From mboxrd@z Thu Jan  1 00:00:00 1970
From: Olivier Galibert <galibert@pobox.com>
Subject: [PATCH 2/9] intel gen4-5: simplify the bfc copy in the
	sf.
Date: Thu, 19 Jul 2012 22:00:17 +0200
Message-ID: <1342728024-15055-3-git-send-email-galibert@pobox.com>
References: <1342728024-15055-1-git-send-email-galibert@pobox.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org>
In-Reply-To: <1342728024-15055-1-git-send-email-galibert@pobox.com>
List-Unsubscribe: <http://lists.freedesktop.org/mailman/options/intel-gfx>,
	<mailto:intel-gfx-request@lists.freedesktop.org?subject=unsubscribe>
List-Archive: <http://lists.freedesktop.org/archives/intel-gfx>
List-Post: <mailto:intel-gfx@lists.freedesktop.org>
List-Help: <mailto:intel-gfx-request@lists.freedesktop.org?subject=help>
List-Subscribe: <http://lists.freedesktop.org/mailman/listinfo/intel-gfx>,
	<mailto:intel-gfx-request@lists.freedesktop.org?subject=subscribe>
Sender: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org
Errors-To: intel-gfx-bounces+gcfxdi-intel-gfx=m.gmane.org@lists.freedesktop.org
To: intel-gfx@lists.freedesktop.org, mesa-dev@lists.freedesktop.org
Cc: Olivier Galibert <galibert@pobox.com>
List-Id: intel-gfx@lists.freedesktop.org

This patch is mostly designed to make followup patches simpler, but
it's a simplification by itself.

Signed-off-by: Olivier Galibert <galibert@pobox.com>
---
 src/mesa/drivers/dri/i965/brw_sf_emit.c |   93 +++++++++++++++++--------------
 1 file changed, 52 insertions(+), 41 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_sf_emit.c b/src/mesa/drivers/dri/i965/brw_sf_emit.c
index ff6383b..9d8aa38 100644
--- a/src/mesa/drivers/dri/i965/brw_sf_emit.c
+++ b/src/mesa/drivers/dri/i965/brw_sf_emit.c
@@ -79,24 +79,9 @@ have_attr(struct brw_sf_compile *c, GLuint attr)
 /*********************************************************************** 
  * Twoside lighting
  */
-static void copy_bfc( struct brw_sf_compile *c,
-		      struct brw_reg vert )
-{
-   struct brw_compile *p = &c->func;
-   GLuint i;
-
-   for (i = 0; i < 2; i++) {
-      if (have_attr(c, VERT_RESULT_COL0+i) &&
-	  have_attr(c, VERT_RESULT_BFC0+i))
-	 brw_MOV(p, 
-		 get_vert_result(c, vert, VERT_RESULT_COL0+i),
-		 get_vert_result(c, vert, VERT_RESULT_BFC0+i));
-   }
-}
-
-
 static void do_twoside_color( struct brw_sf_compile *c )
 {
+   GLuint i, need_0, need_1;
    struct brw_compile *p = &c->func;
    GLuint backface_conditional = c->key.frontface_ccw ? BRW_CONDITIONAL_G : BRW_CONDITIONAL_L;
 
@@ -105,12 +90,14 @@ static void do_twoside_color( struct brw_sf_compile *c )
    if (c->key.primitive == SF_UNFILLED_TRIS)
       return;
 
-   /* XXX: What happens if BFC isn't present?  This could only happen
-    * for user-supplied vertex programs, as t_vp_build.c always does
-    * the right thing.
+   /* If the vertex shader provides both front and backface color, do
+    * the selection.  Otherwise the generated code will pick up
+    * whichever there is.
     */
-   if (!(have_attr(c, VERT_RESULT_COL0) && have_attr(c, VERT_RESULT_BFC0)) &&
-       !(have_attr(c, VERT_RESULT_COL1) && have_attr(c, VERT_RESULT_BFC1)))
+   need_0 = have_attr(c, VERT_RESULT_COL0) && have_attr(c, VERT_RESULT_BFC0);
+   need_1 = have_attr(c, VERT_RESULT_COL1) && have_attr(c, VERT_RESULT_BFC1);
+
+   if (!need_0 && !need_1)
       return;
    
    /* Need to use BRW_EXECUTE_4 and also do an 4-wide compare in order
@@ -121,12 +108,15 @@ static void do_twoside_color( struct brw_sf_compile *c )
    brw_push_insn_state(p);
    brw_CMP(p, vec4(brw_null_reg()), backface_conditional, c->det, brw_imm_f(0));
    brw_IF(p, BRW_EXECUTE_4);
-   {
-      switch (c->nr_verts) {
-      case 3: copy_bfc(c, c->vert[2]);
-      case 2: copy_bfc(c, c->vert[1]);
-      case 1: copy_bfc(c, c->vert[0]);
-      }
+   for (i=0; i<c->nr_verts; i++) {
+      if (need_0)
+	 brw_MOV(p, 
+		 get_vert_result(c, c->vert[i], VERT_RESULT_COL0),
+		 get_vert_result(c, c->vert[i], VERT_RESULT_BFC0));
+      if (need_1)
+	 brw_MOV(p, 
+		 get_vert_result(c, c->vert[i], VERT_RESULT_COL1),
+		 get_vert_result(c, c->vert[i], VERT_RESULT_BFC1));
    }
    brw_ENDIF(p);
    brw_pop_insn_state(p);
@@ -139,20 +129,27 @@ static void do_twoside_color( struct brw_sf_compile *c )
  */
 
 #define VERT_RESULT_COLOR_BITS (BITFIELD64_BIT(VERT_RESULT_COL0) | \
-				BITFIELD64_BIT(VERT_RESULT_COL1))
+                                BITFIELD64_BIT(VERT_RESULT_COL1))
 
 static void copy_colors( struct brw_sf_compile *c,
 		     struct brw_reg dst,
-		     struct brw_reg src)
+                     struct brw_reg src,
+                     int allow_twoside)
 {
    struct brw_compile *p = &c->func;
    GLuint i;
 
    for (i = VERT_RESULT_COL0; i <= VERT_RESULT_COL1; i++) {
-      if (have_attr(c,i))
+      if (have_attr(c,i)) {
 	 brw_MOV(p, 
 		 get_vert_result(c, dst, i),
 		 get_vert_result(c, src, i));
+
+      } else if(allow_twoside && have_attr(c, i - VERT_RESULT_COL0 + VERT_RESULT_BFC0)) {
+	 brw_MOV(p, 
+		 get_vert_result(c, dst, i - VERT_RESULT_COL0 + VERT_RESULT_BFC0),
+		 get_vert_result(c, src, i - VERT_RESULT_COL0 + VERT_RESULT_BFC0));
+      }
    }
 }
 
@@ -167,9 +164,19 @@ static void do_flatshade_triangle( struct brw_sf_compile *c )
    struct brw_compile *p = &c->func;
    struct intel_context *intel = &p->brw->intel;
    struct brw_reg ip = brw_ip_reg();
-   GLuint nr = _mesa_bitcount_64(c->key.attrs & VERT_RESULT_COLOR_BITS);
    GLuint jmpi = 1;
 
+   GLuint nr;
+
+   if (c->key.do_twoside_color) {
+      nr = ((c->key.attrs & (BITFIELD64_BIT(VERT_RESULT_COL0) | BITFIELD64_BIT(VERT_RESULT_BFC0))) != 0) +
+         ((c->key.attrs & (BITFIELD64_BIT(VERT_RESULT_COL1) | BITFIELD64_BIT(VERT_RESULT_BFC1))) != 0);
+
+   } else {
+      nr = ((c->key.attrs & BITFIELD64_BIT(VERT_RESULT_COL0)) != 0) +
+         ((c->key.attrs & BITFIELD64_BIT(VERT_RESULT_COL1)) != 0);
+   }
+
    if (!nr)
       return;
 
@@ -186,16 +193,16 @@ static void do_flatshade_triangle( struct brw_sf_compile *c )
    brw_MUL(p, c->pv, c->pv, brw_imm_d(jmpi*(nr*2+1)));
    brw_JMPI(p, ip, ip, c->pv);
 
-   copy_colors(c, c->vert[1], c->vert[0]);
-   copy_colors(c, c->vert[2], c->vert[0]);
+   copy_colors(c, c->vert[1], c->vert[0], c->key.do_twoside_color);
+   copy_colors(c, c->vert[2], c->vert[0], c->key.do_twoside_color);
    brw_JMPI(p, ip, ip, brw_imm_d(jmpi*(nr*4+1)));
 
-   copy_colors(c, c->vert[0], c->vert[1]);
-   copy_colors(c, c->vert[2], c->vert[1]);
+   copy_colors(c, c->vert[0], c->vert[1], c->key.do_twoside_color);
+   copy_colors(c, c->vert[2], c->vert[1], c->key.do_twoside_color);
    brw_JMPI(p, ip, ip, brw_imm_d(jmpi*nr*2));
 
-   copy_colors(c, c->vert[0], c->vert[2]);
-   copy_colors(c, c->vert[1], c->vert[2]);
+   copy_colors(c, c->vert[0], c->vert[2], c->key.do_twoside_color);
+   copy_colors(c, c->vert[1], c->vert[2], c->key.do_twoside_color);
 
    brw_pop_insn_state(p);
 }
@@ -224,10 +231,10 @@ static void do_flatshade_line( struct brw_sf_compile *c )
    
    brw_MUL(p, c->pv, c->pv, brw_imm_d(jmpi*(nr+1)));
    brw_JMPI(p, ip, ip, c->pv);
-   copy_colors(c, c->vert[1], c->vert[0]);
+   copy_colors(c, c->vert[1], c->vert[0], 0);
 
    brw_JMPI(p, ip, ip, brw_imm_ud(jmpi*nr));
-   copy_colors(c, c->vert[0], c->vert[1]);
+   copy_colors(c, c->vert[0], c->vert[1], 0);
 
    brw_pop_insn_state(p);
 }
@@ -337,13 +344,17 @@ calculate_masks(struct brw_sf_compile *c,
    if (c->key.do_flat_shading)
       persp_mask = c->key.attrs & ~(BITFIELD64_BIT(VERT_RESULT_HPOS) |
                                     BITFIELD64_BIT(VERT_RESULT_COL0) |
-                                    BITFIELD64_BIT(VERT_RESULT_COL1));
+                                    BITFIELD64_BIT(VERT_RESULT_COL1) |
+                                    BITFIELD64_BIT(VERT_RESULT_BFC0) |
+                                    BITFIELD64_BIT(VERT_RESULT_BFC1));
    else
       persp_mask = c->key.attrs & ~(BITFIELD64_BIT(VERT_RESULT_HPOS));
 
    if (c->key.do_flat_shading)
       linear_mask = c->key.attrs & ~(BITFIELD64_BIT(VERT_RESULT_COL0) |
-                                     BITFIELD64_BIT(VERT_RESULT_COL1));
+                                     BITFIELD64_BIT(VERT_RESULT_COL1) |
+                                     BITFIELD64_BIT(VERT_RESULT_BFC0) |
+                                     BITFIELD64_BIT(VERT_RESULT_BFC1));
    else
       linear_mask = c->key.attrs;
 
-- 
1.7.10.280.gaa39