i965/fs: add a helper function to create double immediates

Gen7 hardware does not support double immediates so these need
to be moved in 32-bit chunks to a regular vgrf instead. Instead
of doing this every time we need to create a DF immediate,
create a helper function that does the right thing depending
on the hardware generation.

v2:
- Define setup_imm_df() as an independent function (Curro)
- Create a specific builder to get rid of some instruction field
  assignments (Curro).

v3:
- Get devinfo from builder (Kenneth)

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index 1f88f8fd02631a0ff086167fd77638b36b21fd2b..ca977d4d3437c385a9c5dafe61433cd744d76efd 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -512,3 +512,5 @@ void shuffle_64bit_data_for_32bit_write(const brw::fs_builder &bld,
                                         const fs_reg &dst,
                                         const fs_reg &src,
                                         uint32_t components);
+fs_reg setup_imm_df(const brw::fs_builder &bld,
+                    double v);

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index 04ed42e6acd89ad75133a574d5aa1cdcd8cceb4a..b41fbf8bd4824e4c21b8d4e4892525578590ea48 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -4547,3 +4547,41 @@ shuffle_64bit_data_for_32bit_write(const fs_builder &bld,
       bld.MOV(offset(dst, bld, 2 * i + 1), subscript(component_i, dst.type, 1));
    }
 }
+
+fs_reg
+setup_imm_df(const fs_builder &bld, double v)
+{
+   const struct brw_device_info *devinfo = bld.shader->devinfo;
+   assert(devinfo->gen >= 7);
+
+   if (devinfo->gen >= 8)
+      return brw_imm_df(v);
+
+   /* gen7 does not support DF immediates, so we generate a 64-bit constant by
+    * writing the low 32-bit of the constant to suboffset 0 of a VGRF and
+    * the high 32-bit to suboffset 4 and then applying a stride of 0.
+    *
+    * Alternatively, we could also produce a normal VGRF (without stride 0)
+    * by writing to all the channels in the VGRF, however, that would hit the
+    * gen7 bug where we have to split writes that span more than 1 register
+    * into instructions with a width of 4 (otherwise the write to the second
+    * register written runs into an execmask hardware bug) which isn't very
+    * nice.
+    */
+   union {
+      double d;
+      struct {
+         uint32_t i1;
+         uint32_t i2;
+      };
+   } di;
+
+   di.d = v;
+
+   const fs_builder ubld = bld.exec_all().group(1, 0);
+   const fs_reg tmp = ubld.vgrf(BRW_REGISTER_TYPE_UD, 2);
+   ubld.MOV(tmp, brw_imm_ud(di.i1));
+   ubld.MOV(horiz_offset(tmp, 1), brw_imm_ud(di.i2));
+
+   return component(retype(tmp, BRW_REGISTER_TYPE_DF), 0);
+}