i965/fs: Fix extract_i8/u8 to a 64-bit destination

The MOV instruction can extract bytes to words/double words, and
words/double words to quadwords, but not byte to quadwords.

For unsigned byte to quadword, we can read them as words and AND off the
high byte and extract to quadword in one instruction. For signed bytes,
we need to first sign extend to word and the sign extend that word to a
quadword.

Fixes the following test on CHV, BXT, and GLK:
   KHR-GL46.shader_ballot_tests.ShaderBallotBitmasks
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103628
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

src/intel/compiler/brw_fs_nir.cpp

@@ -1395,10 +1395,31 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr)
 
    case nir_op_extract_u8:
    case nir_op_extract_i8: {
-      const brw_reg_type type = brw_int_type(1, instr->op == nir_op_extract_i8);
       nir_const_value *byte = nir_src_as_const_value(instr->src[1].src);
       assert(byte != NULL);
-      bld.MOV(result, subscript(op[0], type, byte->u32[0]));
+
+      /* The PRMs say:
+       *
+       *    BDW+
+       *    There is no direct conversion from B/UB to Q/UQ or Q/UQ to B/UB.
+       *    Use two instructions and a word or DWord intermediate integer type.
+       */
+      if (nir_dest_bit_size(instr->dest.dest) == 64) {
+         const brw_reg_type type = brw_int_type(2, instr->op == nir_op_extract_i8);
+
+         if (instr->op == nir_op_extract_i8) {
+            /* If we need to sign extend, extract to a word first */
+            fs_reg w_temp = bld.vgrf(BRW_REGISTER_TYPE_W);
+            bld.MOV(w_temp, subscript(op[0], type, byte->u32[0]));
+            bld.MOV(result, w_temp);
+         } else {
+            /* Otherwise use an AND with 0xff and a word type */
+            bld.AND(result, subscript(op[0], type, byte->u32[0] / 2), brw_imm_uw(0xff));
+         }
+      } else {
+         const brw_reg_type type = brw_int_type(1, instr->op == nir_op_extract_i8);
+         bld.MOV(result, subscript(op[0], type, byte->u32[0]));
+      }
       break;
    }