OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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 <siglesias@igalia.com>
Cc: "17.1" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
This commit is contained in:
Samuel Iglesias Gonsálvez
2017-04-19 10:35:07 +02:00
parent 354f7f2cb9
commit 8aa6ada838
1 changed files with 11 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/intel/compiler/brw_vec4_nir.cpp
View File

@@ -769,7 +769,8 @@ 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]);
@@ -777,14 +778,20 @@ 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);