[Mesa-dev] [PATCH v2 32/52] intel/eu: Make automatic exec sizes a configurable option

[Jason Ekstrand]

We have had a feature in codegen for some time that tries to
automatically infer the execution size of an instruction from the width
of its destination.  For things such as fixed function GS, clipper, and
SF programs, this is very useful because they tend to have lots of
hand-rolled register setup and trying to specify the exec size all the
time would be prohibitive.  For things that come from a higher-level IR,
however, it's easier to just set the right size all the time and the
automatic exec sizes can, in fact, cause problems.  This commit makes it
optional while enabling it by default.
---
 src/intel/compiler/brw_eu.c      |  1 +
 src/intel/compiler/brw_eu.h      | 10 ++++++++++
 src/intel/compiler/brw_eu_emit.c | 32 ++++++++++++++++++--------------
 3 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/src/intel/compiler/brw_eu.c b/src/intel/compiler/brw_eu.c
index b0bdc38..bc297a2 100644
--- a/src/intel/compiler/brw_eu.c
+++ b/src/intel/compiler/brw_eu.c
@@ -296,6 +296,7 @@ brw_init_codegen(const struct gen_device_info *devinfo,
    memset(p, 0, sizeof(*p));
 
    p->devinfo = devinfo;
+   p->automatic_exec_sizes = true;
    /*
     * Set the initial instruction store array size to 1024, if found that
     * isn't enough, then it will double the store size at brw_next_insn()
diff --git a/src/intel/compiler/brw_eu.h b/src/intel/compiler/brw_eu.h
index 8e597b2..8abebeb 100644
--- a/src/intel/compiler/brw_eu.h
+++ b/src/intel/compiler/brw_eu.h
@@ -65,6 +65,16 @@ struct brw_codegen {
    bool compressed_stack[BRW_EU_MAX_INSN_STACK];
    brw_inst *current;
 
+   /** Whether or not the user wants automatic exec sizes
+    *
+    * If true, codegen will try to automatically infer the exec size of an
+    * instruction from the width of the destination register.  If false, it
+    * will take whatever is set by brw_set_default_exec_size verbatim.
+    *
+    * This is set to true by default in brw_init_codegen.
+    */
+   bool automatic_exec_sizes;
+
    bool single_program_flow;
    const struct gen_device_info *devinfo;
 
diff --git a/src/intel/compiler/brw_eu_emit.c b/src/intel/compiler/brw_eu_emit.c
index dc0be9a..679832a 100644
--- a/src/intel/compiler/brw_eu_emit.c
+++ b/src/intel/compiler/brw_eu_emit.c
@@ -141,22 +141,26 @@ brw_set_dest(struct brw_codegen *p, brw_inst *inst, struct brw_reg dest)
 
    /* Generators should set a default exec_size of either 8 (SIMD4x2 or SIMD8)
     * or 16 (SIMD16), as that's normally correct.  However, when dealing with
-    * small registers, we automatically reduce it to match the register size.
-    *
-    * In platforms that support fp64 we can emit instructions with a width of
-    * 4 that need two SIMD8 registers and an exec_size of 8 or 16. In these
-    * cases we need to make sure that these instructions have their exec sizes
-    * set properly when they are emitted and we can't rely on this code to fix
-    * it.
+    * small registers, it can be useful for us toautomatically reduce it to
+    * match the register size.
     */
-   bool fix_exec_size;
-   if (devinfo->gen >= 6)
-      fix_exec_size = dest.width < BRW_EXECUTE_4;
-   else
-      fix_exec_size = dest.width < BRW_EXECUTE_8;
+   if (p->automatic_exec_sizes) {
+      /*
+       * In platforms that support fp64 we can emit instructions with a width
+       * of 4 that need two SIMD8 registers and an exec_size of 8 or 16. In
+       * these cases we need to make sure that these instructions have their
+       * exec sizes set properly when they are emitted and we can't rely on
+       * this code to fix it.
+       */
+      bool fix_exec_size;
+      if (devinfo->gen >= 6)
+         fix_exec_size = dest.width < BRW_EXECUTE_4;
+      else
+         fix_exec_size = dest.width < BRW_EXECUTE_8;
 
-   if (fix_exec_size)
-      brw_inst_set_exec_size(devinfo, inst, dest.width);
+      if (fix_exec_size)
+         brw_inst_set_exec_size(devinfo, inst, dest.width);
+   }
 }
 
 void
-- 
2.5.0.400.gff86faf