Merge amd-staging branch (as of f044cd5) to promotion/amd-mainline/20…

…23.07.18

Change-Id: I2df1345b25aa46036469490faf8d7e46da95f46f

CHANGELOG.md

@@ -2,6 +2,22 @@
 
 Full documentation for HIPIFY is available at [hipify.readthedocs.io](https://hipify.readthedocs.io/en/latest/).
 
+## HIPIFY for ROCm 5.7.0
+### Added
+- CUDA 12.2.0 support
+- cuDNN 8.9.2 support
+- LLVM 16.0.6 support
+- Initial rocSPARSE support
+- Initial CUDA2ROC documentation generation for rocBLAS, rocSPARSE, and MIOpen:
+  - in separate files: hipify-clang --md --doc-format=full --doc-roc=separate
+  - in a single file: hipify-clang --md --doc-format=full --doc-roc=joint
+- New options:
+  - --use-hip-data-types (Use 'hipDataType' instead of 'hipblasDatatype_t' or 'rocblas_datatype')
+  - --doc-roc=\<value\> (ROC documentation generation: 'skip' (default), 'separate', or 'joint'; the '--md' or '--csv' option must be specified)
+### Fixed
+- [#822] Add a new function call transformation type "additional const by value arg"
+- [#830] Add a new function call transformation type "move arg from place X to place Y"
+
 ## HIPIFY for ROCm 5.6.0
 ### Added
 - CUDA 12.1.0 support

docs/.sphinx/requirements.in

@@ -1 +1 @@
-rocm-docs-core==0.18.4
+rocm-docs-core==0.19.0

docs/.sphinx/requirements.txt

@@ -92,7 +92,7 @@ requests==2.28.2
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==0.18.4
+rocm-docs-core==0.19.0
     # via -r requirements.in
 smmap==5.0.0
     # via gitdb

docs/hipify-clang.md

@@ -23,7 +23,7 @@ After applying all the matchers, the output HIP source is produced.
 
 1. [**LLVM+CLANG**](http://releases.llvm.org) of at least version [4.0.0](http://releases.llvm.org/download.html#4.0.0); the latest stable and recommended release: [**16.0.6**](https://github.com/llvm/llvm-project/releases/tag/llvmorg-16.0.6).
 
-2. [**CUDA**](https://developer.nvidia.com/cuda-downloads) of at least version [8.0](https://developer.nvidia.com/cuda-80-ga2-download-archive), the latest supported version is [**12.1.1**](https://developer.nvidia.com/cuda-downloads).
+2. [**CUDA**](https://developer.nvidia.com/cuda-downloads) of at least version [8.0](https://developer.nvidia.com/cuda-80-ga2-download-archive), the latest supported version is [**12.2.0**](https://developer.nvidia.com/cuda-downloads).
 
 <table align="center">
   <thead>
@@ -169,12 +169,12 @@ After applying all the matchers, the output HIP source is produced.
                            <a href="https://github.com/llvm/llvm-project/releases/tag/llvmorg-16.0.4">16.0.4</a>,
                            <a href="https://github.com/llvm/llvm-project/releases/tag/llvmorg-16.0.5">16.0.5</a>,<br>
                            <a href="https://github.com/llvm/llvm-project/releases/tag/llvmorg-16.0.6"><b>16.0.6</b></a></td>
-      <td bgcolor="eefaeb"><a href="https://developer.nvidia.com/cuda-downloads"><b>12.1.1</b></a></td>
+      <td bgcolor="eefaeb"><a href="https://developer.nvidia.com/cuda-downloads"><b>12.2.0</b></a></td>
       <td colspan=2 bgcolor="eefaeb"><font color="green"><b>LATEST STABLE CONFIG</b></font></td>
     </tr>
     <tr align="center">
       <td><a href="https://github.com/llvm/llvm-project">17.0.0git</a></td>
-      <td><a href="https://developer.nvidia.com/cuda-downloads">12.1.1</a></td>
+      <td><a href="https://developer.nvidia.com/cuda-downloads">12.2.0</a></td>
       <td>+</td>
       <td>+</td>
     </tr>
@@ -199,14 +199,14 @@ To process a file, `hipify-clang` needs access to the same headers that would be
 For example:
 
 ```shell
-./hipify-clang square.cu --cuda-path=/usr/local/cuda-12.1 -I /usr/local/cuda-12.1/samples/common/inc
+./hipify-clang square.cu --cuda-path=/usr/local/cuda-12.2 -I /usr/local/cuda-12.2/samples/common/inc
 ```
 
 `hipify-clang` arguments are given first, followed by a separator `'--'`, and then the arguments you'd pass to `clang` if you
 were compiling the input file. For example:
 
 ```bash
-./hipify-clang cpp17.cu --cuda-path=/usr/local/cuda-12.1 -- -std=c++17
+./hipify-clang cpp17.cu --cuda-path=/usr/local/cuda-12.2 -- -std=c++17
 ```
 
 The [Clang manual for compiling CUDA](https://llvm.org/docs/CompileCudaWithLLVM.html#compiling-cuda-code) may be useful.
@@ -327,9 +327,9 @@ Run `Visual Studio 17 2022`, open the generated `LLVM.sln`, build all, build pro
 
         - ***Linux***: `-DCUDA_TOOLKIT_ROOT_DIR=/usr/include`
 
-        - ***Windows***: `-DCUDA_TOOLKIT_ROOT_DIR="c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.1"`
+        - ***Windows***: `-DCUDA_TOOLKIT_ROOT_DIR="c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.2"`
 
-          `-DCUDA_SDK_ROOT_DIR="c:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.1"`
+          `-DCUDA_SDK_ROOT_DIR="c:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.2"`
 
 4. Ensure [`cuDNN`](https://developer.nvidia.com/rdp/cudnn-archive) of the version corresponding to CUDA's version is installed.
 
@@ -389,7 +389,7 @@ Ubuntu 14: LLVM 4.0.0 - 7.1.0, CUDA 7.0 - 9.0, cuDNN 5.0.5 - 7.6.5
 
 Ubuntu 16-18: LLVM 8.0.0 - 14.0.6, CUDA 8.0 - 10.2, cuDNN 5.1.10 - 8.0.5
 
-Ubuntu 20-21: LLVM 9.0.0 - 16.0.6, CUDA 8.0 - 12.1.1, cuDNN 5.1.10 - 8.9.2
+Ubuntu 20-21: LLVM 9.0.0 - 16.0.6, CUDA 8.0 - 12.2.0, cuDNN 5.1.10 - 8.9.2
 
 Minimum build system requirements for the above configurations:
 
@@ -443,7 +443,7 @@ cmake
 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD
 -- Performing Test CMAKE_HAVE_LIBC_PTHREAD - Success
 -- Found Threads: TRUE
--- Found CUDA: /usr/local/cuda (found version "12.1")
+-- Found CUDA: /usr/local/cuda (found version "12.2")
 -- Configuring done
 -- Generating done
 -- Build files have been written to: /usr/hipify/build
@@ -457,7 +457,7 @@ make test-hipify
 ```shell
 Running HIPify regression tests
 ========================================
-CUDA 12.1 - will be used for testing
+CUDA 12.2 - will be used for testing
 LLVM 16.0.6 - will be used for testing
 x86_64 - Platform architecture
 Linux 5.13.0-21-generic - Platform OS
@@ -576,8 +576,8 @@ Testing Time: 7.90s
 | 12.0.0 - 13.0.1 | 7.0 - 11.5.1 | 7.6.5  - 8.3.2 | 2017.15.9.43, 2019.16.11.9               | 3.22.2          | 3.10.2        |
 | 14.0.0 - 14.0.6 | 7.0 - 11.7.1 | 8.0.5  - 8.4.1 | 2017.15.9.49, 2019.16.11.17, 2022.17.2.6 | 3.24.0          | 3.10.6        |
 | 15.0.0 - 15.0.7 | 7.0 - 11.8.0 | 8.0.5  - 8.8.1 | 2017.15.9.53, 2019.16.11.25, 2022.17.5.2 | 3.26.0          | 3.11.2        |
-| 16.0.0 - 16.0.6 | 7.0 - 12.1.1 | 8.0.5  - 8.9.2 | 2017.15.9.55, 2019.16.11.27, 2022.17.6.4 | 3.26.4          | 3.11.4        |
-| 17.0.0git       | 7.0 - 12.1.1 | 8.0.5  - 8.9.2 | 2017.15.9.55, 2019.16.11.27, 2022.17.6.4 | 3.26.4          | 3.11.4        |
+| 16.0.0 - 16.0.6 | 7.0 - 12.2.0 | 8.0.5  - 8.9.2 | 2017.15.9.55, 2019.16.11.27, 2022.17.6.4 | 3.26.4          | 3.11.4        |
+| 17.0.0git       | 7.0 - 12.2.0 | 8.0.5  - 8.9.2 | 2017.15.9.55, 2019.16.11.27, 2022.17.6.4 | 3.26.4          | 3.11.4        |
 
 *Building with testing support by `Visual Studio 17 2022` on `Windows 10`:*
 
@@ -590,9 +590,9 @@ cmake
  -DCMAKE_BUILD_TYPE=Release \
  -DCMAKE_INSTALL_PREFIX=../dist \
  -DCMAKE_PREFIX_PATH=d:/LLVM/16.0.6/dist \
- -DCUDA_TOOLKIT_ROOT_DIR="c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.1" \
- -DCUDA_SDK_ROOT_DIR="c:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.1" \
- -DCUDA_DNN_ROOT_DIR=d:/CUDNN/cudnn-12.1-windows-x64-v8.9.2 \
+ -DCUDA_TOOLKIT_ROOT_DIR="c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.2" \
+ -DCUDA_SDK_ROOT_DIR="c:/ProgramData/NVIDIA Corporation/CUDA Samples/v12.2" \
+ -DCUDA_DNN_ROOT_DIR=d:/CUDNN/cudnn-12.2-windows-x64-v8.9.2 \
  -DCUDA_CUB_ROOT_DIR=d:/GIT/cub \
  -DLLVM_EXTERNAL_LIT=d:/LLVM/16.0.6/build/Release/bin/llvm-lit.py \
  ../hipify
@@ -606,7 +606,7 @@ cmake
 -- Found PythonInterp: c:/Program Files/Python311/python.exe (found suitable version "3.11.4", minimum required is "3.6")
 -- Found lit: c:/Program Files/Python311/Scripts/lit.exe
 -- Found FileCheck: d:/LLVM/16.0.6/dist/bin/FileCheck.exe
--- Found CUDA: c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.1 (found version "12.1")
+-- Found CUDA: c:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.2 (found version "12.2")
 -- Configuring done
 -- Generating done
 -- Build files have been written to: d:/hipify/build

docs/tables/CUBLAS_API_supported_by_HIP.md

@@ -182,7 +182,7 @@
 |`cublasSetAtomicsMode`| | | |`hipblasSetAtomicsMode`|3.10.0| | | |
 |`cublasSetKernelStream`| | | | | | | | |
 |`cublasSetLoggerCallback`|9.2| | | | | | | |
-|`cublasSetMathMode`| | | | | | | | |
+|`cublasSetMathMode`|9.0| | | | | | | |
 |`cublasSetMatrix`| | | |`hipblasSetMatrix`|1.8.2| | | |
 |`cublasSetMatrixAsync`| | | |`hipblasSetMatrixAsync`|3.7.0| | | |
 |`cublasSetMatrixAsync_64`|12.0| | | | | | | |

docs/tables/CUBLAS_API_supported_by_HIP_and_ROC.md

@@ -8,7 +8,7 @@
 |`CUBLAS_ATOMICS_NOT_ALLOWED`| | | |`HIPBLAS_ATOMICS_NOT_ALLOWED`|3.10.0| | | |`rocblas_atomics_not_allowed`|3.8.0| | | |
 |`CUBLAS_COMPUTE_16F`|11.0| | | | | | | | | | | | |
 |`CUBLAS_COMPUTE_16F_PEDANTIC`|11.0| | | | | | | | | | | | |
-|`CUBLAS_COMPUTE_32F`|11.0| | | | | | | | | | | | |
+|`CUBLAS_COMPUTE_32F`|11.0| | | | | | | |`rocblas_compute_type_f32`|5.7.0| | | |
 |`CUBLAS_COMPUTE_32F_FAST_16BF`|11.0| | | | | | | | | | | | |
 |`CUBLAS_COMPUTE_32F_FAST_16F`|11.0| | | | | | | | | | | | |
 |`CUBLAS_COMPUTE_32F_FAST_TF32`|11.0| | | | | | | | | | | | |
@@ -17,7 +17,7 @@
 |`CUBLAS_COMPUTE_32I_PEDANTIC`|11.0| | | | | | | | | | | | |
 |`CUBLAS_COMPUTE_64F`|11.0| | | | | | | | | | | | |
 |`CUBLAS_COMPUTE_64F_PEDANTIC`|11.0| | | | | | | | | | | | |
-|`CUBLAS_DEFAULT_MATH`|9.0| | | | | | | | | | | | |
+|`CUBLAS_DEFAULT_MATH`|9.0| | | | | | | |`rocblas_default_math`|5.7.0| | | |
 |`CUBLAS_DIAG_NON_UNIT`| | | |`HIPBLAS_DIAG_NON_UNIT`|1.8.2| | | |`rocblas_diagonal_non_unit`|1.5.0| | | |
 |`CUBLAS_DIAG_UNIT`| | | |`HIPBLAS_DIAG_UNIT`|1.8.2| | | |`rocblas_diagonal_unit`|1.5.0| | | |
 |`CUBLAS_FILL_MODE_FULL`|10.1| | |`HIPBLAS_FILL_MODE_FULL`|1.8.2| | | |`rocblas_fill_full`|1.5.0| | | |
@@ -89,16 +89,16 @@
 |`CUBLAS_STATUS_NOT_SUPPORTED`| | | |`HIPBLAS_STATUS_NOT_SUPPORTED`|1.8.2| | | |`rocblas_status_perf_degraded`|3.5.0| | | |
 |`CUBLAS_STATUS_SUCCESS`| | | |`HIPBLAS_STATUS_SUCCESS`|1.8.2| | | |`rocblas_status_success`|1.5.0| | | |
 |`CUBLAS_TENSOR_OP_MATH`|9.0|11.0| | | | | | | | | | | |
-|`CUBLAS_TF32_TENSOR_OP_MATH`|11.0| | | | | | | | | | | | |
+|`CUBLAS_TF32_TENSOR_OP_MATH`|11.0| | | | | | | |`rocblas_xf32_xdl_math_op`|5.7.0| | | |
 |`cublasAtomicsMode_t`| | | |`hipblasAtomicsMode_t`|3.10.0| | | |`rocblas_atomics_mode`|3.8.0| | | |
-|`cublasComputeType_t`|11.0| | |`hipblasDatatype_t`|1.8.2| | | | | | | | |
+|`cublasComputeType_t`|11.0| | |`hipblasDatatype_t`|1.8.2| | | |`rocblas_computetype`|5.7.0| | | |
 |`cublasContext`| | | | | | | | |`_rocblas_handle`|1.5.0| | | |
 |`cublasDataType_t`|7.5| | |`hipblasDatatype_t`|1.8.2| | | |`rocblas_datatype`|1.8.2| | | |
 |`cublasDiagType_t`| | | |`hipblasDiagType_t`|1.8.2| | | |`rocblas_diagonal`|1.5.0| | | |
 |`cublasFillMode_t`| | | |`hipblasFillMode_t`|1.8.2| | | |`rocblas_fill`|1.5.0| | | |
 |`cublasGemmAlgo_t`|8.0| | |`hipblasGemmAlgo_t`|1.8.2| | | |`rocblas_gemm_algo`|1.8.2| | | |
 |`cublasHandle_t`| | | |`hipblasHandle_t`|3.0.0| | | |`rocblas_handle`|1.5.0| | | |
-|`cublasMath_t`|9.0| | | | | | | | | | | | |
+|`cublasMath_t`|9.0| | | | | | | |`rocblas_math_mode`|5.7.0| | | |
 |`cublasOperation_t`| | | |`hipblasOperation_t`|1.8.2| | | |`rocblas_operation`|1.5.0| | | |
 |`cublasPointerMode_t`| | | |`hipblasPointerMode_t`|1.8.2| | | |`rocblas_pointer_mode`|1.6.0| | | |
 |`cublasSideMode_t`| | | |`hipblasSideMode_t`|1.8.2| | | |`rocblas_side`|1.5.0| | | |
@@ -156,7 +156,7 @@
 |`cublasGetCudartVersion`|10.1| | | | | | | | | | | | |
 |`cublasGetError`| | | | | | | | | | | | | |
 |`cublasGetLoggerCallback`|9.2| | | | | | | | | | | | |
-|`cublasGetMathMode`|9.0| | | | | | | | | | | | |
+|`cublasGetMathMode`|9.0| | | | | | | |`rocblas_get_math_mode`|5.7.0| | | |
 |`cublasGetMatrix`| | | |`hipblasGetMatrix`|1.8.2| | | |`rocblas_get_matrix`|1.6.0| | | |
 |`cublasGetMatrixAsync`| | | |`hipblasGetMatrixAsync`|3.7.0| | | |`rocblas_get_matrix_async`|3.5.0| | | |
 |`cublasGetMatrixAsync_64`|12.0| | | | | | | | | | | | |
@@ -182,7 +182,7 @@
 |`cublasSetAtomicsMode`| | | |`hipblasSetAtomicsMode`|3.10.0| | | |`rocblas_set_atomics_mode`|3.8.0| | | |
 |`cublasSetKernelStream`| | | | | | | | | | | | | |
 |`cublasSetLoggerCallback`|9.2| | | | | | | | | | | | |
-|`cublasSetMathMode`| | | | | | | | | | | | | |
+|`cublasSetMathMode`|9.0| | | | | | | |`rocblas_set_math_mode`|5.7.0| | | |
 |`cublasSetMatrix`| | | |`hipblasSetMatrix`|1.8.2| | | |`rocblas_set_matrix`|1.6.0| | | |
 |`cublasSetMatrixAsync`| | | |`hipblasSetMatrixAsync`|3.7.0| | | |`rocblas_set_matrix_async`|3.5.0| | | |
 |`cublasSetMatrixAsync_64`|12.0| | | | | | | | | | | | |

docs/tables/CUBLAS_API_supported_by_ROC.md

@@ -8,7 +8,7 @@
 |`CUBLAS_ATOMICS_NOT_ALLOWED`| | | |`rocblas_atomics_not_allowed`|3.8.0| | | |
 |`CUBLAS_COMPUTE_16F`|11.0| | | | | | | |
 |`CUBLAS_COMPUTE_16F_PEDANTIC`|11.0| | | | | | | |
-|`CUBLAS_COMPUTE_32F`|11.0| | | | | | | |
+|`CUBLAS_COMPUTE_32F`|11.0| | |`rocblas_compute_type_f32`|5.7.0| | | |
 |`CUBLAS_COMPUTE_32F_FAST_16BF`|11.0| | | | | | | |
 |`CUBLAS_COMPUTE_32F_FAST_16F`|11.0| | | | | | | |
 |`CUBLAS_COMPUTE_32F_FAST_TF32`|11.0| | | | | | | |
@@ -17,7 +17,7 @@
 |`CUBLAS_COMPUTE_32I_PEDANTIC`|11.0| | | | | | | |
 |`CUBLAS_COMPUTE_64F`|11.0| | | | | | | |
 |`CUBLAS_COMPUTE_64F_PEDANTIC`|11.0| | | | | | | |
-|`CUBLAS_DEFAULT_MATH`|9.0| | | | | | | |
+|`CUBLAS_DEFAULT_MATH`|9.0| | |`rocblas_default_math`|5.7.0| | | |
 |`CUBLAS_DIAG_NON_UNIT`| | | |`rocblas_diagonal_non_unit`|1.5.0| | | |
 |`CUBLAS_DIAG_UNIT`| | | |`rocblas_diagonal_unit`|1.5.0| | | |
 |`CUBLAS_FILL_MODE_FULL`|10.1| | |`rocblas_fill_full`|1.5.0| | | |
@@ -89,16 +89,16 @@
 |`CUBLAS_STATUS_NOT_SUPPORTED`| | | |`rocblas_status_perf_degraded`|3.5.0| | | |
 |`CUBLAS_STATUS_SUCCESS`| | | |`rocblas_status_success`|1.5.0| | | |
 |`CUBLAS_TENSOR_OP_MATH`|9.0|11.0| | | | | | |
-|`CUBLAS_TF32_TENSOR_OP_MATH`|11.0| | | | | | | |
+|`CUBLAS_TF32_TENSOR_OP_MATH`|11.0| | |`rocblas_xf32_xdl_math_op`|5.7.0| | | |
 |`cublasAtomicsMode_t`| | | |`rocblas_atomics_mode`|3.8.0| | | |
-|`cublasComputeType_t`|11.0| | | | | | | |
+|`cublasComputeType_t`|11.0| | |`rocblas_computetype`|5.7.0| | | |
 |`cublasContext`| | | |`_rocblas_handle`|1.5.0| | | |
 |`cublasDataType_t`|7.5| | |`rocblas_datatype`|1.8.2| | | |
 |`cublasDiagType_t`| | | |`rocblas_diagonal`|1.5.0| | | |
 |`cublasFillMode_t`| | | |`rocblas_fill`|1.5.0| | | |
 |`cublasGemmAlgo_t`|8.0| | |`rocblas_gemm_algo`|1.8.2| | | |
 |`cublasHandle_t`| | | |`rocblas_handle`|1.5.0| | | |
-|`cublasMath_t`|9.0| | | | | | | |
+|`cublasMath_t`|9.0| | |`rocblas_math_mode`|5.7.0| | | |
 |`cublasOperation_t`| | | |`rocblas_operation`|1.5.0| | | |
 |`cublasPointerMode_t`| | | |`rocblas_pointer_mode`|1.6.0| | | |
 |`cublasSideMode_t`| | | |`rocblas_side`|1.5.0| | | |
@@ -156,7 +156,7 @@
 |`cublasGetCudartVersion`|10.1| | | | | | | |
 |`cublasGetError`| | | | | | | | |
 |`cublasGetLoggerCallback`|9.2| | | | | | | |
-|`cublasGetMathMode`|9.0| | | | | | | |
+|`cublasGetMathMode`|9.0| | |`rocblas_get_math_mode`|5.7.0| | | |
 |`cublasGetMatrix`| | | |`rocblas_get_matrix`|1.6.0| | | |
 |`cublasGetMatrixAsync`| | | |`rocblas_get_matrix_async`|3.5.0| | | |
 |`cublasGetMatrixAsync_64`|12.0| | | | | | | |
@@ -182,7 +182,7 @@
 |`cublasSetAtomicsMode`| | | |`rocblas_set_atomics_mode`|3.8.0| | | |
 |`cublasSetKernelStream`| | | | | | | | |
 |`cublasSetLoggerCallback`|9.2| | | | | | | |
-|`cublasSetMathMode`| | | | | | | | |
+|`cublasSetMathMode`|9.0| | |`rocblas_set_math_mode`|5.7.0| | | |
 |`cublasSetMatrix`| | | |`rocblas_set_matrix`|1.6.0| | | |
 |`cublasSetMatrixAsync`| | | |`rocblas_set_matrix_async`|3.5.0| | | |
 |`cublasSetMatrixAsync_64`|12.0| | | | | | | |

docs/tables/CUDA_Device_API_supported_by_HIP.md

@@ -12,6 +12,7 @@
 |`__ballot`| | | |`__ballot`|1.6.0| | | |
 |`__bfloat1622float2`|11.0| | | | | | | |
 |`__bfloat162bfloat162`|11.0| | | | | | | |
+|`__bfloat162char_rz`|12.2| | | | | | | |
 |`__bfloat162float`|11.0| | | | | | | |
 |`__bfloat162int_rd`|11.0| | | | | | | |
 |`__bfloat162int_rn`|11.0| | | | | | | |
@@ -25,6 +26,7 @@
 |`__bfloat162short_rn`|11.0| | | | | | | |
 |`__bfloat162short_ru`|11.0| | | | | | | |
 |`__bfloat162short_rz`|11.0| | | | | | | |
+|`__bfloat162uchar_rz`|12.2| | | | | | | |
 |`__bfloat162uint_rd`|11.0| | | | | | | |
 |`__bfloat162uint_rn`|11.0| | | | | | | |
 |`__bfloat162uint_ru`|11.0| | | | | | | |
@@ -111,6 +113,7 @@
 |`__finite`| | | | | | | | |
 |`__finitef`| | | | | | | | |
 |`__finitel`| | | | | | | | |
+|`__float22bfloat162_rn`|11.0| | | | | | | |
 |`__float22half2_rn`| | | |`__float22half2_rn`|1.6.0| | | |
 |`__float2bfloat16`|11.0| | | | | | | |
 |`__float2bfloat162_rn`|11.0| | | | | | | |
@@ -183,6 +186,7 @@
 |`__hadd_rn`|11.6| | | | | | | |
 |`__hadd_sat`| | | |`__hadd_sat`|1.6.0| | | |
 |`__half22float2`| | | |`__half22float2`|1.6.0| | | |
+|`__half2char_rz`|12.2| | | | | | | |
 |`__half2float`| | | |`__half2float`|1.6.0| | | |
 |`__half2half2`| | | |`__half2half2`|1.9.0| | | |
 |`__half2int_rd`| | | |`__half2int_rd`|1.6.0| | | |
@@ -197,6 +201,7 @@
 |`__half2short_rn`| | | |`__half2short_rn`|1.6.0| | | |
 |`__half2short_ru`| | | |`__half2short_ru`|1.6.0| | | |
 |`__half2short_rz`| | | |`__half2short_rz`|1.6.0| | | |
+|`__half2uchar_rz`|12.2| | | | | | | |
 |`__half2uint_rd`| | | |`__half2uint_rd`|1.6.0| | | |
 |`__half2uint_rn`| | | |`__half2uint_rn`|1.6.0| | | |
 |`__half2uint_ru`| | | |`__half2uint_ru`|1.6.0| | | |
@@ -707,6 +712,8 @@
 |`lrintf`| | | |`lrintf`|1.6.0| | | |
 |`lround`| | | |`lround`|1.6.0| | | |
 |`lroundf`| | | |`lroundf`|1.6.0| | | |
+|`make_bfloat162`|12.2| | | | | | | |
+|`make_half2`|12.2| | | | | | | |
 |`max`| | | |`max`|1.6.0| | | |
 |`min`| | | |`min`|1.6.0| | | |
 |`modf`| | | |`modf`|1.9.0| | | |