issues
search
NLESC-JCER
/
EigenCuda
Offload Eigen operations to GPUs
Apache License 2.0
17
stars
5
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
CITATION.cff fix and automatic validation of your citation metadata
#27
abelsiqueira
opened
2 years ago
0
Setup github action
#26
cwmeijer
opened
4 years ago
1
Cutensor
#25
felipeZ
opened
4 years ago
0
Use cuTensor
#24
felipeZ
opened
4 years ago
0
Interleave IO operations with kernel calculation
#23
felipeZ
opened
4 years ago
1
Synchronize stream when copying the matrix back
#22
felipeZ
closed
4 years ago
0
Add Batches multplication
#21
felipeZ
opened
4 years ago
0
Eigen
#20
felipeZ
closed
4 years ago
0
Devel
#19
felipeZ
closed
5 years ago
0
Device Out of memory
#18
felipeZ
closed
5 years ago
0
Register host memory
#17
felipeZ
closed
5 years ago
1
Batch
#16
felipeZ
closed
5 years ago
0
Use unified memory
#15
felipeZ
closed
5 years ago
1
Batch
#14
felipeZ
closed
5 years ago
0
Batch
#13
felipeZ
closed
5 years ago
0
used async copies to and from the device
#12
felipeZ
closed
5 years ago
0
Optimize the memory transfer between host and device
#11
felipeZ
closed
5 years ago
0
Implement a right matrix tensor multiplication
#10
felipeZ
closed
5 years ago
0
Public methods should take constant to reference as input
#9
felipeZ
closed
5 years ago
0
Free the resources after matrix multiplication
#8
felipeZ
closed
5 years ago
0
Improve code
#7
felipeZ
closed
5 years ago
0
triplet tensor product doesn't work for rectangular matrices
#6
felipeZ
closed
5 years ago
0
Pass only pointers to GEMM
#5
felipeZ
closed
5 years ago
0
Matrix is not copy to device in call to triple_tensor_product
#4
felipeZ
closed
5 years ago
0
Performance optimization
#3
felipeZ
closed
5 years ago
6
Use cuda-api-wrappers
#2
felipeZ
closed
5 years ago
0
Batching Small Transfers
#1
felipeZ
closed
5 years ago
0