Re: PATCH: Extend gdb remote protocol for AVX

["H.J. Lu" <hjl.tools@gmail.com>]

On Thu, Oct 2, 2008 at 3:26 AM, Mark Kettenis <mark.kettenis@xs4all.nl> wrote:
>> Date: Thu, 18 Sep 2008 10:27:28 -0700
>> From: "H.J. Lu" <hongjiu.lu@intel.com>
>>
>> Hi,
>>
>> Intel AVX extends 128bit XMM registers to 256bit YMM registers. I
>> am enclosing a propose to add YMM register support in gdb.  Since
>> there is no AVX hardware, we can only implement the remote debug
>> with AVX emulator.
>>
>> This patch extends gdb remote protocol for AVX, based on Daniel's
>> patch to auto-detect ia32 and x86-64 executables:
>>
>> http://sources.redhat.com/ml/gdb-patches/2006-11/msg00056.html
>>
>> I tested it by setting x86_sse_unit to avx in gdbserver/i387-fp.c.  OK
>> to install?
>
> Had some time to learn about AVX yesterday.  I noticed that the %ymm
> registers partially overlap with the %xmm registers, and that while

xmm register is the alias of the lower 128bit of ymm register.

> Intel obviously is trying to deprecate the old SSE stuff, the
> instructions will still be present.  As such, I think the goal:
>
>> 1. Only display YMM registers, no XMM registers if the execution
>> environment supports AVX, independent of executables.
>
> is wrong.  People should still be able to debug traditional SSE code
> even if the execution environment supports AVX.  Since the following
> goals follow from #1:

You can still debug SSE code with my proposal.

>> 2. Native:
>>    a. Check native AVX support at run-time.
>>    b. Use AVX registers only if native environment supports AVX.
>>    Otherwise use XMM registers.
>> 3. Remote:
>>    a. Check remote AVX support when setting up connection.
>>    b. Use AVX registers only if remote environment supports AVX.
>>    Otherwise use XMM registers.
>
> I disagree with those as well.
>
> We probably need to play pseudo-register tricks to make sure %xmm and
> %ymm share the data for the lower 128 bits in the register cache, and
> perhaps some option to choose between showing %xmm, %ymm or both in
> the "info registers" output.
>

The relationship between xmm and ymm is similar to eax and rax.
My proposal only deals with how to access xmm/ymm registers and
doesn't affect other aspects. What does your suggestion will buy us
beyond my proposal?

-- 
H.J.