This is the mail archive of the
binutils@sourceware.org
mailing list for the binutils project.
Re: [PATCH] Allow setting CpuVRex bit in .arch directive
- From: "H.J. Lu" <hjl dot tools at gmail dot com>
- To: Jakub Jelinek <jakub at redhat dot com>
- Cc: Binutils <binutils at sourceware dot org>, Uros Bizjak <ubizjak at gmail dot com>, Kirill Yukhin <kirill dot yukhin at gmail dot com>
- Date: Tue, 24 May 2016 10:24:11 -0700
- Subject: Re: [PATCH] Allow setting CpuVRex bit in .arch directive
- Authentication-results: sourceware.org; auth=none
- References: <20160521165405 dot GQ28550 at tucnak dot redhat dot com> <20160521170615 dot GE1875 at tucnak dot redhat dot com>
On Sat, May 21, 2016 at 10:06 AM, Jakub Jelinek <jakub@redhat.com> wrote:
> Hi!
>
> On Sat, May 21, 2016 at 06:54:05PM +0200, Jakub Jelinek wrote:
>> I've tried today to check for the various AVX512* ISA issues in GCC
>> using assembly .arch support. Seems by default all flags (but l10m/k10m)
>> are set, but if I want to allow all insns but say AVX512DQ ISA instructions
>> or something similar, there is no way to do it - there is no way except
>> for explicit no* flags to remove ISA bits from the default, so one has to
>> set some CPU and then add all the ISA flags one wants. Seems most of them
>> can be added, except for one very important one - the CpuVRex bit.
>>
>> Here is a patch to add support for .arch .vrex to set that, another option
>> might be to set CpuVRex whenever CpuAVX512F is set in 64-bit mode.
>> Any preferences?
Do you have a testcase to show how CpuVRex is used?
> BTW, to my surprise, I haven't found any issues in the compiler this way,
> even the known ones that I've just fixed.
> E.g.
> .arch corei7
> .arch .avx512f
> .arch .avx512vl
> vinserti32x4 $0x0, %xmm0, %ymm15, %ymm15
> vinserti32x4 $0x1, %xmm0, %ymm15, %ymm15
> vinserti64x2 $0x0, %xmm0, %ymm15, %ymm15
> vinserti64x2 $0x1, %xmm0, %ymm15, %ymm15
> vinsertf32x4 $0x0, %xmm0, %ymm15, %ymm15
> vinsertf32x4 $0x1, %xmm0, %ymm15, %ymm15
> vinsertf64x2 $0x0, %xmm0, %ymm15, %ymm15
> vinsertf64x2 $0x1, %xmm0, %ymm15, %ymm15
> assembles fine, even when it IMHO should not - the 64x2 instructions
> are all AVX512VL & AVX512DQ.
>
Since vinsertf64x2 is an CpuAVX512VL instruction, I don't see
why it shouldn't assemble.
--
H.J.