Date: Mon, 31 Aug 2015 11:50:07 -0300
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Adrian Hunter <adrian.hunter@intel.com>
Cc: linux-kernel@vger.kernel.org, Jiri Olsa <jolsa@redhat.com>,
        Andy Lutomirski <luto@amacapital.net>,
        Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>,
        Denys Vlasenko <dvlasenk@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Qiaowei Ren <qiaowei.ren@intel.com>, "H. Peter Anvin" <hpa@zytor.com>,
        Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 3/4] x86/insn: perf tools: Add new SHA instructions
Message-ID: <20150831145007.GF663@kernel.org>
References: <1441029522-20235-1-git-send-email-adrian.hunter@intel.com>
 <1441029522-20235-4-git-send-email-adrian.hunter@intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1441029522-20235-4-git-send-email-adrian.hunter@intel.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 65511
Lines: 1156

Em Mon, Aug 31, 2015 at 04:58:41PM +0300, Adrian Hunter escreveu:
> Intel SHA Extensions are explained in the Intel Architecture
> Instruction Set Extensions Programing Reference (Oct 2014).
> There are 7 new instructions.  Add them to the op code map
> and the perf tools new instructions test. e.g.
> 
>     $ tools/perf/perf test list 2>&1 | grep "x86 ins"

I.e., one could short circuit the 'perf test list' step and use:

	perf test "x86 ins" straight away:

[root@zoo linux]# perf test "syscall event"
 2: detect openat syscall event                              : Ok
 3: detect openat syscall event on all cpus                  : Ok
[root@zoo linux]#

>     39: Test x86 instruction decoder - new instructions
>     $ tools/perf/perf test 39
>     39: Test x86 instruction decoder - new instructions          : Ok
> 
> Or to see the details:
> 
>     $ tools/perf/perf test -v 39 2>&1 | grep sha
> 
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> ---
>  arch/x86/lib/x86-opcode-map.txt                    |   7 +
>  tools/perf/tests/insn-x86-dat-32.c                 | 294 ++++++++++++++++
>  tools/perf/tests/insn-x86-dat-64.c                 | 364 ++++++++++++++++++++
>  tools/perf/tests/insn-x86-dat-src.c                | 373 +++++++++++++++++++++
>  .../perf/util/intel-pt-decoder/x86-opcode-map.txt  |   7 +
>  5 files changed, 1045 insertions(+)
> 
> diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
> index a02a195d219c..25dad388b371 100644
> --- a/arch/x86/lib/x86-opcode-map.txt
> +++ b/arch/x86/lib/x86-opcode-map.txt
> @@ -736,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
>  be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
>  bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
>  # 0x0f 0x38 0xc0-0xff
> +c8: sha1nexte Vdq,Wdq
> +c9: sha1msg1 Vdq,Wdq
> +ca: sha1msg2 Vdq,Wdq
> +cb: sha256rnds2 Vdq,Wdq
> +cc: sha256msg1 Vdq,Wdq
> +cd: sha256msg2 Vdq,Wdq
>  db: VAESIMC Vdq,Wdq (66),(v1)
>  dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
>  dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
> @@ -794,6 +800,7 @@ AVXcode: 3
>  61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
>  62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
>  63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
> +cc: sha1rnds4 Vdq,Wdq,Ib
>  df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
>  f0: RORX Gy,Ey,Ib (F2),(v)
>  EndTable
> diff --git a/tools/perf/tests/insn-x86-dat-32.c b/tools/perf/tests/insn-x86-dat-32.c
> index 6a38a34a5a49..83f5078e74e1 100644
> --- a/tools/perf/tests/insn-x86-dat-32.c
> +++ b/tools/perf/tests/insn-x86-dat-32.c
> @@ -322,3 +322,297 @@
>  "f2 ff 21             \tbnd jmp *(%ecx)",},
>  {{0xf2, 0x0f, 0x85, 0xfc, 0xff, 0xff, 0xff, }, 7, 0xfffffffc, "jcc", "conditional",
>  "f2 0f 85 fc ff ff ff \tbnd jne 3de <main+0x3de>",},
> +{{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
> +"0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
> +"0f 3a cc d7 91       \tsha1rnds4 $0x91,%xmm7,%xmm2",},
> +{{0x0f, 0x3a, 0xcc, 0x00, 0x91, }, 5, 0, "", "",
> +"0f 3a cc 00 91       \tsha1rnds4 $0x91,(%eax),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x05, 0x78, 0x56, 0x34, 0x12, 0x91, }, 9, 0, "", "",
> +"0f 3a cc 05 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678,%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x18, 0x91, }, 5, 0, "", "",
> +"0f 3a cc 18 91       \tsha1rnds4 $0x91,(%eax),%xmm3",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x01, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 01 91    \tsha1rnds4 $0x91,(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 04 05 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x08, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 08 91    \tsha1rnds4 $0x91,(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0xc8, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 c8 91    \tsha1rnds4 $0x91,(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x40, 0x12, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 40 12 91    \tsha1rnds4 $0x91,0x12(%eax),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x45, 0x12, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 45 12 91    \tsha1rnds4 $0x91,0x12(%ebp),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x01, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 01 12 91 \tsha1rnds4 $0x91,0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x05, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 05 12 91 \tsha1rnds4 $0x91,0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x08, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 08 12 91 \tsha1rnds4 $0x91,0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0xc8, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 c8 12 91 \tsha1rnds4 $0x91,0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x80, 0x78, 0x56, 0x34, 0x12, 0x91, }, 9, 0, "", "",
> +"0f 3a cc 80 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x85, 0x78, 0x56, 0x34, 0x12, 0x91, }, 9, 0, "", "",
> +"0f 3a cc 85 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 01 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 05 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 08 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 c8 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0xc1, }, 4, 0, "", "",
> +"0f 38 c8 c1          \tsha1nexte %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0xd7, }, 4, 0, "", "",
> +"0f 38 c8 d7          \tsha1nexte %xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xc8, 0x00, }, 4, 0, "", "",
> +"0f 38 c8 00          \tsha1nexte (%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c8 05 78 56 34 12 \tsha1nexte 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x18, }, 4, 0, "", "",
> +"0f 38 c8 18          \tsha1nexte (%eax),%xmm3",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 c8 04 01       \tsha1nexte (%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 04 05 78 56 34 12 \tsha1nexte 0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 c8 04 08       \tsha1nexte (%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 c8 04 c8       \tsha1nexte (%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 c8 40 12       \tsha1nexte 0x12(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 c8 45 12       \tsha1nexte 0x12(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 01 12    \tsha1nexte 0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 05 12    \tsha1nexte 0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 08 12    \tsha1nexte 0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 c8 12    \tsha1nexte 0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c8 80 78 56 34 12 \tsha1nexte 0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c8 85 78 56 34 12 \tsha1nexte 0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 01 78 56 34 12 \tsha1nexte 0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 05 78 56 34 12 \tsha1nexte 0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 08 78 56 34 12 \tsha1nexte 0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 c8 78 56 34 12 \tsha1nexte 0x12345678(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0xc1, }, 4, 0, "", "",
> +"0f 38 c9 c1          \tsha1msg1 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0xd7, }, 4, 0, "", "",
> +"0f 38 c9 d7          \tsha1msg1 %xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xc9, 0x00, }, 4, 0, "", "",
> +"0f 38 c9 00          \tsha1msg1 (%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c9 05 78 56 34 12 \tsha1msg1 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x18, }, 4, 0, "", "",
> +"0f 38 c9 18          \tsha1msg1 (%eax),%xmm3",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 c9 04 01       \tsha1msg1 (%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 04 05 78 56 34 12 \tsha1msg1 0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 c9 04 08       \tsha1msg1 (%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 c9 04 c8       \tsha1msg1 (%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 c9 40 12       \tsha1msg1 0x12(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 c9 45 12       \tsha1msg1 0x12(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 01 12    \tsha1msg1 0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 05 12    \tsha1msg1 0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 08 12    \tsha1msg1 0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 c8 12    \tsha1msg1 0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c9 80 78 56 34 12 \tsha1msg1 0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c9 85 78 56 34 12 \tsha1msg1 0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 01 78 56 34 12 \tsha1msg1 0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 05 78 56 34 12 \tsha1msg1 0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 08 78 56 34 12 \tsha1msg1 0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 c8 78 56 34 12 \tsha1msg1 0x12345678(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0xc1, }, 4, 0, "", "",
> +"0f 38 ca c1          \tsha1msg2 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xca, 0xd7, }, 4, 0, "", "",
> +"0f 38 ca d7          \tsha1msg2 %xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xca, 0x00, }, 4, 0, "", "",
> +"0f 38 ca 00          \tsha1msg2 (%eax),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 ca 05 78 56 34 12 \tsha1msg2 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x18, }, 4, 0, "", "",
> +"0f 38 ca 18          \tsha1msg2 (%eax),%xmm3",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 ca 04 01       \tsha1msg2 (%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 04 05 78 56 34 12 \tsha1msg2 0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 ca 04 08       \tsha1msg2 (%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 ca 04 c8       \tsha1msg2 (%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 ca 40 12       \tsha1msg2 0x12(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 ca 45 12       \tsha1msg2 0x12(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 01 12    \tsha1msg2 0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 05 12    \tsha1msg2 0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 08 12    \tsha1msg2 0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 c8 12    \tsha1msg2 0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 ca 80 78 56 34 12 \tsha1msg2 0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 ca 85 78 56 34 12 \tsha1msg2 0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 01 78 56 34 12 \tsha1msg2 0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 05 78 56 34 12 \tsha1msg2 0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 08 78 56 34 12 \tsha1msg2 0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 c8 78 56 34 12 \tsha1msg2 0x12345678(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcb, 0xcc, }, 4, 0, "", "",
> +"0f 38 cb cc          \tsha256rnds2 %xmm0,%xmm4,%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0xd7, }, 4, 0, "", "",
> +"0f 38 cb d7          \tsha256rnds2 %xmm0,%xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xcb, 0x08, }, 4, 0, "", "",
> +"0f 38 cb 08          \tsha256rnds2 %xmm0,(%eax),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0d, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cb 0d 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678,%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x18, }, 4, 0, "", "",
> +"0f 38 cb 18          \tsha256rnds2 %xmm0,(%eax),%xmm3",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x01, }, 5, 0, "", "",
> +"0f 38 cb 0c 01       \tsha256rnds2 %xmm0,(%ecx,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 0c 05 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x08, }, 5, 0, "", "",
> +"0f 38 cb 0c 08       \tsha256rnds2 %xmm0,(%eax,%ecx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0xc8, }, 5, 0, "", "",
> +"0f 38 cb 0c c8       \tsha256rnds2 %xmm0,(%eax,%ecx,8),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x48, 0x12, }, 5, 0, "", "",
> +"0f 38 cb 48 12       \tsha256rnds2 %xmm0,0x12(%eax),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4d, 0x12, }, 5, 0, "", "",
> +"0f 38 cb 4d 12       \tsha256rnds2 %xmm0,0x12(%ebp),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 01 12    \tsha256rnds2 %xmm0,0x12(%ecx,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 05 12    \tsha256rnds2 %xmm0,0x12(%ebp,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 08 12    \tsha256rnds2 %xmm0,0x12(%eax,%ecx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c c8 12    \tsha256rnds2 %xmm0,0x12(%eax,%ecx,8),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cb 88 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%eax),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8d, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cb 8d 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%ebp),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 01 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%ecx,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 05 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%ebp,%eax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 08 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%eax,%ecx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c c8 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%eax,%ecx,8),%xmm1",},
> +{{0x0f, 0x38, 0xcc, 0xc1, }, 4, 0, "", "",
> +"0f 38 cc c1          \tsha256msg1 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0xd7, }, 4, 0, "", "",
> +"0f 38 cc d7          \tsha256msg1 %xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xcc, 0x00, }, 4, 0, "", "",
> +"0f 38 cc 00          \tsha256msg1 (%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cc 05 78 56 34 12 \tsha256msg1 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x18, }, 4, 0, "", "",
> +"0f 38 cc 18          \tsha256msg1 (%eax),%xmm3",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 cc 04 01       \tsha256msg1 (%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 04 05 78 56 34 12 \tsha256msg1 0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 cc 04 08       \tsha256msg1 (%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 cc 04 c8       \tsha256msg1 (%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 cc 40 12       \tsha256msg1 0x12(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 cc 45 12       \tsha256msg1 0x12(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 01 12    \tsha256msg1 0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 05 12    \tsha256msg1 0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 08 12    \tsha256msg1 0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 c8 12    \tsha256msg1 0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cc 80 78 56 34 12 \tsha256msg1 0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cc 85 78 56 34 12 \tsha256msg1 0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 01 78 56 34 12 \tsha256msg1 0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 05 78 56 34 12 \tsha256msg1 0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 08 78 56 34 12 \tsha256msg1 0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 c8 78 56 34 12 \tsha256msg1 0x12345678(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0xc1, }, 4, 0, "", "",
> +"0f 38 cd c1          \tsha256msg2 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0xd7, }, 4, 0, "", "",
> +"0f 38 cd d7          \tsha256msg2 %xmm7,%xmm2",},
> +{{0x0f, 0x38, 0xcd, 0x00, }, 4, 0, "", "",
> +"0f 38 cd 00          \tsha256msg2 (%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x05, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cd 05 78 56 34 12 \tsha256msg2 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x18, }, 4, 0, "", "",
> +"0f 38 cd 18          \tsha256msg2 (%eax),%xmm3",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 cd 04 01       \tsha256msg2 (%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 04 05 78 56 34 12 \tsha256msg2 0x12345678(,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 cd 04 08       \tsha256msg2 (%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 cd 04 c8       \tsha256msg2 (%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 cd 40 12       \tsha256msg2 0x12(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 cd 45 12       \tsha256msg2 0x12(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 01 12    \tsha256msg2 0x12(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 05 12    \tsha256msg2 0x12(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 08 12    \tsha256msg2 0x12(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 c8 12    \tsha256msg2 0x12(%eax,%ecx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cd 80 78 56 34 12 \tsha256msg2 0x12345678(%eax),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cd 85 78 56 34 12 \tsha256msg2 0x12345678(%ebp),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 01 78 56 34 12 \tsha256msg2 0x12345678(%ecx,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 05 78 56 34 12 \tsha256msg2 0x12345678(%ebp,%eax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 08 78 56 34 12 \tsha256msg2 0x12345678(%eax,%ecx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 c8 78 56 34 12 \tsha256msg2 0x12345678(%eax,%ecx,8),%xmm0",},
> diff --git a/tools/perf/tests/insn-x86-dat-64.c b/tools/perf/tests/insn-x86-dat-64.c
> index 01122421a776..13f008588590 100644
> --- a/tools/perf/tests/insn-x86-dat-64.c
> +++ b/tools/perf/tests/insn-x86-dat-64.c
> @@ -338,3 +338,367 @@
>  "67 f2 ff 21          \tbnd jmpq *(%ecx)",},
>  {{0xf2, 0x0f, 0x85, 0x00, 0x00, 0x00, 0x00, }, 7, 0, "jcc", "conditional",
>  "f2 0f 85 00 00 00 00 \tbnd jne 413 <main+0x413>",},
> +{{0x0f, 0x3a, 0xcc, 0xc1, 0x00, }, 5, 0, "", "",
> +"0f 3a cc c1 00       \tsha1rnds4 $0x0,%xmm1,%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0xd7, 0x91, }, 5, 0, "", "",
> +"0f 3a cc d7 91       \tsha1rnds4 $0x91,%xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x3a, 0xcc, 0xc0, 0x91, }, 6, 0, "", "",
> +"41 0f 3a cc c0 91    \tsha1rnds4 $0x91,%xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x3a, 0xcc, 0xc7, 0x91, }, 6, 0, "", "",
> +"44 0f 3a cc c7 91    \tsha1rnds4 $0x91,%xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x3a, 0xcc, 0xc7, 0x91, }, 6, 0, "", "",
> +"45 0f 3a cc c7 91    \tsha1rnds4 $0x91,%xmm15,%xmm8",},
> +{{0x0f, 0x3a, 0xcc, 0x00, 0x91, }, 5, 0, "", "",
> +"0f 3a cc 00 91       \tsha1rnds4 $0x91,(%rax),%xmm0",},
> +{{0x41, 0x0f, 0x3a, 0xcc, 0x00, 0x91, }, 6, 0, "", "",
> +"41 0f 3a cc 00 91    \tsha1rnds4 $0x91,(%r8),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 04 25 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678,%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x18, 0x91, }, 5, 0, "", "",
> +"0f 3a cc 18 91       \tsha1rnds4 $0x91,(%rax),%xmm3",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x01, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 01 91    \tsha1rnds4 $0x91,(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 04 05 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0x08, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 08 91    \tsha1rnds4 $0x91,(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x04, 0xc8, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 04 c8 91    \tsha1rnds4 $0x91,(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x40, 0x12, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 40 12 91    \tsha1rnds4 $0x91,0x12(%rax),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x45, 0x12, 0x91, }, 6, 0, "", "",
> +"0f 3a cc 45 12 91    \tsha1rnds4 $0x91,0x12(%rbp),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x01, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 01 12 91 \tsha1rnds4 $0x91,0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x05, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 05 12 91 \tsha1rnds4 $0x91,0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0x08, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 08 12 91 \tsha1rnds4 $0x91,0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x44, 0xc8, 0x12, 0x91, }, 7, 0, "", "",
> +"0f 3a cc 44 c8 12 91 \tsha1rnds4 $0x91,0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x80, 0x78, 0x56, 0x34, 0x12, 0x91, }, 9, 0, "", "",
> +"0f 3a cc 80 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x85, 0x78, 0x56, 0x34, 0x12, 0x91, }, 9, 0, "", "",
> +"0f 3a cc 85 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 01 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 05 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 08 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x3a, 0xcc, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x91, }, 10, 0, "", "",
> +"0f 3a cc 84 c8 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x3a, 0xcc, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, 0x91, }, 11, 0, "", "",
> +"44 0f 3a cc bc c8 78 56 34 12 91 \tsha1rnds4 $0x91,0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xc8, 0xc1, }, 4, 0, "", "",
> +"0f 38 c8 c1          \tsha1nexte %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0xd7, }, 4, 0, "", "",
> +"0f 38 c8 d7          \tsha1nexte %xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xc8, 0xc0, }, 5, 0, "", "",
> +"41 0f 38 c8 c0       \tsha1nexte %xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xc8, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 c8 c7       \tsha1nexte %xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xc8, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 c8 c7       \tsha1nexte %xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xc8, 0x00, }, 4, 0, "", "",
> +"0f 38 c8 00          \tsha1nexte (%rax),%xmm0",},
> +{{0x41, 0x0f, 0x38, 0xc8, 0x00, }, 5, 0, "", "",
> +"41 0f 38 c8 00       \tsha1nexte (%r8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 04 25 78 56 34 12 \tsha1nexte 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x18, }, 4, 0, "", "",
> +"0f 38 c8 18          \tsha1nexte (%rax),%xmm3",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 c8 04 01       \tsha1nexte (%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 04 05 78 56 34 12 \tsha1nexte 0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 c8 04 08       \tsha1nexte (%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 c8 04 c8       \tsha1nexte (%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 c8 40 12       \tsha1nexte 0x12(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 c8 45 12       \tsha1nexte 0x12(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 01 12    \tsha1nexte 0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 05 12    \tsha1nexte 0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 08 12    \tsha1nexte 0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 c8 44 c8 12    \tsha1nexte 0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c8 80 78 56 34 12 \tsha1nexte 0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c8 85 78 56 34 12 \tsha1nexte 0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 01 78 56 34 12 \tsha1nexte 0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 05 78 56 34 12 \tsha1nexte 0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 08 78 56 34 12 \tsha1nexte 0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc8, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c8 84 c8 78 56 34 12 \tsha1nexte 0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xc8, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 c8 bc c8 78 56 34 12 \tsha1nexte 0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xc9, 0xc1, }, 4, 0, "", "",
> +"0f 38 c9 c1          \tsha1msg1 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0xd7, }, 4, 0, "", "",
> +"0f 38 c9 d7          \tsha1msg1 %xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xc9, 0xc0, }, 5, 0, "", "",
> +"41 0f 38 c9 c0       \tsha1msg1 %xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xc9, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 c9 c7       \tsha1msg1 %xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xc9, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 c9 c7       \tsha1msg1 %xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xc9, 0x00, }, 4, 0, "", "",
> +"0f 38 c9 00          \tsha1msg1 (%rax),%xmm0",},
> +{{0x41, 0x0f, 0x38, 0xc9, 0x00, }, 5, 0, "", "",
> +"41 0f 38 c9 00       \tsha1msg1 (%r8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 04 25 78 56 34 12 \tsha1msg1 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x18, }, 4, 0, "", "",
> +"0f 38 c9 18          \tsha1msg1 (%rax),%xmm3",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 c9 04 01       \tsha1msg1 (%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 04 05 78 56 34 12 \tsha1msg1 0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 c9 04 08       \tsha1msg1 (%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 c9 04 c8       \tsha1msg1 (%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 c9 40 12       \tsha1msg1 0x12(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 c9 45 12       \tsha1msg1 0x12(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 01 12    \tsha1msg1 0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 05 12    \tsha1msg1 0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 08 12    \tsha1msg1 0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 c9 44 c8 12    \tsha1msg1 0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c9 80 78 56 34 12 \tsha1msg1 0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 c9 85 78 56 34 12 \tsha1msg1 0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 01 78 56 34 12 \tsha1msg1 0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 05 78 56 34 12 \tsha1msg1 0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 08 78 56 34 12 \tsha1msg1 0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xc9, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 c9 84 c8 78 56 34 12 \tsha1msg1 0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xc9, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 c9 bc c8 78 56 34 12 \tsha1msg1 0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xca, 0xc1, }, 4, 0, "", "",
> +"0f 38 ca c1          \tsha1msg2 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xca, 0xd7, }, 4, 0, "", "",
> +"0f 38 ca d7          \tsha1msg2 %xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xca, 0xc0, }, 5, 0, "", "",
> +"41 0f 38 ca c0       \tsha1msg2 %xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xca, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 ca c7       \tsha1msg2 %xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xca, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 ca c7       \tsha1msg2 %xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xca, 0x00, }, 4, 0, "", "",
> +"0f 38 ca 00          \tsha1msg2 (%rax),%xmm0",},
> +{{0x41, 0x0f, 0x38, 0xca, 0x00, }, 5, 0, "", "",
> +"41 0f 38 ca 00       \tsha1msg2 (%r8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 04 25 78 56 34 12 \tsha1msg2 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x18, }, 4, 0, "", "",
> +"0f 38 ca 18          \tsha1msg2 (%rax),%xmm3",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 ca 04 01       \tsha1msg2 (%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 04 05 78 56 34 12 \tsha1msg2 0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 ca 04 08       \tsha1msg2 (%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 ca 04 c8       \tsha1msg2 (%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 ca 40 12       \tsha1msg2 0x12(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 ca 45 12       \tsha1msg2 0x12(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 01 12    \tsha1msg2 0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 05 12    \tsha1msg2 0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 08 12    \tsha1msg2 0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 ca 44 c8 12    \tsha1msg2 0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 ca 80 78 56 34 12 \tsha1msg2 0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 ca 85 78 56 34 12 \tsha1msg2 0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 01 78 56 34 12 \tsha1msg2 0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 05 78 56 34 12 \tsha1msg2 0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 08 78 56 34 12 \tsha1msg2 0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xca, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 ca 84 c8 78 56 34 12 \tsha1msg2 0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xca, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 ca bc c8 78 56 34 12 \tsha1msg2 0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xcb, 0xcc, }, 4, 0, "", "",
> +"0f 38 cb cc          \tsha256rnds2 %xmm0,%xmm4,%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0xd7, }, 4, 0, "", "",
> +"0f 38 cb d7          \tsha256rnds2 %xmm0,%xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xcb, 0xc8, }, 5, 0, "", "",
> +"41 0f 38 cb c8       \tsha256rnds2 %xmm0,%xmm8,%xmm1",},
> +{{0x44, 0x0f, 0x38, 0xcb, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 cb c7       \tsha256rnds2 %xmm0,%xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xcb, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 cb c7       \tsha256rnds2 %xmm0,%xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xcb, 0x08, }, 4, 0, "", "",
> +"0f 38 cb 08          \tsha256rnds2 %xmm0,(%rax),%xmm1",},
> +{{0x41, 0x0f, 0x38, 0xcb, 0x08, }, 5, 0, "", "",
> +"41 0f 38 cb 08       \tsha256rnds2 %xmm0,(%r8),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 0c 25 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678,%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x18, }, 4, 0, "", "",
> +"0f 38 cb 18          \tsha256rnds2 %xmm0,(%rax),%xmm3",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x01, }, 5, 0, "", "",
> +"0f 38 cb 0c 01       \tsha256rnds2 %xmm0,(%rcx,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 0c 05 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0x08, }, 5, 0, "", "",
> +"0f 38 cb 0c 08       \tsha256rnds2 %xmm0,(%rax,%rcx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x0c, 0xc8, }, 5, 0, "", "",
> +"0f 38 cb 0c c8       \tsha256rnds2 %xmm0,(%rax,%rcx,8),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x48, 0x12, }, 5, 0, "", "",
> +"0f 38 cb 48 12       \tsha256rnds2 %xmm0,0x12(%rax),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4d, 0x12, }, 5, 0, "", "",
> +"0f 38 cb 4d 12       \tsha256rnds2 %xmm0,0x12(%rbp),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 01 12    \tsha256rnds2 %xmm0,0x12(%rcx,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 05 12    \tsha256rnds2 %xmm0,0x12(%rbp,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c 08 12    \tsha256rnds2 %xmm0,0x12(%rax,%rcx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x4c, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cb 4c c8 12    \tsha256rnds2 %xmm0,0x12(%rax,%rcx,8),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x88, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cb 88 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rax),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8d, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cb 8d 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rbp),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 01 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rcx,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 05 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rbp,%rax,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c 08 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rax,%rcx,1),%xmm1",},
> +{{0x0f, 0x38, 0xcb, 0x8c, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cb 8c c8 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rax,%rcx,8),%xmm1",},
> +{{0x44, 0x0f, 0x38, 0xcb, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 cb bc c8 78 56 34 12 \tsha256rnds2 %xmm0,0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xcc, 0xc1, }, 4, 0, "", "",
> +"0f 38 cc c1          \tsha256msg1 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0xd7, }, 4, 0, "", "",
> +"0f 38 cc d7          \tsha256msg1 %xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xcc, 0xc0, }, 5, 0, "", "",
> +"41 0f 38 cc c0       \tsha256msg1 %xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xcc, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 cc c7       \tsha256msg1 %xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xcc, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 cc c7       \tsha256msg1 %xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xcc, 0x00, }, 4, 0, "", "",
> +"0f 38 cc 00          \tsha256msg1 (%rax),%xmm0",},
> +{{0x41, 0x0f, 0x38, 0xcc, 0x00, }, 5, 0, "", "",
> +"41 0f 38 cc 00       \tsha256msg1 (%r8),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 04 25 78 56 34 12 \tsha256msg1 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x18, }, 4, 0, "", "",
> +"0f 38 cc 18          \tsha256msg1 (%rax),%xmm3",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 cc 04 01       \tsha256msg1 (%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 04 05 78 56 34 12 \tsha256msg1 0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 cc 04 08       \tsha256msg1 (%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 cc 04 c8       \tsha256msg1 (%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 cc 40 12       \tsha256msg1 0x12(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 cc 45 12       \tsha256msg1 0x12(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 01 12    \tsha256msg1 0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 05 12    \tsha256msg1 0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 08 12    \tsha256msg1 0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cc 44 c8 12    \tsha256msg1 0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cc 80 78 56 34 12 \tsha256msg1 0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cc 85 78 56 34 12 \tsha256msg1 0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 01 78 56 34 12 \tsha256msg1 0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 05 78 56 34 12 \tsha256msg1 0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 08 78 56 34 12 \tsha256msg1 0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcc, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cc 84 c8 78 56 34 12 \tsha256msg1 0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xcc, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 cc bc c8 78 56 34 12 \tsha256msg1 0x12345678(%rax,%rcx,8),%xmm15",},
> +{{0x0f, 0x38, 0xcd, 0xc1, }, 4, 0, "", "",
> +"0f 38 cd c1          \tsha256msg2 %xmm1,%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0xd7, }, 4, 0, "", "",
> +"0f 38 cd d7          \tsha256msg2 %xmm7,%xmm2",},
> +{{0x41, 0x0f, 0x38, 0xcd, 0xc0, }, 5, 0, "", "",
> +"41 0f 38 cd c0       \tsha256msg2 %xmm8,%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xcd, 0xc7, }, 5, 0, "", "",
> +"44 0f 38 cd c7       \tsha256msg2 %xmm7,%xmm8",},
> +{{0x45, 0x0f, 0x38, 0xcd, 0xc7, }, 5, 0, "", "",
> +"45 0f 38 cd c7       \tsha256msg2 %xmm15,%xmm8",},
> +{{0x0f, 0x38, 0xcd, 0x00, }, 4, 0, "", "",
> +"0f 38 cd 00          \tsha256msg2 (%rax),%xmm0",},
> +{{0x41, 0x0f, 0x38, 0xcd, 0x00, }, 5, 0, "", "",
> +"41 0f 38 cd 00       \tsha256msg2 (%r8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x25, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 04 25 78 56 34 12 \tsha256msg2 0x12345678,%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x18, }, 4, 0, "", "",
> +"0f 38 cd 18          \tsha256msg2 (%rax),%xmm3",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x01, }, 5, 0, "", "",
> +"0f 38 cd 04 01       \tsha256msg2 (%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 04 05 78 56 34 12 \tsha256msg2 0x12345678(,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0x08, }, 5, 0, "", "",
> +"0f 38 cd 04 08       \tsha256msg2 (%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x04, 0xc8, }, 5, 0, "", "",
> +"0f 38 cd 04 c8       \tsha256msg2 (%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x40, 0x12, }, 5, 0, "", "",
> +"0f 38 cd 40 12       \tsha256msg2 0x12(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x45, 0x12, }, 5, 0, "", "",
> +"0f 38 cd 45 12       \tsha256msg2 0x12(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x01, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 01 12    \tsha256msg2 0x12(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x05, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 05 12    \tsha256msg2 0x12(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0x08, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 08 12    \tsha256msg2 0x12(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x44, 0xc8, 0x12, }, 6, 0, "", "",
> +"0f 38 cd 44 c8 12    \tsha256msg2 0x12(%rax,%rcx,8),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x80, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cd 80 78 56 34 12 \tsha256msg2 0x12345678(%rax),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x85, 0x78, 0x56, 0x34, 0x12, }, 8, 0, "", "",
> +"0f 38 cd 85 78 56 34 12 \tsha256msg2 0x12345678(%rbp),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x01, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 01 78 56 34 12 \tsha256msg2 0x12345678(%rcx,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x05, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 05 78 56 34 12 \tsha256msg2 0x12345678(%rbp,%rax,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0x08, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 08 78 56 34 12 \tsha256msg2 0x12345678(%rax,%rcx,1),%xmm0",},
> +{{0x0f, 0x38, 0xcd, 0x84, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 9, 0, "", "",
> +"0f 38 cd 84 c8 78 56 34 12 \tsha256msg2 0x12345678(%rax,%rcx,8),%xmm0",},
> +{{0x44, 0x0f, 0x38, 0xcd, 0xbc, 0xc8, 0x78, 0x56, 0x34, 0x12, }, 10, 0, "", "",
> +"44 0f 38 cd bc c8 78 56 34 12 \tsha256msg2 0x12345678(%rax,%rcx,8),%xmm15",},
> diff --git a/tools/perf/tests/insn-x86-dat-src.c b/tools/perf/tests/insn-x86-dat-src.c
> index b506830f33a8..7d06c9b22070 100644
> --- a/tools/perf/tests/insn-x86-dat-src.c
> +++ b/tools/perf/tests/insn-x86-dat-src.c
> @@ -217,6 +217,210 @@ int main(void)
>  	asm volatile("bnd jmp *(%ecx)");  /* Expecting: jmp  indirect      0 */
>  	asm volatile("bnd jne label1");   /* Expecting: jcc  conditional   0 */
>  
> +	/* sha1rnds4 imm8, xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1rnds4 $0x0, %xmm1, %xmm0");
> +	asm volatile("sha1rnds4 $0x91, %xmm7, %xmm2");
> +	asm volatile("sha1rnds4 $0x91, %xmm8, %xmm0");
> +	asm volatile("sha1rnds4 $0x91, %xmm7, %xmm8");
> +	asm volatile("sha1rnds4 $0x91, %xmm15, %xmm8");
> +	asm volatile("sha1rnds4 $0x91, (%rax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%r8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (0x12345678), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%rax), %xmm3");
> +	asm volatile("sha1rnds4 $0x91, (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rbp), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha1nexte xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1nexte %xmm1, %xmm0");
> +	asm volatile("sha1nexte %xmm7, %xmm2");
> +	asm volatile("sha1nexte %xmm8, %xmm0");
> +	asm volatile("sha1nexte %xmm7, %xmm8");
> +	asm volatile("sha1nexte %xmm15, %xmm8");
> +	asm volatile("sha1nexte (%rax), %xmm0");
> +	asm volatile("sha1nexte (%r8), %xmm0");
> +	asm volatile("sha1nexte (0x12345678), %xmm0");
> +	asm volatile("sha1nexte (%rax), %xmm3");
> +	asm volatile("sha1nexte (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha1nexte (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1nexte (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rax), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rbp), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rax), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha1msg1 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1msg1 %xmm1, %xmm0");
> +	asm volatile("sha1msg1 %xmm7, %xmm2");
> +	asm volatile("sha1msg1 %xmm8, %xmm0");
> +	asm volatile("sha1msg1 %xmm7, %xmm8");
> +	asm volatile("sha1msg1 %xmm15, %xmm8");
> +	asm volatile("sha1msg1 (%rax), %xmm0");
> +	asm volatile("sha1msg1 (%r8), %xmm0");
> +	asm volatile("sha1msg1 (0x12345678), %xmm0");
> +	asm volatile("sha1msg1 (%rax), %xmm3");
> +	asm volatile("sha1msg1 (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg1 (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rax), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rbp), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rax), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha1msg2 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1msg2 %xmm1, %xmm0");
> +	asm volatile("sha1msg2 %xmm7, %xmm2");
> +	asm volatile("sha1msg2 %xmm8, %xmm0");
> +	asm volatile("sha1msg2 %xmm7, %xmm8");
> +	asm volatile("sha1msg2 %xmm15, %xmm8");
> +	asm volatile("sha1msg2 (%rax), %xmm0");
> +	asm volatile("sha1msg2 (%r8), %xmm0");
> +	asm volatile("sha1msg2 (0x12345678), %xmm0");
> +	asm volatile("sha1msg2 (%rax), %xmm3");
> +	asm volatile("sha1msg2 (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg2 (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rax), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rbp), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rax), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha256rnds2 <XMM0>, xmm2/m128, xmm1 */
> +	/* Note sha256rnds2 has an implicit operand 'xmm0' */
> +
> +	asm volatile("sha256rnds2 %xmm4, %xmm1");
> +	asm volatile("sha256rnds2 %xmm7, %xmm2");
> +	asm volatile("sha256rnds2 %xmm8, %xmm1");
> +	asm volatile("sha256rnds2 %xmm7, %xmm8");
> +	asm volatile("sha256rnds2 %xmm15, %xmm8");
> +	asm volatile("sha256rnds2 (%rax), %xmm1");
> +	asm volatile("sha256rnds2 (%r8), %xmm1");
> +	asm volatile("sha256rnds2 (0x12345678), %xmm1");
> +	asm volatile("sha256rnds2 (%rax), %xmm3");
> +	asm volatile("sha256rnds2 (%rcx,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 (%rax,%rcx,1), %xmm1");
> +	asm volatile("sha256rnds2 (%rax,%rcx,8), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rax), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rbp), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rcx,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rbp,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rax,%rcx,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%rax,%rcx,8), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rax), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rbp), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rcx,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rbp,%rax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rax,%rcx,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rax,%rcx,8), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha256msg1 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha256msg1 %xmm1, %xmm0");
> +	asm volatile("sha256msg1 %xmm7, %xmm2");
> +	asm volatile("sha256msg1 %xmm8, %xmm0");
> +	asm volatile("sha256msg1 %xmm7, %xmm8");
> +	asm volatile("sha256msg1 %xmm15, %xmm8");
> +	asm volatile("sha256msg1 (%rax), %xmm0");
> +	asm volatile("sha256msg1 (%r8), %xmm0");
> +	asm volatile("sha256msg1 (0x12345678), %xmm0");
> +	asm volatile("sha256msg1 (%rax), %xmm3");
> +	asm volatile("sha256msg1 (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg1 (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rax), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rbp), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rax), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%rax,%rcx,8), %xmm15");
> +
> +	/* sha256msg2 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha256msg2 %xmm1, %xmm0");
> +	asm volatile("sha256msg2 %xmm7, %xmm2");
> +	asm volatile("sha256msg2 %xmm8, %xmm0");
> +	asm volatile("sha256msg2 %xmm7, %xmm8");
> +	asm volatile("sha256msg2 %xmm15, %xmm8");
> +	asm volatile("sha256msg2 (%rax), %xmm0");
> +	asm volatile("sha256msg2 (%r8), %xmm0");
> +	asm volatile("sha256msg2 (0x12345678), %xmm0");
> +	asm volatile("sha256msg2 (%rax), %xmm3");
> +	asm volatile("sha256msg2 (%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 (%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg2 (%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rax), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rbp), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rax), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rbp), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rcx,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rbp,%rax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rax,%rcx,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rax,%rcx,8), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%rax,%rcx,8), %xmm15");
> +
>  #else  /* #ifdef __x86_64__ */
>  
>  	/* bndmk m32, bnd */
> @@ -407,6 +611,175 @@ int main(void)
>  	asm volatile("bnd jmp *(%ecx)");  /* Expecting: jmp  indirect      0 */
>  	asm volatile("bnd jne label1");   /* Expecting: jcc  conditional   0xfffffffc */
>  
> +	/* sha1rnds4 imm8, xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1rnds4 $0x0, %xmm1, %xmm0");
> +	asm volatile("sha1rnds4 $0x91, %xmm7, %xmm2");
> +	asm volatile("sha1rnds4 $0x91, (%eax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (0x12345678), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%eax), %xmm3");
> +	asm volatile("sha1rnds4 $0x91, (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%eax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%ebp), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%eax), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1rnds4 $0x91, 0x12345678(%eax,%ecx,8), %xmm0");
> +
> +	/* sha1nexte xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1nexte %xmm1, %xmm0");
> +	asm volatile("sha1nexte %xmm7, %xmm2");
> +	asm volatile("sha1nexte (%eax), %xmm0");
> +	asm volatile("sha1nexte (0x12345678), %xmm0");
> +	asm volatile("sha1nexte (%eax), %xmm3");
> +	asm volatile("sha1nexte (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha1nexte (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1nexte (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1nexte 0x12(%eax), %xmm0");
> +	asm volatile("sha1nexte 0x12(%ebp), %xmm0");
> +	asm volatile("sha1nexte 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1nexte 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%eax), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1nexte 0x12345678(%eax,%ecx,8), %xmm0");
> +
> +	/* sha1msg1 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1msg1 %xmm1, %xmm0");
> +	asm volatile("sha1msg1 %xmm7, %xmm2");
> +	asm volatile("sha1msg1 (%eax), %xmm0");
> +	asm volatile("sha1msg1 (0x12345678), %xmm0");
> +	asm volatile("sha1msg1 (%eax), %xmm3");
> +	asm volatile("sha1msg1 (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg1 (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1msg1 0x12(%eax), %xmm0");
> +	asm volatile("sha1msg1 0x12(%ebp), %xmm0");
> +	asm volatile("sha1msg1 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg1 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%eax), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg1 0x12345678(%eax,%ecx,8), %xmm0");
> +
> +	/* sha1msg2 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha1msg2 %xmm1, %xmm0");
> +	asm volatile("sha1msg2 %xmm7, %xmm2");
> +	asm volatile("sha1msg2 (%eax), %xmm0");
> +	asm volatile("sha1msg2 (0x12345678), %xmm0");
> +	asm volatile("sha1msg2 (%eax), %xmm3");
> +	asm volatile("sha1msg2 (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg2 (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1msg2 0x12(%eax), %xmm0");
> +	asm volatile("sha1msg2 0x12(%ebp), %xmm0");
> +	asm volatile("sha1msg2 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg2 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%eax), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha1msg2 0x12345678(%eax,%ecx,8), %xmm0");
> +
> +	/* sha256rnds2 <XMM0>, xmm2/m128, xmm1 */
> +	/* Note sha256rnds2 has an implicit operand 'xmm0' */
> +
> +	asm volatile("sha256rnds2 %xmm4, %xmm1");
> +	asm volatile("sha256rnds2 %xmm7, %xmm2");
> +	asm volatile("sha256rnds2 (%eax), %xmm1");
> +	asm volatile("sha256rnds2 (0x12345678), %xmm1");
> +	asm volatile("sha256rnds2 (%eax), %xmm3");
> +	asm volatile("sha256rnds2 (%ecx,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 (%eax,%ecx,1), %xmm1");
> +	asm volatile("sha256rnds2 (%eax,%ecx,8), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%eax), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%ebp), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%ecx,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%ebp,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%eax,%ecx,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12(%eax,%ecx,8), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%eax), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%ebp), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%ecx,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%ebp,%eax,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%eax,%ecx,1), %xmm1");
> +	asm volatile("sha256rnds2 0x12345678(%eax,%ecx,8), %xmm1");
> +
> +	/* sha256msg1 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha256msg1 %xmm1, %xmm0");
> +	asm volatile("sha256msg1 %xmm7, %xmm2");
> +	asm volatile("sha256msg1 (%eax), %xmm0");
> +	asm volatile("sha256msg1 (0x12345678), %xmm0");
> +	asm volatile("sha256msg1 (%eax), %xmm3");
> +	asm volatile("sha256msg1 (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg1 (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha256msg1 0x12(%eax), %xmm0");
> +	asm volatile("sha256msg1 0x12(%ebp), %xmm0");
> +	asm volatile("sha256msg1 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg1 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%eax), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg1 0x12345678(%eax,%ecx,8), %xmm0");
> +
> +	/* sha256msg2 xmm2/m128, xmm1 */
> +
> +	asm volatile("sha256msg2 %xmm1, %xmm0");
> +	asm volatile("sha256msg2 %xmm7, %xmm2");
> +	asm volatile("sha256msg2 (%eax), %xmm0");
> +	asm volatile("sha256msg2 (0x12345678), %xmm0");
> +	asm volatile("sha256msg2 (%eax), %xmm3");
> +	asm volatile("sha256msg2 (%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 (%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg2 (%eax,%ecx,8), %xmm0");
> +	asm volatile("sha256msg2 0x12(%eax), %xmm0");
> +	asm volatile("sha256msg2 0x12(%ebp), %xmm0");
> +	asm volatile("sha256msg2 0x12(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg2 0x12(%eax,%ecx,8), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%eax), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%ebp), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%ecx,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%ebp,%eax,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%eax,%ecx,1), %xmm0");
> +	asm volatile("sha256msg2 0x12345678(%eax,%ecx,8), %xmm0");
> +
>  #endif /* #ifndef __x86_64__ */
>  
>  	/* Following line is a marker for the awk script - do not change */
> diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
> index a02a195d219c..25dad388b371 100644
> --- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
> +++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
> @@ -736,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
>  be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
>  bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
>  # 0x0f 0x38 0xc0-0xff
> +c8: sha1nexte Vdq,Wdq
> +c9: sha1msg1 Vdq,Wdq
> +ca: sha1msg2 Vdq,Wdq
> +cb: sha256rnds2 Vdq,Wdq
> +cc: sha256msg1 Vdq,Wdq
> +cd: sha256msg2 Vdq,Wdq
>  db: VAESIMC Vdq,Wdq (66),(v1)
>  dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
>  dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
> @@ -794,6 +800,7 @@ AVXcode: 3
>  61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
>  62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
>  63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
> +cc: sha1rnds4 Vdq,Wdq,Ib
>  df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
>  f0: RORX Gy,Ey,Ib (F2),(v)
>  EndTable
> -- 
> 1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/