R600/SI: Remove explicit m0 operand from s_sendmsg

Instead add m0 as an implicit operand.  This allows us to avoid using
the M0Reg register class and eliminates a number of unnecessary spills
when using s_sendmsg instructions.  This impacts one shader in the
shader-db:

SGPRS: 48 -> 40 (-16.67 %)
VGPRS: 112 -> 108 (-3.57 %)
Code Size: 40132 -> 38796 (-3.33 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Scratch: 2048 -> 0 (-100.00 %) bytes per wave

llvm-svn: 237133
diff --git a/llvm/lib/Target/R600/AMDGPUISelLowering.h b/llvm/lib/Target/R600/AMDGPUISelLowering.h
index fe657d5..a6bfbbd 100644
--- a/llvm/lib/Target/R600/AMDGPUISelLowering.h
+++ b/llvm/lib/Target/R600/AMDGPUISelLowering.h
@@ -288,6 +288,7 @@
   BUILD_VERTICAL_VECTOR,
   /// Pointer to the start of the shader's constant data.
   CONST_DATA_PTR,
+  SENDMSG,
   FIRST_MEM_OPCODE_NUMBER = ISD::FIRST_TARGET_MEMORY_OPCODE,
   STORE_MSKOR,
   LOAD_CONSTANT,