i965/fs: Allow spilling for SIMD16 compute shaders

For fragment shaders, we can always use a SIMD8 program. Therefore, if
we detect spilling with a SIMD16 program, then it is better to skip
generating a SIMD16 program to only rely on a SIMD8 program.

Unfortunately, this doesn't work for compute shaders. For a compute
shader, we may be required to use SIMD16 if the local workgroup size
is bigger than a certain size. For example, on gen7, if the local
workgroup size is larger than 512, then a SIMD16 program is required.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93840
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Cc: "11.2" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
(cherry picked from commit e1d54b1ba5)

src/mesa/drivers/dri/i965/brw_fs.cpp

@@ -5228,7 +5228,7 @@ fs_visitor::allocate_registers()
        * SIMD8.  There's probably actually some intermediate point where
        * SIMD16 with a couple of spills is still better.
        */
-      if (dispatch_width == 16) {
+      if (dispatch_width == 16 && min_dispatch_width <= 8) {
          fail("Failure to register allocate.  Reduce number of "
               "live scalar values to avoid this.");
       } else {

src/mesa/drivers/dri/i965/brw_fs.h

@@ -407,6 +407,7 @@ public:
    bool spilled_any_registers;
 
    const unsigned dispatch_width; /**< 8 or 16 */
+   unsigned min_dispatch_width;
 
    int shader_time_index;
 

src/mesa/drivers/dri/i965/brw_fs_visitor.cpp

@@ -1021,6 +1021,18 @@ fs_visitor::init()
       unreachable("unhandled shader stage");
    }
 
+   if (stage == MESA_SHADER_COMPUTE) {
+      const brw_cs_prog_data *cs_prog_data =
+         (const brw_cs_prog_data *) prog_data;
+      unsigned size = cs_prog_data->local_size[0] *
+                      cs_prog_data->local_size[1] *
+                      cs_prog_data->local_size[2];
+      size = DIV_ROUND_UP(size, devinfo->max_cs_threads);
+      min_dispatch_width = size > 16 ? 32 : (size > 8 ? 16 : 8);
+   } else {
+      min_dispatch_width = 8;
+   }
+
    this->prog_data = this->stage_prog_data;
 
    this->failed = false;