- Refactoring introduced a bug when user does not specify any target via
--amdgpu-target, but has an invalid target specified in
HCC_AMDGPU_TARGET. In this case the selection logic was defaulting to
gf803.
- Removed defaulting to any specific target if rocm_agent_enumerator
fails. hipcc will report this and die if linking was required.
Change-Id: I76131867049fef92331807dd19a926406dcc1d02
[ROCm/clr commit: 8f6c150134]
SWDEV-2 - Change OpenCL version number from 2464 to 2465.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2212 edit
[ROCm/clr commit: 55a79e227a]
SWDEV-95919 - Avoid flushing when PerfCounter is enabled.
To make sure PerfStart/dispatch/PerfEnd are in the same cmdBuffer
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.cpp#51 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/pal/palvirtual.hpp#27 edit
[ROCm/clr commit: 6b27cc35a1]
Existing logic has a bug. If user specifies targetA via commandline
options, while enumerator returns targetB, hipcc will create a fatbin
containing targets targetA and targetB. enumerator should only be used
when no target is specified by user (commandline or env var).
Change-Id: I6da857f86860c0e671b5988cd858644a08f723b9
[ROCm/clr commit: 2a2c7575eb]
SWDEV-2 - Change OpenCL version number from 2463 to 2464.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2211 edit
[ROCm/clr commit: e69572cd38]
SWDEV-2 - Change OpenCL version number from 2462 to 2463.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2210 edit
[ROCm/clr commit: bbce92464b]
Associated change is to optimize event recording so it uses
agent-scope releaes (since it was only using system-scope release
to support non-coherent host mem).
Flags and environment variables exist to obtain previous behavior
if desired. Options are documented in new performance guide.
[ROCm/clr commit: 6576201ec2]
SWDEV-121486 - Clean up sampler list if we run out of memory.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/rocvirtual.cpp#42 edit
[ROCm/clr commit: 3a805c96cc]
Cmake cache was being rebuilt on each build. This was being done
to update HIP_VERSION, HCC_VERSION, .hipInfo and .hipVersion.
However, rebuilding cache also re-runs HIT parser which is slow.
Removing the cache rebuild should speed up the build. But user
needs to explicitly rebuild the cache in case HIP_VERSION or
HCC_VERSION changes by calling "make rebuild_cache"
Change-Id: Ia5476eb7105aa614239c4dc7968c37f5e6cb0b29
[ROCm/clr commit: 1b5d19ff36]
SWDEV-2 - Change OpenCL version number from 2461 to 2462.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2209 edit
[ROCm/clr commit: 0b5300069f]
[hipify-clang] Finally finished syncing with CUDA 8.0.61 Driver and Runtime API (including missing data types, D3D, OpenGL, VDPAU and EGL interop).
+ All the Modules are supported now:
1) 4.1 – 4.31 from CUDA 8.0.61 Driver API
2) CUDA_Driver_API_functions_supported_by_HIP.md updated accordingly
3) 4.1 – 4.31 from CUDA 8.0.61 Runtime API
4) CUDA_Runtime_API_functions_supported_by_HIP.md updated accordingly
+ Typos fixing
+ Annotating
[ROCm/clr commit: 9b10efe419]
SWDEV-95919 - Make sure PerfCounters_Start, Kernel_dispatch, and PerfCounters_End are in the same command buffer.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/platform/command.hpp#85 edit
... //depot/stg/opencl/drivers/opencl/tests/ocltst/module/runtime/OCLPerfCounters.cpp#38 edit
[ROCm/clr commit: 18617446da]
SWDEV-2 - Change OpenCL version number from 2460 to 2461.
Affected files ...
... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#2208 edit
[ROCm/clr commit: 8a40282f4a]
Ben Sander
Maneesh Gupta
Jenkins
foreman
Rahul Garg
Aditya Atluri
Evgeny Mankov
sunway513
Yifan Sun
Evgeny Mankov