[Mesa-dev] [PATCH] i965: Flush pipeline on EndTransformFeedback.
Paul Berry
stereotype441 at gmail.com
Wed Dec 14 14:54:45 PST 2011
A common use case for transform feedback is to perform one draw
operation that writes transform feedback output to a buffer, followed
by a second draw operation that consumes that buffer as vertex input.
Since vertex input is consumed at an earlier pipeline stage than
writing transform feedback output, we need to flush the pipeline to
ensure that the transform feedback output is completely written before
the data is consumed.
In an ideal world, we would do some dependency tracking, so that we
would only flush the pipeline if the next draw call was about to
consume data generated by a previous draw call in the same batch.
However, since we don't have that sort of dependency tracking
infrastructure right now, we just unconditionally flush the buffer
every time glEndTransformFeedback() is called. This will cause a
performance hit compared to the ideal case (since we will sometimes
flush the pipeline unnecessarily), but fortunately the performance hit
will be confined to circumstances where transform feedback is in use.
---
Ken pointed out to me on IRC that in my last attempt at this patch, I
neglected to back out bogus the extra argument I added to
brwInitDriverFunctions(). This fixes that. I now believe the only
differences between my proposal and Ken's are:
- I'm not doing "if (intel->gen < 6) return;" because I believe that
we will need to do this flush on every platform that supports
transform feedback, not just Gen6.
- I'm calling the function that does the flush
"brw_end_transform_feedback" instead of
"gen6_end_transform_feedback", because it's no longer a
gen6-specific function.
Hopefully I haven't made any other gaffes this time.
src/mesa/drivers/dri/i965/brw_context.c | 1 +
src/mesa/drivers/dri/i965/brw_context.h | 5 +++++
src/mesa/drivers/dri/i965/gen6_sol.c | 16 ++++++++++++++++
3 files changed, 22 insertions(+), 0 deletions(-)
diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c
index eb68bf4..7d360b0 100644
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -117,6 +117,7 @@ static void brwInitDriverFunctions( struct dd_function_table *functions )
brw_init_queryobj_functions(functions);
functions->PrepareExecBegin = brwPrepareExecBegin;
+ functions->EndTransformFeedback = brw_end_transform_feedback;
}
bool
diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index da1de02..8e52488 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -1071,6 +1071,11 @@ void brw_init_surface_formats(struct brw_context *brw);
bool
brw_fprog_uses_noperspective(const struct gl_fragment_program *fprog);
+/* gen6_sol.c */
+void
+brw_end_transform_feedback(struct gl_context *ctx,
+ struct gl_transform_feedback_object *obj);
+
/*======================================================================
diff --git a/src/mesa/drivers/dri/i965/gen6_sol.c b/src/mesa/drivers/dri/i965/gen6_sol.c
index 48f0bfe..b11bce2 100644
--- a/src/mesa/drivers/dri/i965/gen6_sol.c
+++ b/src/mesa/drivers/dri/i965/gen6_sol.c
@@ -28,6 +28,7 @@
#include "brw_context.h"
#include "intel_buffer_objects.h"
+#include "intel_batchbuffer.h"
#include "brw_defines.h"
static void
@@ -98,3 +99,18 @@ const struct brw_tracked_state gen6_sol_surface = {
},
.emit = brw_update_sol_surfaces,
};
+
+void
+brw_end_transform_feedback(struct gl_context *ctx,
+ struct gl_transform_feedback_object *obj)
+{
+ /* After EndTransformFeedback, it's likely that the client program will try
+ * to draw using the contents of the transform feedback buffer as vertex
+ * input. In order for this to work, we need to flush the data through at
+ * least the GS stage of the pipeline, and flush out the render cache. For
+ * simplicity, just do a full flush.
+ */
+ struct brw_context *brw = brw_context(ctx);
+ struct intel_context *intel = &brw->intel;
+ intel_batchbuffer_emit_mi_flush(intel);
+}
--
1.7.6.4
More information about the mesa-dev
mailing list