i965/vec4/nir: allocate two registers for dvec3/dvec4

v2 (Curro):
  - Do not special-case for a bit-size of 64, divide the bit_size by 32
    instead.
  - Use DIV_ROUND_UP so we can handle sub-32-bit types.

v3 (Ian):
  - Make num_regs const.

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
index 7128ca717203304edd2f610b1601f89bead66435..37c99268b5c52e5f3fd9e2bef67ec0c4ec2b0fed 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_vec4_nir.cpp
@@ -140,8 +140,8 @@ vec4_visitor::nir_emit_impl(nir_function_impl *impl)
    foreach_list_typed(nir_register, reg, node, &impl->registers) {
       unsigned array_elems =
          reg->num_array_elems == 0 ? 1 : reg->num_array_elems;
-
-      nir_locals[reg->index] = dst_reg(VGRF, alloc.allocate(array_elems));
+      const unsigned num_regs = array_elems * DIV_ROUND_UP(reg->bit_size, 32);
+      nir_locals[reg->index] = dst_reg(VGRF, alloc.allocate(num_regs));
    }
 
    nir_ssa_values = ralloc_array(mem_ctx, dst_reg, impl->ssa_alloc);
@@ -270,7 +270,8 @@ dst_reg
 vec4_visitor::get_nir_dest(const nir_dest &dest)
 {
    if (dest.is_ssa) {
-      dst_reg dst = dst_reg(VGRF, alloc.allocate(1));
+      dst_reg dst =
+         dst_reg(VGRF, alloc.allocate(DIV_ROUND_UP(dest.ssa.bit_size, 32)));
       nir_ssa_values[dest.ssa.index] = dst;
       return dst;
    } else {