Limitations and unsupported APIs#
2026-10-23
3 min read time
Platform limitations#
libhipcxx has the following platform limitations.
libhipcxx does not support the CUDA backend or NVIDIA hardware.
cuda::std::chrono::system_clock::now()does not return a UNIX timestamp. The host system clock and the device system clock are not synchronized and may run at different clock rates.
Important
Some APIs from libcudacxx may be missing or may not achieve the same performance on AMD GPUs due to fundamental hardware architecture differences between AMD and NVIDIA GPUs. APIs that rely on NVIDIA-specific hardware features (such as PTX instructions, tensor cores, or specific compute capabilities) may be unavailable, provide degraded functionality, or fall back to software implementations with reduced performance.
Unsupported APIs#
The following APIs from libcudacxx are not supported in libhipcxx:
Group |
API |
Description |
|---|---|---|
Synchronization Library |
|
Single-phase asynchronous thread-coordination mechanism. |
Synchronization Library |
|
Multi-phase asynchronous thread-coordination mechanism. |
Synchronization Library |
|
Primitives for constraining concurrent access. |
Extended Synchronization Library |
|
System-wide |
Extended Synchronization Library |
|
System-wide |
Extended Synchronization Library |
|
System-wide primitives for constraining concurrent access. |
Extended Synchronization Library |
|
Coordination mechanisms to sequence asynchronous operations. |
Extended Memory Access Properties Library |
|
Memory access properties for pointers. |
Extended Memory Access Properties Library |
|
Discards modified cache lines without writing them back. The header is available, but
|
Extended Warp Library |
|
Warp shuffle, match and lane-mask functions. The header is available, but
|
Extended Work Stealing Library |
|
|
Device-Level APIs |
|
Hardware-specific device functions including warp shuffles, barrier operations with transaction counts, and async memory operations. These require NVIDIA PTX instructions and SM-specific hardware features not available on AMD GPUs. |
Extended TMA Library |
|
|
Parallel Algorithms |
|
Overloads of the standard algorithms that take an execution policy such as
|
PTX API |
|
The |
CUDA Tile |
Tile mode |
Support for compiling libcudacxx headers in NVIDIA CUDA Tile mode. |
Runtime API |
|
|
Runtime API |
|
Queries for the architecture of the current device. |
Parallel algorithms (experimental)#
The parallel algorithms in <cuda/std/execution> — cuda::std::reduce, sort, transform, and the
other overloads that take an execution policy — are not supported on HIP and are not declared by default.
Calling one is a compile error (no matching function).
Upstream implements them on top of NVIDIA CUB. hipCUB does not yet provide several of the primitives CUB 3.x
expects, including DeviceTransform::Generate, DeviceTransform::TransformIf, and a two-output
DevicePartition. libhipcxx carries a shim that supplies the missing pieces over rocPRIM. That shim is
experimental: it is not covered by the same testing as the rest of the library, and its API surface may change.
To opt in, define LIBHIPCXX_ENABLE_EXPERIMENTAL_HIPCUB_SHIM when compiling your own code:
hipcc -DLIBHIPCXX_ENABLE_EXPERIMENTAL_HIPCUB_SHIM ...
When building libhipcxx itself, the equivalent CMake option is
-DLIBCUDACXX_ENABLE_EXPERIMENTAL_HIPCUB_SHIM=ON. This option only affects libhipcxx’s own build tree.
Code that consumes an installed libhipcxx must define the macro in its own build.
The flag will be removed and the algorithms enabled unconditionally once hipCUB provides the missing primitives.