* Dave Hansen wrote:
> On 04/30/2016 12:53 AM, Ingo Molnar wrote:
> > We can still use the compacted area handling instructions, because
> > presumably
> > those are the fastest and are also the most optimized ones? But I wouldn't
> > use
> > them to do dynamic
* Dave Hansen wrote:
> On 04/30/2016 12:53 AM, Ingo Molnar wrote:
> > We can still use the compacted area handling instructions, because
> > presumably
> > those are the fastest and are also the most optimized ones? But I wouldn't
> > use
> > them to do dynamic allocation: just allocate the
On 04/30/2016 12:53 AM, Ingo Molnar wrote:
> We can still use the compacted area handling instructions, because presumably
> those are the fastest and are also the most optimized ones? But I wouldn't
> use
> them to do dynamic allocation: just allocate the maximum possible FPU save
> area at
On 04/30/2016 12:53 AM, Ingo Molnar wrote:
> We can still use the compacted area handling instructions, because presumably
> those are the fastest and are also the most optimized ones? But I wouldn't
> use
> them to do dynamic allocation: just allocate the maximum possible FPU save
> area at
* Dave Hansen wrote:
> But I also think it would be pretty nice if 'ls' didn't pay the 2k cost to
> have
> AVX-512 state if it's not using AVX-512. [...]
A C library might decide to use AVX-512 memset(). RAM is cheap, while
allocation
complexity, especially in
* Dave Hansen wrote:
> But I also think it would be pretty nice if 'ls' didn't pay the 2k cost to
> have
> AVX-512 state if it's not using AVX-512. [...]
A C library might decide to use AVX-512 memset(). RAM is cheap, while
allocation
complexity, especially in the kernel, has various other
On 04/29/2016 01:49 PM, Andy Lutomirski wrote:
>> >
>> > But I also think it would be pretty nice if 'ls' didn't pay the 2k cost
>> > to have AVX-512 state if it's not using AVX-512. We also don't have to
>> > do this with CR0.TS. We'd actually use a combination of out-of-line
>> > (not appended
On 04/29/2016 01:49 PM, Andy Lutomirski wrote:
>> >
>> > But I also think it would be pretty nice if 'ls' didn't pay the 2k cost
>> > to have AVX-512 state if it's not using AVX-512. We also don't have to
>> > do this with CR0.TS. We'd actually use a combination of out-of-line
>> > (not appended
On Fri, Apr 29, 2016 at 1:40 PM, Dave Hansen
wrote:
> On 04/29/2016 01:25 PM, Andy Lutomirski wrote:
>> On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
>>> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
That's not
On Fri, Apr 29, 2016 at 1:40 PM, Dave Hansen
wrote:
> On 04/29/2016 01:25 PM, Andy Lutomirski wrote:
>> On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
>>> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
That's not feasible. Think of dynamic libraries or just-in-time
On 04/29/2016 01:25 PM, Andy Lutomirski wrote:
> On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
>> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>>> That's not feasible. Think of dynamic libraries or just-in-time
>>> compilers. What instruction set
On 04/29/2016 01:25 PM, Andy Lutomirski wrote:
> On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
>> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>>> That's not feasible. Think of dynamic libraries or just-in-time
>>> compilers. What instruction set does /usr/bin/java use,
On 04/29/2016 01:07 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>>> That's not feasible. Think of dynamic libraries or just-in-time
>>> compilers. What instruction set does /usr/bin/java use, for
>>> instance? :)
> The java argument is true. In that
On 04/29/2016 01:07 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>>> That's not feasible. Think of dynamic libraries or just-in-time
>>> compilers. What instruction set does /usr/bin/java use, for
>>> instance? :)
> The java argument is true. In that
On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>> That's not feasible. Think of dynamic libraries or just-in-time
>> compilers. What instruction set does /usr/bin/java use, for instance? :)
>
> The java
On Fri, Apr 29, 2016 at 1:07 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
>> That's not feasible. Think of dynamic libraries or just-in-time
>> compilers. What instruction set does /usr/bin/java use, for instance? :)
>
> The java argument is true. In
On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
> That's not feasible. Think of dynamic libraries or just-in-time
> compilers. What instruction set does /usr/bin/java use, for instance? :)
The java argument is true. In that case or when the bitmask is missing, we can
allocate for
On Fri, Apr 29, 2016 at 01:03:43PM -0700, Dave Hansen wrote:
> That's not feasible. Think of dynamic libraries or just-in-time
> compilers. What instruction set does /usr/bin/java use, for instance? :)
The java argument is true. In that case or when the bitmask is missing, we can
allocate for
On 04/29/2016 12:57 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 11:09:23AM -0700, Dave Hansen wrote:
>> Once we *HAVE* XSAVES support, it also opens up the possibilities for
>> doing things like dynamic XSAVE buffer allocation. For instance, let
>> threads that are not _using_ AVX-512 not
On 04/29/2016 12:57 PM, Yu-cheng Yu wrote:
> On Fri, Apr 29, 2016 at 11:09:23AM -0700, Dave Hansen wrote:
>> Once we *HAVE* XSAVES support, it also opens up the possibilities for
>> doing things like dynamic XSAVE buffer allocation. For instance, let
>> threads that are not _using_ AVX-512 not
On Fri, Apr 29, 2016 at 11:09:23AM -0700, Dave Hansen wrote:
> Once we *HAVE* XSAVES support, it also opens up the possibilities for
> doing things like dynamic XSAVE buffer allocation. For instance, let
> threads that are not _using_ AVX-512 not waste the 2k of space for it.
If we can somehow
On Fri, Apr 29, 2016 at 11:09:23AM -0700, Dave Hansen wrote:
> Once we *HAVE* XSAVES support, it also opens up the possibilities for
> doing things like dynamic XSAVE buffer allocation. For instance, let
> threads that are not _using_ AVX-512 not waste the 2k of space for it.
If we can somehow
* Dave Hansen wrote:
> Hi Folks,
>
> I've heard through the grapevine that there's some concern that we
> should not be bothering to enable XSAVES because there's not a
> sufficient use case for it. [...]
So I have no fundamental objections against this series - I
* Dave Hansen wrote:
> Hi Folks,
>
> I've heard through the grapevine that there's some concern that we
> should not be bothering to enable XSAVES because there's not a
> sufficient use case for it. [...]
So I have no fundamental objections against this series - I didn't apply it
back
in
Hi Folks,
I've heard through the grapevine that there's some concern that we
should not be bothering to enable XSAVES because there's not a
sufficient use case for it. Maybe it's meager today, but I still think
we should do it.
I'll try to lay out why.
Today, on every Skylake system, this
Hi Folks,
I've heard through the grapevine that there's some concern that we
should not be bothering to enable XSAVES because there's not a
sufficient use case for it. Maybe it's meager today, but I still think
we should do it.
I'll try to lay out why.
Today, on every Skylake system, this
XSAVES is a kernel-mode instruction. It offers a compacted format and
memory-write optimization. These patches fix known issues in the first
implementation. They are intended for discussion and getting feedback
before actually getting applied.
Version 4 adds a new patch (#9) to fix missing XSAVE
XSAVES is a kernel-mode instruction. It offers a compacted format and
memory-write optimization. These patches fix known issues in the first
implementation. They are intended for discussion and getting feedback
before actually getting applied.
Version 4 adds a new patch (#9) to fix missing XSAVE
28 matches
Mail list logo