[BDWgt3e] intermittent deqp-vk.subgroups failures
@majanes
Submitted by Mark Janes Assigned to Intel 3D Bugs Mailing List
Link to original bug (#109682)
Description
In mesa CI, about 10% of test runs generate a single failure in the subgroups category. A quick look at the history shows the following failures:
dEQP-VK.subgroups.shuffle.subgroupshuffleup_uvec2_graphic dEQP-VK.subgroups.shuffle.subgroupshuffleup_vec3_graphic dEQP-VK.subgroups.quad.subgroupquadswapdiagonal_dvec3_graphic dEQP-VK.subgroups.arithmetic.subgroupinclusivemin_uint_graphic dEQP-VK.subgroups.quad.subgroupquadbroadcast_0_bool_graphic dEQP-VK.subgroups.basic.subgroupelect_graphic dEQP-VK.subgroups.quad.subgroupquadswaphorizontal_dvec3_graphic
Typical output for a failure:
1022 / 1023 values passed
All tests in the recent CI history occure on GT3e systems, even though nearly half of the BDW in CI are GT2.
Version: git