Displaying 4 results from an estimated 4 matches for "lwait_for_data".
2016 Jan 14
4
RFC: non-temporal fencing in LLVM IR
...example from here:
> >
> >
> http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.den0024a/CJACGJJF.html
> >
> > Which is correct?
>
> FWIW, I agree with John here. The example I'd give for the unexpected
> behaviour allowed in the spec is:
>
> .Lwait_for_data:
> ldr x0, [x3]
> cbz x0, .Lwait_for_data
> ldnp x2, x1, [x0]
>
> where another thread first writes to a buffer then tells us where that
> buffer is. For a normal ldp, the address dependency rule means we
> don't need a barrier or acquiring load to ensure we see...
2016 Jan 14
2
RFC: non-temporal fencing in LLVM IR
...center.arm.com/help/index.jsp?topic=/com.arm.doc.den0024a/CJACGJJF.html
>>> >
>>> > Which is correct?
>>>
>>> FWIW, I agree with John here. The example I'd give for the unexpected
>>> behaviour allowed in the spec is:
>>>
>>> .Lwait_for_data:
>>> ldr x0, [x3]
>>> cbz x0, .Lwait_for_data
>>> ldnp x2, x1, [x0]
>>>
>>> where another thread first writes to a buffer then tells us where that
>>> buffer is. For a normal ldp, the address dependency rule means we
>>> don...
2016 Jan 13
2
RFC: non-temporal fencing in LLVM IR
On Wed, Jan 13, 2016 at 10:32 AM, John Brawn <John.Brawn at arm.com> wrote:
> *What about non-x86 architectures?*
>
>
>
> Architectures such as ARMv8 support non-temporal instructions and require
> barriers such as DMB nshld to order loads and DMB nshst to order stores.
>
>
>
> Even ARM's address-dependency rule (a.k.a. the ill-fated
>
2016 Jan 14
2
RFC: non-temporal fencing in LLVM IR
...a/CJACGJJF.html
>>>>> >
>>>>> > Which is correct?
>>>>>
>>>>> FWIW, I agree with John here. The example I'd give for the unexpected
>>>>> behaviour allowed in the spec is:
>>>>>
>>>>> .Lwait_for_data:
>>>>> ldr x0, [x3]
>>>>> cbz x0, .Lwait_for_data
>>>>> ldnp x2, x1, [x0]
>>>>>
>>>>> where another thread first writes to a buffer then tells us where that
>>>>> buffer is. For a normal ldp, the a...