[Mesa-dev] [PATCH 4/7] i965: Make use of gl_transform_feedback_info::ComponentOffset.

[Paul Berry]

---
 src/mesa/drivers/dri/i965/brw_gs.c         |    9 +++++++++
 src/mesa/drivers/dri/i965/brw_gs.h         |    7 +++++++
 src/mesa/drivers/dri/i965/brw_gs_emit.c    |    2 +-
 src/mesa/drivers/dri/i965/gen7_sol_state.c |    2 ++
 4 files changed, 19 insertions(+), 1 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_gs.c b/src/mesa/drivers/dri/i965/brw_gs.c
index 850d7b4..f9c4f6a 100644
--- a/src/mesa/drivers/dri/i965/brw_gs.c
+++ b/src/mesa/drivers/dri/i965/brw_gs.c
@@ -154,6 +154,13 @@ static void compile_gs_prog( struct brw_context *brw,
 static void populate_key( struct brw_context *brw,
 			  struct brw_gs_prog_key *key )
 {
+   static const unsigned swizzle_for_offset[4] = {
+      BRW_SWIZZLE4(0, 1, 2, 3),
+      BRW_SWIZZLE4(1, 2, 3, 3),
+      BRW_SWIZZLE4(2, 3, 3, 3),
+      BRW_SWIZZLE4(3, 3, 3, 3)
+   };
+
    struct gl_context *ctx = &brw->intel.ctx;
    struct intel_context *intel = &brw->intel;
 
@@ -207,6 +214,8 @@ static void populate_key( struct brw_context *brw,
          for (i = 0; i < key->num_transform_feedback_bindings; ++i) {
             key->transform_feedback_bindings[i] =
                linked_xfb_info->Outputs[i].OutputRegister;
+            key->transform_feedback_swizzles[i] =
+               swizzle_for_offset[linked_xfb_info->Outputs[i].ComponentOffset];
          }
       }
       /* On Gen6, GS is also used for rasterizer discard. */
diff --git a/src/mesa/drivers/dri/i965/brw_gs.h b/src/mesa/drivers/dri/i965/brw_gs.h
index 2ab8b72..f2597c8 100644
--- a/src/mesa/drivers/dri/i965/brw_gs.h
+++ b/src/mesa/drivers/dri/i965/brw_gs.h
@@ -63,6 +63,13 @@ struct brw_gs_prog_key {
     * entry.
     */
    unsigned char transform_feedback_bindings[BRW_MAX_SOL_BINDINGS];
+
+   /**
+    * Map from the index of a transform feedback binding table entry to the
+    * swizzles that should be used when streaming out data through that
+    * binding table entry.
+    */
+   unsigned char transform_feedback_swizzles[BRW_MAX_SOL_BINDINGS];
 };
 
 struct brw_gs_compile {
diff --git a/src/mesa/drivers/dri/i965/brw_gs_emit.c b/src/mesa/drivers/dri/i965/brw_gs_emit.c
index 4074501..501cee4 100644
--- a/src/mesa/drivers/dri/i965/brw_gs_emit.c
+++ b/src/mesa/drivers/dri/i965/brw_gs_emit.c
@@ -448,7 +448,7 @@ gen6_sol_program(struct brw_gs_compile *c, struct brw_gs_prog_key *key,
             vertex_slot.subnr = (slot % 2) * 16;
             /* gl_PointSize is stored in VERT_RESULT_PSIZ.w. */
             vertex_slot.dw1.bits.swizzle = vert_result == VERT_RESULT_PSIZ
-               ? BRW_SWIZZLE_WWWW : BRW_SWIZZLE_NOOP;
+               ? BRW_SWIZZLE_WWWW : key->transform_feedback_swizzles[binding];
             brw_set_access_mode(p, BRW_ALIGN_16);
             brw_MOV(p, stride(c->reg.header, 4, 4, 1),
                     retype(vertex_slot, BRW_REGISTER_TYPE_UD));
diff --git a/src/mesa/drivers/dri/i965/gen7_sol_state.c b/src/mesa/drivers/dri/i965/gen7_sol_state.c
index df6b9ee..674e14f 100644
--- a/src/mesa/drivers/dri/i965/gen7_sol_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sol_state.c
@@ -129,6 +129,8 @@ upload_3dstate_so_decl_list(struct brw_context *brw,
       if (vert_result == VERT_RESULT_PSIZ) {
          assert(linked_xfb_info->Outputs[i].NumComponents == 1);
          component_mask <<= 3;
+      } else {
+         component_mask <<= linked_xfb_info->Outputs[i].ComponentOffset;
       }
 
       buffer_mask |= 1 << buffer;
-- 
1.7.6.4