intel/fs: Add an UNDEF instruction to avoid excess live ranges

With 8 and 16-bit types and anything where we have to use non-trivial
strides registersto deal with restrictions, we end up with things that
look like partial writes even though we don't care about any values in
the register except those written by that instruction.  This is
particularly important when dealing with loops because liveness sees
is_partial_write and the fact that an old version from a previous loop
iteration may be valid at that point and extends all purely partially
written values to the entire loop.

This commit adds a new UNDEF instruction which does nothing (the
generator doesn't emit anything) but which does a fake write to the
register.  This informs liveness that we don't care about any values
before that point so it won't consider those registers to be falsely
live.  We can safely emit UNDEF instructions for all SSA values that
come in from NIR and nearly all temporaries generated by various stages
of the compiler.  In particular, we need to insert UNDEF instructions
when we handle region restrictions because the newly allocated registers
are almost guaranteed to be partially written.

No shader-db changes.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110432
Reviewed-by: Matt Turner <[email protected]>

1 files changed, 3 insertions, 0 deletions

diff --git a/src/intel/compiler/brw_shader.cpp b/src/intel/compiler/brw_shader.cpp
index 1f98bd08224..2061afc1c24 100644
--- a/src/intel/compiler/brw_shader.cpp
+++ b/src/intel/compiler/brw_shader.cpp
@@ -217,6 +217,9 @@ brw_instruction_name(const struct gen_device_info *devinfo, enum opcode op)
    case SHADER_OPCODE_SEND:
       return "send";
 
+   case SHADER_OPCODE_UNDEF:
+      return "undef";
+
    case SHADER_OPCODE_TEX:
       return "tex";
    case SHADER_OPCODE_TEX_LOGICAL: