| Message ID | 1541477601-10883-1-git-send-email-ankit.p.navik@intel.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | Dynamic EU configuration of Slice/Subslice/EU. | expand |
On 06/11/2018 04:13, Ankit Navik wrote: > drm/i915: Context aware user agnostic EU/Slice/Sub-slice control within kernel > > Current GPU configuration code for i915 does not allow us to change > EU/Slice/Sub-slice configuration dynamically. Its done only once while context > is created. > > While particular graphics application is running, if we examine the command > requests from user space, we observe that command density is not consistent. > It means there is scope to change the graphics configuration dynamically even > while context is running actively. This patch series proposes the solution to > find the active pending load for all active context at given time and based on > that, dynamically perform graphics configuration for each context. > > We use a hr (high resolution) timer with i915 driver in kernel to get a > callback every few milliseconds (this timer value can be configured through > debugfs, default is '0' indicating timer is in disabled state i.e. original > system without any intervention).In the timer callback, we examine pending > commands for a context in the queue, essentially, we intercept them before > they are executed by GPU and we update context with required number of EUs. > > Two questions, how did we arrive at right timer value? and what's the right > number of EUs? For the prior one, empirical data to achieve best performance > in least power was considered. For the later one, we roughly categorized number > of EUs logically based on platform. Now we compare number of pending commands > with a particular threshold and then set number of EUs accordingly with update > context. That threshold is also based on experiments & findings. If GPU is able > to catch up with CPU, typically there are no pending commands, the EU config > would remain unchanged there. In case there are more pending commands we > reprogram context with higher number of EUs. Please note, here we are changing > EUs even while context is running by examining pending commands every 'x' > milliseconds. > > With this solution in place, on KBL-GT3 + Android we saw following pnp > benefits, power numbers mentioned here are system power. > > App /KPI | % Power | > | Benefit | > | (mW) | > ---------------------------------| > 3D Mark (Ice storm) | 2.30% | > TRex On screen | 2.49% | > TRex Off screen | 1.32% | > ManhattanOn screen | 3.11% | > Manhattan Off screen | 0.89% | > AnTuTu 6.1.4 | 3.42% | Were you able to find some benchmarks which regress? Maybe try Synmark2 and more from gfxbench? Not all benchmarks there are equally important, and regressions on some are fine, but I think a fuller set would be interesting to see. Regards, Tvrtko > > Note - For KBL (GEN9) we cannot control at sub-slice level, it was always a > constraint. > We always controlled number of EUs rather than sub-slices/slices. > > Praveen Diwakar (4): > drm/i915: Get active pending request for given context > drm/i915: Update render power clock state configuration for given > context > drm/i915: set optimum eu/slice/sub-slice configuration based on load > type > drm/i915: Predictive governor to control eu/slice/subslice > > drivers/gpu/drm/i915/i915_debugfs.c | 88 +++++++++++++++++++++++++++++- > drivers/gpu/drm/i915/i915_drv.c | 1 + > drivers/gpu/drm/i915/i915_drv.h | 10 ++++ > drivers/gpu/drm/i915/i915_gem_context.c | 26 +++++++++ > drivers/gpu/drm/i915/i915_gem_context.h | 45 +++++++++++++++ > drivers/gpu/drm/i915/i915_gem_execbuffer.c | 5 ++ > drivers/gpu/drm/i915/intel_device_info.c | 44 ++++++++++++++- > drivers/gpu/drm/i915/intel_lrc.c | 20 ++++++- > 8 files changed, 235 insertions(+), 4 deletions(-) >
Hi Tvrtko, > On Wed, Nov 7, 2018 at 4:08 PM Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> wrote: > > > On 06/11/2018 04:13, Ankit Navik wrote: > > drm/i915: Context aware user agnostic EU/Slice/Sub-slice control > > within kernel > > > > Current GPU configuration code for i915 does not allow us to change > > EU/Slice/Sub-slice configuration dynamically. Its done only once while > > context is created. > > > > While particular graphics application is running, if we examine the > > command requests from user space, we observe that command density is not > consistent. > > It means there is scope to change the graphics configuration > > dynamically even while context is running actively. This patch series > > proposes the solution to find the active pending load for all active > > context at given time and based on that, dynamically perform graphics > configuration for each context. > > > > We use a hr (high resolution) timer with i915 driver in kernel to get > > a callback every few milliseconds (this timer value can be configured > > through debugfs, default is '0' indicating timer is in disabled state > > i.e. original system without any intervention).In the timer callback, > > we examine pending commands for a context in the queue, essentially, > > we intercept them before they are executed by GPU and we update context > with required number of EUs. > > > > Two questions, how did we arrive at right timer value? and what's the > > right number of EUs? For the prior one, empirical data to achieve best > > performance in least power was considered. For the later one, we > > roughly categorized number of EUs logically based on platform. Now we > > compare number of pending commands with a particular threshold and > > then set number of EUs accordingly with update context. That threshold > > is also based on experiments & findings. If GPU is able to catch up > > with CPU, typically there are no pending commands, the EU config would > > remain unchanged there. In case there are more pending commands we > > reprogram context with higher number of EUs. Please note, here we are > changing EUs even while context is running by examining pending commands > every 'x' > > milliseconds. > > > > With this solution in place, on KBL-GT3 + Android we saw following pnp > > benefits, power numbers mentioned here are system power. > > > > App /KPI | % Power | > > | Benefit | > > | (mW) | > > ---------------------------------| > > 3D Mark (Ice storm) | 2.30% | > > TRex On screen | 2.49% | > > TRex Off screen | 1.32% | > > ManhattanOn screen | 3.11% | > > Manhattan Off screen | 0.89% | > > AnTuTu 6.1.4 | 3.42% | > > Were you able to find some benchmarks which regress? Maybe try Synmark2 > and more from gfxbench? Not all benchmarks there are equally important, and > regressions on some are fine, but I think a fuller set would be interesting to see. We have not seen much improvement in GFX Carchase, but there was no degradation in performance. Regards, Ankit > > Regards, > > Tvrtko > > > > > Note - For KBL (GEN9) we cannot control at sub-slice level, it was > > always a constraint. > > We always controlled number of EUs rather than sub-slices/slices. > > > > Praveen Diwakar (4): > > drm/i915: Get active pending request for given context > > drm/i915: Update render power clock state configuration for given > > context > > drm/i915: set optimum eu/slice/sub-slice configuration based on load > > type > > drm/i915: Predictive governor to control eu/slice/subslice > > > > drivers/gpu/drm/i915/i915_debugfs.c | 88 > +++++++++++++++++++++++++++++- > > drivers/gpu/drm/i915/i915_drv.c | 1 + > > drivers/gpu/drm/i915/i915_drv.h | 10 ++++ > > drivers/gpu/drm/i915/i915_gem_context.c | 26 +++++++++ > > drivers/gpu/drm/i915/i915_gem_context.h | 45 +++++++++++++++ > > drivers/gpu/drm/i915/i915_gem_execbuffer.c | 5 ++ > > drivers/gpu/drm/i915/intel_device_info.c | 44 ++++++++++++++- > > drivers/gpu/drm/i915/intel_lrc.c | 20 ++++++- > > 8 files changed, 235 insertions(+), 4 deletions(-) > >
drm/i915: Context aware user agnostic EU/Slice/Sub-slice control within kernel Current GPU configuration code for i915 does not allow us to change EU/Slice/Sub-slice configuration dynamically. Its done only once while context is created. While particular graphics application is running, if we examine the command requests from user space, we observe that command density is not consistent. It means there is scope to change the graphics configuration dynamically even while context is running actively. This patch series proposes the solution to find the active pending load for all active context at given time and based on that, dynamically perform graphics configuration for each context. We use a hr (high resolution) timer with i915 driver in kernel to get a callback every few milliseconds (this timer value can be configured through debugfs, default is '0' indicating timer is in disabled state i.e. original system without any intervention).In the timer callback, we examine pending commands for a context in the queue, essentially, we intercept them before they are executed by GPU and we update context with required number of EUs. Two questions, how did we arrive at right timer value? and what's the right number of EUs? For the prior one, empirical data to achieve best performance in least power was considered. For the later one, we roughly categorized number of EUs logically based on platform. Now we compare number of pending commands with a particular threshold and then set number of EUs accordingly with update context. That threshold is also based on experiments & findings. If GPU is able to catch up with CPU, typically there are no pending commands, the EU config would remain unchanged there. In case there are more pending commands we reprogram context with higher number of EUs. Please note, here we are changing EUs even while context is running by examining pending commands every 'x' milliseconds. With this solution in place, on KBL-GT3 + Android we saw following pnp benefits, power numbers mentioned here are system power. App /KPI | % Power | | Benefit | | (mW) | ---------------------------------| 3D Mark (Ice storm) | 2.30% | TRex On screen | 2.49% | TRex Off screen | 1.32% | ManhattanOn screen | 3.11% | Manhattan Off screen | 0.89% | AnTuTu 6.1.4 | 3.42% | Note - For KBL (GEN9) we cannot control at sub-slice level, it was always a constraint. We always controlled number of EUs rather than sub-slices/slices. Praveen Diwakar (4): drm/i915: Get active pending request for given context drm/i915: Update render power clock state configuration for given context drm/i915: set optimum eu/slice/sub-slice configuration based on load type drm/i915: Predictive governor to control eu/slice/subslice drivers/gpu/drm/i915/i915_debugfs.c | 88 +++++++++++++++++++++++++++++- drivers/gpu/drm/i915/i915_drv.c | 1 + drivers/gpu/drm/i915/i915_drv.h | 10 ++++ drivers/gpu/drm/i915/i915_gem_context.c | 26 +++++++++ drivers/gpu/drm/i915/i915_gem_context.h | 45 +++++++++++++++ drivers/gpu/drm/i915/i915_gem_execbuffer.c | 5 ++ drivers/gpu/drm/i915/intel_device_info.c | 44 ++++++++++++++- drivers/gpu/drm/i915/intel_lrc.c | 20 ++++++- 8 files changed, 235 insertions(+), 4 deletions(-)