[1] = gen_rtx_VEC_DUPLICATE (<MODE>mode, val);
> +})
> +
> +(define_insn "<avx512>_vec_dup<mode><mask_name>"
> + [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
> + (vec_duplicate:VI48_AVX512VL
> + (vec_select:<ssescalarmode>
> + (match_operand:<ssexmmmode> 1 "nonimmediate_operand" "vm")
> + (parallel [(const_int 0)]))))]
> + "TARGET_AVX512F"
> + "v<sseintprefix>broadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %<iptr>1}"
> + [(set_attr "type" "ssemov")
> + (set_attr "prefix" "evex")
> + (set_attr "mode" "<sseinsnmode>")])
> +
> (define_insn "<avx512>_vec_dup<mode><mask_name>"
> [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
> (vec_duplicate:VI12_AVX512VL
> @@ -18205,8 +18187,8 @@
> (set_attr "mode" "<sseinsnmode>")])
>
> (define_insn "<mask_codefor><avx512>_vec_dup_gpr<mode><mask_name>"
> - [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v,v")
> - (vec_duplicate:V48_AVX512VL
> + [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v,v")
> + (vec_duplicate:VI48_AVX512VL
> (match_operand:<ssescalarmode> 1 "nonimmediate_operand" "vm,r")))]
> "TARGET_AVX512F"
> "v<sseintprefix>broadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
> @@ -18215,8 +18197,7 @@
> (set_attr "mode" "<sseinsnmode>")
> (set (attr "enabled")
> (if_then_else (eq_attr "alternative" "1")
> - (symbol_ref "GET_MODE_CLASS (<ssescalarmode>mode) == MODE_INT
> - && (<ssescalarmode>mode != DImode || TARGET_64BIT)")
> + (symbol_ref "<ssescalarmode>mode != DImode || TARGET_64BIT")
> (const_int 1)))])
>
> (define_insn "vec_dupv4sf"
> @@ -18545,8 +18526,7 @@
> or VSHUFF128. */
> gcc_assert (<MODE>mode == V8SFmode);
> if ((mask & 1) == 0)
> - emit_insn (gen_avx2_vec_dupv8sf (op0,
> - gen_lowpart (V4SFmode, op0)));
> + emit_insn (gen_vec_dupv8sf (op0, gen_lowpart (V4SFmode, op0)));
> else
> emit_insn (gen_avx512vl_shuf_f32x4_1 (op0, op0, op0,
> GEN_INT (4), GEN_INT (5),
> diff --git a/gcc/testsuite/gcc.target/i386/avx2-vbroadcastss_ps256-1.c b/gcc/testsuite/gcc.target/i386/avx2-vbroadcastss_ps256-1.c
> index dfac3916b08..3ff7497aa21 100644
> --- a/gcc/testsuite/gcc.target/i386/avx2-vbroadcastss_ps256-1.c
> +++ b/gcc/testsuite/gcc.target/i386/avx2-vbroadcastss_ps256-1.c
> @@ -1,6 +1,7 @@
> /* { dg-do compile } */
> /* { dg-options "-mavx2 -O2" } */
> -/* { dg-final { scan-assembler "vbroadcastss\[ \\t\]+\[^\n\]*%xmm\[0-9\]" } } */
> +/* { dg-final { scan-assembler "vbroadcastss\[ \\t\]+\[^\n\]*%ymm\[0-9\]" } } */
> +/* { dg-final { scan-assembler-not "vmovaps\[\t \]*\[^,\]*,%xmm\[0-9\]" } } */
>
> #include <immintrin.h>
>
> diff --git a/gcc/testsuite/gcc.target/i386/avx512-binop-7.h b/gcc/testsuite/gcc.target/i386/avx512-binop-7.h
> new file mode 100644
> index 00000000000..513901847a9
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512-binop-7.h
> @@ -0,0 +1,12 @@
> +#include <immintrin.h>
> +
> +#define PASTER2(x,y) x##y
> +#define PASTER3(x,y,z) _mm##x##_##y##_##z
> +#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
> +#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
> +
> +type
> +foo (type x)
> +{
> + return OP (vec, op, op_suffix) (DUP (vec, dup_suffix, 2.1f), x);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/avx512f-add-sf-zmm-7.c b/gcc/testsuite/gcc.target/i386/avx512f-add-sf-zmm-7.c
> new file mode 100644
> index 00000000000..de23c73e71c
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512f-add-sf-zmm-7.c
> @@ -0,0 +1,14 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2" } */
> +/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
> +/* { dg-final { scan-assembler-times "long\[ \\t\]+1074161254" 1 } } */
> +/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
> +
> +#define type __m512
> +#define vec 512
> +#define op add
> +#define op_suffix ps
> +#define dup_suffix ps
> +#define SCALAR float
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512f-add-si-zmm-7.c b/gcc/testsuite/gcc.target/i386/avx512f-add-si-zmm-7.c
> new file mode 100644
> index 00000000000..9e5f800118d
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512f-add-si-zmm-7.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2" } */
> +/* { dg-final { scan-assembler-times "vpaddd\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
> +
> +#define type __m512i
> +#define vec 512
> +#define op add
> +#define op_suffix epi32
> +#define dup_suffix epi32
> +#define SCALAR int
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-add-di-xmm-7.c b/gcc/testsuite/gcc.target/i386/avx512vl-add-di-xmm-7.c
> new file mode 100644
> index 00000000000..7d921aded31
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-add-di-xmm-7.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2" } */
> +/* { dg-final { scan-assembler-times "vpaddq\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
> +/* { dg-final { scan-assembler-times "(?:long|quad)\[ \\t\]+2" 1 } } */
> +
> +#define type __m128i
> +#define vec
> +#define op add
> +#define op_suffix epi64
> +#define dup_suffix epi64x
> +#define SCALAR int
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-xmm-7.c b/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-xmm-7.c
> new file mode 100644
> index 00000000000..2fc1d5c4824
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-xmm-7.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2" } */
> +/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
> +/* { dg-final { scan-assembler-times "long\[ \\t\]+1074161254" 1 } } */
> +
> +#define type __m128
> +#define vec
> +#define op add
> +#define op_suffix ps
> +#define dup_suffix ps
> +#define SCALAR float
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-ymm-7.c b/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-ymm-7.c
> new file mode 100644
> index 00000000000..436aae757ca
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-add-sf-ymm-7.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2" } */
> +/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %ymm\[0-9\]+, %ymm0" 1 } } */
> +/* { dg-final { scan-assembler-times "long\[ \\t\]+1074161254" 1 } } */
> +
> +#define type __m256
> +#define vec 256
> +#define op add
> +#define op_suffix ps
> +#define dup_suffix ps
> +#define SCALAR float
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-add-si-xmm-7.c b/gcc/testsuite/gcc.target/i386/avx512vl-add-si-xmm-7.c
> new file mode 100644
> index 00000000000..0bd7a0c5e96
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-add-si-xmm-7.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2" } */
> +/* { dg-final { scan-assembler-times "vpaddd\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
> +/* { dg-final { scan-assembler-times "(?:long|quad)\[ \\t\]+2" 1 } } */
> +
> +#define type __m128i
> +#define vec
> +#define op add
> +#define op_suffix epi32
> +#define dup_suffix epi32
> +#define SCALAR int
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-add-si-ymm-7.c b/gcc/testsuite/gcc.target/i386/avx512vl-add-si-ymm-7.c
> new file mode 100644
> index 00000000000..fdde09fca1e
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-add-si-ymm-7.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2" } */
> +/* { dg-final { scan-assembler-times "vpaddd\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %ymm\[0-9\]+, %ymm0" 1 } } */
> +/* { dg-final { scan-assembler-times "(?:long|quad)\[ \\t\]+2" 1 } } */
> +
> +#define type __m256i
> +#define vec 256
> +#define op add
> +#define op_suffix epi32
> +#define dup_suffix epi32
> +#define SCALAR int
> +
> +#include "avx512-binop-7.h"
> diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c b/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c
> index 7233398cd64..1c62364dac4 100644
> --- a/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c
> +++ b/gcc/testsuite/gcc.target/i386/avx512vl-vbroadcast-3.c
> @@ -151,8 +151,8 @@ f16 (V2 *x)
> }
>
> /* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%\[re\]di\[^\n\r]*%xmm16" 4 } } */
> -/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%xmm16\[^\n\r]*%ymm16" 3 } } */
> -/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%\[re\]di\[^\n\r]*%ymm16" 3 } } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%xmm16\[^\n\r]*%ymm16" 1 } } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\r]*%\[re\]di\[^\n\r]*%ymm16" 4 } } */
> /* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$0\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
> /* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$85\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
> /* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$170\[^\n\r]*%xmm16\[^\n\r]*%xmm16" 1 } } */
> @@ -160,3 +160,4 @@ f16 (V2 *x)
> /* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$0\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 1 } } */
> /* { dg-final { scan-assembler-times "vpermilps\[^\n\r]*\\\$85\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 2 } } */
> /* { dg-final { scan-assembler-times "vshuff32x4\[^\n\r]*\\\$3\[^\n\r]*%ymm16\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 2 } } */
> +/* { dg-final { scan-assembler-times "vshuff32x4\[^\n\r]*\\\$0\[^\n\r]*%ymm16\[^\n\r]*%ymm16\[^\n\r]*%ymm16" 1 } } */
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-2.c b/gcc/testsuite/gcc.target/i386/pr87537-2.c
> new file mode 100644
> index 00000000000..19ded7e64b2
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-2.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m512
> +foo (float *x)
> +{
> + return _mm512_broadcastss_ps (_mm_load_ss(x));
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-3.c b/gcc/testsuite/gcc.target/i386/pr87537-3.c
> new file mode 100644
> index 00000000000..ee7781a69e4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-3.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m512
> +foo (void)
> +{
> + return _mm512_set1_ps (2.0f);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-4.c b/gcc/testsuite/gcc.target/i386/pr87537-4.c
> new file mode 100644
> index 00000000000..c5bfef1366e
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-4.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastsd\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovsd" } } */
> +
> +#include <immintrin.h>
> +
> +__m512d
> +foo (double *x)
> +{
> + return _mm512_broadcastsd_pd (_mm_load_sd(x));
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-5.c b/gcc/testsuite/gcc.target/i386/pr87537-5.c
> new file mode 100644
> index 00000000000..4f806f4fbf3
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-5.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512f -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastsd\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovsd" } } */
> +
> +#include <immintrin.h>
> +
> +__m512d
> +foo (void)
> +{
> + return _mm512_set1_pd (2.0f);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-6.c b/gcc/testsuite/gcc.target/i386/pr87537-6.c
> new file mode 100644
> index 00000000000..b53588b907b
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-6.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m256
> +foo (float *x)
> +{
> + return _mm256_broadcastss_ps (_mm_load_ss(x));
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-7.c b/gcc/testsuite/gcc.target/i386/pr87537-7.c
> new file mode 100644
> index 00000000000..d07a1e3de55
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-7.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m256
> +foo (void)
> +{
> + return _mm256_set1_ps (2.0f);
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-8.c b/gcc/testsuite/gcc.target/i386/pr87537-8.c
> new file mode 100644
> index 00000000000..dbf4ee3551d
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-8.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m128
> +foo (float *x)
> +{
> + return _mm_broadcastss_ps (_mm_load_ss(x));
> +}
> diff --git a/gcc/testsuite/gcc.target/i386/pr87537-9.c b/gcc/testsuite/gcc.target/i386/pr87537-9.c
> new file mode 100644
> index 00000000000..8e09382d876
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/pr87537-9.c
> @@ -0,0 +1,12 @@
> +/* { dg-do compile } */
> +/* { dg-options "-mavx512vl -O2 -mtune=skylake" } */
> +/* { dg-final { scan-assembler-times "vbroadcastss\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]" 1 } } */
> +/* { dg-final { scan-assembler-not "vmovss" } } */
> +
> +#include <immintrin.h>
> +
> +__m128
> +foo (void)
> +{
> + return _mm_set1_ps (2.0f);
> +}
> --
> 2.17.2
>