Giters
CNugteren
/
CLBlast
Tuned OpenCL BLAS
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1047
Watchers:
58
Issues:
325
Forks:
205
CNugteren/CLBlast Issues
Banded matrices required buffer size calculated incorrectly (GBMV, HBMV, SBMV & TBMV)
Updated
a month ago
Comments count
8
Support for 'size_t' as index type for 'Max()' and 'Min()'
Updated
2 months ago
What's the meaning of argument 'imax_offset' in clblast::Max()?
Closed
2 months ago
Comments count
1
Segmentation fault for "_routine_" tuners
Updated
2 months ago
Comments count
1
Press a key to 'abort' and 'continue' to next in tuning
Closed
2 months ago
Comments count
1
"make uninstall" support
Updated
2 months ago
Comments count
1
Tuner stuck in 'dead lock' and never completes
Updated
2 months ago
Comments count
3
About the performance in different matrix layouts
Closed
3 months ago
Comments count
1
About the arguments meaning of the matrix operation functions
Closed
3 months ago
Comments count
3
Link error when call "GemmStridedBatched<cl_float2>"
Updated
3 months ago
Comments count
1
when i tune GEMM kernel in clblast, i encountered l2 error
Closed
3 months ago
Comments count
2
ERROR IN ROCK5b
Closed
3 months ago
Comments count
3
How to use 'CLBlastSgemmBatched'?
Updated
3 months ago
Comments count
1
Routines to simply transpose a matrix
Closed
3 months ago
Comments count
1
'cublasSdgmm' equivalent support
Updated
3 months ago
Comments count
1
Segmentation fault with OpenCL 3.0 CUDA (CUDA 12.3)
Closed
4 months ago
Comments count
3
Accuracy problem on Apple M1 and Intel(R) UHD Graphics 770
Closed
4 months ago
Comments count
12
SGEMM broken with 1.6.2 on Intel ARC
Closed
4 months ago
Comments count
24
Android compilation failing
Closed
6 months ago
Comments count
2
Tests don't run on Intel Xe/ARC GPU
Closed
7 months ago
Comments count
1
ruby numo-linalg + clblast: OpenCL error: clCreateContext: -6
Updated
8 months ago
Comments count
1
Version in Python module wrong
Closed
8 months ago
Comments count
2
tunner transpose fails on various specific sizes
Updated
8 months ago
Comments count
1
Unparsed options to tunner are ignored, and better handling of platform/device options
Updated
8 months ago
Comments count
1
Build fails with -Werror=format-security
Closed
8 months ago
Consider add SVM Buffer interface support?
Updated
8 months ago
Comments count
3
gemm performance downgrade for small size M and big size N&K
Updated
8 months ago
Comments count
1
Binary releases on github are not valid tar.gz files
Closed
9 months ago
USing GPU for CLBLAST (need a tutorial)
Closed
9 months ago
Comments count
2
Consider ad
Closed
9 months ago
Comments count
1
Pyclblast float16 scalar conversion
Closed
10 months ago
Comments count
4
Do I have to cross-compile both opencl and clblast for android?
Updated
10 months ago
Comments count
2
need a tutorial on clblast::copy
Closed
a year ago
Comments count
2
Compilining and running SGMM freezes
Closed
a year ago
Comments count
4
HGEMM performance in Adreno(tm) 740 is not faster than SGEMM
Updated
a year ago
Comments count
1
Is it a good idea to use GCN cross lane instruction for optimization?
Updated
a year ago
Comments count
15
compiling CLBlast with my OpenCL drivers on Android
Closed
a year ago
Comments count
3
CMake find package paths broken in MSYS2
Closed
a year ago
Comments count
3
[implement details] usm beheavior
Closed
a year ago
Comments count
2
Cuda execution failed,when running clblast_sample_sgemm_cuda, "CUDA NVRTC error: nvrtcCompileProgram: NVRTC_ERROR_INVALID_OPTION"
Closed
a year ago
Comments count
2
[Question] How to Install on Windows?
Closed
a year ago
Comments count
2
CL kernel preprocess cause compilation error
Closed
a year ago
Comments count
2
Multi-GPU, multi-threaded invocation of CLBlastSgemm seems to be unreliable.
Closed
a year ago
Comments count
16
GemmStridedBatched results question
Closed
a year ago
Comments count
5
make alltuner error
Closed
a year ago
Comments count
7
Segmentation fault with Octave-ocl
Closed
a year ago
Comments count
5
New CLBlast 1.6.0 Release is 3x previous library size
Closed
a year ago
Comments count
4
GEMM Batched Question
Closed
a year ago
Comments count
2
Undefined reference to `clblast::StatusCode clblast::Gemm` on Windows with GCC with the C++ API
Closed
a year ago
Comments count
4
Python Memory Management
Closed
a year ago
Comments count
1
Previous
Next