|
Measure the amount of overhead / gpu memory that will be used by the CUBLAS initialization
|
|
5
|
136
|
July 12, 2021
|
|
Run Parallel Tensor Cores GEMM and Cuda GEMM
|
|
8
|
111
|
July 6, 2021
|
|
cudnnCreate() / cublasCreate() blocked while CUDA kernels run in parallel (irrespective of process)
|
|
3
|
106
|
July 5, 2021
|
|
cuBLAS GEMM INT8 is much slower than FP16 in T4
|
|
3
|
101
|
July 1, 2021
|
|
SCALAPACK with NVBLAS
|
|
0
|
83
|
June 29, 2021
|
|
cuBlasLt's performance on 2080ti and Linux is much worse than on 1650 and Win10
|
|
3
|
92
|
June 25, 2021
|
|
cudnnCreate() / cublasCreate() blocked while gpu kernels run in parallel (irrespective of process)
|
|
0
|
76
|
June 24, 2021
|
|
Noob Question about CUBLAS
|
|
1
|
469
|
June 16, 2021
|
|
Trouble with CUBLAS GEMM Strided Batch
|
|
3
|
101
|
June 8, 2021
|
|
cuBLAS convolution does not use Tensor Cores
|
|
6
|
124
|
June 8, 2021
|
|
Cublas context host RAM footprint >400M
|
|
3
|
102
|
June 8, 2021
|
|
cuBLAS works with 11.2, but not with 11.3 on RTX 3080 Mobile. On A100 both work
|
|
2
|
91
|
May 22, 2021
|
|
CUBLAS_STATUS_NOT_iNITIALIZED
|
|
2
|
487
|
May 18, 2021
|
|
Kernel-level cuBLAS
|
|
2
|
87
|
April 29, 2021
|
|
Segmentation fault using cublas<T>getrsBatched
|
|
2
|
156
|
April 19, 2021
|
