intel/compiler: Do image load/store lowering to NIR

This commit moves our storage image format conversion codegen into NIR
instead of doing it in the back-end.  This has the advantage of letting
us run it through NIR's optimizer which is pretty effective at shrinking
things down.  In the common case of rgba8, the number of instructions
emitted after NIR is done with it is half of what it was with the
lowering happening in the back-end.  On the downside, the back-end's
lowering is able to directly use predicates and the NIR lowering has to
use IFs.

Shader-db results on Kaby Lake:

    total instructions in shared programs: 15166910 -> 15166872 (<.01%)
    instructions in affected programs: 5895 -> 5857 (-0.64%)
    helped: 15
    HURT: 0

Clearly, we don't have that much image_load_store happening in the
shaders in shader-db....

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

src/compiler/nir/nir_intrinsics.py

@@ -312,6 +312,15 @@ intrinsic("image_deref_atomic_fadd",  src_comp=[1, 4, 1, 1], dest_comp=1)
 intrinsic("image_deref_size",    src_comp=[1], dest_comp=0, flags=[CAN_ELIMINATE, CAN_REORDER])
 intrinsic("image_deref_samples", src_comp=[1], dest_comp=1, flags=[CAN_ELIMINATE, CAN_REORDER])
 
+# Intel-specific query for loading from the brw_image_param struct passed
+# into the shader as a uniform.  The variable is a deref to the image
+# variable. The const index specifies which of the six parameters to load.
+intrinsic("image_deref_load_param_intel", src_comp=[1], dest_comp=0,
+          indices=[BASE], flags=[CAN_ELIMINATE, CAN_REORDER])
+intrinsic("image_deref_load_raw_intel", src_comp=[1, 1], dest_comp=0,
+          flags=[CAN_ELIMINATE])
+intrinsic("image_deref_store_raw_intel", src_comp=[1, 1, 0])
+
 # Vulkan descriptor set intrinsics
 #
 # The Vulkan API uses a different binding model from GL.  In the Vulkan