Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-12 Thread Mika Kuoppala
Francisco Jerez writes: > Daniel Vetter writes: > >> On Wed, Jan 11, 2017 at 12:24:59PM +, Chris Wilson wrote: >>> On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote: >>> > Daniel Vetter writes: >>> > >>> > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: >>> >

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Francisco Jerez
Daniel Vetter writes: > On Wed, Jan 11, 2017 at 12:24:59PM +, Chris Wilson wrote: >> On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote: >> > Daniel Vetter writes: >> > >> > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: >> > >> The WaDisableLSQCROPERFforOCL w

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Francisco Jerez
Daniel Vetter writes: > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: >> The WaDisableLSQCROPERFforOCL workaround has the side effect of >> disabling an L3SQ optimization that has huge performance implications >> and is unlikely to be necessary for the correct functioning of us

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Daniel Vetter
On Wed, Jan 11, 2017 at 12:24:59PM +, Chris Wilson wrote: > On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote: > > Daniel Vetter writes: > > > > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: > > >> The WaDisableLSQCROPERFforOCL workaround has the side effect o

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Mika Kuoppala
Chris Wilson writes: > On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote: >> Daniel Vetter writes: >> >> > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: >> >> The WaDisableLSQCROPERFforOCL workaround has the side effect of >> >> disabling an L3SQ optimization that

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Chris Wilson
On Wed, Jan 11, 2017 at 02:07:37PM +0200, Mika Kuoppala wrote: > Daniel Vetter writes: > > > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: > >> The WaDisableLSQCROPERFforOCL workaround has the side effect of > >> disabling an L3SQ optimization that has huge performance implicat

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Mika Kuoppala
Daniel Vetter writes: > On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: >> The WaDisableLSQCROPERFforOCL workaround has the side effect of >> disabling an L3SQ optimization that has huge performance implications >> and is unlikely to be necessary for the correct functioning of us

Re: [Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-11 Thread Daniel Vetter
On Mon, Jan 09, 2017 at 01:07:56PM -0800, Francisco Jerez wrote: > The WaDisableLSQCROPERFforOCL workaround has the side effect of > disabling an L3SQ optimization that has huge performance implications > and is unlikely to be necessary for the correct functioning of usual > graphic workloads. Use

[Intel-gfx] [PATCHv2] drm/i915: Remove WaDisableLSQCROPERFforOCL KBL workaround.

2017-01-09 Thread Francisco Jerez
The WaDisableLSQCROPERFforOCL workaround has the side effect of disabling an L3SQ optimization that has huge performance implications and is unlikely to be necessary for the correct functioning of usual graphic workloads. Userspace is free to re-enable the workaround on demand, and is generally in