RFC: Radeon multi ring support branch

2011-11-20 Thread Jerome Glisse
On Fri, Nov 18, 2011 at 11:34 AM, Jerome Glisse wrote: > On Fri, Nov 18, 2011 at 07:44:19AM -0500, Alex Deucher wrote: >> 2011/11/17 Alex Deucher : >> > 2011/11/17 Christian K?nig : >> >> On 16.11.2011 01:24, Jerome Glisse wrote: >> >>> >> >>> Well as we don't specify on which value semaphore

Re: RFC: Radeon multi ring support branch

2011-11-20 Thread Jerome Glisse
On Fri, Nov 18, 2011 at 11:34 AM, Jerome Glisse j.gli...@gmail.com wrote: On Fri, Nov 18, 2011 at 07:44:19AM -0500, Alex Deucher wrote: 2011/11/17 Alex Deucher alexdeuc...@gmail.com: 2011/11/17 Christian König deathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we

RFC: Radeon multi ring support branch

2011-11-18 Thread Christian König
On 17.11.2011 17:58, Jerome Glisse wrote: > 2011/11/17 Christian K?nig: >> On 16.11.2011 01:24, Jerome Glisse wrote: >>> Well as we don't specify on which value semaphore should wait on, i am >>> prety sure the first ring to increment the semaphore will unblock all >>> waiter. So if you have ring1

RFC: Radeon multi ring support branch

2011-11-18 Thread Jerome Glisse
On Fri, Nov 18, 2011 at 07:44:19AM -0500, Alex Deucher wrote: > 2011/11/17 Alex Deucher : > > 2011/11/17 Christian K?nig : > >> On 16.11.2011 01:24, Jerome Glisse wrote: > >>> > >>> Well as we don't specify on which value semaphore should wait on, i am > >>> prety sure the first ring to increment

RFC: Radeon multi ring support branch

2011-11-18 Thread Jerome Glisse
On Fri, Nov 18, 2011 at 09:21:50AM -0500, Jerome Glisse wrote: > 2011/11/18 Christian K?nig : > > On 17.11.2011 17:58, Jerome Glisse wrote: > >> > >> 2011/11/17 Christian K?nig: > >>> > >>> On 16.11.2011 01:24, Jerome Glisse wrote: > > Well as we don't specify on which value semaphore

RFC: Radeon multi ring support branch

2011-11-18 Thread Jerome Glisse
2011/11/18 Christian K?nig : > On 17.11.2011 17:58, Jerome Glisse wrote: >> >> 2011/11/17 Christian K?nig: >>> >>> On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore

RFC: Radeon multi ring support branch

2011-11-18 Thread Alex Deucher
2011/11/17 Alex Deucher : > 2011/11/17 Christian K?nig : >> On 16.11.2011 01:24, Jerome Glisse wrote: >>> >>> Well as we don't specify on which value semaphore should wait on, i am >>> prety sure the first ring to increment the semaphore will unblock all >>> waiter. So if you have ring1 that want

Re: RFC: Radeon multi ring support branch

2011-11-18 Thread Alex Deucher
2011/11/17 Alex Deucher alexdeuc...@gmail.com: 2011/11/17 Christian König deathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So

Re: RFC: Radeon multi ring support branch

2011-11-18 Thread Jerome Glisse
2011/11/18 Christian König deathsim...@vodafone.de: On 17.11.2011 17:58, Jerome Glisse wrote: 2011/11/17 Christian Königdeathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to

Re: RFC: Radeon multi ring support branch

2011-11-18 Thread Jerome Glisse
On Fri, Nov 18, 2011 at 09:21:50AM -0500, Jerome Glisse wrote: 2011/11/18 Christian König deathsim...@vodafone.de: On 17.11.2011 17:58, Jerome Glisse wrote: 2011/11/17 Christian Königdeathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which

RFC: Radeon multi ring support branch

2011-11-17 Thread Alex Deucher
2011/11/17 Christian K?nig : > On 16.11.2011 01:24, Jerome Glisse wrote: >> >> Well as we don't specify on which value semaphore should wait on, i am >> prety sure the first ring to increment the semaphore will unblock all >> waiter. So if you have ring1 that want to wait on ring2 and ring3 as

RFC: Radeon multi ring support branch

2011-11-17 Thread Jerome Glisse
2011/11/17 Christian K?nig : > On 16.11.2011 01:24, Jerome Glisse wrote: >> >> Well as we don't specify on which value semaphore should wait on, i am >> prety sure the first ring to increment the semaphore will unblock all >> waiter. So if you have ring1 that want to wait on ring2 and ring3 as

Re: RFC: Radeon multi ring support branch

2011-11-17 Thread Christian König
On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So if you have ring1 that want to wait on ring2 and ring3 as soon as ring2 or ring3 is done ring1 will

Re: RFC: Radeon multi ring support branch

2011-11-17 Thread Jerome Glisse
2011/11/17 Christian König deathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So if you have ring1 that want to wait on ring2

Re: RFC: Radeon multi ring support branch

2011-11-17 Thread Alex Deucher
2011/11/17 Christian König deathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So if you have ring1 that want to wait on ring2

RFC: Radeon multi ring support branch

2011-11-16 Thread Christian König
On 15.11.2011 20:32, Jerome Glisse wrote: > On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: >> Hello everybody, >> >> to support multiple compute rings, async DMA engines and UVD we need >> to teach the radeon kernel module how to sync buffers between >> different rings and make

RFC: Radeon multi ring support branch

2011-11-15 Thread Jerome Glisse
2011/11/15 Christian K?nig : > On 15.11.2011 20:32, Jerome Glisse wrote: >> >> On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: >>> >>> Hello everybody, >>> >>> to support multiple compute rings, async DMA engines and UVD we need >>> to teach the radeon kernel module how to sync

RFC: Radeon multi ring support branch

2011-11-15 Thread Jerome Glisse
On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: > Hello everybody, > > to support multiple compute rings, async DMA engines and UVD we need > to teach the radeon kernel module how to sync buffers between > different rings and make some changes to the command submission > ioctls.

Re: RFC: Radeon multi ring support branch

2011-11-15 Thread Jerome Glisse
On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes to the command submission ioctls.

Re: RFC: Radeon multi ring support branch

2011-11-15 Thread Christian König
On 15.11.2011 20:32, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes

Re: RFC: Radeon multi ring support branch

2011-11-15 Thread Jerome Glisse
2011/11/15 Christian König deathsim...@vodafone.de: On 15.11.2011 20:32, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync

RFC: Radeon multi ring support branch

2011-11-02 Thread Christian König
On 31.10.2011 16:05, Jerome Glisse wrote: > On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: >> Hello everybody, >> >> to support multiple compute rings, async DMA engines and UVD we need >> to teach the radeon kernel module how to sync buffers between >> different rings and make

RFC: Radeon multi ring support branch

2011-11-02 Thread Jerome Glisse
On Wed, Nov 02, 2011 at 11:12:42AM +0100, Christian K?nig wrote: > On 31.10.2011 16:05, Jerome Glisse wrote: > >On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: > >>Hello everybody, > >> > >>to support multiple compute rings, async DMA engines and UVD we need > >>to teach the

Re: RFC: Radeon multi ring support branch

2011-11-02 Thread Christian König
On 31.10.2011 16:05, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes

Re: RFC: Radeon multi ring support branch

2011-11-02 Thread Jerome Glisse
On Wed, Nov 02, 2011 at 11:12:42AM +0100, Christian König wrote: On 31.10.2011 16:05, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module

RFC: Radeon multi ring support branch

2011-10-31 Thread Jerome Glisse
On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian K?nig wrote: > Hello everybody, > > to support multiple compute rings, async DMA engines and UVD we need > to teach the radeon kernel module how to sync buffers between > different rings and make some changes to the command submission > ioctls.

Re: RFC: Radeon multi ring support branch

2011-10-31 Thread Jerome Glisse
On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes to the command submission ioctls.

RFC: Radeon multi ring support branch

2011-10-29 Thread Christian König
Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes to the command submission ioctls. Since we can't release any documentation about async DMA or UVD (yet), my

RFC: Radeon multi ring support branch

2011-10-29 Thread Christian König
Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes to the command submission ioctls. Since we can't release any documentation about async DMA or UVD (yet),