[Intel-gfx] [PATCH] drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio

[Intel-gfx] [PATCH] drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio

[Chris Wilson]

Due to the latency from impedance mismatch on memory access, as the GPU
gets faster we need to increase the frequency of the ring to offset.

In effect, we are fixing the topmost frequency selection, and scaling
down faster, so that at low frequencies we will be using lower ring
frequencies and conserving power (and in the process make the scaling
fairer, and aim for a linear increase in performance with frequency).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_llc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c
index e3f637b3650e..27196c303cbe 100644
--- a/drivers/gpu/drm/i915/gt/intel_llc.c
+++ b/drivers/gpu/drm/i915/gt/intel_llc.c
@@ -89,7 +89,7 @@ static void calc_ia_freq(struct intel_llc *llc,
 		 * ring_freq = 2 * GT. ring_freq is in 100MHz units
 		 * No floor required for ring frequency on SKL.
 		 */
-		ring_freq = gpu_freq;
+		ring_freq = consts->max_gpu_freq - mult_frac(diff, 5, 4);
 	} else if (INTEL_GEN(i915) >= 8) {
 		/* max(2 * GT, DDR). NB: GT is 50MHz units */
 		ring_freq = max(consts->min_ring_freq, gpu_freq);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

[Intel-gfx] ✗ Fi.CI.BAT: failure for drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio

[Patchwork]

== Series Details ==

Series: drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio
URL   : https://patchwork.freedesktop.org/series/76254/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_8342 -> Patchwork_17401
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_17401 absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_17401, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/index.html

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_17401:

### IGT changes ###

#### Possible regressions ####

  * igt@i915_selftest@live@gt_timelines:
    - fi-snb-2520m:       [PASS][1] -> [FAIL][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-snb-2520m/igt@i915_selftest@live@gt_timelines.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-snb-2520m/igt@i915_selftest@live@gt_timelines.html

  
Known issues
------------

  Here are the changes found in Patchwork_17401 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_selftest@live@perf:
    - fi-bwr-2160:        [PASS][3] -> [INCOMPLETE][4] ([i915#489])
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-bwr-2160/igt@i915_selftest@live@perf.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-bwr-2160/igt@i915_selftest@live@perf.html

  
#### Possible fixes ####

  * igt@i915_selftest@live@gt_pm:
    - fi-icl-u2:          [DMESG-FAIL][5] -> [PASS][6]
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-icl-u2/igt@i915_selftest@live@gt_pm.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-icl-u2/igt@i915_selftest@live@gt_pm.html
    - fi-glk-dsi:         [DMESG-FAIL][7] ([i915#1751]) -> [PASS][8]
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-glk-dsi/igt@i915_selftest@live@gt_pm.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-glk-dsi/igt@i915_selftest@live@gt_pm.html

  
#### Warnings ####

  * igt@i915_selftest@live@gt_pm:
    - fi-tgl-y:           [DMESG-FAIL][9] ([i915#1744]) -> [DMESG-FAIL][10] ([i915#1759])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-tgl-y/igt@i915_selftest@live@gt_pm.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-tgl-y/igt@i915_selftest@live@gt_pm.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [i915#1744]: https://gitlab.freedesktop.org/drm/intel/issues/1744
  [i915#1751]: https://gitlab.freedesktop.org/drm/intel/issues/1751
  [i915#1759]: https://gitlab.freedesktop.org/drm/intel/issues/1759
  [i915#489]: https://gitlab.freedesktop.org/drm/intel/issues/489


Participating hosts (48 -> 43)
------------------------------

  Additional (1): fi-kbl-7560u 
  Missing    (6): fi-cml-u2 fi-hsw-4200u fi-byt-squawks fi-bsw-cyan fi-byt-clapper fi-bdw-samus 


Build changes
-------------

  * CI: CI-20190529 -> None
  * Linux: CI_DRM_8342 -> Patchwork_17401

  CI-20190529: 20190529
  CI_DRM_8342: 17407a9f61a0ee402254522e391a626acc4375ec @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_5602: a8fcccd15dcc2dd409edd23785a2d6f6e85fb682 @ git://anongit.freedesktop.org/xorg/app/intel-gpu-tools
  Patchwork_17401: 3d9b0e649f1e2eeee8e6858a9dda048773dea350 @ git://anongit.freedesktop.org/gfx-ci/linux


== Linux commits ==

3d9b0e649f1e drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/index.html
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Re: ✗ Fi.CI.BAT: failure for drm/i915/gt: Apply a small scalefactor for the gpu:ring ratio

[Chris Wilson]

Quoting Patchwork (2020-04-21 12:37:30)
> ### IGT changes ###
> 
> #### Possible regressions ####
> 
>   * igt@i915_selftest@live@gt_timelines:
>     - fi-snb-2520m:       [PASS][1] -> [FAIL][2]
>    [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-snb-2520m/igt@i915_selftest@live@gt_timelines.html
>    [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-snb-2520m/igt@i915_selftest@live@gt_timelines.html
> 
> #### Possible fixes ####
> 
>   * igt@i915_selftest@live@gt_pm:
>     - fi-icl-u2:          [DMESG-FAIL][5] -> [PASS][6]
>    [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-icl-u2/igt@i915_selftest@live@gt_pm.html
>    [6]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-icl-u2/igt@i915_selftest@live@gt_pm.html
>     - fi-glk-dsi:         [DMESG-FAIL][7] ([i915#1751]) -> [PASS][8]
>    [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_8342/fi-glk-dsi/igt@i915_selftest@live@gt_pm.html
>    [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_17401/fi-glk-dsi/igt@i915_selftest@live@gt_pm.html

Mostly looks like an improvement.
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx