Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-30 Thread Nanley Chery
On Mon, Mar 20, 2017 at 08:05:22PM -0700, Nanley Chery wrote: Okay, I've re-read the email. > On Mon, Mar 20, 2017 at 08:01:25PM -0700, Nanley Chery wrote: > > On Thu, Mar 16, 2017 at 05:34:13PM -0700, Kenneth Graunke wrote: > > > On Wednesday, March 8, 2017 10:27:20 AM PDT Nanley Chery wrote:

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-20 Thread Nanley Chery
On Mon, Mar 20, 2017 at 08:01:25PM -0700, Nanley Chery wrote: > On Thu, Mar 16, 2017 at 05:34:13PM -0700, Kenneth Graunke wrote: > > On Wednesday, March 8, 2017 10:27:20 AM PDT Nanley Chery wrote: > > > On Wed, Mar 08, 2017 at 10:07:12AM -0800, Nanley Chery wrote: > > > > On Wed, Mar 08, 2017 at

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-20 Thread Nanley Chery
On Thu, Mar 16, 2017 at 05:34:13PM -0700, Kenneth Graunke wrote: > On Wednesday, March 8, 2017 10:27:20 AM PDT Nanley Chery wrote: > > On Wed, Mar 08, 2017 at 10:07:12AM -0800, Nanley Chery wrote: > > > On Wed, Mar 08, 2017 at 02:17:59AM -0800, Kenneth Graunke wrote: > > > > On Thursday, March 2,

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-16 Thread Kenneth Graunke
On Wednesday, March 8, 2017 10:27:20 AM PDT Nanley Chery wrote: > On Wed, Mar 08, 2017 at 10:07:12AM -0800, Nanley Chery wrote: > > On Wed, Mar 08, 2017 at 02:17:59AM -0800, Kenneth Graunke wrote: > > > On Thursday, March 2, 2017 4:36:08 PM PST Nanley Chery wrote: > > > > On Mon, Feb 06, 2017 at

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-16 Thread Nanley Chery
On Wed, Mar 08, 2017 at 10:27:20AM -0800, Nanley Chery wrote: > On Wed, Mar 08, 2017 at 10:07:12AM -0800, Nanley Chery wrote: > > On Wed, Mar 08, 2017 at 02:17:59AM -0800, Kenneth Graunke wrote: > > > On Thursday, March 2, 2017 4:36:08 PM PST Nanley Chery wrote: > > > > On Mon, Feb 06, 2017 at

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-08 Thread Nanley Chery
On Wed, Mar 08, 2017 at 10:07:12AM -0800, Nanley Chery wrote: > On Wed, Mar 08, 2017 at 02:17:59AM -0800, Kenneth Graunke wrote: > > On Thursday, March 2, 2017 4:36:08 PM PST Nanley Chery wrote: > > > On Mon, Feb 06, 2017 at 03:55:49PM -0800, Kenneth Graunke wrote: > > > > If a HiZ op is the first

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-08 Thread Nanley Chery
On Wed, Mar 08, 2017 at 02:17:59AM -0800, Kenneth Graunke wrote: > On Thursday, March 2, 2017 4:36:08 PM PST Nanley Chery wrote: > > On Mon, Feb 06, 2017 at 03:55:49PM -0800, Kenneth Graunke wrote: > > > If a HiZ op is the first thing in the batch, we should make sure > > > to select the render

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-08 Thread Kenneth Graunke
On Thursday, March 2, 2017 4:36:08 PM PST Nanley Chery wrote: > On Mon, Feb 06, 2017 at 03:55:49PM -0800, Kenneth Graunke wrote: > > If a HiZ op is the first thing in the batch, we should make sure > > to select the render pipeline and emit state base address before > > proceeding. > > > > I

Re: [Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-03-02 Thread Nanley Chery
On Mon, Feb 06, 2017 at 03:55:49PM -0800, Kenneth Graunke wrote: > If a HiZ op is the first thing in the batch, we should make sure > to select the render pipeline and emit state base address before > proceeding. > > I believe 3DSTATE_WM_HZ_OP creates 3DPRIMITIVEs internally, and > dispatching

[Mesa-dev] [PATCH] i965: Select pipeline and emit state base address in Gen8+ HiZ ops.

2017-02-06 Thread Kenneth Graunke
If a HiZ op is the first thing in the batch, we should make sure to select the render pipeline and emit state base address before proceeding. I believe 3DSTATE_WM_HZ_OP creates 3DPRIMITIVEs internally, and dispatching those on the GPGPU pipeline seems a bit sketchy. I'm not actually sure that