Spruit, Neil R 3e5f3fe055 Fixed AppendMemoryFill for alignment, multi kernel execution, memory overrun ...

- Fixed Memory Fill to use aligned allocations in Destination and Source
buffer kernel arguments to ensure proper alignment of memory in the
surface state.
- Fixed patternSize == 1 case where simd size is > the size being
written resulting in the inital kernel append with group count of 0 and
the remainder kernel being executed incorrectly.
- Fixed offset calculation in the remainder kernel to be based off of
the aligned allocation offset.
- Fixed memory overrun case where size < patternsize with the minimum
size being used in the kernel.

Change-Id: I39bd83b3a83ceb6df05d374238f85f7fdf0bd09a
Signed-off-by: Spruit, Neil R <neil.r.spruit@intel.com>

2020-11-02 16:49:12 -08:00

..

api

Add boiler plate support for sysman event API

2020-10-21 10:20:00 +05:30

cmake

Move aub and tbx code to shared

2020-10-19 16:04:47 +02:00

core

Fixed AppendMemoryFill for alignment, multi kernel execution, memory overrun

2020-11-02 16:49:12 -08:00

ddi

Restore self-open ze_intel_gpu library on Linux

2020-10-12 14:20:33 +02:00

doc

Update Level Zero BUILD.md file

2020-10-29 11:12:13 +01:00

experimental

Improve thread private data destructor to be more robust

2020-10-29 12:22:14 +01:00

source

Restore self-open ze_intel_gpu library on Linux

2020-10-12 14:20:33 +02:00

tools

Add sysman handles for subdevice only after subdevices are created

2020-10-30 09:45:08 +01:00

CMakeLists.txt

Move aub and tbx code to shared

2020-10-19 16:04:47 +02:00

os_release_info.cmake

Cmake format script

2020-08-19 16:36:30 +02:00