Re: [Qemu-devel] [Bug 1594069] [NEW] SIMD instructions translated to scalar host instructions

[Peter Maydell]

On 19 June 2016 at 06:33, Timothy Pearson  wrote:
> Public bug reported:
>
> SIMD instructions inside the guest (NEON, MMX, SSE, SSE2, AVX) are
> translated to scalar instructions on the host instead of SIMD
> instructions.  It appears that there have been a few efforts to rectify
> this [1], and even a submitted patch series, but all discussion has
> effectively died out [2].
>
> I would like to see better SIMD performance on qemu, especially as
> non-x86 architectures are becoming widely used (e.g. ARM).

I agree it would be nice, but I'm not sure there's much benefit
from filing a bug about it. Bug reports don't magically become
code changes, and doing SIMD-to-SIMD is very difficult when
you need to support multiple host and guest architectures and
get all the details and corner cases correct. QEMU as it stands
isn't behaving wrongly.

thanks
-- PMM

[Qemu-devel] [Bug 1594069] [NEW] SIMD instructions translated to scalar host instructions

[Timothy Pearson]

Public bug reported:

SIMD instructions inside the guest (NEON, MMX, SSE, SSE2, AVX) are
translated to scalar instructions on the host instead of SIMD
instructions.  It appears that there have been a few efforts to rectify
this [1], and even a submitted patch series, but all discussion has
effectively died out [2].

I would like to see better SIMD performance on qemu, especially as
non-x86 architectures are becoming widely used (e.g. ARM).

[1] 
http://dl.acm.org/citation.cfm?id=2757098=ACM=DL=633095244=12352103
[2] https://lists.nongnu.org/archive/html/qemu-devel/2014-10/msg01720.html

** Affects: qemu
 Importance: Undecided
 Status: New

-- 
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1594069

Title:
  SIMD instructions translated to scalar host instructions

Status in QEMU:
  New

Bug description:
  SIMD instructions inside the guest (NEON, MMX, SSE, SSE2, AVX) are
  translated to scalar instructions on the host instead of SIMD
  instructions.  It appears that there have been a few efforts to
  rectify this [1], and even a submitted patch series, but all
  discussion has effectively died out [2].

  I would like to see better SIMD performance on qemu, especially as
  non-x86 architectures are becoming widely used (e.g. ARM).

  [1] 
http://dl.acm.org/citation.cfm?id=2757098=ACM=DL=633095244=12352103
  [2] https://lists.nongnu.org/archive/html/qemu-devel/2014-10/msg01720.html

To manage notifications about this bug go to:
https://bugs.launchpad.net/qemu/+bug/1594069/+subscriptions