compute-runtime/level_zero
Maciej Bielski 97e7cda912 feature: Optimize intra-module kernel ISA allocations
So far, there is a separate page allocated for each kernel's ISA within
`KernelImmutableData::initialize()`. Apparently the ISA blocks are often
much smaller than a 64k page, which leads to poor memory utilization and
was even observed to cause the device OOM error if a single module has
several keys.

Improve the situation by reusing the parent allocation (owned by the
module instance) for modules, which kernel ISAs can fit together within
a single 64k page. This improves the memory utilization on a single
module level.

Related-To: NEO-7788
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
2023-09-21 13:55:45 +02:00
..
api feature: Ray Tracing Acceleration Structure (RTAS) Support 2023-09-20 19:57:56 +02:00
cmake
core feature: Optimize intra-module kernel ISA allocations 2023-09-21 13:55:45 +02:00
ddi refactor: Rename member variables to camelCase 2/n 2023-04-27 20:39:22 +02:00
doc fix: limit ccs number to 1 on dg2 [2nd submission] 2023-08-10 14:03:55 +02:00
experimental refactor: Rename member variables to camelCase 2/n 2023-04-27 20:39:22 +02:00
include feature: initial support for MetricGroupGetExportData 2023-06-27 00:09:45 +02:00
source
sysman fix(sysman): bugfix for return of correct uuid with zesInit flow 2023-09-21 09:41:49 +02:00
tools feature: Report 128 GRF count with zetDebugGetRegisterSetProperties 2023-09-18 11:03:59 +02:00
CMakeLists.txt refactor: Split compiler interface between OSs 2023-09-12 15:56:53 +02:00
os_release_info.cmake
ze_intel_gpu_version.h.in