intel/llvm

View on GitHub

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

Stars: 1.5k
Forks: 854
Open beginner issues: 1
Indexed issues: 662
Avg merge: 3d 17h
Merged PRs (30d): 137

Dominant language: LLVM
License: No license data
Last GitHub push: Sep 15, 2026
Latest indexed: Sep 17, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: help wanted good first issue

Open All

659 open issues indexed

[SYCL-MLIR] error: 'llvm.bitcast' op cannot cast pointers of different address spaces, use 'llvm.addrspacecast' instead Open

enhancement sycl-mlir

intel/llvm#9453 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL-MLIR] error: SYCL vector types can only hold basic scalar types. Got '!llvm.struct<(f16)>'. Open

enhancement sycl-mlir

intel/llvm#9454 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Cleanup pipe extension specifications Open

confirmed enhancement

intel/llvm#9465 · 5 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[SYCL-MLIR] Investigate e2e test failures after 712cb4e Open

bug sycl-mlir

intel/llvm#9535 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[SYCL][CUDA] Copy between device and managed/shared memory fails on WSL Open

bug cuda

intel/llvm#9632 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[OpenCL CPU Runtime] Kernel sensitive failure? Open

bug confirmed OCL CPU Experimental RT

intel/llvm#9662 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL][CUDA] error: no matching function for call to 'make_context' Open

bug cuda

intel/llvm#9704 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Test SYCL :: KernelAndProgram/kernel-bundle-merge-options-env.cpp failed with Linux SYCL-E2E testing Open

bug confirmed

intel/llvm#9804 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[[sycl::vec_type_hint]] kernel attribute doesn't compile with sycl::vec Open

bug confirmed

intel/llvm#9836 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
SPIR-V validation error "OpVariable Initializer is not a constant or module-scope variable." Open

bug confirmed

intel/llvm#9961 · 7 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
request: extend the sycl_ext_oneapi_device_global extension Open

enhancement spec extension

intel/llvm#9965 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Unreliable profiling info with cuda / hip backends Open

bug cuda hip

intel/llvm#10042 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
accessor should export its template arguments / template matching error on accessor<T,int,auto...> Open

bug confirmed

intel/llvm#10057 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
ESIMD/accessor_local.cpp started to fail on Linux after https://github.com/intel/llvm/pull/10054 Open

bug confirmed

intel/llvm#10138 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
memcpy2d and copy2d is failing on HIP target Open

bug confirmed hip

intel/llvm#10157 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Config/device_selector.cpp fails in pre-commit. Open

bug confirmed

intel/llvm#10344 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
More meaningful info::device::version for Intel GPUs Open

enhancement spec extension

intel/llvm#10384 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Memory access fault by GPU node-1 ... Reason: Page not present or supervisor privilege. Open

bug hip

intel/llvm#10460 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Remove `getRawSyclObjImpl()` from DPC++ headers. Open

confirmed runtime

intel/llvm#10474 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Make libdevice work with -ffast-math Open

confirmed enhancement SPIR-V

intel/llvm#10517 · 11 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
`opencl-aot` fails to compile SYCL kernels with an unsupported subgroup size Open

bug confirmed

intel/llvm#10531 · 8 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL-MLIR][UnderlyingValueAnalysis] Improve to handle multiple underlying values from multiple callers Open

enhancement sycl-mlir

intel/llvm#10536 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL] Name mangling of unnamed kernels not sufficiently robust to disambiguate them Open

bug confirmed

intel/llvm#10659 · 5 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[OpaquePointers] Fix SYCL end-to-end tests with enabled opaque pointers. Open

bug confirmed

intel/llvm#10682 · 19 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
`-fsycl` breaks `_OPENMP` preprocessor definition Open

bug confirmed

intel/llvm#10711 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Provide oneAPI binary plugins built with CUDA < 12 Open

bug cuda

intel/llvm#10858 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Allow for stateless addressing flags for >4GB allocations for devices to be passed through SYCL Open

confirmed enhancement

intel/llvm#10946 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
[SYCL] DPC++ support runtime compilation? Open

confirmed enhancement

intel/llvm#11011 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
use_when_link_verify_cache.cpp failed on HIP/AMD with unrelated changes Open

bug confirmed

intel/llvm#11030 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Unable to run CUDA backend compiled sample (Windows 10) Open

bug cuda

intel/llvm#11058 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Extend libclc remangler to support `[u]int64_t` types Open

cuda enhancement hip

intel/llvm#11082 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[CUDA] 'PI_ERROR_INVALID_KERNEL_NAME' when dynamic library with kernel is loaded by dlopen secondly Open

bug cuda

intel/llvm#11089 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Unable to run cuda backend on Windows 11 Open

bug cuda Windows

intel/llvm#11144 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
The class `ext::oneapi::bfloat16` has too greedy and thus wrong definition of math/relative operators Open

bug confirmed

intel/llvm#11244 · 17 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Host task lacks proper synchronization capabilities when used for interoperability Open

enhancement

intel/llvm#11284 · 14 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
sycl-toolchain-hip maxworkgroup return negative number? Open

bug hip

intel/llvm#11322 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[ESIMD] assert test fails after GPU driver uplift Open

bug confirmed esimd

intel/llvm#11359 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
`assert` doesn't work on OpenCL GPU after driver uplift Open

bug confirmed

intel/llvm#11364 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
DeviceLib/built-ins/ftz-flag.cpp timeout on HIP backend Open

bug confirmed hip

intel/llvm#11378 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Remove support of checkForDuplicateAttribute() Open

confirmed

intel/llvm#11385 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Using get_backend on an event from a host task hits an assert Open

bug confirmed

intel/llvm#11479 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
sycl::complex, std::complex, or sycl::ext::oneapi::experimental::complex Open

enhancement spec extension

intel/llvm#11502 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Profile-Guided Optimization (PGO) and LLVM BOLT usage for Release builds Open

help wanted

intel/llvm#11555 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Building a simple SYCL project with CMake results in a "No kernel named _(insert mangled name here)_ was found -46 (PI_ERROR_INVALID_KERNEL_NAME)" error. Open

cuda Documentation Windows

intel/llvm#11568 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL] Line number info looks random and wrong Open

bug confirmed pdtracker

intel/llvm#11573 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
clang-cl does not recognize -Xcuda-ptxas flags Open

cuda enhancement Windows

intel/llvm#11624 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Precompiled header support with -fsycl Open

confirmed enhancement

intel/llvm#11657 · 2 comments · 4 reactions · 0 assignees · Indexed Sep 17, 2026
[SYCL][USM] Trying to use malloc_shared does not raise an exception, but hits an assert instead Open

bug confirmed

intel/llvm#11747 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Attach calling convention to `llvm.call` operations when lowering Open

enhancement sycl-mlir

intel/llvm#11894 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Decrease the latency of pulldown from sycl branch to sycl-mlir branch Open

sycl-mlir

intel/llvm#12047 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026

intel/llvm

Get new issues in your inbox