diff options
author | Cedric Nugteren <web@cedricnugteren.nl> | 2017-03-08 20:10:20 +0100 |
---|---|---|
committer | Cedric Nugteren <web@cedricnugteren.nl> | 2017-03-08 20:10:20 +0100 |
commit | fa0a9c689fc21a2a24aeadf82ae0acdf6d8bf831 (patch) | |
tree | 404e85900a4c9038d407addb38798d06bb48868c /doc/clblast.md | |
parent | 6aba0bbae71702c4eebd88d0fe17739b509185c1 (diff) |
Make batched routines based on offsets instead of a vector of cl_mem objects - undoing many earlier changes
Diffstat (limited to 'doc/clblast.md')
-rw-r--r-- | doc/clblast.md | 34 |
1 files changed, 18 insertions, 16 deletions
diff --git a/doc/clblast.md b/doc/clblast.md index c919169a..120c0c2c 100644 --- a/doc/clblast.md +++ b/doc/clblast.md @@ -2913,8 +2913,8 @@ C++ API: template <typename T> StatusCode AxpyBatched(const size_t n, const T *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) ``` @@ -2923,32 +2923,32 @@ C API: ``` CLBlastStatusCode CLBlastSaxpyBatched(const size_t n, const float *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) CLBlastStatusCode CLBlastDaxpyBatched(const size_t n, const double *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) CLBlastStatusCode CLBlastCaxpyBatched(const size_t n, const cl_float2 *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) CLBlastStatusCode CLBlastZaxpyBatched(const size_t n, const cl_double2 *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) CLBlastStatusCode CLBlastHaxpyBatched(const size_t n, const cl_half *alphas, - const cl_mem *x_buffers, const size_t x_inc, - cl_mem *y_buffers, const size_t y_inc, + const cl_mem x_buffer, const size_t *x_offsets, const size_t x_inc, + cl_mem y_buffer, const size_t *y_offsets, const size_t y_inc, const size_t batch_count, cl_command_queue* queue, cl_event* event) ``` @@ -2957,10 +2957,12 @@ Arguments to AXPYBATCHED: * `const size_t n`: Integer size argument. This value must be positive. * `const T *alphas`: Input scalar constants. -* `const cl_mem *x_buffers`: OpenCL buffers to store the input x vectors. -* `const size_t x_inc`: Stride/increment of the input x vectors. This value must be greater than 0. -* `cl_mem *y_buffers`: OpenCL buffers to store the output y vectors. -* `const size_t y_inc`: Stride/increment of the output y vectors. This value must be greater than 0. +* `const cl_mem x_buffer`: OpenCL buffer to store the input x vector. +* `const size_t *x_offsets`: The offsets in elements from the start of the input x vector. +* `const size_t x_inc`: Stride/increment of the input x vector. This value must be greater than 0. +* `cl_mem y_buffer`: OpenCL buffer to store the output y vector. +* `const size_t *y_offsets`: The offsets in elements from the start of the output y vector. +* `const size_t y_inc`: Stride/increment of the output y vector. This value must be greater than 0. * `const size_t batch_count`: Number of batches. This value must be positive. * `cl_command_queue* queue`: Pointer to an OpenCL command queue associated with a context and device to execute the routine on. * `cl_event* event`: Pointer to an OpenCL event to be able to wait for completion of the routine's OpenCL kernel(s). This is an optional argument. |