Katarzyna Cencelewska e357e7e404 fix: correct limitation for num threads per thread group ...

taking into account the max work group limit
when simd1 don't use the same limitation as for simd32

Resolves: NEO-14922
Related-To: NEO-11881
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>

2025-05-29 16:34:40 +02:00

..

api

refactor: correct names in calcop creation

2025-05-27 18:40:00 +02:00

cmake

build: remove logic of excluding platforms without L0 support

2025-02-04 21:01:18 +01:00

core

fix: correct limitation for num threads per thread group

2025-05-29 16:34:40 +02:00

ddi

fix: add missing L0 API entries in global driver dispatch

2025-04-30 12:57:18 +02:00

doc

feature: add NEO_LOCAL_MEMORY_ALLOCATION_MODE

2025-05-20 14:15:17 +02:00

experimental

feature: update base layout of L0 handles to match ze_handle_t layout

2025-03-28 14:40:20 +01:00

include

refactor: correct names in calcop creation

2025-05-27 18:40:00 +02:00

source

feature: Add extensions to expose dot product capabilities

2023-10-31 21:54:39 +01:00

sysman

fix(sysman): Update fimrware handles discovery using igsc

2025-05-28 21:01:29 +02:00

tools

refactor: correct names in calcop creation

2025-05-27 18:40:00 +02:00

.config

ci: add initial configs

2023-12-12 16:00:46 +01:00

CMakeLists.txt

fix: add missing extension ults

2025-05-20 16:03:18 +02:00

os_release_info.cmake

build: unify minimum required cmake version

2024-05-21 13:10:17 +02:00

ze_intel_gpu_version.h.in

…