similar to: IA64 Xen Bi-endian support - Litlle-endian Dom0 + Big-endianDomU

I have been quietly working on a port of LLVM to Stratus VOS. The OS is always big endian (because customers need to migrate data to new hardware quickly and can't afford to convert). This entails presenting a big endian programming model no matter what the hardware does. We did this about 15 years ago with the Stratus compilers and GCC. We offered the GCC changes back to the

On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > vhost is seriously broken with ppc64le guests, even in the supposedly > supported case where the host is ppc64le and we don't need cross-endian > support. > > The TX virtqueue fails to be handled by vhost and falls back to QEMU. > Despite this unexpected scenario where RX is vhost and TX is QEMU, the > guest

On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > vhost is seriously broken with ppc64le guests, even in the supposedly > supported case where the host is ppc64le and we don't need cross-endian > support. > > The TX virtqueue fails to be handled by vhost and falls back to QEMU. > Despite this unexpected scenario where RX is vhost and TX is QEMU, the > guest

On Thu, 12 Mar 2015 09:18:38 +1100 Benjamin Herrenschmidt <benh at kernel.crashing.org> wrote: > On Wed, 2015-03-11 at 23:03 +0100, Greg Kurz wrote: > > > /* The host notifier will be swapped in adjust_endianness() according to the > > * target default endianness. We need to negate this swap if the device uses > > * an endianness that is not the default (ppc64le

On 12/03/2015 08:08, Michael S. Tsirkin wrote: > But common header format is simple, it's always LE. > It does not depend on target. > To me this looks like a bug in memory_region_add_eventfd, > it should do the right thing depending on device > endian-ness. I agree it seems to be a QEMU bug. Paolo

On Thu, 12 Mar 2015 09:18:38 +1100 Benjamin Herrenschmidt <benh at kernel.crashing.org> wrote: > On Wed, 2015-03-11 at 23:03 +0100, Greg Kurz wrote: > > > /* The host notifier will be swapped in adjust_endianness() according to the > > * target default endianness. We need to negate this swap if the device uses > > * an endianness that is not the default (ppc64le

On 12/03/2015 08:08, Michael S. Tsirkin wrote: > But common header format is simple, it's always LE. > It does not depend on target. > To me this looks like a bug in memory_region_add_eventfd, > it should do the right thing depending on device > endian-ness. I agree it seems to be a QEMU bug. Paolo

On Wed, 2015-03-11 at 23:03 +0100, Greg Kurz wrote: > /* The host notifier will be swapped in adjust_endianness() according to the > * target default endianness. We need to negate this swap if the device uses > * an endianness that is not the default (ppc64le for example). > */ > > > > +static uint16_t cpu_to_host_notifier16(VirtIODevice *vdev, uint16_t val) > >

On Wed, 2015-03-11 at 23:03 +0100, Greg Kurz wrote: > /* The host notifier will be swapped in adjust_endianness() according to the > * target default endianness. We need to negate this swap if the device uses > * an endianness that is not the default (ppc64le for example). > */ > > > > +static uint16_t cpu_to_host_notifier16(VirtIODevice *vdev, uint16_t val) > >

On Fri, Jul 31, 2015 at 12:15 AM, Herbie Robinson <HerbieRobinson at verizon.net> wrote: > I have been quietly working on a port of LLVM to Stratus VOS. The OS is > always big endian (because customers need to migrate data to new hardware > quickly and can't afford to convert). This entails presenting a big endian > programming model no matter what the hardware does. We

On Wed, Mar 11, 2015 at 11:03:14PM +0100, Greg Kurz wrote: > On Wed, 11 Mar 2015 21:06:05 +0100 > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > > > vhost is seriously broken with ppc64le guests, even in the supposedly > > > supported case where the host is ppc64le and we don't

On Wed, Mar 11, 2015 at 11:03:14PM +0100, Greg Kurz wrote: > On Wed, 11 Mar 2015 21:06:05 +0100 > "Michael S. Tsirkin" <mst at redhat.com> wrote: > > > On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > > > vhost is seriously broken with ppc64le guests, even in the supposedly > > > supported case where the host is ppc64le and we don't

Hi Guys, We are trying to come up with Bi-Endian(neutral endiness) compiler using the LLVM. For a introduction . http://www.drdobbs.com/architecture-and-design/writing-a-bi-endian-compiler/240003090 Did someone from the group ,aware of such project . Thank you ~Umesh

Hi All - It seems to be an odd scenario. I have a simple ssh command which establishes connection with a UNIX machine and executes some commands over there. When I ran the command from command window, I was able to successfully run them. In reality I wanted the ssh command to be invoked by a windows 2003 service. I tried to debug the ssh command while running from a service and I get the below

vhost is seriously broken with ppc64le guests, even in the supposedly supported case where the host is ppc64le and we don't need cross-endian support. The TX virtqueue fails to be handled by vhost and falls back to QEMU. Despite this unexpected scenario where RX is vhost and TX is QEMU, the guest runs well with reduced upload performances... until you reboot, migrate, managed save or in fact

vhost is seriously broken with ppc64le guests, even in the supposedly supported case where the host is ppc64le and we don't need cross-endian support. The TX virtqueue fails to be handled by vhost and falls back to QEMU. Despite this unexpected scenario where RX is vhost and TX is QEMU, the guest runs well with reduced upload performances... until you reboot, migrate, managed save or in fact

On Wed, 11 Mar 2015 21:06:05 +0100 "Michael S. Tsirkin" <mst at redhat.com> wrote: > On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > > vhost is seriously broken with ppc64le guests, even in the supposedly > > supported case where the host is ppc64le and we don't need cross-endian > > support. > > > > The TX virtqueue fails to be

On Wed, 11 Mar 2015 21:06:05 +0100 "Michael S. Tsirkin" <mst at redhat.com> wrote: > On Wed, Mar 11, 2015 at 07:04:38PM +0100, Greg Kurz wrote: > > vhost is seriously broken with ppc64le guests, even in the supposedly > > supported case where the host is ppc64le and we don't need cross-endian > > support. > > > > The TX virtqueue fails to be

I tried working with the example on customized autocomplete at http://demo.script.aculo.us/ajax/autocompleter_customized. The code is working fine on Internet Explorer. But I had a problem when working with mozilla. The list was getting displayed but the selected value is not getting pasted in the textbox. can anyone help me with this??? Thanks in advance, Veena www.neevtech.com

Hi, I have made a proposal for changes to integrate bi-grams in Xapian Architecture on Wiki page. Bigram Integration Proposal: http://trac.xapian.org/wiki/GSoC2012/Bi-gram%20Language%20Modeling/Bi-gram%20Integration%20Proposal Since Bi-gram integration will make some difference in how data is accessed from the back-end so its better to get review from whole comunity.Moreover i also have some