diff mbox series

i386, v2: Fix aes/vaes patterns [PR114576]

Message ID ZhUHys0TX5TIGRgM@tucnak
State New
Headers show
Series i386, v2: Fix aes/vaes patterns [PR114576] | expand

Commit Message

Jakub Jelinek April 9, 2024, 9:18 a.m. UTC
On Tue, Apr 09, 2024 at 11:23:40AM +0800, Hongtao Liu wrote:
> I think we can merge alternative 2 with 3 to
> *  return TARGET_AES ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}"\" :
> \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
> Then it can handle vaes_avx512vl + -mno-aes case.

Ok, done in the patch below.

> > @@ -30246,44 +30250,60 @@ (define_insn "vpdpwssds_<mode>_maskz_1"
> >     [(set_attr ("prefix") ("evex"))])
> >
> >  (define_insn "vaesdec_<mode>"
> > -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> > +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
> >         (unspec:VI1_AVX512VL_F
> > -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> > -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> > +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> > +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
> >           UNSPEC_VAESDEC))]
> >    "TARGET_VAES"
> > -  "vaesdec\t{%2, %1, %0|%0, %1, %2}"
> > -)
> > +{
> > +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> > +    return "%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}";
> Similar, but something like
> *  return TARGET_AES || <MODE>mode != V16QImode ? \"vaesenc\t{%2, %1,
> %0|%0, %1, %2}"\" : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";

For a single alternative, it would need to be
{
  return x86_evex_reg_mentioned_p (operands, 3)
	 ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}\"
	 : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
}
(* return would just mean uselessly too long line).
Is that what you want instead?  I thought the 2 separate alternatives
where only the latter covers those cases is more readable...

The following patch just changes the aes* patterns, not the vaes* ones.

2024-04-09  Jakub Jelinek  <jakub@redhat.com>

	PR target/114576
	* config/i386/i386.md (isa): Remove aes, add vaes_avx512vl.
	(enabled): Remove aes isa check, add vaes_avx512vl.
	* config/i386/sse.md (aesenc, aesenclast, aesdec, aesdeclast): Use
	jm instead of m for second alternative and emit {evex} prefix
	for it if !TARGET_AES.  Use noavx,avx,vaes_avx512vl isa attribute.
	(vaesdec_<mode>, vaesdeclast_<mode>, vaesenc_<mode>,
	vaesenclast_<mode>): Add second alternative with x instead of v
	and jm instead of m.

	* gcc.target/i386/aes-pr114576.c: New test.



	Jakub

Comments

Hongtao Liu April 9, 2024, 10:32 a.m. UTC | #1
On Tue, Apr 9, 2024 at 5:18 PM Jakub Jelinek <jakub@redhat.com> wrote:
>
> On Tue, Apr 09, 2024 at 11:23:40AM +0800, Hongtao Liu wrote:
> > I think we can merge alternative 2 with 3 to
> > *  return TARGET_AES ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}"\" :
> > \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
> > Then it can handle vaes_avx512vl + -mno-aes case.
>
> Ok, done in the patch below.
>
> > > @@ -30246,44 +30250,60 @@ (define_insn "vpdpwssds_<mode>_maskz_1"
> > >     [(set_attr ("prefix") ("evex"))])
> > >
> > >  (define_insn "vaesdec_<mode>"
> > > -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> > > +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
> > >         (unspec:VI1_AVX512VL_F
> > > -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> > > -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> > > +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> > > +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
> > >           UNSPEC_VAESDEC))]
> > >    "TARGET_VAES"
> > > -  "vaesdec\t{%2, %1, %0|%0, %1, %2}"
> > > -)
> > > +{
> > > +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> > > +    return "%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}";
> > Similar, but something like
> > *  return TARGET_AES || <MODE>mode != V16QImode ? \"vaesenc\t{%2, %1,
> > %0|%0, %1, %2}"\" : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
>
> For a single alternative, it would need to be
> {
>   return x86_evex_reg_mentioned_p (operands, 3)
>          ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}\"
>          : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
> }
> (* return would just mean uselessly too long line).
> Is that what you want instead?  I thought the 2 separate alternatives
> where only the latter covers those cases is more readable...
>
> The following patch just changes the aes* patterns, not the vaes* ones.
Patch LGTM.
>
> 2024-04-09  Jakub Jelinek  <jakub@redhat.com>
>
>         PR target/114576
>         * config/i386/i386.md (isa): Remove aes, add vaes_avx512vl.
>         (enabled): Remove aes isa check, add vaes_avx512vl.
>         * config/i386/sse.md (aesenc, aesenclast, aesdec, aesdeclast): Use
>         jm instead of m for second alternative and emit {evex} prefix
>         for it if !TARGET_AES.  Use noavx,avx,vaes_avx512vl isa attribute.
>         (vaesdec_<mode>, vaesdeclast_<mode>, vaesenc_<mode>,
>         vaesenclast_<mode>): Add second alternative with x instead of v
>         and jm instead of m.
>
>         * gcc.target/i386/aes-pr114576.c: New test.
>
> --- gcc/config/i386/i386.md.jj  2024-04-09 08:12:29.259451422 +0200
> +++ gcc/config/i386/i386.md     2024-04-09 10:53:24.965516804 +0200
> @@ -568,13 +568,14 @@ (define_attr "unit" "integer,i387,sse,mm
>
>  ;; Used to control the "enabled" attribute on a per-instruction basis.
>  (define_attr "isa" "base,x64,nox64,x64_sse2,x64_sse4,x64_sse4_noavx,
> -                   x64_avx,x64_avx512bw,x64_avx512dq,aes,apx_ndd,
> +                   x64_avx,x64_avx512bw,x64_avx512dq,apx_ndd,
>                     sse_noavx,sse2,sse2_noavx,sse3,sse3_noavx,sse4,sse4_noavx,
>                     avx,noavx,avx2,noavx2,bmi,bmi2,fma4,fma,avx512f,avx512f_512,
>                     noavx512f,avx512bw,avx512bw_512,noavx512bw,avx512dq,
>                     noavx512dq,fma_or_avx512vl,avx512vl,noavx512vl,avxvnni,
>                     avx512vnnivl,avx512fp16,avxifma,avx512ifmavl,avxneconvert,
> -                   avx512bf16vl,vpclmulqdqvl,avx_noavx512f,avx_noavx512vl"
> +                   avx512bf16vl,vpclmulqdqvl,avx_noavx512f,avx_noavx512vl,
> +                   vaes_avx512vl"
>    (const_string "base"))
>
>  ;; The (bounding maximum) length of an instruction immediate.
> @@ -915,7 +916,6 @@ (define_attr "enabled" ""
>            (symbol_ref "TARGET_64BIT && TARGET_AVX512BW")
>          (eq_attr "isa" "x64_avx512dq")
>            (symbol_ref "TARGET_64BIT && TARGET_AVX512DQ")
> -        (eq_attr "isa" "aes") (symbol_ref "TARGET_AES")
>          (eq_attr "isa" "sse_noavx")
>            (symbol_ref "TARGET_SSE && !TARGET_AVX")
>          (eq_attr "isa" "sse2") (symbol_ref "TARGET_SSE2")
> @@ -968,6 +968,8 @@ (define_attr "enabled" ""
>            (symbol_ref "TARGET_VPCLMULQDQ && TARGET_AVX512VL")
>          (eq_attr "isa" "apx_ndd")
>            (symbol_ref "TARGET_APX_NDD")
> +        (eq_attr "isa" "vaes_avx512vl")
> +          (symbol_ref "TARGET_VAES && TARGET_AVX512VL")
>
>          (eq_attr "mmx_isa" "native")
>            (symbol_ref "!TARGET_MMX_WITH_SSE")
> --- gcc/config/i386/sse.md.jj   2024-04-04 10:43:32.107789627 +0200
> +++ gcc/config/i386/sse.md      2024-04-09 10:53:06.138772957 +0200
> @@ -26279,72 +26279,72 @@ (define_insn "xop_vpermil2<mode>3"
>  (define_insn "aesenc"
>    [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
>         (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
> -                      (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
> +                      (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
>                       UNSPEC_AESENC))]
>    "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
>    "@
>     aesenc\t{%2, %0|%0, %2}
> -   vaesenc\t{%2, %1, %0|%0, %1, %2}
> +   * return TARGET_AES ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
>     vaesenc\t{%2, %1, %0|%0, %1, %2}"
> -  [(set_attr "isa" "noavx,aes,avx512vl")
> +  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
>     (set_attr "type" "sselog1")
>     (set_attr "addr" "gpr16,*,*")
>     (set_attr "prefix_extra" "1")
> -   (set_attr "prefix" "orig,vex,evex")
> +   (set_attr "prefix" "orig,maybe_evex,evex")
>     (set_attr "btver2_decode" "double,double,double")
>     (set_attr "mode" "TI")])
>
>  (define_insn "aesenclast"
>    [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
>         (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
> -                      (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
> +                      (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
>                       UNSPEC_AESENCLAST))]
>    "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
>    "@
>     aesenclast\t{%2, %0|%0, %2}
> -   vaesenclast\t{%2, %1, %0|%0, %1, %2}
> +   * return TARGET_AES ? \"vaesenclast\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesenclast\t{%2, %1, %0|%0, %1, %2}\";
>     vaesenclast\t{%2, %1, %0|%0, %1, %2}"
> -  [(set_attr "isa" "noavx,aes,avx512vl")
> +  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
>     (set_attr "type" "sselog1")
>     (set_attr "addr" "gpr16,*,*")
>     (set_attr "prefix_extra" "1")
> -   (set_attr "prefix" "orig,vex,evex")
> -   (set_attr "btver2_decode" "double,double,double")
> +   (set_attr "prefix" "orig,maybe_evex,evex")
> +   (set_attr "btver2_decode" "double,double,double")
>     (set_attr "mode" "TI")])
>
>  (define_insn "aesdec"
>    [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
>         (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
> -                      (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
> +                      (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
>                       UNSPEC_AESDEC))]
>    "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
>    "@
>     aesdec\t{%2, %0|%0, %2}
> -   vaesdec\t{%2, %1, %0|%0, %1, %2}
> +   * return TARGET_AES ? \"vaesdec\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}\";
>     vaesdec\t{%2, %1, %0|%0, %1, %2}"
> -  [(set_attr "isa" "noavx,aes,avx512vl")
> +  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
>     (set_attr "type" "sselog1")
>     (set_attr "addr" "gpr16,*,*")
>     (set_attr "prefix_extra" "1")
> -   (set_attr "prefix" "orig,vex,evex")
> +   (set_attr "prefix" "orig,maybe_evex,evex")
>     (set_attr "btver2_decode" "double,double,double")
>     (set_attr "mode" "TI")])
>
>  (define_insn "aesdeclast"
>    [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
>         (unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
> -                      (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
> +                      (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
>                       UNSPEC_AESDECLAST))]
>    "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
>    "@
>     aesdeclast\t{%2, %0|%0, %2}
> -   vaesdeclast\t{%2, %1, %0|%0, %1, %2}
> +   * return TARGET_AES ? \"vaesdeclast\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesdeclast\t{%2, %1, %0|%0, %1, %2}\";
>     vaesdeclast\t{%2, %1, %0|%0, %1, %2}"
> -  [(set_attr "isa" "noavx,aes,avx512vl")
> +  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
>     (set_attr "addr" "gpr16,*,*")
>     (set_attr "type" "sselog1")
>     (set_attr "prefix_extra" "1")
> -   (set_attr "prefix" "orig,vex,evex")
> +   (set_attr "prefix" "orig,maybe_evex,evex")
>     (set_attr "btver2_decode" "double,double,double")
>     (set_attr "mode" "TI")])
>
> @@ -30246,44 +30246,60 @@ (define_insn "vpdpwssds_<mode>_maskz_1"
>     [(set_attr ("prefix") ("evex"))])
>
>  (define_insn "vaesdec_<mode>"
> -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
>         (unspec:VI1_AVX512VL_F
> -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
>           UNSPEC_VAESDEC))]
>    "TARGET_VAES"
> -  "vaesdec\t{%2, %1, %0|%0, %1, %2}"
> -)
> +{
> +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> +    return "%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}";
> +  else
> +    return "vaesdec\t{%2, %1, %0|%0, %1, %2}";
> +})
>
>  (define_insn "vaesdeclast_<mode>"
> -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
>         (unspec:VI1_AVX512VL_F
> -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
>           UNSPEC_VAESDECLAST))]
>    "TARGET_VAES"
> -  "vaesdeclast\t{%2, %1, %0|%0, %1, %2}"
> -)
> +{
> +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> +    return "%{evex%} vaesdeclast\t{%2, %1, %0|%0, %1, %2}";
> +  else
> +    return "vaesdeclast\t{%2, %1, %0|%0, %1, %2}";
> +})
>
>  (define_insn "vaesenc_<mode>"
> -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
>         (unspec:VI1_AVX512VL_F
> -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
>           UNSPEC_VAESENC))]
>    "TARGET_VAES"
> -  "vaesenc\t{%2, %1, %0|%0, %1, %2}"
> -)
> +{
> +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> +    return "%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}";
> +  else
> +    return "vaesenc\t{%2, %1, %0|%0, %1, %2}";
> +})
>
>  (define_insn "vaesenclast_<mode>"
> -  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
> +  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
>         (unspec:VI1_AVX512VL_F
> -         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
> -          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
> +         [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
> +          (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
>           UNSPEC_VAESENCLAST))]
>    "TARGET_VAES"
> -  "vaesenclast\t{%2, %1, %0|%0, %1, %2}"
> -)
> +{
> +  if (which_alternative == 0 && <MODE>mode == V16QImode)
> +    return "%{evex%} vaesenclast\t{%2, %1, %0|%0, %1, %2}";
> +  else
> +    return "vaesenclast\t{%2, %1, %0|%0, %1, %2}";
> +})
>
>  (define_insn "vpclmulqdq_<mode>"
>    [(set (match_operand:VI8_FVL 0 "register_operand" "=v")
> --- gcc/testsuite/gcc.target/i386/aes-pr114576.c.jj     2024-04-09 10:27:32.782646751 +0200
> +++ gcc/testsuite/gcc.target/i386/aes-pr114576.c        2024-04-09 10:27:32.782646751 +0200
> @@ -0,0 +1,63 @@
> +/* PR target/114576 */
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -maes -mno-avx" } */
> +/* { dg-final { scan-assembler-times "\taesenc\t" 2 } } */
> +/* { dg-final { scan-assembler-times "\taesdec\t" 2 } } */
> +/* { dg-final { scan-assembler-times "\taesenclast\t" 2 } } */
> +/* { dg-final { scan-assembler-times "\taesdeclast\t" 2 } } */
> +/* { dg-final { scan-assembler-not "\tvaesenc" } } */
> +/* { dg-final { scan-assembler-not "\tvaesdec" } } */
> +
> +#include <immintrin.h>
> +
> +__m128i
> +f1 (__m128i x, __m128i y)
> +{
> +  return _mm_aesenc_si128 (x, y);
> +}
> +
> +__m128i
> +f2 (__m128i x, __m128i y)
> +{
> +  __m128i z = _mm_aesenc_si128 (x, y);
> +  return z + x + y;
> +}
> +
> +__m128i
> +f3 (__m128i x, __m128i y)
> +{
> +  return _mm_aesdec_si128 (x, y);
> +}
> +
> +__m128i
> +f4 (__m128i x, __m128i y)
> +{
> +  __m128i z = _mm_aesdec_si128 (x, y);
> +  return z + x + y;
> +}
> +
> +__m128i
> +f5 (__m128i x, __m128i y)
> +{
> +  return _mm_aesenclast_si128 (x, y);
> +}
> +
> +__m128i
> +f6 (__m128i x, __m128i y)
> +{
> +  __m128i z = _mm_aesenclast_si128 (x, y);
> +  return z + x + y;
> +}
> +
> +__m128i
> +f7 (__m128i x, __m128i y)
> +{
> +  return _mm_aesdeclast_si128 (x, y);
> +}
> +
> +__m128i
> +f8 (__m128i x, __m128i y)
> +{
> +  __m128i z = _mm_aesdeclast_si128 (x, y);
> +  return z + x + y;
> +}
>
>
>         Jakub
>
diff mbox series

Patch

--- gcc/config/i386/i386.md.jj	2024-04-09 08:12:29.259451422 +0200
+++ gcc/config/i386/i386.md	2024-04-09 10:53:24.965516804 +0200
@@ -568,13 +568,14 @@  (define_attr "unit" "integer,i387,sse,mm
 
 ;; Used to control the "enabled" attribute on a per-instruction basis.
 (define_attr "isa" "base,x64,nox64,x64_sse2,x64_sse4,x64_sse4_noavx,
-		    x64_avx,x64_avx512bw,x64_avx512dq,aes,apx_ndd,
+		    x64_avx,x64_avx512bw,x64_avx512dq,apx_ndd,
 		    sse_noavx,sse2,sse2_noavx,sse3,sse3_noavx,sse4,sse4_noavx,
 		    avx,noavx,avx2,noavx2,bmi,bmi2,fma4,fma,avx512f,avx512f_512,
 		    noavx512f,avx512bw,avx512bw_512,noavx512bw,avx512dq,
 		    noavx512dq,fma_or_avx512vl,avx512vl,noavx512vl,avxvnni,
 		    avx512vnnivl,avx512fp16,avxifma,avx512ifmavl,avxneconvert,
-		    avx512bf16vl,vpclmulqdqvl,avx_noavx512f,avx_noavx512vl"
+		    avx512bf16vl,vpclmulqdqvl,avx_noavx512f,avx_noavx512vl,
+		    vaes_avx512vl"
   (const_string "base"))
 
 ;; The (bounding maximum) length of an instruction immediate.
@@ -915,7 +916,6 @@  (define_attr "enabled" ""
 	   (symbol_ref "TARGET_64BIT && TARGET_AVX512BW")
 	 (eq_attr "isa" "x64_avx512dq")
 	   (symbol_ref "TARGET_64BIT && TARGET_AVX512DQ")
-	 (eq_attr "isa" "aes") (symbol_ref "TARGET_AES")
 	 (eq_attr "isa" "sse_noavx")
 	   (symbol_ref "TARGET_SSE && !TARGET_AVX")
 	 (eq_attr "isa" "sse2") (symbol_ref "TARGET_SSE2")
@@ -968,6 +968,8 @@  (define_attr "enabled" ""
 	   (symbol_ref "TARGET_VPCLMULQDQ && TARGET_AVX512VL")
 	 (eq_attr "isa" "apx_ndd")
 	   (symbol_ref "TARGET_APX_NDD")
+	 (eq_attr "isa" "vaes_avx512vl")
+	   (symbol_ref "TARGET_VAES && TARGET_AVX512VL")
 
 	 (eq_attr "mmx_isa" "native")
 	   (symbol_ref "!TARGET_MMX_WITH_SSE")
--- gcc/config/i386/sse.md.jj	2024-04-04 10:43:32.107789627 +0200
+++ gcc/config/i386/sse.md	2024-04-09 10:53:06.138772957 +0200
@@ -26279,72 +26279,72 @@  (define_insn "xop_vpermil2<mode>3"
 (define_insn "aesenc"
   [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
 	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
-		       (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
+		       (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
 		      UNSPEC_AESENC))]
   "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
   "@
    aesenc\t{%2, %0|%0, %2}
-   vaesenc\t{%2, %1, %0|%0, %1, %2}
+   * return TARGET_AES ? \"vaesenc\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}\";
    vaesenc\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "isa" "noavx,aes,avx512vl")
+  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
    (set_attr "type" "sselog1")
    (set_attr "addr" "gpr16,*,*")
    (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "orig,vex,evex")
+   (set_attr "prefix" "orig,maybe_evex,evex")
    (set_attr "btver2_decode" "double,double,double")
    (set_attr "mode" "TI")])
 
 (define_insn "aesenclast"
   [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
 	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
-		       (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
+		       (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
 		      UNSPEC_AESENCLAST))]
   "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
   "@
    aesenclast\t{%2, %0|%0, %2}
-   vaesenclast\t{%2, %1, %0|%0, %1, %2}
+   * return TARGET_AES ? \"vaesenclast\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesenclast\t{%2, %1, %0|%0, %1, %2}\";
    vaesenclast\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "isa" "noavx,aes,avx512vl")
+  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
    (set_attr "type" "sselog1")
    (set_attr "addr" "gpr16,*,*")
    (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "orig,vex,evex")
-   (set_attr "btver2_decode" "double,double,double") 
+   (set_attr "prefix" "orig,maybe_evex,evex")
+   (set_attr "btver2_decode" "double,double,double")
    (set_attr "mode" "TI")])
 
 (define_insn "aesdec"
   [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
 	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
-		       (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
+		       (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
 		      UNSPEC_AESDEC))]
   "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
   "@
    aesdec\t{%2, %0|%0, %2}
-   vaesdec\t{%2, %1, %0|%0, %1, %2}
+   * return TARGET_AES ? \"vaesdec\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}\";
    vaesdec\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "isa" "noavx,aes,avx512vl")
+  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
    (set_attr "type" "sselog1")
    (set_attr "addr" "gpr16,*,*")
    (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "orig,vex,evex")
+   (set_attr "prefix" "orig,maybe_evex,evex")
    (set_attr "btver2_decode" "double,double,double") 
    (set_attr "mode" "TI")])
 
 (define_insn "aesdeclast"
   [(set (match_operand:V2DI 0 "register_operand" "=x,x,v")
 	(unspec:V2DI [(match_operand:V2DI 1 "register_operand" "0,x,v")
-		       (match_operand:V2DI 2 "vector_operand" "xja,xm,vm")]
+		       (match_operand:V2DI 2 "vector_operand" "xja,xjm,vm")]
 		      UNSPEC_AESDECLAST))]
   "TARGET_AES || (TARGET_VAES && TARGET_AVX512VL)"
   "@
    aesdeclast\t{%2, %0|%0, %2}
-   vaesdeclast\t{%2, %1, %0|%0, %1, %2}
+   * return TARGET_AES ? \"vaesdeclast\t{%2, %1, %0|%0, %1, %2}\" : \"%{evex%} vaesdeclast\t{%2, %1, %0|%0, %1, %2}\";
    vaesdeclast\t{%2, %1, %0|%0, %1, %2}"
-  [(set_attr "isa" "noavx,aes,avx512vl")
+  [(set_attr "isa" "noavx,avx,vaes_avx512vl")
    (set_attr "addr" "gpr16,*,*")
    (set_attr "type" "sselog1")
    (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "orig,vex,evex")
+   (set_attr "prefix" "orig,maybe_evex,evex")
    (set_attr "btver2_decode" "double,double,double")
    (set_attr "mode" "TI")])
 
@@ -30246,44 +30246,60 @@  (define_insn "vpdpwssds_<mode>_maskz_1"
    [(set_attr ("prefix") ("evex"))])
 
 (define_insn "vaesdec_<mode>"
-  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
+  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
 	(unspec:VI1_AVX512VL_F
-	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
-	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
+	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
+	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
 	  UNSPEC_VAESDEC))]
   "TARGET_VAES"
-  "vaesdec\t{%2, %1, %0|%0, %1, %2}"
-)
+{
+  if (which_alternative == 0 && <MODE>mode == V16QImode)
+    return "%{evex%} vaesdec\t{%2, %1, %0|%0, %1, %2}";
+  else
+    return "vaesdec\t{%2, %1, %0|%0, %1, %2}";
+})
 
 (define_insn "vaesdeclast_<mode>"
-  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
+  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
 	(unspec:VI1_AVX512VL_F
-	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
-	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
+	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
+	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
 	  UNSPEC_VAESDECLAST))]
   "TARGET_VAES"
-  "vaesdeclast\t{%2, %1, %0|%0, %1, %2}"
-)
+{
+  if (which_alternative == 0 && <MODE>mode == V16QImode)
+    return "%{evex%} vaesdeclast\t{%2, %1, %0|%0, %1, %2}";
+  else
+    return "vaesdeclast\t{%2, %1, %0|%0, %1, %2}";
+})
 
 (define_insn "vaesenc_<mode>"
-  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
+  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
 	(unspec:VI1_AVX512VL_F
-	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
-	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
+	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
+	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
 	  UNSPEC_VAESENC))]
   "TARGET_VAES"
-  "vaesenc\t{%2, %1, %0|%0, %1, %2}"
-)
+{
+  if (which_alternative == 0 && <MODE>mode == V16QImode)
+    return "%{evex%} vaesenc\t{%2, %1, %0|%0, %1, %2}";
+  else
+    return "vaesenc\t{%2, %1, %0|%0, %1, %2}";
+})
 
 (define_insn "vaesenclast_<mode>"
-  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=v")
+  [(set (match_operand:VI1_AVX512VL_F 0 "register_operand" "=x,v")
 	(unspec:VI1_AVX512VL_F
-	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "v")
-	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "vm")]
+	  [(match_operand:VI1_AVX512VL_F 1 "register_operand" "x,v")
+	   (match_operand:VI1_AVX512VL_F 2 "vector_operand" "xjm,vm")]
 	  UNSPEC_VAESENCLAST))]
   "TARGET_VAES"
-  "vaesenclast\t{%2, %1, %0|%0, %1, %2}"
-)
+{
+  if (which_alternative == 0 && <MODE>mode == V16QImode)
+    return "%{evex%} vaesenclast\t{%2, %1, %0|%0, %1, %2}";
+  else
+    return "vaesenclast\t{%2, %1, %0|%0, %1, %2}";
+})
 
 (define_insn "vpclmulqdq_<mode>"
   [(set (match_operand:VI8_FVL 0 "register_operand" "=v")
--- gcc/testsuite/gcc.target/i386/aes-pr114576.c.jj	2024-04-09 10:27:32.782646751 +0200
+++ gcc/testsuite/gcc.target/i386/aes-pr114576.c	2024-04-09 10:27:32.782646751 +0200
@@ -0,0 +1,63 @@ 
+/* PR target/114576 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -maes -mno-avx" } */
+/* { dg-final { scan-assembler-times "\taesenc\t" 2 } } */
+/* { dg-final { scan-assembler-times "\taesdec\t" 2 } } */
+/* { dg-final { scan-assembler-times "\taesenclast\t" 2 } } */
+/* { dg-final { scan-assembler-times "\taesdeclast\t" 2 } } */
+/* { dg-final { scan-assembler-not "\tvaesenc" } } */
+/* { dg-final { scan-assembler-not "\tvaesdec" } } */
+
+#include <immintrin.h>
+
+__m128i
+f1 (__m128i x, __m128i y)
+{
+  return _mm_aesenc_si128 (x, y);
+}
+
+__m128i
+f2 (__m128i x, __m128i y)
+{
+  __m128i z = _mm_aesenc_si128 (x, y);
+  return z + x + y;
+}
+
+__m128i
+f3 (__m128i x, __m128i y)
+{
+  return _mm_aesdec_si128 (x, y);
+}
+
+__m128i
+f4 (__m128i x, __m128i y)
+{
+  __m128i z = _mm_aesdec_si128 (x, y);
+  return z + x + y;
+}
+
+__m128i
+f5 (__m128i x, __m128i y)
+{
+  return _mm_aesenclast_si128 (x, y);
+}
+
+__m128i
+f6 (__m128i x, __m128i y)
+{
+  __m128i z = _mm_aesenclast_si128 (x, y);
+  return z + x + y;
+}
+
+__m128i
+f7 (__m128i x, __m128i y)
+{
+  return _mm_aesdeclast_si128 (x, y);
+}
+
+__m128i
+f8 (__m128i x, __m128i y)
+{
+  __m128i z = _mm_aesdeclast_si128 (x, y);
+  return z + x + y;
+}