Cupy

This is the release note of v5.0.0a1. See [here](https://github.com/cupy/cupy/milestone/25?closed=1) for the complete list of solved issues and merged PRs.

New Features
- Expose context management API in driver (977)
- Add 'edge' and 'reflect' mode to `cupy.pad` (1040, thanks wkentaro!)
- Implement `histogram` (1049, thanks IshitaTakeshi!)
- Implement multi-dimensional image processing (1066)
- Implement `cupy.show_config` and `cupyx.get_runtime_info` (1067)

Enhancements
- Expose all supported dtypes from numpy (1070)
- Support double precision `atomicAdd` on Maxwell or older GPUs (1071, thanks anaruse!)
- Use cuDNN v7 APIs to get convolution algorithms for TensorCore (1095, thanks anaruse!)
- Handle errors in `cupy.show_config()` (1132)
- Fix to capture CuDNNError in `cupyx.runtime` (1136)

Bug Fixes
- Fix `moveaxis` bug (1023, thanks fukatani!)
- Fix `diagflat` to fail if argument is not `cupy.ndarray` (1036)
- Limit arch to the maximum value allowed in each NVRTC version (1055)
- Fix `ndarray.real` and `ndarray.imag` to return view (1089)
- Fix `cupy.concatenate` to support arrays with >= 2**31 elements (1101)
- Use streams when calling libraries (1107)
- Fix duplicate declaration of EigMode in cuSPARSE (1108)
- Fix duplicate delcaration of `cudaError_t` (1112)
- Fix `cupy.linalg.inv()` breaks its argument (1123, thanks hyabe!)
- Use `cusolverSpSetStream` for `cuSolverSP` library calls (1152)
- Do not use platform-specific CC (1157)

Documents
- Fix typos: (1046, 1077)
- Update documentation for `chainer.backends.cuda` (1047)
- Rewrite installation guide (1064)
- Remove invalid argument description in `cupy.tensordot` (1069)
- Fix document of `for_unsigned_dtypes` (1076)
- Fix wrong references of document (1078)
- Fix document of `ndimage` (1131)
- Enable flake8 in cupy/indexing/generate.py (1141)
- Fix document of `r_` and `c_` (1142)
- Fix document of `MemoryHook` (1143)

Installation
- Use `--no-cache-dir` in Dockerfile (1060)
- Avoid embedding `CUDA_PATH` to `RPATH` in wheels (1065)

Examples
- Avoid to `import matplotlib` to set its backend Agg (976)

Tests
- Remove platform-dependent dtype (1091)
- Remove nose dependency (1125)

This is the release note of v4.5.0. See [here](https://github.com/cupy/cupy/milestone/36?closed=1) for the complete list of solved issues and merged PRs.

Highlights

This stable update adds scipy 1.0+ support.

Enhancements

- Support SciPy 1.0+ (1588)
- Improve exception handling performance in Cython (1598)
- Fallback to synchronous transfer if pinned memory could not be allocated (1603)
- Improve cudnn.pyx to up speed (1652)

Bug Fixes

- Fix cupy not working in thread other than one imported cupy (1585)
- Reset cuda runtime error (1597)
- Improve exception handling performance in Cython (1598)

Tests

- Add test for thread use case of fusion (1595)
- Fix invalid escape sequence warnings in Python 3.6 (1627)

This is the release note of v4.4.1. See [here](https://github.com/cupy/cupy/milestone/38?closed=1) for the complete list of solved issues and merged PRs.

This is a hot-fix release for v4.4.0 to address the issue reported in 1579 (thanks BobLiu20 for reporting this!). Users calling CuPy functions on non-main threads may have been affected by this issue.

Bug Fixes

- Fix cupy not working in thread other than one imported cupy (1591)

Tests

- Add test for thread use case of fusion (1596)

This is the release note of v4.4.0. See [here](https://github.com/cupy/cupy/milestone/34?closed=1) for the complete list of solved issues and merged PRs.

New Features

- Add `divmod` function to `cupy` namespace (1480)
- Allow more natural fusion notation (1481)

Enhancements

- Avoid `collections.sequence` (1472)
- Support negative indices in `array_split` (1475)
- Avoid variable name `l` to follow pep8 (1479)
- Reduce Python function call in `ElementwiseKernel` (1482)
- Speed up `ElementwiseKernel` launch (1488)
- Improve memory allocation performance (1490)
- Fix type of return value of fused function (1491)
- Support composition of fused functions (1494)
- Add compilation methods in Fusion class (1497)
- Allow `cupy.get_array_module` take fusion parameters (1498)
- Use CScalar in elementwise and reduction (1508)
- Use `collections.abc` to avoid DeprecationWarning in Python 3.7 (1517)
- Fix unit test errors in NumPy 1.15 (1549)

Bug Fixes

- Use `cython.no_gc` to avoid memory leak (1474)
- Fix errors on 0-sized inputs (1485)
- Fix type of reduction (1502)
- Avoid compile error in old GCC (CentOS6) (1516)
- Fix thrust memory allocation problem (1525)
- Fix dtype order of `create_comparison` (1553)
- Raise error when trying to broadcast `out_params` in `ElementwiseKernel` (1556)

Documentation

- Add upgrade guide for `cupyx` namespaces (1496)
- Update agnostic code tutorial (1528, thanks w-m!)

Tests

- Add `.pytest_cache/` to `.gitignore` (1530)
- Avoid hacking: Use the same test settings as Chainer (1536)

Support for ROCm 4.3 has been added in the latest release and binary wheels are provided as well. Note that there is currently an issue with ROCm 4.3 that prevents it from running in several environments. The current workaround is to set the `LLVM_PATH` variable to the llvm folder included in ROCm 4.3 installation (e.g., `export LLVM_PATH=/opt/rocm-4.3/llvm`).

Changes

Enhancements

- Compile with SASS for CUDA versions >= 11.1 (5611)
- Allow to compile using PTX with an envvar (5634)
- Add `ncclAvg` and `ncclBfloat16` for NCCL (5656)
- Fix version check for new ROCm version definition (5661)
- Rest of version check fix for new ROCm version definition (5670)

Bug Fixes

- Fix FFT convolve for shapes containing 1 (5613)
- Fix the RTC call path for HIP (5620)
- Fix compute capability check (5646)
- Fix squareness checks (5652)
- Fix `unique` for empty array (5658)

Code Fixes

- Fix kernel names to be consistent (5625)
- Remove unnecessary comments (5635)

Documentation

- Update Sphinx to 4.1.2 (5616)
- `__array_function__` feature by default (5653)
- Support ROCm v4.3 in document (5674)

Tests

- Increase test timeout (5615)
- Increase timeout for CUDA 11.4 tests (5617)
- Add CI for ROCm 4.3 (5632)
- Reload GPG key for ROCm 4.2 test (5637)
- Fix cubic `for_all_dtypes_combination` tests (5639)
- Add a workaround for ROCm 4.3.0 for testing (5663)
- Fix `skipTest` in `test_decomp_lu` (5672)

Others

- Bump version to v9.4.0 (5680)

Contributors

The CuPy Team would like to thank all those who contributed to this release!

grlee77 leofang yashasvimisra2798

This is the release note of v4.3.0. See [here](https://github.com/cupy/cupy/milestone/31?closed=1) for the complete list of solved issues and merged PRs.

Enhancements

- Improve `reduce_dims` for speed up (1424)
- Remove overhead in `creation/basic.py` (1425)
- Improve performance of host to device memory copy (1426)

Bug Fixes

- Fix to accept longer order names (1395)
- Fix `Module` and `LinkState` not freed (1441)
- Fix error in `PooledMemory` in Python 3.7 (1462)

Documentation

- Fix documentation of the `option` arg of `ElementwiseKernel` (1438)

Installation

- Support bundling dependent DLLs for Windows wheel support (1410)
- Change required Cython version to 0.28 or later (1412)

Tests

- Refactor `TestOrder` (1408)