[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [qemu-s390x] [Qemu-devel] [PATCH v1 08/33] s390x/tcg: Implement VECT
|
From: |
Richard Henderson |
|
Subject: |
Re: [qemu-s390x] [Qemu-devel] [PATCH v1 08/33] s390x/tcg: Implement VECTOR LOAD |
|
Date: |
Thu, 28 Feb 2019 08:34:33 -0800 |
|
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Thunderbird/60.4.0 |
On 2/27/19 11:48 PM, David Hildenbrand wrote:
> I think that would be wrong. It is only an alignment hint.
>
> "Setting the alignment hint to a non-zero value
> that doesn’t correspond to the alignment of the second operand may
> reduce performance on some models."
>
> So we must not inject an exception when unaligned. This, however would
> be the result of MO_ALIGN,, right?
Ah, I didn't get that an alignment exception is not raised. (I do find that
odd. If the user is asserting a given alignment, why would we not tell him if
he is wrong?)
So, yes, ignore all of this from me -- leave MO_ALIGN off.
r~
[qemu-s390x] [PATCH v1 05/33] s390x/tcg: Implement VECTOR GATHER ELEMENT, David Hildenbrand, 2019/02/26
[qemu-s390x] [PATCH v1 12/33] s390x/tcg: Implement VECTOR LOAD GR FROM VR ELEMENT, David Hildenbrand, 2019/02/26
[qemu-s390x] [PATCH v1 20/33] s390x/tcg: Implement VECTOR PACK, David Hildenbrand, 2019/02/26
[qemu-s390x] [PATCH v1 15/33] s390x/tcg: Implement VECTOR LOAD TO BLOCK BOUNDARY, David Hildenbrand, 2019/02/26