radeonsi: disable CE by default

It makes performance worse by a very small (hard to measure) amount.
We've done extensive profiling of this feature internally.

Cc: 17.1 17.2 <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Acked-by: Christian König <[email protected]>

3 files changed, 21 insertions, 8 deletions

diff --git a/src/gallium/drivers/radeon/r600_pipe_common.c b/src/gallium/drivers/radeon/r600_pipe_common.c
index 95458d2e15b..960b59c5b29 100644
--- a/src/gallium/drivers/radeon/r600_pipe_common.c
+++ b/src/gallium/drivers/radeon/r600_pipe_common.c
@@ -775,6 +775,7 @@ static const struct debug_named_value common_debug_options[] = {
 	{ "norbplus", DBG_NO_RB_PLUS, "Disable RB+." },
 	{ "sisched", DBG_SI_SCHED, "Enable LLVM SI Machine Instruction Scheduler." },
 	{ "mono", DBG_MONOLITHIC_SHADERS, "Use old-style monolithic shaders compiled on demand" },
+	{ "ce", DBG_CE, "Force enable the constant engine" },
 	{ "noce", DBG_NO_CE, "Disable the constant engine"},
 	{ "unsafemath", DBG_UNSAFE_MATH, "Enable unsafe math shader optimizations" },
 	{ "nodccfb", DBG_NO_DCC_FB, "Disable separate DCC on the main framebuffer" },
diff --git a/src/gallium/drivers/radeon/r600_pipe_common.h b/src/gallium/drivers/radeon/r600_pipe_common.h
index 67b3c874f4d..14bc63ed2ba 100644
--- a/src/gallium/drivers/radeon/r600_pipe_common.h
+++ b/src/gallium/drivers/radeon/r600_pipe_common.h
@@ -65,12 +65,12 @@
 #define R600_PRIM_RECTANGLE_LIST	PIPE_PRIM_MAX
 
 /* Debug flags. */
-/* logging */
+/* logging and features */
 #define DBG_TEX			(1 << 0)
 #define DBG_NIR			(1 << 1)
 #define DBG_COMPUTE		(1 << 2)
 #define DBG_VM			(1 << 3)
-/* gap - reuse */
+#define DBG_CE			(1 << 4)
 /* shader logging */
 #define DBG_FS			(1 << 5)
 #define DBG_VS			(1 << 6)
diff --git a/src/gallium/drivers/radeonsi/si_pipe.c b/src/gallium/drivers/radeonsi/si_pipe.c
index 2c65cc886fb..cac1d015593 100644
--- a/src/gallium/drivers/radeonsi/si_pipe.c
+++ b/src/gallium/drivers/radeonsi/si_pipe.c
@@ -201,12 +201,24 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
 	sctx->b.gfx.cs = ws->cs_create(sctx->b.ctx, RING_GFX,
 				       si_context_gfx_flush, sctx);
 
-	/* SI + AMDGPU + CE = GPU hang */
-	if (!(sscreen->b.debug_flags & DBG_NO_CE) && ws->cs_add_const_ib &&
-	    sscreen->b.chip_class != SI &&
-	    /* These can't use CE due to a power gating bug in the kernel. */
-	    sscreen->b.family != CHIP_CARRIZO &&
-	    sscreen->b.family != CHIP_STONEY) {
+	bool enable_ce = sscreen->b.chip_class != SI && /* SI hangs */
+			 /* These can't use CE due to a power gating bug in the kernel. */
+			 sscreen->b.family != CHIP_CARRIZO &&
+			 sscreen->b.family != CHIP_STONEY;
+
+	/* CE is currently disabled by default, because it makes s_load latency
+	 * worse, because CE IB doesn't run in lockstep with DE.
+	 * Remove this line after that performance issue has been resolved.
+	 */
+	enable_ce = false;
+
+	/* Apply CE overrides. */
+	if (sscreen->b.debug_flags & DBG_NO_CE)
+		enable_ce = false;
+	else if (sscreen->b.debug_flags & DBG_CE)
+		enable_ce = true;
+
+	if (ws->cs_add_const_ib && enable_ce) {
 		sctx->ce_ib = ws->cs_add_const_ib(sctx->b.gfx.cs);
 		if (!sctx->ce_ib)
 			goto fail;