[Intel-gfx] [PATCH 7/7] drm/i915/gen8: Move HiZ RAW stall optimization disable WA to common init fn

Arun Siluvery arun.siluvery at linux.intel.com
Fri Sep 25 06:23:34 PDT 2015


Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c681c66..fdff606 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -819,6 +819,16 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 	/* Wa4x4STCOptimizationDisable:bdw,chv */
 	WA_SET_BIT_MASKED(CACHE_MODE_1, GEN8_4x4_STC_OPTIMIZATION_DISABLE);
 
+	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
+	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
+	 *  polygons in the same 8x4 pixel/sample area to be processed without
+	 *  stalling waiting for the earlier ones to write to Hierarchical Z
+	 *  buffer."
+	 *
+	 * This optimization is off by default for BDW and CHV; turn it on.
+	 */
+	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
+
 	/*
 	 * BSpec recommends 8x4 when MSAA is used,
 	 * however in practice 16x4 seems fastest.
@@ -865,16 +875,6 @@ static int bdw_init_workarounds(struct intel_engine_cs *ring)
 			  /* WaDisableFenceDestinationToSLM:bdw (pre-prod) */
 			  (IS_BDW_GT3(dev) ? HDC_FENCE_DEST_SLM_DISABLE : 0));
 
-	/* From the Haswell PRM, Command Reference: Registers, CACHE_MODE_0:
-	 * "The Hierarchical Z RAW Stall Optimization allows non-overlapping
-	 *  polygons in the same 8x4 pixel/sample area to be processed without
-	 *  stalling waiting for the earlier ones to write to Hierarchical Z
-	 *  buffer."
-	 *
-	 * This optimization is off by default for Broadwell; turn it on.
-	 */
-	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
 	return 0;
 }
 
@@ -898,11 +898,6 @@ static int chv_init_workarounds(struct intel_engine_cs *ring)
 			  HDC_FORCE_NON_COHERENT |
 			  HDC_DONOT_FETCH_MEM_WHEN_MASKED);
 
-	/* According to the CACHE_MODE_0 default value documentation, some
-	 * CHV platforms disable this optimization by default.  Turn it on.
-	 */
-	WA_CLR_BIT_MASKED(CACHE_MODE_0_GEN7, HIZ_RAW_STALL_OPT_DISABLE);
-
 	/* Improve HiZ throughput on CHV. */
 	WA_SET_BIT_MASKED(HIZ_CHICKEN, CHV_HZ_8X8_MODE_IN_1X);
 
-- 
1.9.1



More information about the Intel-gfx mailing list