Haswell significantly improved the performance of sampler_c messages,
but the optimization appears to be off by default. Later platforms
remove this bit, and apparently always enable the optimization.
Improves performance in "Counter Strike: Global Offensive" by 18%
at default settings on Iris Pro. No Piglit regressions.
Signed-off-by: Kenneth Graunke <kenneth@xxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_reg.h | 1 +
drivers/gpu/drm/i915/intel_pm.c | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 77fce96..340821a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5952,6 +5952,7 @@ enum punit_power_well {
#define HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE (1 << 6)
#define HALF_SLICE_CHICKEN3 0xe184
+#define HSW_SAMPLE_C_PERFORMANCE (1<<9)
#define GEN8_CENTROID_PIXEL_OPT_DIS (1<<8)
#define GEN8_SAMPLER_POWER_BYPASS_DIS (1<<1)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7a69eba..50c72a7 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5736,6 +5736,10 @@ static void haswell_init_clock_gating(struct drm_device *dev)
I915_WRITE(GEN7_GT_MODE,
GEN6_WIZ_HASHING_MASK | GEN6_WIZ_HASHING_16x4);
+ /* Make sample_c messages faster. */
+ I915_WRITE(HALF_SLICE_CHICKEN3,
+ _MASKED_BIT_ENABLE(HSW_SAMPLE_C_PERFORMANCE));
+
/* WaSwitchSolVfFArbitrationPriority:hsw */
I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | HSW_ECOCHK_ARB_PRIO_SOL);
--
2.1.2
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
