[Mesa-dev] [PATCH 3/8] i965/vec4: Add the ability to suppress register spilling.

[Paul Berry]

In future patches, this will allow us to first try compiling a
geometry shader in DUAL_OBJECT mode (which is more efficient but uses
more registers) and then if spilling is required, fall back on
DUAL_INSTANCED mode.
---
 src/mesa/drivers/dri/i965/brw_vec4.h                      | 9 ++++++++-
 src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp         | 7 ++++---
 src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.h           | 3 ++-
 src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp       | 5 ++++-
 src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp            | 5 +++--
 src/mesa/drivers/dri/i965/brw_vec4_vs_visitor.cpp         | 2 +-
 src/mesa/drivers/dri/i965/test_vec4_register_coalesce.cpp | 2 +-
 7 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_vec4.h b/src/mesa/drivers/dri/i965/brw_vec4.h
index f99fdfa..fc8804f 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4.h
+++ b/src/mesa/drivers/dri/i965/brw_vec4.h
@@ -232,7 +232,8 @@ public:
 		struct gl_shader_program *shader_prog,
 		struct brw_shader *shader,
 		void *mem_ctx,
-                bool debug_flag);
+                bool debug_flag,
+                bool no_spills);
    ~vec4_visitor();
 
    dst_reg dst_null_f()
@@ -531,6 +532,12 @@ protected:
    virtual int compute_array_stride(ir_dereference_array *ir);
 
    const bool debug_flag;
+
+private:
+   /**
+    * If true, then register allocation should fail instead of spilling.
+    */
+   const bool no_spills;
 };
 
 
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
index bd13082..8d8f20e 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp
@@ -37,10 +37,11 @@ vec4_gs_visitor::vec4_gs_visitor(struct brw_context *brw,
                                  struct brw_gs_compile *c,
                                  struct gl_shader_program *prog,
                                  struct brw_shader *shader,
-                                 void *mem_ctx)
+                                 void *mem_ctx,
+                                 bool no_spills)
    : vec4_visitor(brw, &c->base, &c->gp->program.Base, &c->key.base,
                   &c->prog_data.base, prog, shader, mem_ctx,
-                  INTEL_DEBUG & DEBUG_GS),
+                  INTEL_DEBUG & DEBUG_GS, no_spills),
      c(c)
 {
 }
@@ -562,7 +563,7 @@ brw_gs_emit(struct brw_context *brw,
       printf("\n\n");
    }
 
-   vec4_gs_visitor v(brw, c, prog, shader, mem_ctx);
+   vec4_gs_visitor v(brw, c, prog, shader, mem_ctx, false /* no_spills */);
    if (!v.run()) {
       prog->LinkStatus = false;
       ralloc_strcat(&prog->InfoLog, v.fail_msg);
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.h b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.h
index bdcb415..f7ca5f0 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.h
+++ b/src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.h
@@ -81,7 +81,8 @@ public:
                    struct brw_gs_compile *c,
                    struct gl_shader_program *prog,
                    struct brw_shader *shader,
-                   void *mem_ctx);
+                   void *mem_ctx,
+                   bool no_spills);
 
 protected:
    virtual dst_reg *make_reg_for_system_value(ir_variable *ir);
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp b/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp
index 3777027..807c2f3 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp
@@ -214,7 +214,10 @@ vec4_visitor::reg_allocate()
        * loop back into here to try again.
        */
       int reg = choose_spill_reg(g);
-      if (reg == -1) {
+      if (this->no_spills) {
+         fail("Failure to register allocate.  Reduce number of live "
+              "values to avoid this.");
+      } else if (reg == -1) {
          fail("no register to spill\n");
       } else {
          spill_reg(reg);
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
index 231815f..ecc6fe6 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_visitor.cpp
@@ -3143,8 +3143,9 @@ vec4_visitor::vec4_visitor(struct brw_context *brw,
 			   struct gl_shader_program *shader_prog,
 			   struct brw_shader *shader,
 			   void *mem_ctx,
-                           bool debug_flag)
-   : debug_flag(debug_flag)
+                           bool debug_flag,
+                           bool no_spills)
+   : debug_flag(debug_flag), no_spills(no_spills)
 {
    this->brw = brw;
    this->ctx = &brw->ctx;
diff --git a/src/mesa/drivers/dri/i965/brw_vec4_vs_visitor.cpp b/src/mesa/drivers/dri/i965/brw_vec4_vs_visitor.cpp
index 1f5cc25..31c42c4 100644
--- a/src/mesa/drivers/dri/i965/brw_vec4_vs_visitor.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_vs_visitor.cpp
@@ -215,7 +215,7 @@ vec4_vs_visitor::vec4_vs_visitor(struct brw_context *brw,
                                  void *mem_ctx)
    : vec4_visitor(brw, &vs_compile->base, &vs_compile->vp->program.Base,
                   &vs_compile->key.base, &vs_prog_data->base, prog, shader,
-                  mem_ctx, INTEL_DEBUG & DEBUG_VS),
+                  mem_ctx, INTEL_DEBUG & DEBUG_VS, false /* no_spills */),
      vs_compile(vs_compile),
      vs_prog_data(vs_prog_data)
 {
diff --git a/src/mesa/drivers/dri/i965/test_vec4_register_coalesce.cpp b/src/mesa/drivers/dri/i965/test_vec4_register_coalesce.cpp
index ab4498b..c5a3cfc 100644
--- a/src/mesa/drivers/dri/i965/test_vec4_register_coalesce.cpp
+++ b/src/mesa/drivers/dri/i965/test_vec4_register_coalesce.cpp
@@ -49,7 +49,7 @@ public:
    register_coalesce_vec4_visitor(struct brw_context *brw,
                                   struct gl_shader_program *shader_prog)
       : vec4_visitor(brw, NULL, NULL, NULL, NULL, shader_prog, NULL, NULL,
-                     false)
+                     false, false /* no_spills */)
    {
    }
 
-- 
1.8.4.1