i965/vec4: fix swizzle and writemask when loading an uniform with constant offset

It was setting XYWZ swizzle and writemask to all uniforms, no matter if they
were a vector or scalar, so this can lead to problems when loading them
to the push constant buffer.

Moreover, 'shift' calculation was designed to calculate the offset in
DWORDS, but it doesn't take into account DFs, so the calculated swizzle
for the later ones was wrong.

The indirect case is not changed because MOV INDIRECT will write
to all components. Added an assert to verify that these uniforms
are aligned.

v2:
- Fix 'shift' calculation (Curro)
- Set both swizzle and writemask.
- Add assert(shift == 0) for the indirect case.

Signed-off-by: Samuel Iglesias Gonsálvez <[email protected]>
Cc: "17.1" <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
(cherry picked from commit 8aa6ada8384a961b37dfefec7f9e40e5a4e27ce7)

1 files changed, 11 insertions, 4 deletions

diff --git a/src/intel/compiler/brw_vec4_nir.cpp b/src/intel/compiler/brw_vec4_nir.cpp
index a82d52088a8..80115aca0f9 100644
--- a/src/intel/compiler/brw_vec4_nir.cpp
+++ b/src/intel/compiler/brw_vec4_nir.cpp
@@ -852,7 +852,8 @@ vec4_visitor::nir_emit_intrinsic(nir_intrinsic_instr *instr)
        * The swizzle also works in the indirect case as the generator adds
        * the swizzle to the offset for us.
        */
-      unsigned shift = (nir_intrinsic_base(instr) % 16) / 4;
+      const int type_size = type_sz(src.type);
+      unsigned shift = (nir_intrinsic_base(instr) % 16) / type_size;
       assert(shift + instr->num_components <= 4);
 
       nir_const_value *const_offset = nir_src_as_const_value(instr->src[0]);
@@ -860,14 +861,20 @@ vec4_visitor::nir_emit_intrinsic(nir_intrinsic_instr *instr)
          /* Offsets are in bytes but they should always be multiples of 4 */
          assert(const_offset->u32[0] % 4 == 0);
 
-         unsigned offset = const_offset->u32[0] + shift * 4;
+         src.swizzle = brw_swizzle_for_size(instr->num_components);
+         dest.writemask = brw_writemask_for_size(instr->num_components);
+         unsigned offset = const_offset->u32[0] + shift * type_size;
          src.offset = ROUND_DOWN_TO(offset, 16);
-         shift = (offset % 16) / 4;
+         shift = (offset % 16) / type_size;
+         assert(shift + instr->num_components <= 4);
          src.swizzle += BRW_SWIZZLE4(shift, shift, shift, shift);
 
          emit(MOV(dest, src));
       } else {
-         src.swizzle += BRW_SWIZZLE4(shift, shift, shift, shift);
+         /* Uniform arrays are vec4 aligned, because of std140 alignment
+          * rules.
+          */
+         assert(shift == 0);
 
          src_reg indirect = get_nir_src(instr->src[0], BRW_REGISTER_TYPE_UD, 1);