|
Batch matrix/vector operations with CUDA.jl
|
|
5
|
582
|
September 4, 2024
|
|
Testing GPU compatability in CI
|
|
2
|
130
|
September 4, 2024
|
|
Writing a Metal Kernel
|
|
9
|
751
|
September 1, 2024
|
|
Need a basic example on using custom structs in CUDA.jl with Adapt.jl
|
|
2
|
333
|
August 31, 2024
|
|
Float16 with AMDGPU
|
|
10
|
324
|
August 30, 2024
|
|
Source code annotation using NVTX in CUDA.jl
|
|
2
|
92
|
August 28, 2024
|
|
Matrix Multiplication Using oneAPI.jl Fails on Second Invocation
|
|
3
|
172
|
August 26, 2024
|
|
Questions about CUDA.dot() function
|
|
4
|
639
|
August 25, 2024
|
|
Synchronize streams in CUDA.jl
|
|
11
|
827
|
August 23, 2024
|
|
Most efficient way to find cholesky decomposition of slices of a 3D array in KernelAbstractions
|
|
4
|
144
|
August 21, 2024
|
|
Putting obj files on the GPU with Metal.jl
|
|
0
|
56
|
August 20, 2024
|
|
Invalid LLVM IR error using CUDA
|
|
3
|
311
|
August 17, 2024
|
|
Raspberry Pi AI Kit
|
|
1
|
237
|
August 15, 2024
|
|
Different results with different macros for profiling
|
|
3
|
153
|
August 6, 2024
|
|
Using views of CuArray with CUDA-aware MPI is extremely slow
|
|
14
|
433
|
August 5, 2024
|
|
Delays shown in Nsight Systems between HtoD memcopy and kernel launch when using CUDA.jl
|
|
9
|
291
|
July 31, 2024
|
|
Test a package with a CUDA dependency through GitHub Actions CI
|
|
2
|
302
|
July 31, 2024
|
|
Dynamic parallelism slow in CUDA.jl
|
|
1
|
118
|
July 25, 2024
|
|
CUDA: CUDA driver not found
|
|
24
|
706
|
July 24, 2024
|
|
Variable scoping issue when using multiple GPUs in CUDA.jl
|
|
1
|
58
|
July 17, 2024
|
|
Suggestion: abstraction for integrated GPUs?
|
|
7
|
257
|
July 16, 2024
|
|
Metal Kernel 3D indices
|
|
4
|
237
|
July 14, 2024
|
|
External functions in GPU ODE example
|
|
7
|
283
|
July 11, 2024
|
|
Passing `::Type{InconcreteType}` to CUDA kernel
|
|
2
|
122
|
July 11, 2024
|
|
CUDA.compute_sanitizer() method not defined
|
|
1
|
106
|
July 11, 2024
|
|
Rubbish values from gpu kernel
|
|
5
|
259
|
July 8, 2024
|
|
Basic NN forward passage: CuArray fine, oneAPI array:
|
|
0
|
76
|
June 28, 2024
|
|
Do a function like relu need a kernel ? When you need to write a GPU kernel rather than "just" using CuArray?
|
|
3
|
221
|
June 26, 2024
|
|
CUDA: unsupported dynamic function invocation for closure
|
|
3
|
424
|
June 23, 2024
|
|
Running CUDA.jl with JULIA_DEPOT_PATH read-only
|
|
8
|
256
|
June 21, 2024
|