index
:
debian-clblast
debian/sid
upstream/latest
Debian package for CLBlast.
gspr@nonempty.org
summary
refs
log
tree
commit
diff
log msg
author
committer
range
path:
root
/
src
/
routines
/
levelx
Age
Commit message (
Expand
)
Author
2018-11-12
Add kernel_mode option to im2col, col2im, and convgemm functions
Koichi Akabe
2018-10-30
Fix col2im implementation
Koichi Akabe
2018-10-23
Added groundwork for col2im algorithm plus first non-working version of kerne...
Cedric Nugteren
2018-10-22
Some name changes in im2col code
Cedric Nugteren
2018-09-16
Merge branch 'master' into convgemm_multi_kernel
Cedric Nugteren
2018-09-15
Fixed an MSVC compilation error due to large strings
Cedric Nugteren
2018-09-07
Added xCONVGEMM as im2col plus a batched GEMM kernel
Cedric Nugteren
2018-06-03
Merge branch 'master' into CLBlast-267-convgemm
Cedric Nugteren
2018-06-01
Fixes for Apple OpenCL CPU implementation which requires a LWGS of 1 when bar...
Cedric Nugteren
2018-05-31
Added error-checking for half-empty local work group sizes; fixed a minor TRS...
Cedric Nugteren
2018-05-31
Some potential fixes for error -54 when launching TRSV and TRSM kernels
Cedric Nugteren
2018-05-27
Added a check to return 'NotImplemented' error code in case of systems with <...
Cedric Nugteren
2018-05-27
Made FillMatrix and FillVector functions take a configurable local workgroup ...
Cedric Nugteren
2018-05-21
Added method selection option to switch between im2col and single-kernel appr...
Cedric Nugteren
2018-05-19
Moved new convgemm kernel to levelx kernel folder
Cedric Nugteren
2018-05-19
Second version of direct reading from image tensor for convgemm: also with lo...
Cedric Nugteren
2018-05-17
First version of direct reading from image tensor for convgemm: only for edge...
Cedric Nugteren
2018-05-13
Created a dedicated convgemm GEMM kernel as a copy of the batched direct gemm...
Cedric Nugteren
2018-05-13
Plugged in the code of strided-batched-gemm into convgemm in preparation of a...
Cedric Nugteren
2018-05-09
Changed temporary convgemm implementation to use batched-strided GEMM
Cedric Nugteren
2018-05-09
Implemented convolution as im2col + GEMM
Cedric Nugteren
2018-05-06
Added convgemm skeleton, test infrastructure, and first reference implementation
Cedric Nugteren
2018-04-15
Fixed some failing tests for GEMM and batched GEMM routines
Cedric Nugteren
2018-04-13
Made GEMM rotation expectations kernel-specific
Cedric Nugteren
2018-02-02
Implemented the XHAD Hadamard product routine
Cedric Nugteren
2018-01-31
Created the API and stubs for the HAD (hadamard-product) routines
Cedric Nugteren
2018-01-26
Fixed an event synchronisation issue in the batched gemm routines
Cedric Nugteren
2018-01-18
Made the batched routines also chose direct/indirect kernel like the main GEM...
Cedric Nugteren
2018-01-08
Implemented the in-direct version of the strided-batched GEMM kernel
Cedric Nugteren
2018-01-07
Implemented direct version of strided-batched GEMM kernel
Cedric Nugteren
2018-01-07
Added API and tests for new GemmStridedBatched routine
Cedric Nugteren
2018-01-06
Reduced duplicate code in the batched GEMM implementation
Cedric Nugteren
2017-12-23
Split the invert kernel in two parts to prevent error C1091 in MSVC 2013
Cedric Nugteren
2017-12-23
Added TRSV block-size tuner
Cedric Nugteren
2017-12-10
Split GEMM kernel in 4 files instead of 3 due to MSVC 2013 string length limit
Cedric Nugteren
2017-11-02
Integrated the GEMM routine tuner for kernel selection; added first tuning re...
Cedric Nugteren
2017-10-17
Made buffers of batched routines read/write (was: read-only)
Cedric Nugteren
2017-09-19
Fixed type conversion warnings under MSVC 2013
Cedric Nugteren
2017-08-31
Fixed a bug in im2col: process only valid channel IDs
Cedric Nugteren
2017-08-31
Fixed a bug in im2col confusing first and second workgroup size; made im2col ...
Cedric Nugteren
2017-08-24
Completed im2col implementation
Cedric Nugteren
2017-08-19
First version of im2col kernel, unoptimized but working
Cedric Nugteren
2017-08-12
Merge branch 'master' into im_to_col
Cedric Nugteren
2017-07-12
Relaxed requirement on a_ld and b_ld for batched GEMM
Cedric Nugteren
2017-07-02
Added interface and stubs for the im2col routine
Cedric Nugteren
2017-03-19
Added an (optional) non-direct implementation of the batched GEMM routine
Cedric Nugteren
2017-03-11
Added initial naive version of the batched GEMM routine based on the direct G...
Cedric Nugteren
2017-03-10
Added API and test infrastructure for the batched GEMM routine
Cedric Nugteren
2017-03-08
Implemented a batched version of the AXPY kernel
Cedric Nugteren
2017-03-08
Make batched routines based on offsets instead of a vector of cl_mem objects ...
Cedric Nugteren
[next]