llvm
llvm copied to clipboard
intel
Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.
### Describe the bug https://github.com/intel/llvm/actions/runs/10952456651/job/30411378740 ``` ******************** Expectedly Failed Tests (1): SYCL :: AddressSanitizer/nullpointer/private_nullptr.cpp ******************** Failed Tests (37): SYCL :: AddressSanitizer/common/config-red-zone-size.cpp SYCL :: AddressSanitizer/common/demangle-kernel-name.cpp SYCL :: AddressSanitizer/common/kernel-debug.cpp SYCL :: AddressSanitizer/invalid-argument/host-pointer.cpp...
The capitalization of cuda and hip in `Basic/interop/interop_all_backends.cpp` makes the test always unsupported. This patch should fix this to allow the test to run again on machines with cuda/hip devices....
### Describe the bug The E2E test Scheduler/ReleaseResources.cpp is marked as XFAIL on hip_nvidia platform. This issue is to make sure we have a tracker for it so that it...
These corner cases are: 1. AccessChain uses are optimized out of LLVM IR modules, leaving the call unused; 2. AccessChain result is used in GEP 0,0 instruction for bfloat16 (instead...
### Describe the bug The E2E test Tracing/buffer_printers.cpp is marked as XFAIL on hip_nvidia platform. This issue is to make sure we have a tracker for it so that it...
### Describe the bug The E2E test `Scheduler/MemObjRemapping.cpp` is marked as XFAIL on hip_nvidia platform. This issue is to make sure we have a tracker for it so that it...
### Describe the bug The E2E test `Scheduler/InOrderQueueDeps.cpp` is marked as XFAIL on hip_nvidia platform. This issue is to make sure we have a tracker for it so that it...
### Describe the bug The E2E test Scheduler/MemObjRemapping.cpp is marked as XFAIL on hip_nvidia platform. This issue is to make sure we have a tracker for it so that it...
Implement Dynamic Command-Group feature specified in PR [[SYCL][Graph] Add specification for kernel binary updates](https://github.com/intel/llvm/pull/14896) This feature enables updating `ur_kernel_handle_t` objects in graph nodes between executions as well as parameters and...
