-
Notifications
You must be signed in to change notification settings - Fork 787
[SYCL] Support parallel_for() accepting many reductions #3123
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
[SYCL] Support parallel_for() accepting many reductions #3123
Conversation
Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
…ng c++11 (changed to c++14) Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
…reduction_N_vars_perf
Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
I added a LIT test for this patch: intel/llvm-test-suite#131 An additional test-case accepting lambda-func instead of functors showed a minor issue in this implementation. |
Please add this info to commit message as requested in https://github.com/intel/llvm/blob/sycl/CONTRIBUTING.md |
…reduction_N_vars_perf
…:gpu) pass testing Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
efcd7e1
…reduction_N_vars_perf
This test verifies the following change-set in compiler: intel/llvm#3123 Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
…ode-gen at this moment. Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
…reduction_N_vars_perf
d1fbc3b
This test verifies the following change-set in compiler: intel/llvm#3123 Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
…el/llvm-test-suite#131) This test verifies the following change-set in compiler: intel#3123 Signed-off-by: Vyacheslav N Klochkov <vyacheslav.n.klochkov@intel.com>
- Implemented the TODO in the visitCallEnqueueKernel function - Takes param size and align from literal block - If dynamic allocation is used store instructions are processed to obtain size and align - Modified test Original commit: KhronosGroup/SPIRV-LLVM-Translator@ff7db6ef1c71860
The LIT test testing this change-set: intel/llvm-test-suite#131
Signed-off-by: Vyacheslav N Klochkov vyacheslav.n.klochkov@intel.com