On Fri, Jul 18, 2014 at 07:00:40PM -0700, Ben Widawsky wrote:
On Fri, Jul 18, 2014 at 02:19:40AM -0700, Rodrigo Vivi wrote:
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic
to do that
is
On Thu, Jul 17, 2014 at 02:31:14PM -0700, Ben Widawsky wrote:
- for_each_ring(useless, dev_priv, i) {
+ for_each_ring(to, dev_priv, i) {
u16 signal_offset =
(GEN8_SIGNAL_OFFSET(ring, i) PAGE_MASK) / 4;
u32 *tmp =
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
* vcs - 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
On Fri, Jul 18, 2014 at 01:39:29AM -0700, Rodrigo Vivi wrote:
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs,
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
* vcs - 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
On Fri, Jul 18, 2014 at 02:05:16AM -0700, Rodrigo Vivi wrote:
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs,
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
* vcs - 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
On Fri, Jul 18, 2014 at 02:19:40AM -0700, Rodrigo Vivi wrote:
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs,
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
* vcs - 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
On Thu, Jul 17, 2014 at 05:35:20AM -0700, Rodrigo Vivi wrote:
semaphore _sync_seqno, _seqno and _mbox are smaller than number of rings.
This optimization is to remove the ring itself from the list and the logic to
do that
is at intel_ring_sync_index as below:
/*
* rcs - 0 = vcs, 1 = bcs,
10 matches
Mail list logo