[Mesa-dev] [PATCH v2 2/8] i965/fs: shuffle_32bit_load_result_to_16bit_data now skips components

[Jose Maria Casanova Crespo]

This helper used to load 16bit components from 32-bits read now allows
skipping components with the new parameter first_component. The semantics
now skip components until we reach the first_component, and then reads the
number of components passed to the function.

All previous uses of the helper are updated to use 0 as first_component.
This will allow read 16-bit components when the first one is not aligned
32-bit. Enabling more usages of untyped_reads with 16-bit types.
---
 src/intel/compiler/brw_fs.cpp     | 2 +-
 src/intel/compiler/brw_fs.h       | 3 ++-
 src/intel/compiler/brw_fs_nir.cpp | 8 +++++---
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/src/intel/compiler/brw_fs.cpp b/src/intel/compiler/brw_fs.cpp
index bed632d21b9..e961b76ab61 100644
--- a/src/intel/compiler/brw_fs.cpp
+++ b/src/intel/compiler/brw_fs.cpp
@@ -194,7 +194,7 @@ fs_visitor::VARYING_PULL_CONSTANT_LOAD(const fs_builder &bld,
    fs_reg dw = offset(vec4_result, bld, (const_offset & 0xf) / 4);
    switch (type_sz(dst.type)) {
    case 2:
-      shuffle_32bit_load_result_to_16bit_data(bld, dst, dw, 1);
+      shuffle_32bit_load_result_to_16bit_data(bld, dst, dw, 1, 0);
       bld.MOV(dst, subscript(dw, dst.type, (const_offset / 2) & 1));
       break;
    case 4:
diff --git a/src/intel/compiler/brw_fs.h b/src/intel/compiler/brw_fs.h
index 63373580ee4..52dd5e1d6bb 100644
--- a/src/intel/compiler/brw_fs.h
+++ b/src/intel/compiler/brw_fs.h
@@ -503,7 +503,8 @@ fs_reg shuffle_64bit_data_for_32bit_write(const brw::fs_builder &bld,
 void shuffle_32bit_load_result_to_16bit_data(const brw::fs_builder &bld,
                                              const fs_reg &dst,
                                              const fs_reg &src,
-                                             uint32_t components);
+                                             uint32_t components,
+                                             uint32_t first_component);
 
 void shuffle_16bit_data_for_32bit_write(const brw::fs_builder &bld,
                                         const fs_reg &dst,
diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp
index 4aa411d149f..5567433a19e 100644
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -2316,7 +2316,7 @@ do_untyped_vector_read(const fs_builder &bld,
          shuffle_32bit_load_result_to_16bit_data(bld,
                retype(dest, BRW_REGISTER_TYPE_W),
                retype(read_result, BRW_REGISTER_TYPE_D),
-               num_components);
+               num_components, 0);
       } else {
          assert(num_components == 1);
          /* scalar 16-bit are read using one byte_scattered_read message */
@@ -4908,7 +4908,8 @@ void
 shuffle_32bit_load_result_to_16bit_data(const fs_builder &bld,
                                         const fs_reg &dst,
                                         const fs_reg &src,
-                                        uint32_t components)
+                                        uint32_t components,
+                                        uint32_t first_component)
 {
    assert(type_sz(src.type) == 4);
    assert(type_sz(dst.type) == 2);
@@ -4922,7 +4923,8 @@ shuffle_32bit_load_result_to_16bit_data(const fs_builder &bld,
 
    for (unsigned i = 0; i < components; i++) {
       const fs_reg component_i =
-         subscript(offset(src, bld, i / 2), dst.type, i % 2);
+         subscript(offset(src, bld, (first_component + i) / 2), dst.type,
+                   (first_component + i) % 2);
 
       bld.MOV(offset(tmp, bld, i % 2), component_i);
 
-- 
2.14.3