Age | Commit message (Collapse) | Author |
|
|
|
NVIDIA and ARM GPUs
|
|
sets of input parameters
|
|
|
|
|
|
|
|
struct; fixes bug on Apple OpenCL
|
|
|
|
|
|
GEMM kernel
|
|
implementation
|
|
|
|
- undoing many earlier changes
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
TRSM
|
|
OpenCL 1.1 or lower
|
|
|
|
specific tuning parameters (2)
|
|
specific tuning parameters
|
|
kernel
|
|
for the GEMM direct kernels
|
|
incomplete rectangles
|
|
transposing/non-transposing: NN, NT, TN, TT
|
|
to 256-256-256
|
|
|
|
NWGD and KWGD into one WGD parameter
|
|
indirect version
|
|
|
|
|
|
can't handle long strings
|
|
problems if C contains NaNs
|
|
dvasschemacq-master
Conflicts:
src/kernels/level1/xaxpy.opencl
src/kernels/level2/xgemv.opencl
src/kernels/level2/xgemv_fast.opencl
src/kernels/level2/xger.opencl
src/kernels/level2/xher.opencl
src/kernels/level2/xher2.opencl
src/kernels/level3/xgemm_part2.opencl
|
|
In OpenCL 1.1 __kernel has to be before __attribute__, at least with
Vivante compiler.
|
|
|
|
|
|
|
|
enabling better memory performance
|
|
though
|
|
slow reference kernel as a place-holder
|
|
case of fp16 arguments are cast on host and in kernel
|
|
and/or transposing
|