Mesa (master): prog_to_nir: Fix fragment depth writes.

[Kenneth Graunke]

Module: Mesa
Branch: master
Commit: 7b8f20ec5505a25958bcd98aabe73a7ca2b6cbba
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=7b8f20ec5505a25958bcd98aabe73a7ca2b6cbba

Author: Kenneth Graunke <kenneth at whitecape.org>
Date:   Thu Jun  4 17:00:17 2015 -0700

prog_to_nir: Fix fragment depth writes.

In the ARB_fragment_program specification, the result.depth output
variable is treated as a vec4, where the fragment depth is stored in the
.z component, and the other three components are undefined.

This is different than GLSL, which uses a scalar value (gl_FragDepth).

To make this consistent for driver backends, this patch makes
prog_to_nir use a scalar output variable for FRAG_RESULT_DEPTH,
moving result.depth.z into the first component.

Fixes Glean's fragProg1 "Z-write test" subtest.

Cc: mesa-stable at lists.freedesktop.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90000
Signed-off-by: Kenneth Graunke <kenneth at whitecape.org>
Reviewed-by: Matt Turner <mattst88 at gmail.com>

---

 src/mesa/program/prog_to_nir.c |   22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

diff --git a/src/mesa/program/prog_to_nir.c b/src/mesa/program/prog_to_nir.c
index d3e3f15..d54f934 100644
--- a/src/mesa/program/prog_to_nir.c
+++ b/src/mesa/program/prog_to_nir.c
@@ -924,10 +924,23 @@ ptn_add_output_stores(struct ptn_compile *c)
    foreach_list_typed(nir_variable, var, node, &b->shader->outputs) {
       nir_intrinsic_instr *store =
          nir_intrinsic_instr_create(b->shader, nir_intrinsic_store_var);
-      store->num_components = 4;
+      store->num_components = glsl_get_vector_elements(var->type);
       store->variables[0] =
          nir_deref_var_create(store, c->output_vars[var->data.location]);
-      store->src[0].reg.reg = c->output_regs[var->data.location];
+
+      if (c->prog->Target == GL_FRAGMENT_PROGRAM_ARB &&
+          var->data.location == FRAG_RESULT_DEPTH) {
+         /* result.depth has this strange convention of being the .z component of
+          * a vec4 with undefined .xyw components.  We resolve it to a scalar, to
+          * match GLSL's gl_FragDepth and the expectations of most backends.
+          */
+         nir_alu_src alu_src = { NIR_SRC_INIT };
+         alu_src.src = nir_src_for_reg(c->output_regs[FRAG_RESULT_DEPTH]);
+         alu_src.swizzle[0] = SWIZZLE_Z;
+         store->src[0] = nir_src_for_ssa(nir_fmov_alu(b, alu_src, 1));
+      } else {
+         store->src[0].reg.reg = c->output_regs[var->data.location];
+      }
       nir_instr_insert_after_cf_list(c->build.cf_node_list, &store->instr);
    }
 }
@@ -1020,7 +1033,10 @@ setup_registers_and_variables(struct ptn_compile *c)
       reg->num_components = 4;
 
       nir_variable *var = rzalloc(shader, nir_variable);
-      var->type = glsl_vec4_type();
+      if (c->prog->Target == GL_FRAGMENT_PROGRAM_ARB && i == FRAG_RESULT_DEPTH)
+         var->type = glsl_float_type();
+      else
+         var->type = glsl_vec4_type();
       var->data.mode = nir_var_shader_out;
       var->name = ralloc_asprintf(var, "out_%d", i);