llvm
llvm copied to clipboard
intel
Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.
1. Added all remaining functions needed for the `single_task` test case in supported function list. Only declaration remains in the generated LLVMIR: ``` declare i8* @malloc(i64) declare void @free(i8*) declare...
SYCL kernels are GPUFuncOps residing in the new GPUModuleOp, keeping host code in the regular module. Functions to be used by kernels must be cloned to the GPU module. When...
Greetings, I'm getting the below compilation error when I target my gpu. I don't get the same issue when i target the intel fpga simulator or intel cpu. code is...
Currently PI_KERNEL_MAX_SUB_GROUP_SIZE in the PI OpenCL backend uses the max work item sizes as the input to the corresponding OpenCL query to avoid truncation. However, using the max work item...
For OpenCL backends currently piProgramCreate() queries the platform version (CL_PLATFORM_VERSION) and platform extensions (CL_PLATFORM_EXTENSIONS) to check whether we're capable of running on top of a particular OpenCL backend. However, there...
This patch is to fix two known issues with debugging caused by integration footer presence, without redesigning the integration footer approach. One issue is the missing checksum for the main...
llvm-test-suite patch: https://github.com/intel/llvm-test-suite/pull/1265
For test purpose only! Do not merge.
Expands spir64_gen target capabilities with -fsycl by introducing a number of GPU specific targets that can be specified via -fsycl-targets. These targets (intel_gpu_* in format) are a set of reserved...
**Describe the bug** With ROCm 4.5.2, trying to call `device.get_info()` on an AMD device throws `cl::sycl::runtime_error`. **To Reproduce** ```cpp #include #include int main() { std::vector devices = sycl::device::get_devices(); for (const...
