i965: Optimize batchbuffer macros.

Previously OUT_BATCH was just a macro around an inline function which
does

   brw->batch.map[brw->batch.used++] = dword;

When making consecutive calls to intel_batchbuffer_emit_dword() the
compiler isn't able to recognize that we're writing consecutive memory
locations or that it doesn't need to write batch.used back to memory
each time.

We can avoid both of these problems by making a local pointer to the
next location in the batch in BEGIN_BATCH().

Cuts 18k from the .text size.

   text     data      bss      dec      hex  filename
4946956   195152    26192  5168300   4edcac  i965_dri.so before
4928956   195152    26192  5150300   4e965c  i965_dri.so after

This series (including commit c0433948) improves performance of Synmark
OglBatch7 by 8.01389% +/- 0.63922% (n=83) on Ivybridge.

Reviewed-by: Chris Wilson <[email protected]>

1 files changed, 8 insertions, 4 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c
index e0b55c6b620..c95f0c37f89 100644
--- a/src/mesa/drivers/dri/i965/brw_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c
@@ -604,14 +604,15 @@ brw_prepare_shader_draw_parameters(struct brw_context *brw)
 /**
  * Emit a VERTEX_BUFFER_STATE entry (part of 3DSTATE_VERTEX_BUFFERS).
  */
-static void
+static uint32_t *
 emit_vertex_buffer_state(struct brw_context *brw,
                          unsigned buffer_nr,
                          drm_intel_bo *bo,
                          unsigned bo_ending_address,
                          unsigned bo_offset,
                          unsigned stride,
-                         unsigned step_rate)
+                         unsigned step_rate,
+                         uint32_t *__map)
 {
    struct gl_context *ctx = &brw->ctx;
    uint32_t dw0;
@@ -643,7 +644,10 @@ emit_vertex_buffer_state(struct brw_context *brw,
       OUT_BATCH(0);
    }
    OUT_BATCH(step_rate);
+
+   return __map;
 }
+#define EMIT_VERTEX_BUFFER_STATE(...) __map = emit_vertex_buffer_state(__VA_ARGS__, __map)
 
 static void brw_emit_vertices(struct brw_context *brw)
 {
@@ -704,14 +708,14 @@ static void brw_emit_vertices(struct brw_context *brw)
       OUT_BATCH((_3DSTATE_VERTEX_BUFFERS << 16) | (4 * nr_buffers - 1));
       for (i = 0; i < brw->vb.nr_buffers; i++) {
 	 struct brw_vertex_buffer *buffer = &brw->vb.buffers[i];
-         emit_vertex_buffer_state(brw, i, buffer->bo, buffer->bo->size - 1,
+         EMIT_VERTEX_BUFFER_STATE(brw, i, buffer->bo, buffer->bo->size - 1,
                                   buffer->offset, buffer->stride,
                                   buffer->step_rate);
 
       }
 
       if (brw->vs.prog_data->uses_vertexid) {
-         emit_vertex_buffer_state(brw, brw->vb.nr_buffers,
+         EMIT_VERTEX_BUFFER_STATE(brw, brw->vb.nr_buffers,
                                   brw->draw.draw_params_bo,
                                   brw->draw.draw_params_bo->size - 1,
                                   brw->draw.draw_params_offset,