fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-04-28 04:20:40 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

ac/nir/ngg: fix nogs culling with nuw add

Browse source 
We should not use "nuw" here as negative add positive may wrap
around (negative is 0xffffff??).

This problem can be observed with LLVM15 (I can't see when LLVM14):
  %.neg = mul nsw i32 %31, -4
  %163 = add nuw nsw i32 %.neg, 16
  %164 = lshr i32 257, %.neg
  %165 = lshr i32 %164, %163

LLVM just assume %.neg is possitive, so pre-shift 0x01010101 by 16.
This get wrong value because we can't get back the shifted bits with
a negative shift right.

Fixes: 75dbb40439 ("ac/nir: Remove byte permute from prefix sum of the repack sequence.")
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19718>
(cherry picked from commit 982b523769)
This commit is contained in:
Qiang Yu 2022-11-14 15:01:51 +08:00 • committed by Dylan Baker
parent c0c5eed580
commit af4c9789bb
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.pick_status.json
View file

@ -661,7 +661,7 @@
"description": "ac/nir/ngg: fix nogs culling with nuw add",
"nominated": true,
"nomination_type": 1,
"resolution": 0,
"resolution": 1,
"main_sha": null,
"because_sha": "75dbb404393a5ae99adb90a156fa5a084aa79c4d"
},

2
src/amd/common/ac_nir_lower_ngg.c
View file

@ -234,7 +234,7 @@ summarize_repack(nir_builder *b, nir_ssa_def *packed_counts, unsigned num_lds_dw
*/
nir_ssa_def *lane_id = nir_load_subgroup_invocation(b);
nir_ssa_def *shift = nir_iadd_imm_nuw(b, nir_imul_imm(b, lane_id, -4u), num_lds_dwords * 16);
nir_ssa_def *shift = nir_iadd_imm(b, nir_imul_imm(b, lane_id, -4u), num_lds_dwords * 16);
bool use_dot = b->shader->options->has_udot_4x8;
if (num_lds_dwords == 1) {