![]() |
MAGMA 2.9.0
Matrix Algebra for GPU and Multicore Architectures
|
Macros | |
| #define | magma_icopyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for magma_int_t arrays. | |
| #define | magma_icopyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for magma_int_t arrays. | |
| #define | magma_index_copyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for magma_index_t arrays. | |
| #define | magma_index_copyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for magma_index_t arrays. | |
| #define | magma_uindex_copyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for magma_uindex_t arrays. | |
| #define | magma_uindex_copyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for magma_uindex_t arrays. | |
| #define | magma_ccopyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for magmaFloatComplex arrays. | |
| #define | magma_ccopyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for magmaFloatComplex arrays. | |
| #define | magma_dcopyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for double arrays. | |
| #define | magma_dcopyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for double arrays. | |
| #define | magma_scopyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for float arrays. | |
| #define | magma_scopyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for float arrays. | |
| #define | magma_zcopyvector( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector() for magmaDoubleComplex arrays. | |
| #define | magma_zcopyvector_async( n, dx_src, incx, dy_dst, incy, queue) |
| Type-safe version of magma_copyvector_async() for magmaDoubleComplex arrays. | |
| #define | magma_copyvector( n, elemSize, dx_src, incx, dy_dst, incy, queue) |
| Copy vector dx_src on GPU device to dy_dst on GPU device. | |
| #define | magma_copyvector_async( n, elemSize, dx_src, incx, dy_dst, incy, queue) |
| Copy vector dx_src on GPU device to dy_dst on GPU device. | |
| #define magma_copyvector | ( | n, | |
| elemSize, | |||
| dx_src, | |||
| incx, | |||
| dy_dst, | |||
| incy, | |||
| queue ) |
Copy vector dx_src on GPU device to dy_dst on GPU device.
Elements may be arbitrary size. Type-safe versions set elemSize appropriately. With CUDA unified addressing, dx and dy can be on different GPUs.
This version synchronizes the queue after the transfer. See magma_copyvector_async() for an asynchronous version.
| [in] | n | Number of elements in vector. |
| [in] | elemSize | Size of each element, e.g., sizeof(double). |
| [in] | dx_src | Source array of dimension (1 + (n-1))*incx, on GPU device. |
| [in] | incx | Increment between elements of hx_src. incx > 0. |
| [out] | dy_dst | Destination array of dimension (1 + (n-1))*incy, on GPU device. |
| [in] | incy | Increment between elements of dy_dst. incy > 0. |
| [in] | queue | Queue to execute in. |
| #define magma_copyvector_async | ( | n, | |
| elemSize, | |||
| dx_src, | |||
| incx, | |||
| dy_dst, | |||
| incy, | |||
| queue ) |
Copy vector dx_src on GPU device to dy_dst on GPU device.
Elements may be arbitrary size. Type-safe versions set elemSize appropriately. With CUDA unified addressing, dx and dy can be on different GPUs.
This version is asynchronous: it may return before the transfer finishes. See magma_copyvector() for a synchronous version.
| [in] | n | Number of elements in vector. |
| [in] | elemSize | Size of each element, e.g., sizeof(double). |
| [in] | dx_src | Source array of dimension (1 + (n-1))*incx, on GPU device. |
| [in] | incx | Increment between elements of hx_src. incx > 0. |
| [out] | dy_dst | Destination array of dimension (1 + (n-1))*incy, on GPU device. |
| [in] | incy | Increment between elements of dy_dst. incy > 0. |
| [in] | queue | Queue to execute in. |