svga: rework the FS white fragments code

When we forcibly write white to FS outputs (for XOR mode emulation)
we were using a temp register.  But that's not really necessary.
This also fixes the case of writing white to multiple color buffers.

Subsequent changes will build on this.

Reviewed-by: Charmaine Lee <charmainel@vmware.com>

diff --git a/src/gallium/drivers/svga/svga_state_fs.c b/src/gallium/drivers/svga/svga_state_fs.c
index 07a3614d79d7b33124ac494701b57e67ce615f6e..bf452163049f0f59a1d81bf2753fd328fdfb7561 100644 (file)
--- a/src/gallium/drivers/svga/svga_state_fs.c
+++ b/src/gallium/drivers/svga/svga_state_fs.c
@@ -232,9 +232,7 @@ make_fs_key(const struct svga_context *svga,
     *   
     * SVGA_NEW_BLEND
     */
-   if (svga->curr.blend->need_white_fragments) {
-      key->fs.white_fragments = 1;
-   }
+   key->fs.white_fragments = svga->curr.blend->need_white_fragments;
 
 #ifdef DEBUG
    /*
@@ -349,9 +347,10 @@ make_fs_key(const struct svga_context *svga,
       }
    }
 
-   /* SVGA_NEW_FRAME_BUFFER */
-   if (fs->base.info.properties[TGSI_PROPERTY_FS_COLOR0_WRITES_ALL_CBUFS]) {
-      /* Replicate color0 output to N colorbuffers */
+   /* SVGA_NEW_FRAME_BUFFER | SVGA_NEW_BLEND */
+   if (fs->base.info.properties[TGSI_PROPERTY_FS_COLOR0_WRITES_ALL_CBUFS] ||
+       svga->curr.blend->need_white_fragments) {
+      /* Replicate color0 output (or white) to N colorbuffers */
       key->fs.write_color0_to_n_cbufs = svga->curr.framebuffer.nr_cbufs;
    }
 

diff --git a/src/gallium/drivers/svga/svga_tgsi_vgpu10.c b/src/gallium/drivers/svga/svga_tgsi_vgpu10.c
index d9b76c265ab862724e0c8e4af3e32c2b6b24be86..9f5cd4b285bae52b61d64c039d323c2f07855a9c 100644 (file)
--- a/src/gallium/drivers/svga/svga_tgsi_vgpu10.c
+++ b/src/gallium/drivers/svga/svga_tgsi_vgpu10.c
@@ -2707,7 +2707,6 @@ emit_temporaries_declaration(struct svga_shader_emitter_v10 *emit)
    }
    else if (emit->unit == PIPE_SHADER_FRAGMENT) {
       if (emit->key.fs.alpha_func != SVGA3D_CMP_ALWAYS ||
-          emit->key.fs.white_fragments ||
           emit->key.fs.write_color0_to_n_cbufs > 1) {
          /* Allocate a temp to hold the output color */
          emit->fs.color_tmp_index = total_temps;
@@ -6414,11 +6413,9 @@ emit_alpha_test_instructions(struct svga_shader_emitter_v10 *emit,
    emit_src_register(emit, &tmp_src_x);
    end_emit_instruction(emit);
 
-   /* If we don't need to broadcast the color below or set fragments to
-    * white, emit final color here.
+   /* If we don't need to broadcast the color below, emit the final color here.
     */
-   if (emit->key.fs.write_color0_to_n_cbufs <= 1 &&
-       !emit->key.fs.white_fragments) {
+   if (emit->key.fs.write_color0_to_n_cbufs <= 1) {
       /* MOV output.color, tempcolor */
       emit_instruction_op1(emit, VGPU10_OPCODE_MOV, &color_dst,
                            &color_src, FALSE);     /* XXX saturate? */
@@ -6428,23 +6425,6 @@ emit_alpha_test_instructions(struct svga_shader_emitter_v10 *emit,
 }
 
 
-/**
- * When we need to emit white for all fragments (for emulating XOR logicop
- * mode), this function copies white into the temporary color output register.
- */
-static void
-emit_set_color_white(struct svga_shader_emitter_v10 *emit,
-                     unsigned fs_color_tmp_index)
-{
-   struct tgsi_full_dst_register color_dst =
-      make_dst_temp_reg(fs_color_tmp_index);
-   struct tgsi_full_src_register white =
-      make_immediate_reg_float(emit, 1.0f);
-
-   emit_instruction_op1(emit, VGPU10_OPCODE_MOV, &color_dst, &white, FALSE);
-}
-
-
 /**
  * Emit instructions for writing a single color output to multiple
  * color buffers.
@@ -6460,8 +6440,17 @@ emit_broadcast_color_instructions(struct svga_shader_emitter_v10 *emit,
 {
    const unsigned n = emit->key.fs.write_color0_to_n_cbufs;
    unsigned i;
-   struct tgsi_full_src_register color_src =
-      make_src_temp_reg(fs_color_tmp_index);
+   struct tgsi_full_src_register color_src;
+
+   if (emit->key.fs.white_fragments) {
+      /* set all color outputs to white */
+      color_src = make_immediate_reg_float(emit, 1.0f);
+   }
+   else {
+      /* set all color outputs to TEMP[fs_color_tmp_index] */
+      assert(fs_color_tmp_index != INVALID_INDEX);
+      color_src = make_src_temp_reg(fs_color_tmp_index);
+   }
 
    assert(emit->unit == PIPE_SHADER_FRAGMENT);
 
@@ -6497,6 +6486,9 @@ emit_post_helpers(struct svga_shader_emitter_v10 *emit)
    else if (emit->unit == PIPE_SHADER_FRAGMENT) {
       const unsigned fs_color_tmp_index = emit->fs.color_tmp_index;
 
+      assert(!(emit->key.fs.white_fragments &&
+               emit->key.fs.write_color0_to_n_cbufs == 0));
+
       /* We no longer want emit_dst_register() to substitute the
        * temporary fragment color register for the real color output.
        */
@@ -6505,9 +6497,6 @@ emit_post_helpers(struct svga_shader_emitter_v10 *emit)
       if (emit->key.fs.alpha_func != SVGA3D_CMP_ALWAYS) {
          emit_alpha_test_instructions(emit, fs_color_tmp_index);
       }
-      if (emit->key.fs.white_fragments) {
-         emit_set_color_white(emit, fs_color_tmp_index);
-      }
       if (emit->key.fs.write_color0_to_n_cbufs > 1 ||
           emit->key.fs.white_fragments) {
          emit_broadcast_color_instructions(emit, fs_color_tmp_index);