i965/fs: add shuffle_32bit_load_result_to_64bit_data helper

There will be a few places where we need to shuffle the result of a 32-bit
load into valid 64-bit data, so extract this logic into a separate helper
that we can reuse.

v2 (Curro):
- Use subscript() instead of stride()
- Assert on the input types rather than retyping.
- Use offset() instead of horiz_offset(), drop the multiplier definition.
- Don't use  force_writemask_all.
- Mark component_i as const.
- Make the function name lower case.

v3 (Curro):
- Pass src and dst by reference.
- Move to brw_fs_nir.cpp

Reviewed-by: Kenneth Graunke <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>

2 files changed, 58 insertions, 0 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h
index d4eb8fb7be4..286e7186d1f 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -535,3 +535,8 @@ private:
 
 bool brw_do_channel_expressions(struct exec_list *instructions);
 bool brw_do_vector_splitting(struct exec_list *instructions);
+
+void shuffle_32bit_load_result_to_64bit_data(const brw::fs_builder &bld,
+                                             const fs_reg &dst,
+                                             const fs_reg &src,
+                                             uint32_t components);
diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index 7458b73b1d4..584a0d6bd52 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -3980,3 +3980,56 @@ fs_visitor::nir_emit_jump(const fs_builder &bld, nir_jump_instr *instr)
       unreachable("unknown jump");
    }
 }
+
+/**
+ * This helper takes the result of a load operation that reads 32-bit elements
+ * in this format:
+ *
+ * x x x x x x x x
+ * y y y y y y y y
+ * z z z z z z z z
+ * w w w w w w w w
+ *
+ * and shuffles the data to get this:
+ *
+ * x y x y x y x y
+ * x y x y x y x y
+ * z w z w z w z w
+ * z w z w z w z w
+ *
+ * Which is exactly what we want if the load is reading 64-bit components
+ * like doubles, where x represents the low 32-bit of the x double component
+ * and y represents the high 32-bit of the x double component (likewise with
+ * z and w for double component y). The parameter @components represents
+ * the number of 64-bit components present in @src. This would typically be
+ * 2 at most, since we can only fit 2 double elements in the result of a
+ * vec4 load.
+ *
+ * Notice that @dst and @src can be the same register.
+ */
+void
+shuffle_32bit_load_result_to_64bit_data(const fs_builder &bld,
+                                        const fs_reg &dst,
+                                        const fs_reg &src,
+                                        uint32_t components)
+{
+   assert(type_sz(src.type) == 4);
+   assert(type_sz(dst.type) == 8);
+
+   /* A temporary that we will use to shuffle the 32-bit data of each
+    * component in the vector into valid 64-bit data. We can't write directly
+    * to dst because dst can be (and would usually be) the same as src
+    * and in that case the first MOV in the loop below would overwrite the
+    * data read in the second MOV.
+    */
+   fs_reg tmp = bld.vgrf(dst.type);
+
+   for (unsigned i = 0; i < components; i++) {
+      const fs_reg component_i = offset(src, bld, 2 * i);
+
+      bld.MOV(subscript(tmp, src.type, 0), component_i);
+      bld.MOV(subscript(tmp, src.type, 1), offset(component_i, bld, 1));
+
+      bld.MOV(offset(dst, bld, i), tmp);
+   }
+}