Krystian Chmielewski 3731ee89d8 Do not enforce LWS in dec order when smaller than half simd ...

When generating work group sizes first try with enforcing decremental
order X >= Y >= Z if generated work group size X * Y * Z is smaller
than half the kernel's SIMD size then generate again without
enforcing decremental order.

Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>

2023-01-05 15:55:14 +01:00

..

generate_cpp_array

Fix help in generate_cpp_array tool

2022-10-10 13:19:07 +02:00

offline_compiler

style: format code using clang-format 15.0.6

2023-01-05 10:33:47 +01:00

source

Do not enforce LWS in dec order when smaller than half simd

2023-01-05 15:55:14 +01:00

test

Move clGfxCoreHelper ownership to rootDeviceEnv

2023-01-05 12:58:38 +01:00

wsl_compute_helper/source

Add wddm ult for wsl build [5/n]

2022-12-14 16:32:37 +01:00

CMakeLists.txt

CMake: don't include shared/test/unit_test when shared tests are skipped

2022-08-25 10:48:37 +02:00