Skip to content

Commit 3ec66d2

Browse files
committed
Update docs
1 parent 609be14 commit 3ec66d2

File tree

7 files changed

+15
-15
lines changed

7 files changed

+15
-15
lines changed

Libraries/hipBLAS/gemm_strided_batched/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -59,8 +59,8 @@ We can apply the same multiplication operator for several matrices if we combine
5959
- `H`(half-precision: `hipblasHalf`)
6060
- `S` (single-precision: `float`)
6161
- `D` (double-precision: `double`)
62-
- `C` (single-precision complex: `hipblasComplex`)
63-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
62+
- `C` (single-precision complex: `hipComplex`)
63+
- `Z` (double-precision complex: `hipDoubleComplex`).
6464

6565
Input parameters for `hipblasSgemmStridedBatched`:
6666
- `hipblasHandle_t handle`

Libraries/hipBLAS/her/README.md

+3-3
Original file line numberDiff line numberDiff line change
@@ -35,7 +35,7 @@ The application provides the following optional command line arguments:
3535
- hipBLAS is initialized by calling `hipblasCreate(hipblasHandle_t*)` and it is terminated by calling `hipblasDestroy(hipblasHandle_t)`.
3636
- The _pointer mode_ controls whether scalar parameters must be allocated on the host (`HIPBLAS_POINTER_MODE_HOST`) or on the device (`HIPBLAS_POINTER_MODE_DEVICE`). It is controlled by `hipblasSetPointerMode`.
3737
- `hipblasSetVector` and `hipblasSetMatrix` are helper functions provided by the hipBLAS API for writing data to the GPU, whereas `hipblasGetVector` and `hipblasGetMatrix` are intended for retrieving data from the GPU. Note that `hipMemcpy` can also be used to copy/get data to/from the GPU in the usual way.
38-
- `hipblas[CZ]her2(handle, uplo, n, *alpha, *x, incx, *y, incy, *AP, lda)` computes a Hermitian rank-2 update. The character matched in `[CZ]` denotes the data type of the operation, and can be either `C` (complex float: `hipblasComplex`), or `Z` (complex double: `hipblasDoubleComplex`). The required arguments come as the following:
38+
- `hipblas[CZ]her2(handle, uplo, n, *alpha, *x, incx, *y, incy, *AP, lda)` computes a Hermitian rank-2 update. The character matched in `[CZ]` denotes the data type of the operation, and can be either `C` (complex float: `hipComplex`), or `Z` (complex double: `hipDoubleComplex`). The required arguments come as the following:
3939
- `handle`, the hipBLAS API handle.
4040
- `uplo`. Because a Hermitian matrix is symmetric over the diagonal, except that the values in the upper triangle are the complex conjugate of the values in the lower triangle, the required work can be reduced by only updating a single half of the matrix. The part of the matrix to update is given by `uplo`: `HIPBLAS_FILL_MODE_UPPER` (used in this example) indicates that the upper triangle of $A$ should be updated, `HIPBLAS_FILL_MODE_LOWER` indicates that the lower triangle of $A$ should be updated and `HIPBLAS_FILL_MODE_FULL` indicates that the full matrix will be updated.
4141
- `n` gives the dimensions of the vector and matrix inputs.
@@ -44,7 +44,7 @@ The application provides the following optional command line arguments:
4444
- `AP` is the device pointer to matrix $A$ in device memory.
4545
- `lda` is the _leading dimension_ of $A$, that is, the number of elements between the starts of the columns of $A$. Note that hipBLAS matrices are laid out in _column major_ ordering.
4646

47-
- If `ROCM_MATHLIBS_API_USE_HIP_COMPLEX` is defined (adding `#define ROCM_MATHLIBS_API_USE_HIP_COMPLEX` before `#include <hipblas/hipblas.h>`), the hipBLAS API is exposed as using the hip defined complex types. That is, `hipblasComplex` is a typedef of `hipFloatComplex` (also named `hipComplex`) and they can be used equivalently.
47+
- If `ROCM_MATHLIBS_API_USE_HIP_COMPLEX` is defined (adding `#define ROCM_MATHLIBS_API_USE_HIP_COMPLEX` before `#include <hipblas/hipblas.h>`), the hipBLAS API is exposed as using the hip defined complex types. That is, `hipComplex` is a typedef of `hipFloatComplex` (also named `hipComplex`) and they can be used equivalently.
4848
- `hipFloatComplex` and `std::complex<float>` have compatible memory layout, and performing a memory copy between values of these types will correctly perform the expected copy.
4949
- `hipCaddf(a, b)` adds `hipFloatComplex` values `a` and `b` element-wise together. This function is from a family of host/device HIP functions which operate on complex values.
5050

@@ -55,7 +55,7 @@ The application provides the following optional command line arguments:
5555
- `HIPBLAS_FILL_MODE_UPPER`
5656
- `HIPBLAS_POINTER_MODE_HOST`
5757
- `hipblasCher2`
58-
- `hipblasComplex`
58+
- `hipComplex`
5959
- `hipblasCreate`
6060
- `hipblasDestroy`
6161
- `hipblasFillMode_t`

Libraries/hipBLAS/scal/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -32,8 +32,8 @@ The application provides the following optional command line arguments:
3232
- `hipblas[SDCZ]scal` multiplies each element of the vector by a scalar. Depending on the character matched in `[SDCZ]`, the scaling can be obtained with different precisions:
3333
- `S` (single-precision: `float`)
3434
- `D` (double-precision: `double`)
35-
- `C` (single-precision complex: `hipblasComplex`)
36-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
35+
- `C` (single-precision complex: `hipComplex`)
36+
- `Z` (double-precision complex: `hipDoubleComplex`).
3737

3838
## Demonstrated API Calls
3939

Libraries/hipSOLVER/gesvd/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -96,8 +96,8 @@ The application provides the following optional command line arguments:
9696

9797
- `S` (single-precision real: `float`)
9898
- `D` (double-precision real: `double`)
99-
- `C` (single-precision complex: `hipblasComplex`)
100-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
99+
- `C` (single-precision complex: `hipComplex`)
100+
- `Z` (double-precision complex: `hipDoubleComplex`).
101101

102102
Return type: `hipblasStatus_t`.
103103

Libraries/hipSOLVER/syevdx/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -116,8 +116,8 @@ $A x_i = \lambda_i x_i$ for $i = 0, \dots, n-1$.
116116

117117
- `S` (single-precision real: `float`)
118118
- `D` (double-precision real: `double`)
119-
- `C` (single-precision complex: `hipblasComplex`)
120-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
119+
- `C` (single-precision complex: `hipComplex`)
120+
- `Z` (double-precision complex: `hipDoubleComplex`).
121121

122122
Return type: `hipblasStatus_t`.
123123

Libraries/hipSOLVER/syevj_batched/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -111,8 +111,8 @@ The application provides the following command line arguments:
111111
The correct function signature should be chosen based on the datatype of the input matrices:
112112
- `S` (single-precision real: `float`)
113113
- `D` (double-precision real: `double`)
114-
- `C` (single-precision complex: `hipblasComplex`)
115-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
114+
- `C` (single-precision complex: `hipComplex`)
115+
- `Z` (double-precision complex: `hipDoubleComplex`).
116116

117117
Return type: `hipblasStatus_t`.
118118
- The `hipblasPointerMode_t` type controls whether scalar parameters must be allocated on the host (`HIPBLAS_POINTER_MODE_HOST`) or on the device (`HIPBLAS_POINTER_MODE_DEVICE`). It is set by using `hipblasSetPointerMode`.

Libraries/hipSOLVER/sygvd/README.md

+2-2
Original file line numberDiff line numberDiff line change
@@ -114,8 +114,8 @@ $(A - \lambda_i B)x_i = 0$ for $i = 0, \dots, n-1$.
114114

115115
- `S` (single-precision real: `float`)
116116
- `D` (double-precision real: `double`)
117-
- `C` (single-precision complex: `hipblasComplex`)
118-
- `Z` (double-precision complex: `hipblasDoubleComplex`).
117+
- `C` (single-precision complex: `hipComplex`)
118+
- `Z` (double-precision complex: `hipDoubleComplex`).
119119

120120
Return type: `hipblasStatus_t`.
121121

0 commit comments

Comments
 (0)