nir: Optimize mask+downcast to just downcast

[mesa.git] / src / compiler / nir / nir_builder_opcodes_h.py

diff --git a/src/compiler/nir/nir_builder_opcodes_h.py b/src/compiler/nir/nir_builder_opcodes_h.py
index 72cf5b4549da6d1d127d146377e9024b90b33a8e..2c37be7c20ee7f5e65ea8528f09b18a7468fb6aa 100644 (file)
--- a/src/compiler/nir/nir_builder_opcodes_h.py
+++ b/src/compiler/nir/nir_builder_opcodes_h.py
@@ -31,35 +31,82 @@ def src_decl_list(num_srcs):
    return ', '.join('nir_ssa_def *src' + str(i) for i in range(num_srcs))
 
 def src_list(num_srcs):
-   return ', '.join('src' + str(i) if i < num_srcs else 'NULL' for i in range(4))
+   if num_srcs <= 4:
+      return ', '.join('src' + str(i) if i < num_srcs else 'NULL' for i in range(4))
+   else:
+      return ', '.join('src' + str(i) for i in range(num_srcs))
 %>
 
-% for name, opcode in sorted(opcodes.iteritems()):
+% for name, opcode in sorted(opcodes.items()):
 static inline nir_ssa_def *
 nir_${name}(nir_builder *build, ${src_decl_list(opcode.num_inputs)})
 {
+% if opcode.num_inputs <= 4:
    return nir_build_alu(build, nir_op_${name}, ${src_list(opcode.num_inputs)});
+% else:
+   nir_ssa_def *srcs[${opcode.num_inputs}] = {${src_list(opcode.num_inputs)}};
+   return nir_build_alu_src_arr(build, nir_op_${name}, srcs);
+% endif
 }
 % endfor
 
 /* Generic builder for system values. */
 static inline nir_ssa_def *
-nir_load_system_value(nir_builder *build, nir_intrinsic_op op, int index)
+nir_load_system_value(nir_builder *build, nir_intrinsic_op op, int index,
+                      unsigned num_components, unsigned bit_size)
 {
    nir_intrinsic_instr *load = nir_intrinsic_instr_create(build->shader, op);
-   load->num_components = nir_intrinsic_infos[op].dest_components;
+   if (nir_intrinsic_infos[op].dest_components > 0)
+      assert(num_components == nir_intrinsic_infos[op].dest_components);
+   else
+      load->num_components = num_components;
    load->const_index[0] = index;
+
    nir_ssa_dest_init(&load->instr, &load->dest,
-                     nir_intrinsic_infos[op].dest_components, 32, NULL);
+                     num_components, bit_size, NULL);
    nir_builder_instr_insert(build, &load->instr);
    return &load->dest.ssa;
 }
 
-% for name, opcode in filter(lambda v: v[1].sysval, sorted(INTR_OPCODES.iteritems())):
+<%
+def sysval_decl_list(opcode):
+   res = ''
+   if opcode.indices:
+      res += ', unsigned ' + opcode.indices[0].lower()
+   if opcode.dest_components == 0:
+      res += ', unsigned num_components'
+   if len(opcode.bit_sizes) != 1:
+      res += ', unsigned bit_size'
+   return res
+
+def sysval_arg_list(opcode):
+   args = []
+   if opcode.indices:
+      args.append(opcode.indices[0].lower())
+   else:
+      args.append('0')
+
+   if opcode.dest_components == 0:
+      args.append('num_components')
+   else:
+      args.append(str(opcode.dest_components))
+
+   if len(opcode.bit_sizes) == 1:
+      bit_size = opcode.bit_sizes[0]
+      args.append(str(bit_size))
+   else:
+      args.append('bit_size')
+
+   return ', '.join(args)
+%>
+
+% for name, opcode in filter(lambda v: v[1].sysval, sorted(INTR_OPCODES.items())):
+<% assert len(opcode.bit_sizes) > 0 %>
 static inline nir_ssa_def *
-nir_${name}(nir_builder *build)
+nir_${name}(nir_builder *build${sysval_decl_list(opcode)})
 {
-   return nir_load_system_value(build, nir_intrinsic_${name}, 0);
+   return nir_load_system_value(build, nir_intrinsic_${name},
+                                ${sysval_arg_list(opcode)});
 }
 % endfor