Skip to content

[SYCL][L0] Add temporary option to allow user to use copy engine for device to device copy #4127

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Jul 22, 2021
Merged

[SYCL][L0] Add temporary option to allow user to use copy engine for device to device copy #4127

merged 5 commits into from
Jul 22, 2021

Conversation

asudarsa
Copy link
Contributor

This option has been added to enable users to analyze performance of device to device copy operations on the copy engine.

@asudarsa asudarsa requested a review from smaslov-intel as a code owner July 16, 2021 22:15
smaslov-intel
smaslov-intel previously approved these changes Jul 19, 2021
@bader bader requested a review from pvchupin July 19, 2021 18:47
bader
bader previously approved these changes Jul 20, 2021
Copy link
Contributor

@bader bader left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks!

Please comment on the wording here.

@pvchupin, does it look good to you?

smaslov-intel
smaslov-intel previously approved these changes Jul 20, 2021
@asudarsa
Copy link
Contributor Author

I am not sure why "buildbot/Lit_With_Cuda" job is reporting a failure. It does not look like anything related to my changes.

@asudarsa asudarsa dismissed stale reviews from smaslov-intel and bader via 6f09bc3 July 20, 2021 20:02
@bader
Copy link
Contributor

bader commented Jul 21, 2021

I am not sure why "buildbot/Lit_With_Cuda" job is reporting a failure. It does not look like anything related to my changes.

http://ci.llvm.intel.com:8010/#/builders/37/builds/10068/steps/16/logs/stdio

sys_bbs+ 20997 99.2 0.0 168184 8768 ? R 18:25 37:16 /localdisk2/sycl_ci/buildbot/worker/Lit_With_Cuda/llvm.obj/tools/sycl/test/group_algorithms_sycl2020/Output/group_broadcast.cpp.tmp.out

group_broadcast.cpp test hung

@bader bader requested a review from smaslov-intel July 22, 2021 14:17
@bader bader merged commit 32be008 into intel:sycl Jul 22, 2021
alexbatashev added a commit to alexbatashev/llvm that referenced this pull request Jul 27, 2021
…ackend_plugin

* upstream/sycl: (755 commits)
  [SYCL] Add operator= to atomic_ref specializations (intel#4183)
  [SYCL] Make spelling of Debug value for CMAKE_BUILD_TYPE variable case insensitive (intel#4069)
  [SYCL][LIBCLC] Add atan and cbrt for amdgcn-amdhsa (intel#4180)
  [SYCL][CUDA] Correctly free managed memory (intel#4181)
  [SYCL] Revert barrier deprecation note (intel#4162)
  [SYCL][FPGA] Refactor of statement attributes (intel#4136)
  [Driver][SYCL] Enable way to emit int-footer source to a specific dir (intel#4167)
  [Driver] Fix default MSVC version setting for -fms-compatibilty-version (intel#4165)
  [BuildBot] Add llvm-enable-projects flag to configure.py (intel#4169)
  [Driver][SYCL][FPGA] Improve aocx archive processing for FPGA (intel#4160)
  [SYCL] Correct int-header emission with type aliases
  [SYCL] Fix name collisions in SYCL enums (intel#4154)
  [SYCL] Return the correct status info for host_task event (intel#4161)
  [ESIMD][NFC] Added tests for simd class type traits (intel#4146)
  [SYCL][ROCm] Fix missing parameter in ROCm plugin (intel#4166)
  [SYCL][L0] Add temporary option to allow user to use copy engine for device to device copy (intel#4127)
  Remove check for AMD HIP to fix Driver/cuda-arch-translation.cu
  Reapply after conflict resolution 418a6d6 "Fix nvptx_target_teams_distribute_parallel_for_simd_codegen failure"
  Revert "[SYCL] Removes redefinitions of macros in libclc (intel#3505)"
  [PGO] Change test-run line to check NewPM pass behavior
  ...
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants